]> Raphaël G. Git Repositories - youtubedl/commitdiff
Imported Upstream version 2015.07.21
authorRogério Brito <rbrito@ime.usp.br>
Wed, 22 Jul 2015 03:58:04 +0000 (00:58 -0300)
committerRogério Brito <rbrito@ime.usp.br>
Wed, 22 Jul 2015 03:58:04 +0000 (00:58 -0300)
160 files changed:
README.md
README.txt
docs/supportedsites.md
test/test_compat.py
youtube-dl
youtube-dl.1
youtube-dl.bash-completion
youtube-dl.fish
youtube-dl.zsh
youtube_dl/YoutubeDL.py
youtube_dl/__init__.py
youtube_dl/compat.py
youtube_dl/downloader/__init__.py
youtube_dl/downloader/dash.py [new file with mode: 0644]
youtube_dl/downloader/external.py
youtube_dl/extractor/__init__.py
youtube_dl/extractor/adobetv.py
youtube_dl/extractor/appleconnect.py [new file with mode: 0644]
youtube_dl/extractor/ard.py
youtube_dl/extractor/baidu.py
youtube_dl/extractor/bbccouk.py
youtube_dl/extractor/bet.py
youtube_dl/extractor/bilibili.py
youtube_dl/extractor/bliptv.py
youtube_dl/extractor/brightcove.py
youtube_dl/extractor/cbs.py
youtube_dl/extractor/ceskatelevize.py
youtube_dl/extractor/clipsyndicate.py
youtube_dl/extractor/cnet.py
youtube_dl/extractor/common.py
youtube_dl/extractor/crunchyroll.py
youtube_dl/extractor/ctsnews.py
youtube_dl/extractor/dailymotion.py
youtube_dl/extractor/dfb.py
youtube_dl/extractor/discovery.py
youtube_dl/extractor/douyutv.py
youtube_dl/extractor/dramafever.py [new file with mode: 0644]
youtube_dl/extractor/drbonanza.py
youtube_dl/extractor/drtuber.py
youtube_dl/extractor/ehow.py
youtube_dl/extractor/empflix.py [deleted file]
youtube_dl/extractor/facebook.py
youtube_dl/extractor/faz.py
youtube_dl/extractor/fivetv.py [new file with mode: 0644]
youtube_dl/extractor/francetv.py
youtube_dl/extractor/gamespot.py
youtube_dl/extractor/generic.py
youtube_dl/extractor/gfycat.py
youtube_dl/extractor/gorillavid.py
youtube_dl/extractor/hentaistigma.py
youtube_dl/extractor/hostingbulk.py
youtube_dl/extractor/howcast.py
youtube_dl/extractor/howstuffworks.py
youtube_dl/extractor/imdb.py
youtube_dl/extractor/ina.py
youtube_dl/extractor/infoq.py
youtube_dl/extractor/instagram.py
youtube_dl/extractor/iqiyi.py [new file with mode: 0644]
youtube_dl/extractor/izlesene.py
youtube_dl/extractor/jeuxvideo.py
youtube_dl/extractor/karaoketv.py
youtube_dl/extractor/kickstarter.py
youtube_dl/extractor/kuwo.py [new file with mode: 0644]
youtube_dl/extractor/letv.py
youtube_dl/extractor/lifenews.py
youtube_dl/extractor/liveleak.py
youtube_dl/extractor/lynda.py
youtube_dl/extractor/malemotion.py
youtube_dl/extractor/metacafe.py
youtube_dl/extractor/mitele.py
youtube_dl/extractor/mixcloud.py
youtube_dl/extractor/mofosex.py
youtube_dl/extractor/myspass.py
youtube_dl/extractor/myvi.py [new file with mode: 0644]
youtube_dl/extractor/myvideo.py
youtube_dl/extractor/nationalgeographic.py
youtube_dl/extractor/neteasemusic.py [new file with mode: 0644]
youtube_dl/extractor/newstube.py
youtube_dl/extractor/nextmedia.py
youtube_dl/extractor/nfl.py
youtube_dl/extractor/niconico.py
youtube_dl/extractor/noco.py
youtube_dl/extractor/nowtv.py
youtube_dl/extractor/npo.py
youtube_dl/extractor/nrk.py
youtube_dl/extractor/odnoklassniki.py
youtube_dl/extractor/onionstudios.py [new file with mode: 0644]
youtube_dl/extractor/openfilm.py
youtube_dl/extractor/pbs.py
youtube_dl/extractor/photobucket.py
youtube_dl/extractor/pinkbike.py [new file with mode: 0644]
youtube_dl/extractor/planetaplay.py
youtube_dl/extractor/played.py
youtube_dl/extractor/playvid.py
youtube_dl/extractor/pornhub.py
youtube_dl/extractor/pornovoisines.py
youtube_dl/extractor/primesharetv.py
youtube_dl/extractor/promptfile.py
youtube_dl/extractor/prosiebensat1.py
youtube_dl/extractor/qqmusic.py
youtube_dl/extractor/quickvid.py
youtube_dl/extractor/rds.py [new file with mode: 0644]
youtube_dl/extractor/rtbf.py
youtube_dl/extractor/rtlnl.py
youtube_dl/extractor/ruutu.py [new file with mode: 0644]
youtube_dl/extractor/safari.py
youtube_dl/extractor/sbs.py
youtube_dl/extractor/shared.py
youtube_dl/extractor/smotri.py
youtube_dl/extractor/snagfilms.py [new file with mode: 0644]
youtube_dl/extractor/sohu.py
youtube_dl/extractor/soundcloud.py
youtube_dl/extractor/spankwire.py
youtube_dl/extractor/spiegeltv.py
youtube_dl/extractor/sunporno.py
youtube_dl/extractor/tagesschau.py
youtube_dl/extractor/teamcoco.py
youtube_dl/extractor/theplatform.py
youtube_dl/extractor/thesixtyone.py
youtube_dl/extractor/thisamericanlife.py [new file with mode: 0644]
youtube_dl/extractor/tlc.py
youtube_dl/extractor/tnaflix.py
youtube_dl/extractor/tube8.py
youtube_dl/extractor/tumblr.py
youtube_dl/extractor/turbo.py
youtube_dl/extractor/tvc.py [new file with mode: 0644]
youtube_dl/extractor/tvplay.py
youtube_dl/extractor/twitch.py
youtube_dl/extractor/twitter.py [new file with mode: 0644]
youtube_dl/extractor/udemy.py
youtube_dl/extractor/udn.py
youtube_dl/extractor/vbox7.py
youtube_dl/extractor/veehd.py
youtube_dl/extractor/vice.py
youtube_dl/extractor/videomega.py
youtube_dl/extractor/viki.py
youtube_dl/extractor/vimeo.py
youtube_dl/extractor/vimple.py
youtube_dl/extractor/vk.py
youtube_dl/extractor/vodlocker.py
youtube_dl/extractor/vube.py
youtube_dl/extractor/webofstories.py
youtube_dl/extractor/xbef.py
youtube_dl/extractor/xhamster.py
youtube_dl/extractor/xnxx.py
youtube_dl/extractor/xtube.py
youtube_dl/extractor/xuite.py
youtube_dl/extractor/xvideos.py
youtube_dl/extractor/yam.py
youtube_dl/extractor/yinyuetai.py [new file with mode: 0644]
youtube_dl/extractor/ynet.py
youtube_dl/extractor/youku.py
youtube_dl/extractor/youtube.py
youtube_dl/options.py
youtube_dl/postprocessor/common.py
youtube_dl/postprocessor/embedthumbnail.py
youtube_dl/postprocessor/ffmpeg.py
youtube_dl/update.py
youtube_dl/utils.py
youtube_dl/version.py

index f3d83c89fafbdff0dc6b22b6d207a28428b59f96..ac54d7b67b8c36d370495759153678f711ac614e 100644 (file)
--- a/README.md
+++ b/README.md
@@ -52,8 +52,9 @@ which means you can modify it, redistribute it or use it however you like.
     -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
     --dump-user-agent                Display the current browser identification
     -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
     --dump-user-agent                Display the current browser identification
-    --list-extractors                List all supported extractors and the URLs they would handle
+    --list-extractors                List all supported extractors
     --extractor-descriptions         Output descriptions of all supported extractors
     --extractor-descriptions         Output descriptions of all supported extractors
+    --force-generic-extractor        Force extraction to use the generic extractor
     --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
     --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
@@ -74,7 +75,7 @@ which means you can modify it, redistribute it or use it however you like.
 ## Video Selection:
     --playlist-start NUMBER          Playlist video to start at (default is 1)
     --playlist-end NUMBER            Playlist video to end at (default is last)
 ## Video Selection:
     --playlist-start NUMBER          Playlist video to start at (default is 1)
     --playlist-end NUMBER            Playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8"
                                      if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
                                      download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
     --match-title REGEX              Download only matching titles (regex or caseless sub-string)
                                      if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
                                      download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
     --match-title REGEX              Download only matching titles (regex or caseless sub-string)
@@ -107,7 +108,7 @@ which means you can modify it, redistribute it or use it however you like.
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
-    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
+    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
     --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
@@ -189,8 +190,8 @@ which means you can modify it, redistribute it or use it however you like.
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific one is requested
     -F, --list-formats               List all available formats
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific one is requested
     -F, --list-formats               List all available formats
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
+    --youtube-skip-dash-manifest     Do not download the DASH manifests and related data on YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no
                                      merge is required
 
 ## Subtitle Options:
                                      merge is required
 
 ## Subtitle Options:
@@ -213,7 +214,8 @@ which means you can modify it, redistribute it or use it however you like.
     --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
     --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
                                      5)
     --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
     --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
                                      5)
-    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
+    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)
+    --postprocessor-args ARGS        Give these arguments to the postprocessor
     -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
     --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
     --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
     -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
     --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
     --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
@@ -223,7 +225,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
                                      parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
+    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
@@ -236,6 +238,26 @@ which means you can modify it, redistribute it or use it however you like.
 
 You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
 
 
 You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
 
+### Authentication with `.netrc` file ###
+
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+```
+touch $HOME/.netrc
+chmod a-rwx,u+rw $HOME/.netrc
+```
+After that you can add credentials for extractor in the following format, where *extractor* is the name of extractor in lowercase:
+```
+machine <extractor> login <login> password <password>
+```
+For example:
+```
+machine youtube login myaccount@gmail.com password my_youtube_password
+machine twitch login my_twitch_account_name password my_twitch_password
+```
+To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or to place it in [configuration file](#configuration).
+
+On Windows you may also need to setup `%HOME%` environment variable manually.
+
 # OUTPUT TEMPLATE
 
 The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
 # OUTPUT TEMPLATE
 
 The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
@@ -379,7 +401,7 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 ### HTTP Error 429: Too Many Requests or 402: Payment Required
 
 
 ### HTTP Error 429: Too Many Requests or 402: Payment Required
 
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
 ### SyntaxError: Non-ASCII character ###
 
 
 ### SyntaxError: Non-ASCII character ###
 
index bc4f294d922e5b53d0c4d0f2e9662de1b9be6677..e40f1d4a8b309cc95c6a50ce859a28b0623b66f8 100644 (file)
@@ -68,8 +68,9 @@ OPTIONS
     -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
     --dump-user-agent                Display the current browser identification
     -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
     --dump-user-agent                Display the current browser identification
-    --list-extractors                List all supported extractors and the URLs they would handle
+    --list-extractors                List all supported extractors
     --extractor-descriptions         Output descriptions of all supported extractors
     --extractor-descriptions         Output descriptions of all supported extractors
+    --force-generic-extractor        Force extraction to use the generic extractor
     --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
     --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
@@ -94,7 +95,7 @@ Video Selection:
 
     --playlist-start NUMBER          Playlist video to start at (default is 1)
     --playlist-end NUMBER            Playlist video to end at (default is last)
 
     --playlist-start NUMBER          Playlist video to start at (default is 1)
     --playlist-end NUMBER            Playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8"
                                      if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
                                      download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
     --match-title REGEX              Download only matching titles (regex or caseless sub-string)
                                      if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
                                      download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
     --match-title REGEX              Download only matching titles (regex or caseless sub-string)
@@ -129,7 +130,7 @@ Download Options:
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
-    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
+    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external downloader
 
 
     --external-downloader-args ARGS  Give these arguments to the external downloader
 
 
@@ -221,8 +222,8 @@ Video Format Options:
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific one is requested
     -F, --list-formats               List all available formats
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific one is requested
     -F, --list-formats               List all available formats
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
+    --youtube-skip-dash-manifest     Do not download the DASH manifests and related data on YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no
                                      merge is required
 
 
                                      merge is required
 
 
@@ -251,7 +252,8 @@ Post-processing Options:
     --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
     --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
                                      5)
     --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
     --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
                                      5)
-    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
+    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)
+    --postprocessor-args ARGS        Give these arguments to the postprocessor
     -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
     --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
     --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
     -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
     --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
     --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
@@ -261,7 +263,7 @@ Post-processing Options:
                                      parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
                                      parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
+    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
@@ -282,6 +284,36 @@ Windows, the configuration file locations are
 %APPDATA%\youtube-dl\config.txt and
 C:\Users\<user name>\youtube-dl.conf.
 
 %APPDATA%\youtube-dl\config.txt and
 C:\Users\<user name>\youtube-dl.conf.
 
+Authentication with .netrc file
+
+You may also want to configure automatic credentials storage for
+extractors that support authentication (by providing login and password
+with --username and --password) in order not to pass credentials as
+command line arguments on every youtube-dl execution and prevent
+tracking plain text passwords in shell command history. You can achieve
+this using .netrc file on per extractor basis. For that you will need to
+create .netrc file in your $HOME and restrict permissions to read/write
+by you only:
+
+    touch $HOME/.netrc
+    chmod a-rwx,u+rw $HOME/.netrc
+
+After that you can add credentials for extractor in the following
+format, where _extractor_ is the name of extractor in lowercase:
+
+    machine <extractor> login <login> password <password>
+
+For example:
+
+    machine youtube login myaccount@gmail.com password my_youtube_password
+    machine twitch login my_twitch_account_name password my_twitch_password
+
+To activate authentication with .netrc file you should pass --netrc to
+youtube-dl or to place it in configuration file.
+
+On Windows you may also need to setup %HOME% environment variable
+manually.
+
 
 
 OUTPUT TEMPLATE
 
 
 OUTPUT TEMPLATE
@@ -556,7 +588,7 @@ HTTP Error 429: Too Many Requests or 402: Payment Required
 These two error codes indicate that the service is blocking your IP
 address because of overuse. Contact the service and ask them to unblock
 your IP address, or - if you have acquired a whitelisted IP address
 These two error codes indicate that the service is blocking your IP
 address because of overuse. Contact the service and ask them to unblock
 your IP address, or - if you have acquired a whitelisted IP address
-already - use the --proxy or --network-address options to select another
+already - use the --proxy or --source-address options to select another
 IP address.
 
 SyntaxError: Non-ASCII character
 IP address.
 
 SyntaxError: Non-ASCII character
index d147b53fe60a5bba6f9d33d1fba684014513f83b..73445137f3f165de4d98b6f1c367553f5ce9345a 100644 (file)
@@ -17,6 +17,7 @@
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
@@ -27,7 +28,8 @@
  - **anitube.se**
  - **AnySex**
  - **Aparat**
  - **anitube.se**
  - **AnySex**
  - **Aparat**
- - **AppleDaily**
+ - **AppleConnect**
+ - **AppleDaily**: 臺灣蘋果日報
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -44,7 +46,7 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
- - **BaiduVideo**
+ - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
- - **CtsNews**
+ - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
+ - **DailymotionCloud**
  - **daum.net**
  - **DBTV**
  - **DctpTv**
  - **daum.net**
  - **DBTV**
  - **DctpTv**
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
- - **DouyuTV**
+ - **DouyuTV**: 斗鱼
+ - **dramafever**
+ - **dramafever:series**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
  - **Firstpost**
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
  - **Firstpost**
+ - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
+ - **iqiyi**: 爱奇艺
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
+ - **kuwo:album**: 酷我音乐 - 专辑
+ - **kuwo:category**: 酷我音乐 - 分类
+ - **kuwo:chart**: 酷我音乐 - 排行榜
+ - **kuwo:mv**: 酷我音乐 - MV
+ - **kuwo:singer**: 酷我音乐 - 歌手
+ - **kuwo:song**: 酷我音乐
  - **la7.tv**
  - **Laola1Tv**
  - **la7.tv**
  - **Laola1Tv**
- - **Letv**
+ - **Letv**: 乐视网
  - **LetvPlaylist**
  - **LetvTv**
  - **Libsyn**
  - **LetvPlaylist**
  - **LetvTv**
  - **Libsyn**
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
+ - **MovieFap**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
+ - **Myvi**
  - **myvideo**
  - **MyVidster**
  - **N-JOY**
  - **myvideo**
  - **MyVidster**
  - **N-JOY**
  - **NDTV**
  - **NerdCubedFeed**
  - **Nerdist**
  - **NDTV**
  - **NerdCubedFeed**
  - **Nerdist**
+ - **netease:album**: 网易云音乐 - 专辑
+ - **netease:djradio**: 网易云音乐 - 电台
+ - **netease:mv**: 网易云音乐 - MV
+ - **netease:playlist**: 网易云音乐 - 歌单
+ - **netease:program**: 网易云音乐 - 电台节目
+ - **netease:singer**: 网易云音乐 - 歌手
+ - **netease:song**: 网易云音乐
  - **Netzkino**
  - **Newgrounds**
  - **Newstube**
  - **Netzkino**
  - **Newgrounds**
  - **Newstube**
- - **NextMedia**
- - **NextMediaActionNews**
+ - **NextMedia**: 蘋果日報
+ - **NextMediaActionNews**: 蘋果日報 - 動新聞
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
  - **Nowness**
  - **NowTV**
  - **nowvideo**: NowVideo
  - **Nowness**
  - **NowTV**
  - **nowvideo**: NowVideo
- - **npo.nl**
+ - **npo**: npo.nl and ntr.nl
+ - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
  - **NRKPlaylist**
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
  - **NRKPlaylist**
- - **NRKTV**
+ - **NRKTV**: NRK TV and NRK Radio
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
  - **OpenFilm**
  - **Ooyala**
  - **OoyalaExternal**
  - **OpenFilm**
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pinkbike**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
- - **qqmusic**
- - **qqmusic:album**
- - **qqmusic:singer**
- - **qqmusic:toplist**
+ - **qqmusic**: QQ音乐
+ - **qqmusic:album**: QQ音乐 - 专辑
+ - **qqmusic:playlist**: QQ音乐 - 歌单
+ - **qqmusic:singer**: QQ音乐 - 歌手
+ - **qqmusic:toplist**: QQ音乐 - 排行榜
  - **QuickVid**
  - **R7**
  - **radio.de**
  - **QuickVid**
  - **R7**
  - **radio.de**
  - **RadioJavan**
  - **Rai**
  - **RBMARadio**
  - **RadioJavan**
  - **Rai**
  - **RBMARadio**
+ - **RDS**: RDS.ca
  - **RedTube**
  - **Restudy**
  - **ReverbNation**
  - **RedTube**
  - **Restudy**
  - **ReverbNation**
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
+ - **Ruutu**
  - **safari**: safaribooksonline.com online video
  - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **safari**: safaribooksonline.com online video
  - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
  - **soompi**
  - **Snotr**
  - **Sohu**
  - **soompi**
  - **SportBox**
  - **SportBoxEmbed**
  - **SportDeutschland**
  - **SportBox**
  - **SportBoxEmbed**
  - **SportDeutschland**
+ - **Sportschau**
  - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
  - **SSA**
  - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
  - **SSA**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
- - **tegenlicht.vpro.nl**
  - **TeleBruxelles**
  - **telecinco.es**
  - **TeleMB**
  - **TeleBruxelles**
  - **telecinco.es**
  - **TeleMB**
  - **TheOnion**
  - **ThePlatform**
  - **TheSixtyOne**
  - **TheOnion**
  - **ThePlatform**
  - **TheSixtyOne**
+ - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
  - **TV2**
  - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
  - **TV2**
  - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
+ - **TVC**
+ - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
  - **tvp.pl:Series**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
  - **tvp.pl:Series**
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
+ - **TwitterCard**
  - **Ubu**
  - **udemy**
  - **udemy:course**
  - **Ubu**
  - **udemy**
  - **udemy:course**
- - **UDNEmbed**
+ - **UDNEmbed**: 聯合影音
  - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
- - **vk.com**
- - **vk.com:user-videos**: vk.com:All of a user's videos
+ - **vk**: VK
+ - **vk:uservideos**: VK - User's Videos
  - **Vodlocker**
  - **VoiceRepublic**
  - **Vporn**
  - **Vodlocker**
  - **VoiceRepublic**
  - **Vporn**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
  - **WebOfStories**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
  - **WebOfStories**
+ - **WebOfStoriesPlaylist**
  - **Weibo**
  - **Wimp**
  - **Wistia**
  - **Weibo**
  - **Wimp**
  - **Wistia**
+ - **WNL**
  - **WorldStarHipHop**
  - **wrzuta.pl**
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
  - **XHamster**
  - **WorldStarHipHop**
  - **wrzuta.pl**
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
  - **XHamster**
+ - **XHamsterEmbed**
  - **XMinus**
  - **XNXX**
  - **Xstream**
  - **XTube**
  - **XTubeUser**: XTube user profile
  - **XMinus**
  - **XNXX**
  - **Xstream**
  - **XTube**
  - **XTubeUser**: XTube user profile
- - **Xuite**
+ - **Xuite**: 隨意窩Xuite影音
  - **XVideos**
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **XVideos**
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
- - **Yam**
+ - **Yam**: 蕃薯藤yam天空部落
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
+ - **yinyuetai:video**: 音悦Tai
  - **Ynet**
  - **YouJizz**
  - **Ynet**
  - **YouJizz**
- - **Youku**
+ - **youku**: 优酷
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com
index 1eb454e068970eb1a0d48cc3cd881e0bf71f9463..c3ba8ad2e3aa1f5cd33dd5a61a184d52cc0c07a9 100644 (file)
@@ -14,6 +14,8 @@ from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
     compat_expanduser,
 from youtube_dl.compat import (
     compat_getenv,
     compat_expanduser,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
 )
 
 
 )
 
 
@@ -42,5 +44,28 @@ class TestCompat(unittest.TestCase):
             dir(youtube_dl.compat))) - set(['unicode_literals'])
         self.assertEqual(all_names, sorted(present_names))
 
             dir(youtube_dl.compat))) - set(['unicode_literals'])
         self.assertEqual(all_names, sorted(present_names))
 
+    def test_compat_urllib_parse_unquote(self):
+        self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
+        self.assertEqual(compat_urllib_parse_unquote(''), '')
+        self.assertEqual(compat_urllib_parse_unquote('%'), '%')
+        self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
+        self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
+        self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
+%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
+            '''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
+%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%86%B6%I%Break%25Things%'''),
+            '''(^◣_◢^)っ︻デ═一    ⇀    ⇀    ⇀    ⇀    ⇀    ↶%I%Break%Things%''')
+
+    def test_compat_urllib_parse_unquote_plus(self):
+        self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
+
 if __name__ == '__main__':
     unittest.main()
 if __name__ == '__main__':
     unittest.main()
index 79f0e0607c75c77a21bd207defc2fa5f144a0953..aeb2b547475ff46cd39df03ba841e083d86dae41 100755 (executable)
Binary files a/youtube-dl and b/youtube-dl differ
index 5b15884592fe3add779cd2ca64db4d0be3a0970c..cde2abf5713580069128dcf377a7188d8aa97f9a 100644 (file)
@@ -24,8 +24,9 @@ redistribute it or use it however you like.
 \-i,\ \-\-ignore\-errors\ \ \ \ \ \ \ \ \ \ \ \ \ \ Continue\ on\ download\ errors,\ for\ example\ to\ skip\ unavailable\ videos\ in\ a\ playlist
 \-\-abort\-on\-error\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Abort\ downloading\ of\ further\ videos\ (in\ the\ playlist\ or\ the\ command\ line)\ if\ an\ error\ occurs
 \-\-dump\-user\-agent\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Display\ the\ current\ browser\ identification
 \-i,\ \-\-ignore\-errors\ \ \ \ \ \ \ \ \ \ \ \ \ \ Continue\ on\ download\ errors,\ for\ example\ to\ skip\ unavailable\ videos\ in\ a\ playlist
 \-\-abort\-on\-error\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Abort\ downloading\ of\ further\ videos\ (in\ the\ playlist\ or\ the\ command\ line)\ if\ an\ error\ occurs
 \-\-dump\-user\-agent\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Display\ the\ current\ browser\ identification
-\-\-list\-extractors\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ List\ all\ supported\ extractors\ and\ the\ URLs\ they\ would\ handle
+\-\-list\-extractors\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ List\ all\ supported\ extractors
 \-\-extractor\-descriptions\ \ \ \ \ \ \ \ \ Output\ descriptions\ of\ all\ supported\ extractors
 \-\-extractor\-descriptions\ \ \ \ \ \ \ \ \ Output\ descriptions\ of\ all\ supported\ extractors
+\-\-force\-generic\-extractor\ \ \ \ \ \ \ \ Force\ extraction\ to\ use\ the\ generic\ extractor
 \-\-default\-search\ PREFIX\ \ \ \ \ \ \ \ \ \ Use\ this\ prefix\ for\ unqualified\ URLs.\ For\ example\ "gvsearch2:"\ downloads\ two\ videos\ from\ google\ videos\ for\ youtube\-dl\ "large\ apple".
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ value\ "auto"\ to\ let\ youtube\-dl\ guess\ ("auto_warning"\ to\ emit\ a\ warning\ when\ guessing).\ "error"\ just\ throws\ an\ error.\ The
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default\ value\ "fixup_error"\ repairs\ broken\ URLs,\ but\ emits\ an\ error\ if\ this\ is\ not\ possible\ instead\ of\ searching.
 \-\-default\-search\ PREFIX\ \ \ \ \ \ \ \ \ \ Use\ this\ prefix\ for\ unqualified\ URLs.\ For\ example\ "gvsearch2:"\ downloads\ two\ videos\ from\ google\ videos\ for\ youtube\-dl\ "large\ apple".
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ value\ "auto"\ to\ let\ youtube\-dl\ guess\ ("auto_warning"\ to\ emit\ a\ warning\ when\ guessing).\ "error"\ just\ throws\ an\ error.\ The
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default\ value\ "fixup_error"\ repairs\ broken\ URLs,\ but\ emits\ an\ error\ if\ this\ is\ not\ possible\ instead\ of\ searching.
@@ -54,7 +55,7 @@ redistribute it or use it however you like.
 \f[C]
 \-\-playlist\-start\ NUMBER\ \ \ \ \ \ \ \ \ \ Playlist\ video\ to\ start\ at\ (default\ is\ 1)
 \-\-playlist\-end\ NUMBER\ \ \ \ \ \ \ \ \ \ \ \ Playlist\ video\ to\ end\ at\ (default\ is\ last)
 \f[C]
 \-\-playlist\-start\ NUMBER\ \ \ \ \ \ \ \ \ \ Playlist\ video\ to\ start\ at\ (default\ is\ 1)
 \-\-playlist\-end\ NUMBER\ \ \ \ \ \ \ \ \ \ \ \ Playlist\ video\ to\ end\ at\ (default\ is\ last)
-\-\-playlist\-items\ ITEM_SPEC\ \ \ \ \ \ \ Playlist\ video\ items\ to\ download.\ Specify\ indices\ of\ the\ videos\ in\ the\ playlist\ seperated\ by\ commas\ like:\ "\-\-playlist\-items\ 1,2,5,8"
+\-\-playlist\-items\ ITEM_SPEC\ \ \ \ \ \ \ Playlist\ video\ items\ to\ download.\ Specify\ indices\ of\ the\ videos\ in\ the\ playlist\ separated\ by\ commas\ like:\ "\-\-playlist\-items\ 1,2,5,8"
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ if\ you\ want\ to\ download\ videos\ indexed\ 1,\ 2,\ 5,\ 8\ in\ the\ playlist.\ You\ can\ specify\ range:\ "\-\-playlist\-items\ 1\-3,7,10\-13",\ it\ will
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ download\ the\ videos\ at\ index\ 1,\ 2,\ 3,\ 7,\ 10,\ 11,\ 12\ and\ 13.
 \-\-match\-title\ REGEX\ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ only\ matching\ titles\ (regex\ or\ caseless\ sub\-string)
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ if\ you\ want\ to\ download\ videos\ indexed\ 1,\ 2,\ 5,\ 8\ in\ the\ playlist.\ You\ can\ specify\ range:\ "\-\-playlist\-items\ 1\-3,7,10\-13",\ it\ will
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ download\ the\ videos\ at\ index\ 1,\ 2,\ 3,\ 7,\ 10,\ 11,\ 12\ and\ 13.
 \-\-match\-title\ REGEX\ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ only\ matching\ titles\ (regex\ or\ caseless\ sub\-string)
@@ -91,7 +92,7 @@ redistribute it or use it however you like.
 \-\-playlist\-reverse\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ playlist\ videos\ in\ reverse\ order
 \-\-xattr\-set\-filesize\ \ \ \ \ \ \ \ \ \ \ \ \ Set\ file\ xattribute\ ytdl.filesize\ with\ expected\ filesize\ (experimental)
 \-\-hls\-prefer\-native\ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ native\ HLS\ downloader\ instead\ of\ ffmpeg\ (experimental)
 \-\-playlist\-reverse\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ playlist\ videos\ in\ reverse\ order
 \-\-xattr\-set\-filesize\ \ \ \ \ \ \ \ \ \ \ \ \ Set\ file\ xattribute\ ytdl.filesize\ with\ expected\ filesize\ (experimental)
 \-\-hls\-prefer\-native\ \ \ \ \ \ \ \ \ \ \ \ \ \ Use\ the\ native\ HLS\ downloader\ instead\ of\ ffmpeg\ (experimental)
-\-\-external\-downloader\ COMMAND\ \ \ \ Use\ the\ specified\ external\ downloader.\ Currently\ supports\ aria2c,curl,wget
+\-\-external\-downloader\ COMMAND\ \ \ \ Use\ the\ specified\ external\ downloader.\ Currently\ supports\ aria2c,curl,httpie,wget
 \-\-external\-downloader\-args\ ARGS\ \ Give\ these\ arguments\ to\ the\ external\ downloader
 \f[]
 .fi
 \-\-external\-downloader\-args\ ARGS\ \ Give\ these\ arguments\ to\ the\ external\ downloader
 \f[]
 .fi
@@ -193,8 +194,8 @@ redistribute it or use it however you like.
 \-\-all\-formats\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ all\ available\ video\ formats
 \-\-prefer\-free\-formats\ \ \ \ \ \ \ \ \ \ \ \ Prefer\ free\ video\ formats\ unless\ a\ specific\ one\ is\ requested
 \-F,\ \-\-list\-formats\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ List\ all\ available\ formats
 \-\-all\-formats\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ all\ available\ video\ formats
 \-\-prefer\-free\-formats\ \ \ \ \ \ \ \ \ \ \ \ Prefer\ free\ video\ formats\ unless\ a\ specific\ one\ is\ requested
 \-F,\ \-\-list\-formats\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ List\ all\ available\ formats
-\-\-youtube\-skip\-dash\-manifest\ \ \ \ \ Do\ not\ download\ the\ DASH\ manifest\ on\ YouTube\ videos
-\-\-merge\-output\-format\ FORMAT\ \ \ \ \ If\ a\ merge\ is\ required\ (e.g.\ bestvideo+bestaudio),\ output\ to\ given\ container\ format.\ One\ of\ mkv,\ mp4,\ ogg,\ webm,\ flv.Ignored\ if\ no
+\-\-youtube\-skip\-dash\-manifest\ \ \ \ \ Do\ not\ download\ the\ DASH\ manifests\ and\ related\ data\ on\ YouTube\ videos
+\-\-merge\-output\-format\ FORMAT\ \ \ \ \ If\ a\ merge\ is\ required\ (e.g.\ bestvideo+bestaudio),\ output\ to\ given\ container\ format.\ One\ of\ mkv,\ mp4,\ ogg,\ webm,\ flv.Ignored\ if\ no
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ merge\ is\ required
 \f[]
 .fi
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ merge\ is\ required
 \f[]
 .fi
@@ -229,7 +230,8 @@ redistribute it or use it however you like.
 \-\-audio\-format\ FORMAT\ \ \ \ \ \ \ \ \ \ \ \ Specify\ audio\ format:\ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ "opus",\ or\ "wav";\ "best"\ by\ default
 \-\-audio\-quality\ QUALITY\ \ \ \ \ \ \ \ \ \ Specify\ ffmpeg/avconv\ audio\ quality,\ insert\ a\ value\ between\ 0\ (better)\ and\ 9\ (worse)\ for\ VBR\ or\ a\ specific\ bitrate\ like\ 128K\ (default
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 5)
 \-\-audio\-format\ FORMAT\ \ \ \ \ \ \ \ \ \ \ \ Specify\ audio\ format:\ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ "opus",\ or\ "wav";\ "best"\ by\ default
 \-\-audio\-quality\ QUALITY\ \ \ \ \ \ \ \ \ \ Specify\ ffmpeg/avconv\ audio\ quality,\ insert\ a\ value\ between\ 0\ (better)\ and\ 9\ (worse)\ for\ VBR\ or\ a\ specific\ bitrate\ like\ 128K\ (default
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 5)
-\-\-recode\-video\ FORMAT\ \ \ \ \ \ \ \ \ \ \ \ Encode\ the\ video\ to\ another\ format\ if\ necessary\ (currently\ supported:\ mp4|flv|ogg|webm|mkv)
+\-\-recode\-video\ FORMAT\ \ \ \ \ \ \ \ \ \ \ \ Encode\ the\ video\ to\ another\ format\ if\ necessary\ (currently\ supported:\ mp4|flv|ogg|webm|mkv|avi)
+\-\-postprocessor\-args\ ARGS\ \ \ \ \ \ \ \ Give\ these\ arguments\ to\ the\ postprocessor
 \-k,\ \-\-keep\-video\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Keep\ the\ video\ file\ on\ disk\ after\ the\ post\-processing;\ the\ video\ is\ erased\ by\ default
 \-\-no\-post\-overwrites\ \ \ \ \ \ \ \ \ \ \ \ \ Do\ not\ overwrite\ post\-processed\ files;\ the\ post\-processed\ files\ are\ overwritten\ by\ default
 \-\-embed\-subs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Embed\ subtitles\ in\ the\ video\ (only\ for\ mkv\ and\ mp4\ videos)
 \-k,\ \-\-keep\-video\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Keep\ the\ video\ file\ on\ disk\ after\ the\ post\-processing;\ the\ video\ is\ erased\ by\ default
 \-\-no\-post\-overwrites\ \ \ \ \ \ \ \ \ \ \ \ \ Do\ not\ overwrite\ post\-processed\ files;\ the\ post\-processed\ files\ are\ overwritten\ by\ default
 \-\-embed\-subs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Embed\ subtitles\ in\ the\ video\ (only\ for\ mkv\ and\ mp4\ videos)
@@ -239,7 +241,7 @@ redistribute it or use it however you like.
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ parameters\ replace\ existing\ values.\ Additional\ templates:\ %(album)s,\ %(artist)s.\ Example:\ \-\-metadata\-from\-title\ "%(artist)s\ \-
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(title)s"\ matches\ a\ title\ like\ "Coldplay\ \-\ Paradise"
 \-\-xattrs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Write\ metadata\ to\ the\ video\ file\[aq]s\ xattrs\ (using\ dublin\ core\ and\ xdg\ standards)
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ parameters\ replace\ existing\ values.\ Additional\ templates:\ %(album)s,\ %(artist)s.\ Example:\ \-\-metadata\-from\-title\ "%(artist)s\ \-
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(title)s"\ matches\ a\ title\ like\ "Coldplay\ \-\ Paradise"
 \-\-xattrs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Write\ metadata\ to\ the\ video\ file\[aq]s\ xattrs\ (using\ dublin\ core\ and\ xdg\ standards)
-\-\-fixup\ POLICY\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Automatically\ correct\ known\ faults\ of\ the\ file.\ One\ of\ never\ (do\ nothing),\ warn\ (only\ emit\ a\ warning),\ detect_or_warn(the\ default;
+\-\-fixup\ POLICY\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Automatically\ correct\ known\ faults\ of\ the\ file.\ One\ of\ never\ (do\ nothing),\ warn\ (only\ emit\ a\ warning),\ detect_or_warn(the\ default;
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ fix\ file\ if\ we\ can,\ warn\ otherwise)
 \-\-prefer\-avconv\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ avconv\ over\ ffmpeg\ for\ running\ the\ postprocessors\ (default)
 \-\-prefer\-ffmpeg\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ ffmpeg\ over\ avconv\ for\ running\ the\ postprocessors
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ fix\ file\ if\ we\ can,\ warn\ otherwise)
 \-\-prefer\-avconv\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ avconv\ over\ ffmpeg\ for\ running\ the\ postprocessors\ (default)
 \-\-prefer\-ffmpeg\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ ffmpeg\ over\ avconv\ for\ running\ the\ postprocessors
@@ -258,6 +260,50 @@ and not copy the mtime) into \f[C]/etc/youtube\-dl.conf\f[] and/or
 On Windows, the configuration file locations are
 \f[C]%APPDATA%\\youtube\-dl\\config.txt\f[] and
 \f[C]C:\\Users\\<user\ name>\\youtube\-dl.conf\f[].
 On Windows, the configuration file locations are
 \f[C]%APPDATA%\\youtube\-dl\\config.txt\f[] and
 \f[C]C:\\Users\\<user\ name>\\youtube\-dl.conf\f[].
+.SS Authentication with \f[C]\&.netrc\f[] file
+.PP
+You may also want to configure automatic credentials storage for
+extractors that support authentication (by providing login and password
+with \f[C]\-\-username\f[] and \f[C]\-\-password\f[]) in order not to
+pass credentials as command line arguments on every youtube\-dl
+execution and prevent tracking plain text passwords in shell command
+history.
+You can achieve this using \f[C]\&.netrc\f[]
+file (http://stackoverflow.com/tags/.netrc/info) on per extractor basis.
+For that you will need to create \f[C]\&.netrc\f[] file in your
+\f[C]$HOME\f[] and restrict permissions to read/write by you only:
+.IP
+.nf
+\f[C]
+touch\ $HOME/.netrc
+chmod\ a\-rwx,u+rw\ $HOME/.netrc
+\f[]
+.fi
+.PP
+After that you can add credentials for extractor in the following
+format, where \f[I]extractor\f[] is the name of extractor in lowercase:
+.IP
+.nf
+\f[C]
+machine\ <extractor>\ login\ <login>\ password\ <password>
+\f[]
+.fi
+.PP
+For example:
+.IP
+.nf
+\f[C]
+machine\ youtube\ login\ myaccount\@gmail.com\ password\ my_youtube_password
+machine\ twitch\ login\ my_twitch_account_name\ password\ my_twitch_password
+\f[]
+.fi
+.PP
+To activate authentication with \f[C]\&.netrc\f[] file you should pass
+\f[C]\-\-netrc\f[] to youtube\-dl or to place it in configuration
+file (#configuration).
+.PP
+On Windows you may also need to setup \f[C]%HOME%\f[] environment
+variable manually.
 .SH OUTPUT TEMPLATE
 .PP
 The \f[C]\-o\f[] option allows users to indicate a template for the
 .SH OUTPUT TEMPLATE
 .PP
 The \f[C]\-o\f[] option allows users to indicate a template for the
@@ -571,7 +617,7 @@ These two error codes indicate that the service is blocking your IP
 address because of overuse.
 Contact the service and ask them to unblock your IP address, or \- if
 you have acquired a whitelisted IP address already \- use the
 address because of overuse.
 Contact the service and ask them to unblock your IP address, or \- if
 you have acquired a whitelisted IP address already \- use the
-\f[C]\-\-proxy\f[] or \f[C]\-\-network\-address\f[]
+\f[C]\-\-proxy\f[] or \f[C]\-\-source\-address\f[]
 options (#network-options) to select another IP address.
 .SS SyntaxError: Non\-ASCII character
 .PP
 options (#network-options) to select another IP address.
 .SS SyntaxError: Non\-ASCII character
 .PP
index 8367bdbfddd573ab7c2579e9cbfd8a55719766ce..893d7e7fc954f7445aa820d08096b11c0fc8636a 100644 (file)
@@ -4,7 +4,7 @@ __youtube_dl()
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
     prev="${COMP_WORDS[COMP_CWORD-1]}"
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
     prev="${COMP_WORDS[COMP_CWORD-1]}"
-    opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --no-color --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --cn-verification-proxy --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --match-filter --no-playlist --yes-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --hls-prefer-native --external-downloader --external-downloader-args --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --metadata-from-title --xattrs --fixup --prefer-avconv --prefer-ffmpeg --ffmpeg-location --exec --convert-subtitles"
+    opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --force-generic-extractor --default-search --ignore-config --flat-playlist --no-color --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --cn-verification-proxy --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --match-filter --no-playlist --yes-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --hls-prefer-native --external-downloader --external-downloader-args --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --postprocessor-args --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --metadata-from-title --xattrs --fixup --prefer-avconv --prefer-ffmpeg --ffmpeg-location --exec --convert-subtitles"
     keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
     fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
     diropts="--cache-dir"
     keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
     fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
     diropts="--cache-dir"
index 82f424b2e0f516b3be9aaf1bd563aae22492bfcb..eb9828dec78a0253446a7ef51a98d222d0a2a02f 100644 (file)
@@ -5,8 +5,9 @@ complete --command youtube-dl --long-option update --short-option U --descriptio
 complete --command youtube-dl --long-option ignore-errors --short-option i --description 'Continue on download errors, for example to skip unavailable videos in a playlist'
 complete --command youtube-dl --long-option abort-on-error --description 'Abort downloading of further videos (in the playlist or the command line) if an error occurs'
 complete --command youtube-dl --long-option dump-user-agent --description 'Display the current browser identification'
 complete --command youtube-dl --long-option ignore-errors --short-option i --description 'Continue on download errors, for example to skip unavailable videos in a playlist'
 complete --command youtube-dl --long-option abort-on-error --description 'Abort downloading of further videos (in the playlist or the command line) if an error occurs'
 complete --command youtube-dl --long-option dump-user-agent --description 'Display the current browser identification'
-complete --command youtube-dl --long-option list-extractors --description 'List all supported extractors and the URLs they would handle'
+complete --command youtube-dl --long-option list-extractors --description 'List all supported extractors'
 complete --command youtube-dl --long-option extractor-descriptions --description 'Output descriptions of all supported extractors'
 complete --command youtube-dl --long-option extractor-descriptions --description 'Output descriptions of all supported extractors'
+complete --command youtube-dl --long-option force-generic-extractor --description 'Force extraction to use the generic extractor'
 complete --command youtube-dl --long-option default-search --description 'Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.'
 complete --command youtube-dl --long-option ignore-config --description 'Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)'
 complete --command youtube-dl --long-option flat-playlist --description 'Do not extract the videos of a playlist, only list them.'
 complete --command youtube-dl --long-option default-search --description 'Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.'
 complete --command youtube-dl --long-option ignore-config --description 'Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)'
 complete --command youtube-dl --long-option flat-playlist --description 'Do not extract the videos of a playlist, only list them.'
@@ -19,7 +20,7 @@ complete --command youtube-dl --long-option force-ipv6 --short-option 6 --descri
 complete --command youtube-dl --long-option cn-verification-proxy --description 'Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading. (experimental)'
 complete --command youtube-dl --long-option playlist-start --description 'Playlist video to start at (default is %default)'
 complete --command youtube-dl --long-option playlist-end --description 'Playlist video to end at (default is last)'
 complete --command youtube-dl --long-option cn-verification-proxy --description 'Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading. (experimental)'
 complete --command youtube-dl --long-option playlist-start --description 'Playlist video to start at (default is %default)'
 complete --command youtube-dl --long-option playlist-end --description 'Playlist video to end at (default is last)'
-complete --command youtube-dl --long-option playlist-items --description 'Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.'
+complete --command youtube-dl --long-option playlist-items --description 'Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.'
 complete --command youtube-dl --long-option match-title --description 'Download only matching titles (regex or caseless sub-string)'
 complete --command youtube-dl --long-option reject-title --description 'Skip download for matching titles (regex or caseless sub-string)'
 complete --command youtube-dl --long-option max-downloads --description 'Abort after downloading NUMBER files'
 complete --command youtube-dl --long-option match-title --description 'Download only matching titles (regex or caseless sub-string)'
 complete --command youtube-dl --long-option reject-title --description 'Skip download for matching titles (regex or caseless sub-string)'
 complete --command youtube-dl --long-option max-downloads --description 'Abort after downloading NUMBER files'
@@ -44,7 +45,7 @@ complete --command youtube-dl --long-option test
 complete --command youtube-dl --long-option playlist-reverse --description 'Download playlist videos in reverse order'
 complete --command youtube-dl --long-option xattr-set-filesize --description 'Set file xattribute ytdl.filesize with expected filesize (experimental)'
 complete --command youtube-dl --long-option hls-prefer-native --description 'Use the native HLS downloader instead of ffmpeg (experimental)'
 complete --command youtube-dl --long-option playlist-reverse --description 'Download playlist videos in reverse order'
 complete --command youtube-dl --long-option xattr-set-filesize --description 'Set file xattribute ytdl.filesize with expected filesize (experimental)'
 complete --command youtube-dl --long-option hls-prefer-native --description 'Use the native HLS downloader instead of ffmpeg (experimental)'
-complete --command youtube-dl --long-option external-downloader --description 'Use the specified external downloader. Currently supports aria2c,curl,wget'
+complete --command youtube-dl --long-option external-downloader --description 'Use the specified external downloader. Currently supports aria2c,curl,httpie,wget'
 complete --command youtube-dl --long-option external-downloader-args --description 'Give these arguments to the external downloader'
 complete --command youtube-dl --long-option batch-file --short-option a --description 'File containing URLs to download ('"'"'-'"'"' for stdin)' --require-parameter
 complete --command youtube-dl --long-option id --description 'Use only video ID in file name'
 complete --command youtube-dl --long-option external-downloader-args --description 'Give these arguments to the external downloader'
 complete --command youtube-dl --long-option batch-file --short-option a --description 'File containing URLs to download ('"'"'-'"'"' for stdin)' --require-parameter
 complete --command youtube-dl --long-option id --description 'Use only video ID in file name'
@@ -108,8 +109,8 @@ complete --command youtube-dl --long-option all-formats --description 'Download
 complete --command youtube-dl --long-option prefer-free-formats --description 'Prefer free video formats unless a specific one is requested'
 complete --command youtube-dl --long-option list-formats --short-option F --description 'List all available formats'
 complete --command youtube-dl --long-option youtube-include-dash-manifest
 complete --command youtube-dl --long-option prefer-free-formats --description 'Prefer free video formats unless a specific one is requested'
 complete --command youtube-dl --long-option list-formats --short-option F --description 'List all available formats'
 complete --command youtube-dl --long-option youtube-include-dash-manifest
-complete --command youtube-dl --long-option youtube-skip-dash-manifest --description 'Do not download the DASH manifest on YouTube videos'
-complete --command youtube-dl --long-option merge-output-format --description 'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no merge is required'
+complete --command youtube-dl --long-option youtube-skip-dash-manifest --description 'Do not download the DASH manifests and related data on YouTube videos'
+complete --command youtube-dl --long-option merge-output-format --description 'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no merge is required'
 complete --command youtube-dl --long-option write-sub --description 'Write subtitle file'
 complete --command youtube-dl --long-option write-auto-sub --description 'Write automatic subtitle file (YouTube only)'
 complete --command youtube-dl --long-option all-subs --description 'Download all the available subtitles of the video'
 complete --command youtube-dl --long-option write-sub --description 'Write subtitle file'
 complete --command youtube-dl --long-option write-auto-sub --description 'Write automatic subtitle file (YouTube only)'
 complete --command youtube-dl --long-option all-subs --description 'Download all the available subtitles of the video'
@@ -124,7 +125,8 @@ complete --command youtube-dl --long-option video-password --description 'Video
 complete --command youtube-dl --long-option extract-audio --short-option x --description 'Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)'
 complete --command youtube-dl --long-option audio-format --description 'Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default'
 complete --command youtube-dl --long-option audio-quality --description 'Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)'
 complete --command youtube-dl --long-option extract-audio --short-option x --description 'Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)'
 complete --command youtube-dl --long-option audio-format --description 'Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default'
 complete --command youtube-dl --long-option audio-quality --description 'Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)'
-complete --command youtube-dl --long-option recode-video --description 'Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)' --arguments 'mp4 flv ogg webm mkv' --exclusive
+complete --command youtube-dl --long-option recode-video --description 'Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)' --arguments 'mp4 flv ogg webm mkv' --exclusive
+complete --command youtube-dl --long-option postprocessor-args --description 'Give these arguments to the postprocessor'
 complete --command youtube-dl --long-option keep-video --short-option k --description 'Keep the video file on disk after the post-processing; the video is erased by default'
 complete --command youtube-dl --long-option no-post-overwrites --description 'Do not overwrite post-processed files; the post-processed files are overwritten by default'
 complete --command youtube-dl --long-option embed-subs --description 'Embed subtitles in the video (only for mkv and mp4 videos)'
 complete --command youtube-dl --long-option keep-video --short-option k --description 'Keep the video file on disk after the post-processing; the video is erased by default'
 complete --command youtube-dl --long-option no-post-overwrites --description 'Do not overwrite post-processed files; the post-processed files are overwritten by default'
 complete --command youtube-dl --long-option embed-subs --description 'Embed subtitles in the video (only for mkv and mp4 videos)'
@@ -132,7 +134,7 @@ complete --command youtube-dl --long-option embed-thumbnail --description 'Embed
 complete --command youtube-dl --long-option add-metadata --description 'Write metadata to the video file'
 complete --command youtube-dl --long-option metadata-from-title --description 'Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like "Coldplay - Paradise"'
 complete --command youtube-dl --long-option xattrs --description 'Write metadata to the video file'"'"'s xattrs (using dublin core and xdg standards)'
 complete --command youtube-dl --long-option add-metadata --description 'Write metadata to the video file'
 complete --command youtube-dl --long-option metadata-from-title --description 'Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like "Coldplay - Paradise"'
 complete --command youtube-dl --long-option xattrs --description 'Write metadata to the video file'"'"'s xattrs (using dublin core and xdg standards)'
-complete --command youtube-dl --long-option fixup --description 'Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default; fix file if we can, warn otherwise)'
+complete --command youtube-dl --long-option fixup --description 'Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default; fix file if we can, warn otherwise)'
 complete --command youtube-dl --long-option prefer-avconv --description 'Prefer avconv over ffmpeg for running the postprocessors (default)'
 complete --command youtube-dl --long-option prefer-ffmpeg --description 'Prefer ffmpeg over avconv for running the postprocessors'
 complete --command youtube-dl --long-option ffmpeg-location --description 'Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.'
 complete --command youtube-dl --long-option prefer-avconv --description 'Prefer avconv over ffmpeg for running the postprocessors (default)'
 complete --command youtube-dl --long-option prefer-ffmpeg --description 'Prefer ffmpeg over avconv for running the postprocessors'
 complete --command youtube-dl --long-option ffmpeg-location --description 'Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.'
index 7dc3ad403d89d2fb7076dae2c6a8c053780ff5bd..73c95b090200a16f8e6e99a57429b3fbe305de61 100644 (file)
@@ -19,7 +19,7 @@ __youtube_dl() {
             elif [[ ${prev} == "--recode-video" ]]; then
                 _arguments '*: :(mp4 flv ogg webm mkv)'
             else
             elif [[ ${prev} == "--recode-video" ]]; then
                 _arguments '*: :(mp4 flv ogg webm mkv)'
             else
-                _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --no-color --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --cn-verification-proxy --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --match-filter --no-playlist --yes-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --hls-prefer-native --external-downloader --external-downloader-args --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --metadata-from-title --xattrs --fixup --prefer-avconv --prefer-ffmpeg --ffmpeg-location --exec --convert-subtitles)'
+                _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --force-generic-extractor --default-search --ignore-config --flat-playlist --no-color --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --cn-verification-proxy --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --match-filter --no-playlist --yes-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --hls-prefer-native --external-downloader --external-downloader-args --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --postprocessor-args --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --metadata-from-title --xattrs --fixup --prefer-avconv --prefer-ffmpeg --ffmpeg-location --exec --convert-subtitles)'
             fi
         ;;
     esac
             fi
         ;;
     esac
index aa6ec9d9a0721efbd5257750fda37b86fe024d8b..00af78e0600f8d2136116e91bcda179f70dbf9a5 100755 (executable)
@@ -119,7 +119,7 @@ class YoutubeDL(object):
 
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
 
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
-    videopassword:     Password for acces a video.
+    videopassword:     Password for accessing a video.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
@@ -139,6 +139,7 @@ class YoutubeDL(object):
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
+    force_generic_extractor: Force downloader to use the generic extractor
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
@@ -261,6 +262,8 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
+    postprocessor_args: A list of additional command-line arguments for the
+                        postprocessor.
     """
 
     params = None
     """
 
     params = None
@@ -626,13 +629,16 @@ class YoutubeDL(object):
             info_dict.setdefault(key, value)
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
             info_dict.setdefault(key, value)
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
-                     process=True):
+                     process=True, force_generic_extractor=False):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
         '''
 
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
         '''
 
+        if not ie_key and force_generic_extractor:
+            ie_key = 'Generic'
+
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
         else:
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
         else:
@@ -1004,7 +1010,7 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
-                if 'width' in t and 'height' in t:
+                if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
@@ -1016,13 +1022,13 @@ class YoutubeDL(object):
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
-            # Working around negative timestamps in Windows
-            # (see http://bugs.python.org/issue1646728)
-            if info_dict['timestamp'] < 0 and os.name == 'nt':
-                info_dict['timestamp'] = 0
-            upload_date = datetime.datetime.utcfromtimestamp(
-                info_dict['timestamp'])
-            info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+            # see http://bugs.python.org/issue1646728)
+            try:
+                upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp'])
+                info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            except (ValueError, OverflowError, OSError):
+                pass
 
         if self.params.get('listsubtitles', False):
             if 'automatic_captions' in info_dict:
 
         if self.params.get('listsubtitles', False):
             if 'automatic_captions' in info_dict:
@@ -1033,12 +1039,6 @@ class YoutubeDL(object):
             info_dict['id'], info_dict.get('subtitles'),
             info_dict.get('automatic_captions'))
 
             info_dict['id'], info_dict.get('subtitles'),
             info_dict.get('automatic_captions'))
 
-        # This extractors handle format selection themselves
-        if info_dict['extractor'] in ['Youku']:
-            if download:
-                self.process_info(info_dict)
-            return info_dict
-
         # We now pick which formats have to be downloaded
         if info_dict.get('formats') is None:
             # There's only one format available
         # We now pick which formats have to be downloaded
         if info_dict.get('formats') is None:
             # There's only one format available
@@ -1499,7 +1499,8 @@ class YoutubeDL(object):
         for url in url_list:
             try:
                 # It also downloads the videos
         for url in url_list:
             try:
                 # It also downloads the videos
-                res = self.extract_info(url)
+                res = self.extract_info(
+                    url, force_generic_extractor=self.params.get('force_generic_extractor', False))
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
index ace17857c8cb28320ba1fab2988e56c020583af7..55b22c889f97c73d28e732466f850bcfb1615c83 100644 (file)
@@ -169,7 +169,7 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:
         if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:
         if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
@@ -263,6 +263,9 @@ def _real_main(argv=None):
     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = shlex.split(opts.external_downloader_args)
     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = shlex.split(opts.external_downloader_args)
+    postprocessor_args = None
+    if opts.postprocessor_args:
+        postprocessor_args = shlex.split(opts.postprocessor_args)
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
@@ -293,6 +296,7 @@ def _real_main(argv=None):
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
+        'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts_retries,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts_retries,
@@ -366,6 +370,7 @@ def _real_main(argv=None):
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
         'external_downloader_args': external_downloader_args,
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
         'external_downloader_args': external_downloader_args,
+        'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
     }
 
         'cn_verification_proxy': opts.cn_verification_proxy,
     }
 
index f9529210dd955932eca837aa7022696470c557ed..0c57c7aebf6bd45a8f9edfc7e1d585f1bbf2f23a 100644 (file)
@@ -9,6 +9,7 @@ import shutil
 import socket
 import subprocess
 import sys
 import socket
 import subprocess
 import sys
+import itertools
 
 
 try:
 
 
 try:
@@ -74,42 +75,74 @@ except ImportError:
     import BaseHTTPServer as compat_http_server
 
 try:
     import BaseHTTPServer as compat_http_server
 
 try:
+    from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
     from urllib.parse import unquote as compat_urllib_parse_unquote
-except ImportError:
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
-        if string == '':
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
+except ImportError:  # Python 2
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
+    # implementations from cpython 3.4.3's stdlib. Python 2's version
+    # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
+
+    def compat_urllib_parse_unquote_to_bytes(string):
+        """unquote_to_bytes('abc%20def') -> b'abc def'."""
+        # Note: strings are encoded as UTF-8. This is only an issue if it contains
+        # unescaped non-ASCII characters, which URIs should not.
+        if not string:
+            # Is it a string-like object?
+            string.split
+            return b''
+        if isinstance(string, unicode):
+            string = string.encode('utf-8')
+        bits = string.split(b'%')
+        if len(bits) == 1:
             return string
             return string
-        res = string.split('%')
-        if len(res) == 1:
+        res = [bits[0]]
+        append = res.append
+        for item in bits[1:]:
+            try:
+                append(compat_urllib_parse._hextochr[item[:2]])
+                append(item[2:])
+            except KeyError:
+                append(b'%')
+                append(item)
+        return b''.join(res)
+
+    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        """Replace %xx escapes by their single-character equivalent. The optional
+        encoding and errors parameters specify how to decode percent-encoded
+        sequences into Unicode characters, as accepted by the bytes.decode()
+        method.
+        By default, percent-encoded sequences are decoded with UTF-8, and invalid
+        sequences are replaced by a placeholder character.
+
+        unquote('abc%20def') -> 'abc def'.
+        """
+        if '%' not in string:
+            string.split
             return string
         if encoding is None:
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
             return string
         if encoding is None:
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
-        pct_sequence = b''
-        string = res[0]
-        for item in res[1:]:
-            try:
-                if not item:
-                    raise ValueError
-                pct_sequence += item[:2].decode('hex')
-                rest = item[2:]
-                if not rest:
-                    # This segment was just a single percent-encoded character.
-                    # May be part of a sequence of code units, so delay decoding.
-                    # (Stored in pct_sequence).
-                    continue
-            except ValueError:
-                rest = '%' + item
-            # Encountered non-percent-encoded characters. Flush the current
-            # pct_sequence.
-            string += pct_sequence.decode(encoding, errors) + rest
-            pct_sequence = b''
-        if pct_sequence:
-            # Flush the final pct_sequence
-            string += pct_sequence.decode(encoding, errors)
-        return string
+        bits = _asciire.split(string)
+        res = [bits[0]]
+        append = res.append
+        for i in range(1, len(bits), 2):
+            append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors))
+            append(bits[i + 1])
+        return ''.join(res)
+
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
 
 try:
     compat_str = unicode  # Python 2
 
 try:
     compat_str = unicode  # Python 2
@@ -388,6 +421,15 @@ else:
             pass
         return _terminal_size(columns, lines)
 
             pass
         return _terminal_size(columns, lines)
 
+try:
+    itertools.count(start=0, step=1)
+    compat_itertools_count = itertools.count
+except TypeError:  # Python 2.6
+    def compat_itertools_count(start=0, step=1):
+        n = start
+        while True:
+            yield n
+            n += step
 
 __all__ = [
     'compat_HTTPError',
 
 __all__ = [
     'compat_HTTPError',
@@ -401,6 +443,7 @@ __all__ = [
     'compat_html_entities',
     'compat_http_client',
     'compat_http_server',
     'compat_html_entities',
     'compat_http_client',
     'compat_http_server',
+    'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
@@ -411,6 +454,8 @@ __all__ = [
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
+    'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
     'compat_urlparse',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
     'compat_urlparse',
index f110830c472eb451d77b48fa9337bd5feee55952..dccc59212d3028bb9a96f0eb9ffff4acb0be681e 100644 (file)
@@ -8,6 +8,7 @@ from .hls import NativeHlsFD
 from .http import HttpFD
 from .rtsp import RtspFD
 from .rtmp import RtmpFD
 from .http import HttpFD
 from .rtsp import RtspFD
 from .rtmp import RtmpFD
+from .dash import DashSegmentsFD
 
 from ..utils import (
     determine_protocol,
 
 from ..utils import (
     determine_protocol,
@@ -20,6 +21,7 @@ PROTOCOL_MAP = {
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
+    'http_dash_segments': DashSegmentsFD,
 }
 
 
 }
 
 
diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py
new file mode 100644 (file)
index 0000000..a4685d3
--- /dev/null
@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import FileDownloader
+from ..compat import compat_urllib_request
+
+
+class DashSegmentsFD(FileDownloader):
+    """
+    Download segments in a DASH manifest
+    """
+    def real_download(self, filename, info_dict):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+        base_url = info_dict['url']
+        segment_urls = info_dict['segment_urls']
+
+        is_test = self.params.get('test', False)
+        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+        byte_counter = 0
+
+        def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
+            self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
+            req = compat_urllib_request.Request(target_url)
+            if remaining_bytes is not None:
+                req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+            data = self.ydl.urlopen(req).read()
+
+            if remaining_bytes is not None:
+                data = data[:remaining_bytes]
+
+            outf.write(data)
+            return len(data)
+
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s/%s' % (base_url, target_url)
+
+        with open(tmpfilename, 'wb') as outf:
+            append_url_to_file(
+                outf, combine_url(base_url, info_dict['initialization_url']),
+                'initialization segment')
+            for i, segment_url in enumerate(segment_urls):
+                segment_len = append_url_to_file(
+                    outf, combine_url(base_url, segment_url),
+                    'segment %d / %d' % (i + 1, len(segment_urls)),
+                    remaining_bytes)
+                byte_counter += segment_len
+                if remaining_bytes is not None:
+                    remaining_bytes -= segment_len
+                    if remaining_bytes <= 0:
+                        break
+
+        self.try_rename(tmpfilename, filename)
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True
index 7ca2d314348400fc6ba3095e23d69e1c925ad7dd..1d5cc99043d02f658064e688c268c37171c37325 100644 (file)
@@ -109,6 +109,14 @@ class Aria2cFD(ExternalFD):
         cmd += ['--', info_dict['url']]
         return cmd
 
         cmd += ['--', info_dict['url']]
         return cmd
 
+
+class HttpieFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['%s:%s' % (key, val)]
+        return cmd
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()
@@ -123,5 +131,6 @@ def list_external_downloaders():
 def get_external_downloader(external_downloader):
     """ Given the name of the executable, see whether we support the given
         downloader . """
 def get_external_downloader(external_downloader):
     """ Given the name of the executable, see whether we support the given
         downloader . """
-    bn = os.path.basename(external_downloader)
+    # Drop .exe extension on Windows
+    bn = os.path.splitext(os.path.basename(external_downloader))[0]
     return _BY_NAME[bn]
     return _BY_NAME[bn]
index 67eb960575a9495e8499506b9cb6ef6b32d55eb6..50da088306a2476e16031318416df70ea0602bea 100644 (file)
@@ -4,7 +4,10 @@ from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+    AdobeTVIE,
+    AdobeTVVideoIE,
+)
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
@@ -16,9 +19,14 @@ from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
+from .appleconnect import AppleConnectIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE, ARDMediathekIE
+from .ard import (
+    ARDIE,
+    ARDMediathekIE,
+    SportschauIE,
+)
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -103,6 +111,7 @@ from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
+    DailymotionCloudIE,
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
@@ -112,6 +121,10 @@ from .dfb import DFBIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
+from .dramafever import (
+    DramaFeverIE,
+    DramaFeverSeriesIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -136,7 +149,6 @@ from .ellentv import (
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
@@ -152,6 +164,7 @@ from .fc2 import FC2IE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
+from .fivetv import FiveTVIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
@@ -229,6 +242,7 @@ from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
+from .iqiyi import IqiyiIE
 from .ivi import (
     IviIE,
     IviCompilationIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -251,6 +265,14 @@ from .keek import KeekIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
+from .kuwo import (
+    KuwoIE,
+    KuwoAlbumIE,
+    KuwoChartIE,
+    KuwoSingerIE,
+    KuwoCategoryIE,
+    KuwoMvIE,
+)
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
 from .letv import (
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
 from .letv import (
@@ -314,6 +336,7 @@ from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
+from .myvi import MyviIE
 from .myvideo import MyVideoIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import NationalGeographicIE
 from .myvideo import MyVideoIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import NationalGeographicIE
@@ -333,6 +356,15 @@ from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
 from .nerdist import NerdistIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
 from .nerdist import NerdistIE
+from .neteasemusic import (
+    NetEaseMusicIE,
+    NetEaseMusicAlbumIE,
+    NetEaseMusicSingerIE,
+    NetEaseMusicListIE,
+    NetEaseMusicMvIE,
+    NetEaseMusicProgramIE,
+    NetEaseMusicDjRadioIE,
+)
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nextmedia import (
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nextmedia import (
@@ -362,7 +394,8 @@ from .npo import (
     NPOLiveIE,
     NPORadioIE,
     NPORadioFragmentIE,
     NPOLiveIE,
     NPORadioIE,
     NPORadioFragmentIE,
-    TegenlichtVproIE,
+    VPROIE,
+    WNLIE
 )
 from .nrk import (
     NRKIE,
 )
 from .nrk import (
     NRKIE,
@@ -378,6 +411,7 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
 from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
 from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
@@ -395,6 +429,7 @@ from .pbs import PBSIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
 from .planetaplay import PlanetaPlayIE
 from .pladform import PladformIE
 from .played import PlayedIE
 from .planetaplay import PlanetaPlayIE
 from .pladform import PladformIE
 from .played import PlayedIE
@@ -421,6 +456,7 @@ from .qqmusic import (
     QQMusicSingerIE,
     QQMusicAlbumIE,
     QQMusicToplistIE,
     QQMusicSingerIE,
     QQMusicAlbumIE,
     QQMusicToplistIE,
+    QQMusicPlaylistIE,
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
@@ -430,6 +466,7 @@ from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
+from .rds import RDSIE
 from .redtube import RedTubeIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
 from .redtube import RedTubeIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
@@ -453,6 +490,7 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .ruutu import RuutuIE
 from .sandia import SandiaIE
 from .safari import (
     SafariIE,
 from .sandia import SandiaIE
 from .safari import (
     SafariIE,
@@ -480,6 +518,10 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .soompi import (
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .soompi import (
@@ -553,6 +595,7 @@ from .tf1 import TF1IE
 from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
 from .thesixtyone import TheSixtyOneIE
 from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
 from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
@@ -560,7 +603,11 @@ from .tmz import (
     TMZIE,
     TMZArticleIE,
 )
     TMZIE,
     TMZArticleIE,
 )
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -582,6 +629,10 @@ from .tv2 import (
     TV2ArticleIE,
 )
 from .tv4 import TV4IE
     TV2ArticleIE,
 )
 from .tv4 import TV4IE
+from .tvc import (
+    TVCIE,
+    TVCArticleIE,
+)
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
@@ -600,6 +651,7 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
+from .twitter import TwitterCardIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -676,7 +728,10 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
     WDRMobileIE,
     WDRMausIE,
 )
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+    WebOfStoriesIE,
+    WebOfStoriesPlaylistIE,
+)
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -685,7 +740,10 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
-from .xhamster import XHamsterIE
+from .xhamster import (
+    XHamsterIE,
+    XHamsterEmbedIE,
+)
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE
@@ -704,6 +762,7 @@ from .yandexmusic import (
     YandexMusicPlaylistIE,
 )
 from .yesjapan import YesJapanIE
     YandexMusicPlaylistIE,
 )
 from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
index 97d12856092975a094ec18a5fd7ecafef39c255a..5e43adc51f98c2f22e728c49150b84ae64f704e3 100644 (file)
@@ -5,6 +5,8 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
     parse_duration,
     unified_strdate,
     str_to_int,
+    float_or_none,
+    ISO639Utils,
 )
 
 
 )
 
 
@@ -69,3 +71,61 @@ class AdobeTVIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
         }
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class AdobeTVVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+
+    _TEST = {
+        # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
+        'url': 'https://video.tv.adobe.com/v/2456/',
+        'md5': '43662b577c018ad707a63766462b1e87',
+        'info_dict': {
+            'id': '2456',
+            'ext': 'mp4',
+            'title': 'New experience with Acrobat DC',
+            'description': 'New experience with Acrobat DC',
+            'duration': 248.667,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_params = self._parse_json(self._search_regex(
+            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
+            video_id)
+
+        formats = [{
+            'url': source['src'],
+            'width': source.get('width'),
+            'height': source.get('height'),
+            'tbr': source.get('bitrate'),
+        } for source in player_params['sources']]
+
+        # For both metadata and downloaded files the duration varies among
+        # formats. I just pick the max one
+        duration = max(filter(None, [
+            float_or_none(source.get('duration'), scale=1000)
+            for source in player_params['sources']]))
+
+        subtitles = {}
+        for translation in player_params.get('translations', []):
+            lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
+            if lang_id not in subtitles:
+                subtitles[lang_id] = []
+            subtitles[lang_id].append({
+                'url': translation['vttPath'],
+                'ext': 'vtt',
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': player_params['title'],
+            'description': self._og_search_description(webpage),
+            'duration': duration,
+            'subtitles': subtitles,
+        }
diff --git a/youtube_dl/extractor/appleconnect.py b/youtube_dl/extractor/appleconnect.py
new file mode 100644 (file)
index 0000000..ea7a703
--- /dev/null
@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    str_to_int,
+    ExtractorError
+)
+
+
+class AppleConnectIE(InfoExtractor):
+    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
+    _TEST = {
+        'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+        'md5': '10d0f2799111df4cb1c924520ca78f98',
+        'info_dict': {
+            'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+            'ext': 'm4v',
+            'title': 'Energy',
+            'uploader': 'Drake',
+            'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
+            'upload_date': '20150710',
+            'timestamp': 1436545535,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        try:
+            video_json = self._html_search_regex(
+                r'class="auc-video-data">(\{.*?\})', webpage, 'json')
+        except ExtractorError:
+            raise ExtractorError('This post doesn\'t contain a video', expected=True)
+
+        video_data = self._parse_json(video_json, video_id)
+        timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
+        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
+
+        return {
+            'id': video_id,
+            'url': video_data['sslSrc'],
+            'title': video_data['title'],
+            'description': video_data['description'],
+            'uploader': video_data['artistName'],
+            'thumbnail': video_data['artworkUrl'],
+            'timestamp': timestamp,
+            'like_count': like_count,
+        }
index 6a35ea463edcafe3b9d7db4c53b9bf0c53198fd0..6f465789b497a6625776c383ff699a64b0b5c346 100644 (file)
@@ -8,6 +8,7 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
     qualities,
     int_or_none,
     parse_duration,
@@ -22,19 +23,125 @@ class ARDMediathekIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
-        'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
-        'only_matching': True,
+        'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
+        'info_dict': {
+            'id': '29582122',
+            'ext': 'mp4',
+            'title': 'Ich liebe das Leben trotzdem',
+            'description': 'md5:45e4c225c72b27993314b31a84a5261c',
+            'duration': 4557,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
     }, {
-        'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
+        'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
         'info_dict': {
         'info_dict': {
-            'id': '22490580',
+            'id': '29522730',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
-            'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
+            'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
+            'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
+            'duration': 5252,
         },
         },
-        'skip': 'Blocked outside of Germany',
+    }, {
+        # audio
+        'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
+        'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
+        'info_dict': {
+            'id': '28488308',
+            'ext': 'mp3',
+            'title': 'Tod eines Fußballers',
+            'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
+            'duration': 3240,
+        },
+    }, {
+        'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
+        'only_matching': True,
     }]
 
     }]
 
+    def _extract_media_info(self, media_info_url, webpage, video_id):
+        media_info = self._download_json(
+            media_info_url, video_id, 'Downloading media JSON')
+
+        formats = self._extract_formats(media_info, video_id)
+
+        if not formats:
+            if '"fsk"' in webpage:
+                raise ExtractorError(
+                    'This video is only available after 20:00', expected=True)
+            elif media_info.get('_geoblocked'):
+                raise ExtractorError('This video is not available due to geo restriction', expected=True)
+
+        self._sort_formats(formats)
+
+        duration = int_or_none(media_info.get('_duration'))
+        thumbnail = media_info.get('_previewImage')
+
+        subtitles = {}
+        subtitle_url = media_info.get('_subtitleUrl')
+        if subtitle_url:
+            subtitles['de'] = [{
+                'ext': 'srt',
+                'url': subtitle_url,
+            }]
+
+        return {
+            'id': video_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _extract_formats(self, media_info, video_id):
+        type_ = media_info.get('_type')
+        media_array = media_info.get('_mediaArray', [])
+        formats = []
+        for num, media in enumerate(media_array):
+            for stream in media.get('_mediaStreamArray', []):
+                stream_urls = stream.get('_stream')
+                if not stream_urls:
+                    continue
+                if not isinstance(stream_urls, list):
+                    stream_urls = [stream_urls]
+                quality = stream.get('_quality')
+                server = stream.get('_server')
+                for stream_url in stream_urls:
+                    ext = determine_ext(stream_url)
+                    if ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
+                            video_id, preference=-1, f4m_id='hds'))
+                    elif ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                    else:
+                        if server and server.startswith('rtmp'):
+                            f = {
+                                'url': server,
+                                'play_path': stream_url,
+                                'format_id': 'a%s-rtmp-%s' % (num, quality),
+                            }
+                        elif stream_url.startswith('http'):
+                            f = {
+                                'url': stream_url,
+                                'format_id': 'a%s-%s-%s' % (num, ext, quality)
+                            }
+                        else:
+                            continue
+                        m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
+                        if m:
+                            f.update({
+                                'width': int(m.group('width')),
+                                'height': int(m.group('height')),
+                            })
+                        if type_ == 'audio':
+                            f['vcodec'] = 'none'
+                        formats.append(f)
+        return formats
+
     def _real_extract(self, url):
         # determine video id from url
         m = re.match(self._VALID_URL, url)
     def _real_extract(self, url):
         # determine video id from url
         m = re.match(self._VALID_URL, url)
@@ -92,46 +199,22 @@ class ARDMediathekIE(InfoExtractor):
                     'format_id': fid,
                     'url': furl,
                 })
                     'format_id': fid,
                     'url': furl,
                 })
+            self._sort_formats(formats)
+            info = {
+                'formats': formats,
+            }
         else:  # request JSON file
         else:  # request JSON file
-            media_info = self._download_json(
-                'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
-            # The second element of the _mediaArray contains the standard http urls
-            streams = media_info['_mediaArray'][1]['_mediaStreamArray']
-            if not streams:
-                if '"fsk"' in webpage:
-                    raise ExtractorError('This video is only available after 20:00')
-
-            formats = []
-            for s in streams:
-                if type(s['_stream']) == list:
-                    for index, url in enumerate(s['_stream'][::-1]):
-                        quality = s['_quality'] + index
-                        formats.append({
-                            'quality': quality,
-                            'url': url,
-                            'format_id': '%s-%s' % (determine_ext(url), quality)
-                        })
-                    continue
-
-                format = {
-                    'quality': s['_quality'],
-                    'url': s['_stream'],
-                }
-
-                format['format_id'] = '%s-%s' % (
-                    determine_ext(format['url']), format['quality'])
+            info = self._extract_media_info(
+                'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id)
 
 
-                formats.append(format)
-
-        self._sort_formats(formats)
-
-        return {
+        info.update({
             'id': video_id,
             'title': title,
             'description': description,
             'id': video_id,
             'title': title,
             'description': description,
-            'formats': formats,
             'thumbnail': thumbnail,
             'thumbnail': thumbnail,
-        }
+        })
+
+        return info
 
 
 class ARDIE(InfoExtractor):
 
 
 class ARDIE(InfoExtractor):
@@ -189,3 +272,41 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
+
+
+class SportschauIE(ARDMediathekIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
+    _TESTS = [{
+        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
+        'info_dict': {
+            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
+            'ext': 'mp4',
+            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        base_url = mobj.group('baseurl')
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_media_info(
+            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info
index 906895c1e197f510c358e47376c6f50d81bd8bdf..e37ee44403a34afe03c02660a71765e2af89cdba 100644 (file)
@@ -8,6 +8,7 @@ from ..compat import compat_urlparse
 
 
 class BaiduVideoIE(InfoExtractor):
 
 
 class BaiduVideoIE(InfoExtractor):
+    IE_DESC = '百度视频'
     _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
     _TESTS = [{
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
     _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
     _TESTS = [{
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
index 249bc6bbde85dc568796f094f421f989df664a1c..5825d286774fa003d343f41c85e07e35340cb428 100644 (file)
@@ -129,6 +129,20 @@ class BBCCoUkIE(InfoExtractor):
                 'skip_download': True,
             },
             'skip': 'geolocation',
                 'skip_download': True,
             },
             'skip': 'geolocation',
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
+            'info_dict': {
+                'id': 'b05zmgw1',
+                'ext': 'flv',
+                'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
+                'title': 'Royal Academy Summer Exhibition',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -237,26 +251,11 @@ class BBCCoUkIE(InfoExtractor):
         for connection in self._extract_connections(media):
             captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
         for connection in self._extract_connections(media):
             captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
-            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
-            srt = ''
-
-            def _extract_text(p):
-                if p.text is not None:
-                    stripped_text = p.text.strip()
-                    if stripped_text:
-                        return stripped_text
-                return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span'))
-            for pos, p in enumerate(ps):
-                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p))
             subtitles[lang] = [
                 {
                     'url': connection.get('href'),
                     'ext': 'ttml',
                 },
             subtitles[lang] = [
                 {
                     'url': connection.get('href'),
                     'ext': 'ttml',
                 },
-                {
-                    'data': srt,
-                    'ext': 'srt',
-                },
             ]
         return subtitles
 
             ]
         return subtitles
 
@@ -267,7 +266,7 @@ class BBCCoUkIE(InfoExtractor):
                 programme_id, 'Downloading media selection XML')
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
                 programme_id, 'Downloading media selection XML')
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
+                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
             else:
                 raise
 
             else:
                 raise
 
@@ -362,7 +361,7 @@ class BBCCoUkIE(InfoExtractor):
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
-                r'<p class="medium-description">([^<]+)</p>',
+                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
                 webpage, 'description', fatal=False)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
                 webpage, 'description', fatal=False)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
index 26b934543a7ac0d28cabf0ca70610460fc253a2f..03dad4636afdf0443735fde8f1d643aea553ba10 100644 (file)
@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     xpath_text,
     xpath_with_ns,
 from ..utils import (
     xpath_text,
     xpath_with_ns,
@@ -57,7 +57,7 @@ class BetIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
-        media_url = compat_urllib_parse.unquote(self._search_regex(
+        media_url = compat_urllib_parse_unquote(self._search_regex(
             [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
             webpage, 'media URL'))
 
             [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
             webpage, 'media URL'))
 
index 2103ed73aad860738bba5108ee27a86fd921d29c..ecc17ebebca9e1819fc804f37d48dcceb80c44c5 100644 (file)
@@ -41,8 +41,15 @@ class BiliBiliIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
-            raise ExtractorError('The video does not exist or was deleted', expected=True)
+        if '(此视频不存在或被删除)' in webpage:
+            raise ExtractorError(
+                'The video does not exist or was deleted', expected=True)
+
+        if '>你没有权限浏览! 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
+            raise ExtractorError(
+                'The video is not available in your region due to copyright reasons',
+                expected=True)
+
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
@@ -105,7 +112,7 @@ class BiliBiliIE(InfoExtractor):
                 'filesize': int_or_none(
                     lq_durl.find('./size'), get_attr='text'),
             }]
                 'filesize': int_or_none(
                     lq_durl.find('./size'), get_attr='text'),
             }]
-            if hq_durl:
+            if hq_durl is not None:
                 formats.append({
                     'format_id': 'hq',
                     'quality': 2,
                 formats.append({
                     'format_id': 'hq',
                     'quality': 2,
index fb56cd78d07ab396ae26ff5a15ac7ebdef933237..c3296283d0dfd1dd753b6e31082e48361414baa3 100644 (file)
@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 
 from ..compat import (
 from .common import InfoExtractor
 
 from ..compat import (
-    compat_str,
     compat_urllib_request,
     compat_urlparse,
 )
     compat_urllib_request,
     compat_urlparse,
 )
@@ -14,6 +13,8 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     unescapeHTML,
     int_or_none,
     parse_iso8601,
     unescapeHTML,
+    xpath_text,
+    xpath_with_ns,
 )
 
 
 )
 
 
@@ -23,10 +24,10 @@ class BlipTVIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
     _TESTS = [
         {
             'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+            'md5': '80baf1ec5c3d2019037c1c707d676b9f',
             'info_dict': {
                 'id': '5779306',
             'info_dict': {
                 'id': '5779306',
-                'ext': 'mov',
+                'ext': 'm4v',
                 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
                 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
                 'timestamp': 1323138843,
                 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
                 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
                 'timestamp': 1323138843,
@@ -100,6 +101,20 @@ class BlipTVIE(InfoExtractor):
                 'vcodec': 'none',
             }
         },
                 'vcodec': 'none',
             }
         },
+        {
+            # missing duration
+            'url': 'http://blip.tv/rss/flash/6700880',
+            'info_dict': {
+                'id': '6684191',
+                'ext': 'm4v',
+                'title': 'Cowboy Bebop: Gateway Shuffle Review',
+                'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8',
+                'timestamp': 1386639757,
+                'upload_date': '20131210',
+                'uploader': 'sfdebris',
+                'uploader_id': '706520',
+            }
+        }
     ]
 
     @staticmethod
     ]
 
     @staticmethod
@@ -128,35 +143,34 @@ class BlipTVIE(InfoExtractor):
 
         rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
 
 
         rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
 
-        def blip(s):
-            return '{http://blip.tv/dtd/blip/1.0}%s' % s
-
-        def media(s):
-            return '{http://search.yahoo.com/mrss/}%s' % s
-
-        def itunes(s):
-            return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s
+        def _x(p):
+            return xpath_with_ns(p, {
+                'blip': 'http://blip.tv/dtd/blip/1.0',
+                'media': 'http://search.yahoo.com/mrss/',
+                'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
+            })
 
         item = rss.find('channel/item')
 
 
         item = rss.find('channel/item')
 
-        video_id = item.find(blip('item_id')).text
-        title = item.find('./title').text
-        description = clean_html(compat_str(item.find(blip('puredescription')).text))
-        timestamp = parse_iso8601(item.find(blip('datestamp')).text)
-        uploader = item.find(blip('user')).text
-        uploader_id = item.find(blip('userid')).text
-        duration = int(item.find(blip('runtime')).text)
-        media_thumbnail = item.find(media('thumbnail'))
-        thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text
-        categories = [category.text for category in item.findall('category')]
+        video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id
+        title = xpath_text(item, 'title', 'title', fatal=True)
+        description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description'))
+        timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp'))
+        uploader = xpath_text(item, _x('blip:user'), 'uploader')
+        uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id')
+        duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration'))
+        media_thumbnail = item.find(_x('media:thumbnail'))
+        thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None
+                     else xpath_text(item, 'image', 'thumbnail'))
+        categories = [category.text for category in item.findall('category') if category is not None]
 
         formats = []
         subtitles_urls = {}
 
 
         formats = []
         subtitles_urls = {}
 
-        media_group = item.find(media('group'))
-        for media_content in media_group.findall(media('content')):
+        media_group = item.find(_x('media:group'))
+        for media_content in media_group.findall(_x('media:content')):
             url = media_content.get('url')
             url = media_content.get('url')
-            role = media_content.get(blip('role'))
+            role = media_content.get(_x('blip:role'))
             msg = self._download_webpage(
                 url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                 video_id, 'Resolving URL for %s' % role)
             msg = self._download_webpage(
                 url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                 video_id, 'Resolving URL for %s' % role)
@@ -175,8 +189,8 @@ class BlipTVIE(InfoExtractor):
                     'url': real_url,
                     'format_id': role,
                     'format_note': media_type,
                     'url': real_url,
                     'format_id': role,
                     'format_note': media_type,
-                    'vcodec': media_content.get(blip('vcodec')) or 'none',
-                    'acodec': media_content.get(blip('acodec')),
+                    'vcodec': media_content.get(_x('blip:vcodec')) or 'none',
+                    'acodec': media_content.get(_x('blip:acodec')),
                     'filesize': media_content.get('filesize'),
                     'width': int_or_none(media_content.get('width')),
                     'height': int_or_none(media_content.get('height')),
                     'filesize': media_content.get('filesize'),
                     'width': int_or_none(media_content.get('width')),
                     'height': int_or_none(media_content.get('height')),
index 4f60d53660fa7777b9e1b6152967ce2e7e567ec9..4721c22930f15cb51d0daaac294eeeca3a329092 100644 (file)
@@ -13,6 +13,7 @@ from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 )
 from ..utils import (
     determine_ext,
 )
 from ..utils import (
     determine_ext,
@@ -119,7 +120,7 @@ class BrightcoveIE(InfoExtractor):
 
         try:
             object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
 
         try:
             object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
-        except xml.etree.ElementTree.ParseError:
+        except compat_xml_parse_error:
             return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
             return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
@@ -156,6 +157,28 @@ class BrightcoveIE(InfoExtractor):
         linkBase = find_param('linkBaseURL')
         if linkBase is not None:
             params['linkBaseURL'] = linkBase
         linkBase = find_param('linkBaseURL')
         if linkBase is not None:
             params['linkBaseURL'] = linkBase
+        return cls._make_brightcove_url(params)
+
+    @classmethod
+    def _build_brighcove_url_from_js(cls, object_js):
+        # The layout of JS is as follows:
+        # customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
+        #   // build Brightcove <object /> XML
+        # }
+        m = re.search(
+            r'''(?x)customBC.\createVideo\(
+                .*?                                                  # skipping width and height
+                ["\'](?P<playerID>\d+)["\']\s*,\s*                   # playerID
+                ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s*  # playerKey begins with AQ and is 50 characters
+                                                                     # in length, however it's appended to itself
+                                                                     # in places, so truncate
+                ["\'](?P<videoID>\d+)["\']                           # @videoPlayer
+            ''', object_js)
+        if m:
+            return cls._make_brightcove_url(m.groupdict())
+
+    @classmethod
+    def _make_brightcove_url(cls, params):
         data = compat_urllib_parse.urlencode(params)
         return cls._FEDERATED_URL_TEMPLATE % data
 
         data = compat_urllib_parse.urlencode(params)
         return cls._FEDERATED_URL_TEMPLATE % data
 
@@ -172,7 +195,7 @@ class BrightcoveIE(InfoExtractor):
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
-            r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"',
+            r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
             webpage)
         if url_m:
             url = unescapeHTML(url_m.group(1))
             webpage)
         if url_m:
             url = unescapeHTML(url_m.group(1))
@@ -188,7 +211,12 @@ class BrightcoveIE(InfoExtractor):
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?>\s*</object>''',
             webpage)
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?>\s*</object>''',
             webpage)
-        return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+        if matches:
+            return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+
+        return list(filter(None, [
+            cls._build_brighcove_url_from_js(custom_bc)
+            for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
index 1ceb9d8d9df6c0268e33de5e34c01a245e134e05..75fffb1563ae9f95bf862ad156111b6962a8429e 100644 (file)
@@ -4,12 +4,13 @@ from .common import InfoExtractor
 
 
 class CBSIE(InfoExtractor):
 
 
 class CBSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '4JUVEwq3wUT7',
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '4JUVEwq3wUT7',
+            'display_id': 'connect-chat-feat-garth-brooks',
             'ext': 'flv',
             'title': 'Connect Chat feat. Garth Brooks',
             'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
             'ext': 'flv',
             'title': 'Connect Chat feat. Garth Brooks',
             'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
@@ -24,6 +25,7 @@ class CBSIE(InfoExtractor):
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
             'id': 'WWF_5KqY3PK1',
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
             'id': 'WWF_5KqY3PK1',
+            'display_id': 'st-vincent',
             'ext': 'flv',
             'title': 'Live on Letterman - St. Vincent',
             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
             'ext': 'flv',
             'title': 'Live on Letterman - St. Vincent',
             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
@@ -34,12 +36,23 @@ class CBSIE(InfoExtractor):
             'skip_download': True,
         },
         '_skip': 'Blocked outside the US',
             'skip_download': True,
         },
         '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
         real_id = self._search_regex(
         real_id = self._search_regex(
-            r"video\.settings\.pid\s*=\s*'([^']+)';",
+            [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
             webpage, 'real video ID')
             webpage, 'real video ID')
-        return self.url_result('theplatform:%s' % real_id)
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': 'theplatform:%s' % real_id,
+            'display_id': display_id,
+        }
index 65f6be62313dfc623cf1f9aa7adc52282872aade..dda583680a03ba3cb420beb74a99af2ec60cbc83 100644 (file)
@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -88,7 +89,7 @@ class CeskaTelevizeIE(InfoExtractor):
         if playlist_url == 'error_region':
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
         if playlist_url == 'error_region':
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
+        req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
         playlist = self._download_json(req, video_id)
         req.add_header('Referer', url)
 
         playlist = self._download_json(req, video_id)
index d07d544eaf7742bb782a8b367a09561f14c44a4e..8306d6fb7d0d4414cff36f7b381ca9c877820f58 100644 (file)
@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
@@ -10,9 +8,9 @@ from ..utils import (
 
 
 class ClipsyndicateIE(InfoExtractor):
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+    _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
         'info_dict': {
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
         'info_dict': {
@@ -22,11 +20,13 @@ class ClipsyndicateIE(InfoExtractor):
             'duration': 612,
             'thumbnail': 're:^https?://.+\.jpg',
         },
             'duration': 612,
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
             video_id, 'Downlaoding player')
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
             video_id, 'Downlaoding player')
index 3145b30514ea2a075f92077b9f87b64c9e8820a7..5dd69bff7ac73bcc0adc4d91c614045ddf116a9c 100644 (file)
@@ -11,7 +11,7 @@ from ..utils import (
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
@@ -25,7 +25,20 @@ class CNETIE(InfoExtractor):
         'params': {
             'skip_download': 'requires rtmpdump',
         }
         'params': {
             'skip_download': 'requires rtmpdump',
         }
-    }
+    }, {
+        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
+        'info_dict': {
+            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
+            'ext': 'flv',
+            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
+            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
+            'uploader': 'Ashley Esqueda',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -42,7 +55,7 @@ class CNETIE(InfoExtractor):
             raise ExtractorError('Cannot find video data')
 
         mpx_account = data['config']['players']['default']['mpx_account']
             raise ExtractorError('Cannot find video data')
 
         mpx_account = data['config']['players']['default']['mpx_account']
-        vid = vdata['files']['rtmp']
+        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
         tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
 
         video_id = vdata['id']
         tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
 
         video_id = vdata['id']
index cecf917ffb67040739bbacf573297ba891ec9ea1..b9014fc23e53eaf335d65ee56c3db560d218d642 100644 (file)
@@ -22,18 +22,20 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
     compat_str,
 )
 from ..utils import (
+    NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,
     compiled_regex_type,
     age_restricted,
     bug_reports_message,
     clean_html,
     compiled_regex_type,
+    determine_ext,
     ExtractorError,
     ExtractorError,
+    fix_xml_ampersands,
     float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
 )
     float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
 )
-_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
 
 
 class InfoExtractor(object):
@@ -523,7 +525,7 @@ class InfoExtractor(object):
             video_info['description'] = playlist_description
         return video_info
 
             video_info['description'] = playlist_description
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -549,7 +551,7 @@ class InfoExtractor(object):
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
-        elif default is not _NO_DEFAULT:
+        elif default is not NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
@@ -557,7 +559,7 @@ class InfoExtractor(object):
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -705,6 +707,25 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
+    @staticmethod
+    def _hidden_inputs(html):
+        return dict([
+            (input.group('name'), input.group('value')) for input in re.finditer(
+                r'''(?x)
+                    <input\s+
+                        type=(?P<q_hidden>["\'])hidden(?P=q_hidden)\s+
+                        name=(?P<q_name>["\'])(?P<name>.+?)(?P=q_name)\s+
+                        (?:id=(?P<q_id>["\']).+?(?P=q_id)\s+)?
+                        value=(?P<q_value>["\'])(?P<value>.*?)(?P=q_value)
+                ''', html)
+        ])
+
+    def _form_hidden_inputs(self, form_id, html):
+        form = self._search_regex(
+            r'(?s)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
+            html, '%s form' % form_id, group='form')
+        return self._hidden_inputs(form)
+
     def _sort_formats(self, formats, field_preference=None):
         if not formats:
             raise ExtractorError('No video formats found')
     def _sort_formats(self, formats, field_preference=None):
         if not formats:
             raise ExtractorError('No video formats found')
@@ -815,10 +836,14 @@ class InfoExtractor(object):
         self.to_screen(msg)
         time.sleep(timeout)
 
         self.to_screen(msg)
         time.sleep(timeout)
 
-    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
+    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
+                             transform_source=lambda s: fix_xml_ampersands(s).strip()):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
-            'Unable to download f4m manifest')
+            'Unable to download f4m manifest',
+            # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
+            # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
+            transform_source=transform_source)
 
         formats = []
         manifest_version = '1.0'
 
         formats = []
         manifest_version = '1.0'
@@ -828,8 +853,19 @@ class InfoExtractor(object):
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
-                manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' +
-                                (media_el.attrib.get('href') or media_el.attrib.get('url')))
+                media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
+                if not media_url:
+                    continue
+                manifest_url = (
+                    media_url if media_url.startswith('http://') or media_url.startswith('https://')
+                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
+                # If media_url is itself a f4m manifest do the recursive extraction
+                # since bitrates in parent manifest (this one) and media_url manifest
+                # may differ leading to inability to resolve the format by requested
+                # bitrate in f4m downloader
+                if determine_ext(manifest_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(manifest_url, video_id, preference, f4m_id))
+                    continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
                 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
                 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
@@ -846,7 +882,8 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None,
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None,
-                              m3u8_id=None):
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True):
 
         formats = [{
             'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
 
         formats = [{
             'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
@@ -865,8 +902,11 @@ class InfoExtractor(object):
 
         m3u8_doc = self._download_webpage(
             m3u8_url, video_id,
 
         m3u8_doc = self._download_webpage(
             m3u8_url, video_id,
-            note='Downloading m3u8 information',
-            errnote='Failed to download m3u8 information')
+            note=note or 'Downloading m3u8 information',
+            errnote=errnote or 'Failed to download m3u8 information',
+            fatal=fatal)
+        if m3u8_doc is False:
+            return m3u8_doc
         last_info = None
         last_media = None
         kv_rex = re.compile(
         last_info = None
         last_media = None
         kv_rex = re.compile(
@@ -956,7 +996,7 @@ class InfoExtractor(object):
     def _parse_smil_video(self, video, video_id, base, rtmp_count):
         src = video.get('src')
         if not src:
     def _parse_smil_video(self, video, video_id, base, rtmp_count):
         src = video.get('src')
         if not src:
-            return ([], rtmp_count)
+            return [], rtmp_count
         bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
         width = int_or_none(video.get('width'))
         height = int_or_none(video.get('height'))
         bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
         width = int_or_none(video.get('width'))
         height = int_or_none(video.get('height'))
@@ -969,7 +1009,7 @@ class InfoExtractor(object):
                     proto = 'http'
         ext = video.get('ext')
         if proto == 'm3u8':
                     proto = 'http'
         ext = video.get('ext')
         if proto == 'm3u8':
-            return (self._extract_m3u8_formats(src, video_id, ext), rtmp_count)
+            return self._extract_m3u8_formats(src, video_id, ext), rtmp_count
         elif proto == 'rtmp':
             rtmp_count += 1
             streamer = video.get('streamer') or base
         elif proto == 'rtmp':
             rtmp_count += 1
             streamer = video.get('streamer') or base
index 41f0c736d98c229518bacb41fac2f35ce9b80958..d1b6d7366e847015af4581160c918d4a1ee6e11f 100644 (file)
@@ -12,6 +12,7 @@ from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
     compat_urllib_request,
 )
 from ..utils import (
@@ -27,7 +28,7 @@ from ..aes import (
 
 
 class CrunchyrollIE(InfoExtractor):
 
 
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
     _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
@@ -45,6 +46,22 @@ class CrunchyrollIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
             # rtmp
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
+        'info_dict': {
+            'id': '589804',
+            'ext': 'flv',
+            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
+            'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Danny Choo Network',
+            'upload_date': '20120213',
+        },
+        'params': {
+            # rtmp
+            'skip_download': True,
+        },
+
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -238,7 +255,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             video_upload_date = unified_strdate(video_upload_date)
         video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
 
             video_upload_date = unified_strdate(video_upload_date)
         video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
 
-        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
+        playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = compat_urllib_request.Request(playerdata_url)
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
         playerdata_req = compat_urllib_request.Request(playerdata_url)
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -251,16 +268,17 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
-            # urlencode doesn't work!
-            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
+            streamdata_req = compat_urllib_request.Request(
+                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+                % (stream_id, stream_format, stream_quality),
+                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
-            video_url = streamdata.find('./host').text
-            video_play_path = streamdata.find('./file').text
+            stream_info = streamdata.find('./{default}preload/stream_info')
+            video_url = stream_info.find('./host').text
+            video_play_path = stream_info.find('./file').text
             formats.append({
                 'url': video_url,
                 'play_path': video_play_path,
             formats.append({
                 'url': video_url,
                 'play_path': video_play_path,
index 0226f8036c81d97246c87f2308614d84202ae540..45049bf371370da6e4b64952441e76d86814fd6a 100644 (file)
@@ -6,6 +6,7 @@ from ..utils import parse_iso8601, ExtractorError
 
 
 class CtsNewsIE(InfoExtractor):
 
 
 class CtsNewsIE(InfoExtractor):
+    IE_DESC = '華視新聞'
     # https connection failed (Connection reset)
     _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{
     # https connection failed (Connection reset)
     _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{
index 70aa4333c773c39c4e3be451f8b632045ac85b51..1a41c0db181c43c9c35d24988b9fd118c248f399 100644 (file)
@@ -53,6 +53,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'uploader': 'IGN',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
                 'upload_date': '20150306',
                 'uploader': 'IGN',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
                 'upload_date': '20150306',
+                'duration': 74,
             }
         },
         # Vevo video
             }
         },
         # Vevo video
@@ -164,6 +165,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
+            'duration': info['duration']
         }
 
     def _get_subtitles(self, video_id, webpage):
         }
 
     def _get_subtitles(self, video_id, webpage):
@@ -251,3 +253,53 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': full_user,
             'entries': self._extract_entries(user),
         }
             'title': full_user,
             'entries': self._extract_entries(user),
         }
+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+    _TESTS = [{
+        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+        # Tested at FranceTvInfo_2
+        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+        'only_matching': True,
+    }, {
+        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_dmcloud_url(self, webpage):
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        if mobj:
+            return mobj.group(1)
+
+        mobj = re.search(
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            webpage)
+        if mobj:
+            return mobj.group(1)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = self._build_request(url)
+        webpage = self._download_webpage(request, video_id)
+
+        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+        video_info = self._parse_json(self._search_regex(
+            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+        # TODO: parse ios_url, which is in fact a manifest
+        video_url = video_info['mp4_url']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': video_info.get('thumbnail_url'),
+        }
index 8049779b0a31049f704bae256a3752a9a22ad789..263532cc6e66a94c79670caa5e1600444ce909da 100644 (file)
@@ -3,42 +3,47 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class DFBIE(InfoExtractor):
     IE_NAME = 'tv.dfb.de'
 
 
 class DFBIE(InfoExtractor):
     IE_NAME = 'tv.dfb.de'
-    _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://tv\.dfb\.de/video/(?P<display_id>[^/]+)/(?P<id>\d+)'
 
     _TEST = {
 
     _TEST = {
-        'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/',
+        'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/',
         # The md5 is different each time
         'info_dict': {
         # The md5 is different each time
         'info_dict': {
-            'id': '9070',
+            'id': '11633',
+            'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland',
             'ext': 'flv',
             'ext': 'flv',
-            'title': 'Highlights des Empfangs in Berlin',
-            'upload_date': '20140716',
+            'title': 'U 19-EM: Stimmen zum Spiel gegen Russland',
+            'upload_date': '20150714',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
         player_info = self._download_xml(
             'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
         player_info = self._download_xml(
             'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
-            video_id)
+            display_id)
         video_info = player_info.find('video')
 
         video_info = player_info.find('video')
 
-        f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
+        f4m_info = self._download_xml(
+            self._proto_relative_url(video_info.find('url').text.strip()), display_id)
         token_el = f4m_info.find('token')
         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
         token_el = f4m_info.find('token')
         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
+        formats = self._extract_f4m_formats(manifest_url, display_id)
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_info.find('title').text,
             'title': video_info.find('title').text,
-            'url': manifest_url,
-            'ext': 'flv',
             'thumbnail': self._og_search_thumbnail(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
-            'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]),
+            'upload_date': unified_strdate(video_info.find('time_date').text),
+            'formats': formats,
         }
         }
index d3e6675283cddcb8f6a6dfffbfbd1e1ea3da11bc..d6723ecf26ea67356b288df6e5f3bf612141b91a 100644 (file)
@@ -2,19 +2,19 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (
+    parse_duration,
     parse_iso8601,
     parse_iso8601,
-    int_or_none,
 )
 )
+from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
     _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
 
 
 class DiscoveryIE(InfoExtractor):
     _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
         'info_dict': {
         'info_dict': {
-            'id': 'mission-impossible-outtakes',
-            'ext': 'flv',
+            'id': '20769',
+            'ext': 'mp4',
             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
@@ -24,22 +24,36 @@ class DiscoveryIE(InfoExtractor):
             'timestamp': 1303099200,
             'upload_date': '20110418',
         },
             'timestamp': 1303099200,
             'upload_date': '20110418',
         },
-    }
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        }
+    }, {
+        'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
+        'info_dict': {
+            'id': 'mythbusters-the-simpsons',
+            'title': 'MythBusters: The Simpsons',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        info = self._download_json(url + '?flat=1', video_id)
 
 
-        info = self._parse_json(self._search_regex(
-            r'(?s)<script type="application/ld\+json">(.*?)</script>',
-            webpage, 'video info'), video_id)
+        video_title = info.get('playlist_title') or info.get('video_title')
 
 
-        return {
-            'id': video_id,
-            'title': info['name'],
-            'url': info['contentURL'],
-            'description': info.get('description'),
-            'thumbnail': info.get('thumbnailUrl'),
-            'timestamp': parse_iso8601(info.get('uploadDate')),
-            'duration': int_or_none(info.get('duration')),
-        }
+        entries = [{
+            'id': compat_str(video_info['id']),
+            'formats': self._extract_m3u8_formats(
+                video_info['src'], video_id, ext='mp4',
+                note='Download m3u8 information for video %d' % (idx + 1)),
+            'title': video_info['title'],
+            'description': video_info.get('description'),
+            'duration': parse_duration(video_info.get('video_length')),
+            'webpage_url': video_info.get('href'),
+            'thumbnail': video_info.get('thumbnailURL'),
+            'alt_title': video_info.get('secondary_title'),
+            'timestamp': parse_iso8601(video_info.get('publishedDate')),
+        } for idx, video_info in enumerate(info['playlist'])]
+
+        return self.playlist_result(entries, video_id, video_title)
index 479430c51072ab91e976df4d459af372c5608cdd..373b3b4b4735d8544128c48a10037eed3c570e5d 100644 (file)
@@ -9,6 +9,7 @@ from ..compat import (compat_str, compat_basestring)
 
 
 class DouyuTVIE(InfoExtractor):
 
 
 class DouyuTVIE(InfoExtractor):
+    IE_DESC = '斗鱼'
     _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://www.douyutv.com/iseven',
     _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://www.douyutv.com/iseven',
diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py
new file mode 100644 (file)
index 0000000..38e6597
--- /dev/null
@@ -0,0 +1,216 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_HTTPError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DramaFeverBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
+    _NETRC_MACHINE = 'dramafever'
+
+    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
+
+    _consumer_secret = None
+
+    def _get_consumer_secret(self):
+        mainjs = self._download_webpage(
+            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
+            None, 'Downloading main.js', fatal=False)
+        if not mainjs:
+            return self._CONSUMER_SECRET
+        return self._search_regex(
+            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
+            'consumer secret', default=self._CONSUMER_SECRET)
+
+    def _real_initialize(self):
+        self._login()
+        self._consumer_secret = self._get_consumer_secret()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'username': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if all(logout_pattern not in response
+               for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
+            error = self._html_search_regex(
+                r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+
+class DramaFeverIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+    _TEST = {
+        'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512.1',
+            'ext': 'flv',
+            'title': 'Cooking with Shin 4512.1',
+            'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1404336058,
+            'upload_date': '20140702',
+            'duration': 343,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).replace('/', '.')
+
+        try:
+            feed = self._download_json(
+                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
+                video_id, 'Downloading episode JSON')['channel']['item']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                raise ExtractorError(
+                    'Currently unavailable in your country.', expected=True)
+            raise
+
+        media_group = feed.get('media-group', {})
+
+        formats = []
+        for media_content in media_group['media-content']:
+            src = media_content.get('@attributes', {}).get('url')
+            if not src:
+                continue
+            ext = determine_ext(src)
+            if ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    src, video_id, f4m_id='hds'))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        title = media_group.get('media-title')
+        description = media_group.get('media-description')
+        duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
+        thumbnail = self._proto_relative_url(
+            media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
+        timestamp = parse_iso8601(feed.get('pubDate'), ' ')
+
+        subtitles = {}
+        for media_subtitle in media_group.get('media-subTitle', []):
+            lang = media_subtitle.get('@attributes', {}).get('lang')
+            href = media_subtitle.get('@attributes', {}).get('href')
+            if not lang or not href:
+                continue
+            subtitles[lang] = [{
+                'ext': 'ttml',
+                'url': href,
+            }]
+
+        series_id, episode_number = video_id.split('.')
+        episode_info = self._download_json(
+            # We only need a single episode info, so restricting page size to one episode
+            # and dealing with page number as with episode number
+            r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
+            % (self._consumer_secret, series_id, episode_number),
+            video_id, 'Downloading episode info JSON', fatal=False)
+        if episode_info:
+            value = episode_info.get('value')
+            if value:
+                subfile = value[0].get('subfile') or value[0].get('new_subfile')
+                if subfile and subfile != 'http://www.dramafever.com/st/':
+                    subtitles.setdefault('English', []).append({
+                        'ext': 'srt',
+                        'url': subfile,
+                    })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class DramaFeverSeriesIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever:series'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+    _TESTS = [{
+        'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512',
+            'title': 'Cooking with Shin',
+            'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'http://www.dramafever.com/drama/124/IRIS/',
+        'info_dict': {
+            'id': '124',
+            'title': 'IRIS',
+            'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
+        },
+        'playlist_count': 20,
+    }]
+
+    _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+
+        series = self._download_json(
+            'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
+            % (self._consumer_secret, series_id),
+            series_id, 'Downloading series JSON')['series'][series_id]
+
+        title = clean_html(series['name'])
+        description = clean_html(series.get('description') or series.get('description_short'))
+
+        entries = []
+        for page_num in itertools.count(1):
+            episodes = self._download_json(
+                'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
+                % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
+                series_id, 'Downloading episodes JSON page #%d' % page_num)
+            for episode in episodes.get('value', []):
+                episode_url = episode.get('episode_url')
+                if not episode_url:
+                    continue
+                entries.append(self.url_result(
+                    compat_urlparse.urljoin(url, episode_url),
+                    'DramaFever', episode.get('guid')))
+            if page_num == episodes['num_pages']:
+                break
+
+        return self.playlist_result(entries, series_id, title, description)
index 7626219baf33522958960bca0d8babe67b8a332e..8b98b013adeee32c67c769acfb88d76edff9a1f7 100644 (file)
@@ -15,7 +15,6 @@ class DRBonanzaIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
 
     _TESTS = [{
         'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
-        'md5': 'fe330252ddea607635cf2eb2c99a0af3',
         'info_dict': {
             'id': '65517',
             'ext': 'mp4',
         'info_dict': {
             'id': '65517',
             'ext': 'mp4',
@@ -26,6 +25,9 @@ class DRBonanzaIE(InfoExtractor):
             'upload_date': '20110120',
             'duration': 3664,
         },
             'upload_date': '20110120',
             'duration': 3664,
         },
+        'params': {
+            'skip_download': True,  # requires rtmp
+        },
     }, {
         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
         'md5': '6dfe039417e76795fb783c52da3de11d',
     }, {
         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
         'md5': '6dfe039417e76795fb783c52da3de11d',
@@ -93,6 +95,11 @@ class DRBonanzaIE(InfoExtractor):
                         'format_id': file['Type'].replace('Video', ''),
                         'preference': preferencemap.get(file['Type'], -10),
                     })
                         'format_id': file['Type'].replace('Video', ''),
                         'preference': preferencemap.get(file['Type'], -10),
                     })
+                    if format['url'].startswith('rtmp'):
+                        rtmp_url = format['url']
+                        format['rtmp_live'] = True  # --resume does not work
+                        if '/bonanza/' in rtmp_url:
+                            format['play_path'] = rtmp_url.split('/bonanza/')[1]
                     formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
                     formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
@@ -111,9 +118,6 @@ class DRBonanzaIE(InfoExtractor):
         description = '%s\n%s\n%s\n' % (
             info['Description'], info['Actors'], info['Colophon'])
 
         description = '%s\n%s\n%s\n' % (
             info['Description'], info['Actors'], info['Colophon'])
 
-        for f in formats:
-            f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
-            f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
         self._sort_formats(formats)
 
         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
         self._sort_formats(formats)
 
         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
index 37c5c181f799efd8ee69d850c0b6076130c64073..639f9182c5484a22f0056e25fc6aa7e56f193df5 100644 (file)
@@ -36,25 +36,24 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
+            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        like_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        dislike_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        comment_count = str_to_int(self._html_search_regex(
-            r'<span class="comments_count">([\d,\.]+)</span>',
-            webpage, 'comment count', fatal=False))
+        def extract_count(id_, name):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike')
+        comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
 
         cats_str = self._search_regex(
-            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
         categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {
         categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {
index 9cb1bf301b9ae3e327e4831bdb8a7d2437b43803..b1cd4f5d4e6fe1dbaaf6ec230aad75947887301d 100644 (file)
@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-from ..compat import (
-    compat_urllib_parse,
-)
 from .common import InfoExtractor
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 
 
 class EHowIE(InfoExtractor):
 
 
 class EHowIE(InfoExtractor):
@@ -26,7 +24,7 @@ class EHowIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
-        final_url = compat_urllib_parse.unquote(video_url)
+        final_url = compat_urllib_parse_unquote(video_url)
         uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')
 
         uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')
 
diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
deleted file mode 100644 (file)
index 4827022..0000000
+++ /dev/null
@@ -1,31 +0,0 @@
-from __future__ import unicode_literals
-
-from .tnaflix import TNAFlixIE
-
-
-class EMPFlixIE(TNAFlixIE):
-    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
-
-    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
-    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-            'md5': 'b1bc15b6412d33902d6e5952035fcabc',
-            'info_dict': {
-                'id': '33051',
-                'display_id': 'Amateur-Finger-Fuck',
-                'ext': 'mp4',
-                'title': 'Amateur Finger Fuck',
-                'description': 'Amateur solo finger fucking.',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
-            'only_matching': True,
-        }
-    ]
index 82dc27bc6ff3ed2edd3b318f3ed3d14e360ef22d..e17bb9aeac51e2e10e2b68b4391d3022af35bcd5 100644 (file)
@@ -9,7 +9,7 @@ from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_http_client,
     compat_str,
     compat_urllib_error,
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
     compat_urllib_request,
 )
 from ..utils import (
@@ -136,7 +136,7 @@ class FacebookIE(InfoExtractor):
             else:
                 raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
             else:
                 raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
-        params_raw = compat_urllib_parse.unquote(data['params'])
+        params_raw = compat_urllib_parse_unquote(data['params'])
         params = json.loads(params_raw)
         video_data = params['video_data'][0]
 
         params = json.loads(params_raw)
         video_data = params['video_data'][0]
 
index 3c39ca451a38e69a822968911e758847657380e9..cebdd0193a82eaccc673dffe9d001f766e9e31d1 100644 (file)
@@ -6,9 +6,9 @@ from .common import InfoExtractor
 
 class FazIE(InfoExtractor):
     IE_NAME = 'faz.net'
 
 class FazIE(InfoExtractor):
     IE_NAME = 'faz.net'
-    _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
         'info_dict': {
             'id': '12610585',
         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
         'info_dict': {
             'id': '12610585',
@@ -16,7 +16,22 @@ class FazIE(InfoExtractor):
             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
-    }
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/foobarblafasel-13659345.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
diff --git a/youtube_dl/extractor/fivetv.py b/youtube_dl/extractor/fivetv.py
new file mode 100644 (file)
index 0000000..13fbc4d
--- /dev/null
@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FiveTVIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    http://
+                        (?:www\.)?5-tv\.ru/
+                        (?:
+                            (?:[^/]+/)+(?P<id>\d+)|
+                            (?P<path>[^/?#]+)(?:[/?#])?
+                        )
+                    '''
+
+    _TESTS = [{
+        'url': 'http://5-tv.ru/news/96814/',
+        'md5': 'bbff554ad415ecf5416a2f48c22d9283',
+        'info_dict': {
+            'id': '96814',
+            'ext': 'mp4',
+            'title': 'Россияне выбрали имя для общенациональной платежной системы',
+            'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 180,
+        },
+    }, {
+        'url': 'http://5-tv.ru/video/1021729/',
+        'info_dict': {
+            'id': '1021729',
+            'ext': 'mp4',
+            'title': '3D принтер',
+            'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 180,
+        },
+    }, {
+        'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
+        'info_dict': {
+            'id': 'glavnoe',
+            'ext': 'mp4',
+            'title': 'Итоги недели с 8 по 14 июня 2015 года',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/films/1507502/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/programs/broadcast/508713/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/angel/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.5-tv.ru/schedule/?iframe=true&width=900&height=450',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id') or mobj.group('path')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"',
+            webpage, 'video url')
+
+        title = self._og_search_title(webpage, default=None) or self._search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        duration = int_or_none(self._og_search_property(
+            'video:duration', webpage, 'duration', default=None))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+        }
index edf555b2987520618b70bf8bd423c5fc1f60e5a9..75723c00dc9e96c018e3b6771e634ff93c293ba1 100644 (file)
@@ -6,18 +6,15 @@ import re
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlparse,
-    compat_urlparse,
-)
+from ..compat import compat_urlparse
 from ..utils import (
     clean_html,
     ExtractorError,
     int_or_none,
 from ..utils import (
     clean_html,
     ExtractorError,
     int_or_none,
-    float_or_none,
     parse_duration,
     determine_ext,
 )
     parse_duration,
     determine_ext,
 )
+from .dailymotion import DailymotionCloudIE
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -58,12 +55,12 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                     # See https://github.com/rg3/youtube-dl/issues/3963
                     # m3u8 urls work fine
                     continue
                     # See https://github.com/rg3/youtube-dl/issues/3963
                     # m3u8 urls work fine
                     continue
-                video_url_parsed = compat_urllib_parse_urlparse(video_url)
                 f4m_url = self._download_webpage(
                 f4m_url = self._download_webpage(
-                    'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
+                    'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
                     video_id, 'Downloading f4m manifest token', fatal=False)
                 if f4m_url:
                     video_id, 'Downloading f4m manifest token', fatal=False)
                 if f4m_url:
-                    formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
+                    formats.extend(self._extract_f4m_formats(
+                        f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
             elif ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
             elif video_url.startswith('rtmp'):
             elif ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
             elif video_url.startswith('rtmp'):
@@ -86,7 +83,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
             'title': info['titre'],
             'description': clean_html(info['synopsis']),
             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
             'title': info['titre'],
             'description': clean_html(info['synopsis']),
             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
-            'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
+            'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
             'timestamp': int_or_none(info['diffusion']['timestamp']),
             'formats': formats,
         }
             'timestamp': int_or_none(info['diffusion']['timestamp']),
             'formats': formats,
         }
@@ -131,12 +128,26 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
             'skip_download': 'HLS (reqires ffmpeg)'
         },
         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
             'skip_download': 'HLS (reqires ffmpeg)'
         },
         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
+    }, {
+        'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
+        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
+        'info_dict': {
+            'id': '556e03339473995ee145930c',
+            'ext': 'mp4',
+            'title': 'Les entreprises familiales : le secret de la réussite',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
+
+        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+        if dmcloud_url:
+            return self.url_result(dmcloud_url, 'DailymotionCloud')
+
         video_id, catalogue = self._search_regex(
             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
         return self._extract_video(video_id, catalogue)
         video_id, catalogue = self._search_regex(
             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
         return self._extract_video(video_id, catalogue)
@@ -145,11 +156,21 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 class FranceTVIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetv'
     IE_DESC = 'France 2, 3, 4, 5 and Ô'
 class FranceTVIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetv'
     IE_DESC = 'France 2, 3, 4, 5 and Ô'
-    _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
-        (?:
-            emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
-        |   (emissions?|jt)/(?P<key>[^/?]+)
-        )'''
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?france[2345o]\.fr/
+                                (?:
+                                    emissions/[^/]+/(?:videos|diffusions)|
+                                    emission/[^/]+|
+                                    videos|
+                                    jt
+                                )
+                            /|
+                            embed\.francetv\.fr/\?ue=
+                        )
+                        (?P<id>[^/?]+)
+                    '''
 
     _TESTS = [
         # france2
 
     _TESTS = [
         # france2
@@ -206,24 +227,46 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
         },
         # franceo
         {
         },
         # franceo
         {
-            'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
-            'md5': '52f0bfe202848b15915a2f39aaa8981b',
+            'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
+            'md5': '47d5816d3b24351cdce512ad7ab31da8',
             'info_dict': {
             'info_dict': {
-                'id': '108634970',
+                'id': '125377621',
                 'ext': 'flv',
                 'ext': 'flv',
-                'title': 'Infô Afrique',
-                'description': 'md5:ebf346da789428841bee0fd2a935ea55',
-                'upload_date': '20140915',
-                'timestamp': 1410822000,
+                'title': 'Infô soir',
+                'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
+                'upload_date': '20150718',
+                'timestamp': 1437241200,
+                'duration': 414,
+            },
+        },
+        {
+            # francetv embed
+            'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
+            'info_dict': {
+                'id': 'EV_30231',
+                'ext': 'flv',
+                'title': 'Alcaline, le concert avec Calogero',
+                'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
+                'upload_date': '20150226',
+                'timestamp': 1424989860,
+                'duration': 5400,
             },
         },
             },
         },
+        {
+            'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://www.franceo.fr/videos/125377617',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
         video_id, catalogue = self._html_search_regex(
         video_id, catalogue = self._html_search_regex(
-            r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
+            r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
             webpage, 'video ID').split('@')
         return self._extract_video(video_id, catalogue)
 
             webpage, 'video ID').split('@')
         return self._extract_video(video_id, catalogue)
 
index 2d33fa7f50d203a4522229d319467595881b138a..b3f1bafcc37ee98f1c5b89a644909f3ee0a32049 100644 (file)
@@ -5,7 +5,7 @@ import json
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urlparse,
 )
 from ..utils import (
     compat_urlparse,
 )
 from ..utils import (
@@ -75,7 +75,7 @@ class GameSpotIE(InfoExtractor):
         return {
             'id': data_video['guid'],
             'display_id': page_id,
         return {
             'id': data_video['guid'],
             'display_id': page_id,
-            'title': compat_urllib_parse.unquote(data_video['title']),
+            'title': compat_urllib_parse_unquote(data_video['title']),
             'formats': formats,
             'description': self._html_search_meta('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'description': self._html_search_meta('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
index 96ca398de7ce46599e532a5d1adb4a05ac2fb939..cd133a10c38c6d7bf081d550160bf730b456515e 100644 (file)
@@ -8,7 +8,6 @@ import re
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..compat import (
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..compat import (
-    compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_request,
     compat_urlparse,
     compat_urllib_parse_unquote,
     compat_urllib_request,
     compat_urlparse,
@@ -34,13 +33,21 @@ from .brightcove import BrightcoveIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
+from .tvc import TVCIE
 from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
 from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
+from .myvi import MyviIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .svt import SVTIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .svt import SVTIE
+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .snagfilms import SnagFilmsEmbedIE
 
 
 class GenericIE(InfoExtractor):
 
 
 class GenericIE(InfoExtractor):
@@ -291,6 +298,15 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },
+        # TVC embed
+        {
+            'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
+            'info_dict': {
+                'id': '55304',
+                'ext': 'mp4',
+                'title': 'Дошкольное воспитание',
+            },
+        },
         # SportBox embed
         {
             'url': 'http://www.vestifinance.ru/articles/25753',
         # SportBox embed
         {
             'url': 'http://www.vestifinance.ru/articles/25753',
@@ -322,6 +338,26 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },
+        # Myvi.ru embed
+        {
+            'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
+            'info_dict': {
+                'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
+                'ext': 'mp4',
+                'title': 'Ужастики, русский трейлер (2015)',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 153,
+            }
+        },
+        # XHamster embed
+        {
+            'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
+            'info_dict': {
+                'id': 'showthread',
+                'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+            },
+            'playlist_mincount': 7,
+        },
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
@@ -371,6 +407,26 @@ class GenericIE(InfoExtractor):
                 'skip_download': 'Requires rtmpdump'
             }
         },
                 'skip_download': 'Requires rtmpdump'
             }
         },
+        # francetv embed
+        {
+            'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
+            'info_dict': {
+                'id': 'EV_30231',
+                'ext': 'mp4',
+                'title': 'Alcaline, le concert avec Calogero',
+                'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
+                'upload_date': '20150226',
+                'timestamp': 1424989860,
+                'duration': 5400,
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            },
+            'expected_warnings': [
+                'Forbidden'
+            ]
+        },
         # Condé Nast embed
         {
             'url': 'http://www.wired.com/2014/04/honda-asimo/',
         # Condé Nast embed
         {
             'url': 'http://www.wired.com/2014/04/honda-asimo/',
@@ -644,6 +700,18 @@ class GenericIE(InfoExtractor):
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },
+        # Kaltura embed (different embed code)
+        {
+            'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+            'info_dict': {
+                'id': '1_a52wc67y',
+                'ext': 'flv',
+                'upload_date': '20150127',
+                'uploader_id': 'PremierMedia',
+                'timestamp': int,
+                'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+            },
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -789,6 +857,62 @@ class GenericIE(InfoExtractor):
                 # rtmpe downloads
                 'skip_download': True,
             }
                 # rtmpe downloads
                 'skip_download': True,
             }
+        },
+        # Brightcove URL in single quotes
+        {
+            'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
+            'md5': '4ae374f1f8b91c889c4b9203c8c752af',
+            'info_dict': {
+                'id': '4255764656001',
+                'ext': 'mp4',
+                'title': 'SN Presents: Russell Martin, World Citizen',
+                'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
+                'uploader': 'Rogers Sportsnet',
+            },
+        },
+        # Dailymotion Cloud video
+        {
+            'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+            'md5': '49444254273501a64675a7e68c502681',
+            'info_dict': {
+                'id': '5585de919473990de4bee11b',
+                'ext': 'mp4',
+                'title': 'Le débat',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+            }
+        },
+        # OnionStudios embed
+        {
+            'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+            'info_dict': {
+                'id': '2855',
+                'ext': 'mp4',
+                'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+                'uploader': 'ClickHole',
+                'uploader_id': 'clickhole',
+            }
+        },
+        # SnagFilms embed
+        {
+            'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
+            'info_dict': {
+                'id': '74849a00-85a9-11e1-9660-123139220831',
+                'ext': 'mp4',
+                'title': '#whilewewatch',
+            }
+        },
+        # AdobeTVVideo embed
+        {
+            'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+            'md5': '43662b577c018ad707a63766462b1e87',
+            'info_dict': {
+                'id': '2456',
+                'ext': 'mp4',
+                'title': 'New experience with Acrobat DC',
+                'description': 'New experience with Acrobat DC',
+                'duration': 248.667,
+            },
         }
     ]
 
         }
     ]
 
@@ -956,7 +1080,9 @@ class GenericIE(InfoExtractor):
             }
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             }
 
         if not self._downloader.params.get('test', False) and not is_intentional:
-            self._downloader.report_warning('Falling back on generic information extractor.')
+            force = self._downloader.params.get('force_generic_extractor', False)
+            self._downloader.report_warning(
+                '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
 
         if not full_response:
             request = compat_urllib_request.Request(url)
 
         if not full_response:
             request = compat_urllib_request.Request(url)
@@ -1008,7 +1134,7 @@ class GenericIE(InfoExtractor):
         # Sometimes embedded video player is hidden behind percent encoding
         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
         # Unescaping the whole page allows to handle those cases in a generic way
         # Sometimes embedded video player is hidden behind percent encoding
         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
         # Unescaping the whole page allows to handle those cases in a generic way
-        webpage = compat_urllib_parse.unquote(webpage)
+        webpage = compat_urllib_parse_unquote(webpage)
 
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
 
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
@@ -1061,23 +1187,20 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded rtl.nl player
         matches = re.findall(
 
         # Look for embedded rtl.nl player
         matches = re.findall(
-            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+            r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
             webpage)
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
             webpage)
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
-        # Look for embedded (iframe) Vimeo player
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
-        if mobj:
-            player_url = unescapeHTML(mobj.group('url'))
-            surl = smuggle_url(player_url, {'Referer': url})
-            return self.url_result(surl)
-        # Look for embedded (swf embed) Vimeo player
-        mobj = re.search(
-            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
-        if mobj:
-            return self.url_result(mobj.group(1))
+        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+        if vimeo_url is not None:
+            return self.url_result(vimeo_url)
+
+        vid_me_embed_url = self._search_regex(
+            r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+            webpage, 'vid.me embed', default=None)
+        if vid_me_embed_url is not None:
+            return self.url_result(vid_me_embed_url, 'Vidme')
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
@@ -1271,7 +1394,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'))
         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'))
         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
         if mobj is not None:
-            return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+            return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
 
         # Look for funnyordie embed
         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
 
         # Look for funnyordie embed
         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
@@ -1289,11 +1412,32 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
+        # Look for embedded TVC player
+        tvc_url = TVCIE._extract_url(webpage)
+        if tvc_url:
+            return self.url_result(tvc_url, 'TVC')
+
         # Look for embedded SportBox player
         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
         # Look for embedded SportBox player
         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
+        # Look for embedded PornHub player
+        pornhub_url = PornHubIE._extract_url(webpage)
+        if pornhub_url:
+            return self.url_result(pornhub_url, 'PornHub')
+
+        # Look for embedded XHamster player
+        xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
+        if xhamster_urls:
+            return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+        # Look for embedded Tvigle player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Tvigle')
+
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
@@ -1313,11 +1457,23 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
 
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
 
+        # Look for embedded francetv player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for embedded smotri.com player
         smotri_url = SmotriIE._extract_url(webpage)
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 
         # Look for embedded smotri.com player
         smotri_url = SmotriIE._extract_url(webpage)
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 
+        # Look for embedded Myvi.ru player
+        myvi_url = MyviIE._extract_url(webpage)
+        if myvi_url:
+            return self.url_result(myvi_url)
+
         # Look for embeded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
         # Look for embeded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
@@ -1397,8 +1553,8 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
-        mobj = re.search(
-            r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
+                re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 
@@ -1455,6 +1611,30 @@ class GenericIE(InfoExtractor):
         if senate_isvp_url:
             return self.url_result(senate_isvp_url, 'SenateISVP')
 
         if senate_isvp_url:
             return self.url_result(senate_isvp_url, 'SenateISVP')
 
+        # Look for Dailymotion Cloud videos
+        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+        if dmcloud_url:
+            return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+        # Look for OnionStudios embeds
+        onionstudios_url = OnionStudiosIE._extract_url(webpage)
+        if onionstudios_url:
+            return self.url_result(onionstudios_url)
+
+        # Look for SnagFilms embeds
+        snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
+        if snagfilms_url:
+            return self.url_result(snagfilms_url)
+
+        # Look for AdobeTVVideo embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))),
+                'AdobeTVVideo')
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
@@ -1534,7 +1714,7 @@ class GenericIE(InfoExtractor):
         entries = []
         for video_url in found:
             video_url = compat_urlparse.urljoin(url, video_url)
         entries = []
         for video_url in found:
             video_url = compat_urlparse.urljoin(url, video_url)
-            video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+            video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
 
             # Sometimes, jwplayer extraction will result in a YouTube URL
             if YoutubeIE.suitable(video_url):
 
             # Sometimes, jwplayer extraction will result in a YouTube URL
             if YoutubeIE.suitable(video_url):
index 397f1d42eea83b774791b6a53ce087f60a5dcca1..884700c52b90b53fdc8f581378d28611d7c36f33 100644 (file)
@@ -6,12 +6,13 @@ from ..utils import (
     int_or_none,
     float_or_none,
     qualities,
     int_or_none,
     float_or_none,
     qualities,
+    ExtractorError,
 )
 
 
 class GfycatIE(InfoExtractor):
 )
 
 
 class GfycatIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/)?(?P<id>[^/?#]+)'
+    _TESTS = [{
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
             'id': 'DeadlyDecisiveGermanpinscher',
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
             'id': 'DeadlyDecisiveGermanpinscher',
@@ -27,14 +28,33 @@ class GfycatIE(InfoExtractor):
             'categories': list,
             'age_limit': 0,
         }
             'categories': list,
             'age_limit': 0,
         }
-    }
+    }, {
+        'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
+        'info_dict': {
+            'id': 'JauntyTimelyAmazontreeboa',
+            'ext': 'mp4',
+            'title': 'JauntyTimelyAmazontreeboa',
+            'timestamp': 1411720126,
+            'upload_date': '20140926',
+            'uploader': 'anonymous',
+            'duration': 3.52,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'categories': list,
+            'age_limit': 0,
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         gfy = self._download_json(
             'http://gfycat.com/cajax/get/%s' % video_id,
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         gfy = self._download_json(
             'http://gfycat.com/cajax/get/%s' % video_id,
-            video_id, 'Downloading video info')['gfyItem']
+            video_id, 'Downloading video info')
+        if 'error' in gfy:
+            raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
+        gfy = gfy['gfyItem']
 
         title = gfy.get('title') or gfy['gfyName']
         description = gfy.get('description')
 
         title = gfy.get('title') or gfy['gfyName']
         description = gfy.get('description')
index 6147596e4c5d082d54f975b7428a400679b9dc32..f006f0cb105dc9d7b0c1f495dbcd4c840597858a 100644 (file)
@@ -78,12 +78,7 @@ class GorillaVidIE(InfoExtractor):
         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
-            value="([^"]*)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':
             countdown = int_or_none(self._search_regex(
 
         if fields['op'] == 'download1':
             countdown = int_or_none(self._search_regex(
index 63d87b74cc2d5258960fce3b0c6cd5eca48a0b11..f5aa73d18b47ff225b7e7e332051b97583ca8237 100644 (file)
@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 from .common import InfoExtractor
 
 
@@ -19,20 +17,19 @@ class HentaiStigmaIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
 
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
+            r'<h2[^>]+class="posttitle"[^>]*><a[^>]*>([^<]+)</a>',
             webpage, 'title')
         wrap_url = self._html_search_regex(
             webpage, 'title')
         wrap_url = self._html_search_regex(
-            r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
+            r'<iframe[^>]+src="([^"]+mp4)"', webpage, 'wrapper url')
         wrap_webpage = self._download_webpage(wrap_url, video_id)
 
         video_url = self._html_search_regex(
         wrap_webpage = self._download_webpage(wrap_url, video_id)
 
         video_url = self._html_search_regex(
-            r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
+            r'file\s*:\s*"([^"]+)"', wrap_webpage, 'video url')
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,
index 704d0285d3e1c2ce10e8f3929543c6c66b0fd58a..a3154cfdeccf9b4c18cf5a5b01f7944243fb1509 100644 (file)
@@ -58,11 +58,7 @@ class HostingBulkIE(InfoExtractor):
             r'<img src="([^"]+)".+?class="pic"',
             webpage, 'thumbnail', fatal=False)
 
             r'<img src="([^"]+)".+?class="pic"',
             webpage, 'thumbnail', fatal=False)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            value="([^"]*)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
 
         request = compat_urllib_request.Request(url, urlencode_postdata(fields))
         request.add_header('Content-type', 'application/x-www-form-urlencoded')
 
         request = compat_urllib_request.Request(url, urlencode_postdata(fields))
         request.add_header('Content-type', 'application/x-www-form-urlencoded')
index 3f7d6666c0810e545c0f285dcf70689806c4dac7..16677f179ecd77040e8fdc42bfb9e4095aa1774a 100644 (file)
@@ -1,8 +1,7 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from .common import InfoExtractor
+from ..utils import parse_iso8601
 
 
 class HowcastIE(InfoExtractor):
 
 
 class HowcastIE(InfoExtractor):
@@ -13,29 +12,31 @@ class HowcastIE(InfoExtractor):
         'info_dict': {
             'id': '390161',
             'ext': 'mp4',
         'info_dict': {
             'id': '390161',
             'ext': 'mp4',
-            'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.',
             'title': 'How to Tie a Square Knot Properly',
             'title': 'How to Tie a Square Knot Properly',
-        }
+            'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
+            'timestamp': 1276081287,
+            'upload_date': '20100609',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
 
 
-        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
         webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
-
-        video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
-                                       webpage, 'video URL')
-
-        video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
-                                                    webpage, 'description', fatal=False)
+        embed_code = self._search_regex(
+            r'<iframe[^>]+src="[^"]+\bembed_code=([^\b]+)\b',
+            webpage, 'ooyala embed code')
 
         return {
 
         return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % embed_code,
             'id': video_id,
             'id': video_id,
-            'url': video_url,
-            'title': self._og_search_title(webpage),
-            'description': video_description,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'timestamp': parse_iso8601(self._html_search_meta(
+                'article:published_time', webpage, 'timestamp')),
         }
         }
index e9733912132798d99be18bb935dcd3c3b190525d..663e6632a194d8ee271a0c031a921d7eed139005 100644 (file)
@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class HowStuffWorksIE(InfoExtractor):
 
 
 class HowStuffWorksIE(InfoExtractor):
-    _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm'
+    _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*(?:\d+-)?(?P<id>.+?)-video\.htm'
     _TESTS = [
         {
             'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
     _TESTS = [
         {
             'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
@@ -46,6 +46,10 @@ class HowStuffWorksIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        {
+            'url': 'http://shows.howstuffworks.com/stuff-to-blow-your-mind/optical-illusions-video.htm',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):
index f29df36b5bf6bd7e732ad84cbfd7d3eeb412f5ff..4bb574cf37df2421721b088ded37a3fc66c8c2ea 100644 (file)
@@ -46,7 +46,7 @@ class ImdbIE(InfoExtractor):
             format_info = info['videoPlayerObject']['video']
             formats.append({
                 'format_id': f_id,
             format_info = info['videoPlayerObject']['video']
             formats.append({
                 'format_id': f_id,
-                'url': format_info['url'],
+                'url': format_info['videoInfoList'][0]['videoUrl'],
             })
 
         return {
             })
 
         return {
index 0847074eeb0f0f258db079495c7f30777b2d1838..65712abc28c3cc68cab7052ab709b2c1e6500cb5 100644 (file)
@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class InaIE(InfoExtractor):
 
 
 class InaIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
     _TEST = {
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
     _TEST = {
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
index f25f43664e262b25473557c5f11dae91e697e3f6..71cfd12c56549d0be540c9daee6a2732959039de 100644 (file)
@@ -4,14 +4,15 @@ import base64
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urlparse,
 )
 
 
 class InfoQIE(InfoExtractor):
 )
 
 
 class InfoQIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
         'info_dict': {
         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
         'info_dict': {
@@ -20,7 +21,10 @@ class InfoQIE(InfoExtractor):
             'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
             'title': 'A Few of My Favorite [Python] Things',
         },
             'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
             'title': 'A Few of My Favorite [Python] Things',
         },
-    }
+    }, {
+        'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -35,14 +39,14 @@ class InfoQIE(InfoExtractor):
         # Extract video URL
         encoded_id = self._search_regex(
             r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
         # Extract video URL
         encoded_id = self._search_regex(
             r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
-        real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
+        real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
         playpath = 'mp4:' + real_id
 
         video_filename = playpath.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
         http_base = self._search_regex(
         playpath = 'mp4:' + real_id
 
         video_filename = playpath.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
         http_base = self._search_regex(
-            r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
+            r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage,
             'HTTP base URL')
 
         formats = [{
             'HTTP base URL')
 
         formats = [{
@@ -52,7 +56,7 @@ class InfoQIE(InfoExtractor):
             'play_path': playpath,
         }, {
             'format_id': 'http',
             'play_path': playpath,
         }, {
             'format_id': 'http',
-            'url': http_base + real_id,
+            'url': compat_urlparse.urljoin(url, http_base) + real_id,
         }]
         self._sort_formats(formats)
 
         }]
         self._sort_formats(formats)
 
index b107557880345157fcf66cb7e6e1b4a92b25af2e..3d78f78c46d1ad004339bc33ebcb09d1286e5092 100644 (file)
@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    limit_length,
+)
 
 
 class InstagramIE(InfoExtractor):
 
 
 class InstagramIE(InfoExtractor):
@@ -100,11 +103,13 @@ class InstagramUserIE(InfoExtractor):
                 thumbnails_el = it.get('images', {})
                 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
 
                 thumbnails_el = it.get('images', {})
                 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
 
-                title = it.get('caption', {}).get('text', it['id'])
+                # In some cases caption is null, which corresponds to None
+                # in python. As a result, it.get('caption', {}) gives None
+                title = (it.get('caption') or {}).get('text', it['id'])
 
                 entries.append({
                     'id': it['id'],
 
                 entries.append({
                     'id': it['id'],
-                    'title': title,
+                    'title': limit_length(title, 80),
                     'formats': formats,
                     'thumbnail': thumbnail,
                     'webpage_url': it.get('link'),
                     'formats': formats,
                     'thumbnail': thumbnail,
                     'webpage_url': it.get('link'),
diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py
new file mode 100644 (file)
index 0000000..afb7f4e
--- /dev/null
@@ -0,0 +1,273 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import math
+import random
+import time
+import uuid
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import ExtractorError
+
+
+class IqiyiIE(InfoExtractor):
+    IE_NAME = 'iqiyi'
+    IE_DESC = '爱奇艺'
+
+    _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'
+
+    _TESTS = [{
+        'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
+        'md5': '2cb594dc2781e6c941a110d8f358118b',
+        'info_dict': {
+            'id': '9c1fb1b99d192b21c559e5a1a2cb3c73',
+            'title': '美国德州空中惊现奇异云团 酷似UFO',
+            'ext': 'f4v',
+        }
+    }, {
+        'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
+        'info_dict': {
+            'id': 'e3f585b550a280af23c98b6cb2be19fb',
+            'title': '名侦探柯南第752集',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }],
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _FORMATS_MAP = [
+        ('1', 'h6'),
+        ('2', 'h5'),
+        ('3', 'h4'),
+        ('4', 'h3'),
+        ('5', 'h2'),
+        ('10', 'h1'),
+    ]
+
+    def construct_video_urls(self, data, video_id, _uuid):
+        def do_xor(x, y):
+            a = y % 3
+            if a == 1:
+                return x ^ 121
+            if a == 2:
+                return x ^ 72
+            return x ^ 103
+
+        def get_encode_code(l):
+            a = 0
+            b = l.split('-')
+            c = len(b)
+            s = ''
+            for i in range(c - 1, -1, -1):
+                a = do_xor(int(b[c - i - 1], 16), i)
+                s += chr(a)
+            return s[::-1]
+
+        def get_path_key(x, format_id, segment_index):
+            mg = ')(*&^flash@#$%a'
+            tm = self._download_json(
+                'http://data.video.qiyi.com/t?tn=' + str(random.random()), video_id,
+                note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
+            )['t']
+            t = str(int(math.floor(int(tm) / (600.0))))
+            return hashlib.md5((t + mg + x).encode('utf8')).hexdigest()
+
+        video_urls_dict = {}
+        for format_item in data['vp']['tkl'][0]['vs']:
+            if 0 < int(format_item['bid']) <= 10:
+                format_id = self.get_format(format_item['bid'])
+            else:
+                continue
+
+            video_urls = []
+
+            video_urls_info = format_item['fs']
+            if not format_item['fs'][0]['l'].startswith('/'):
+                t = get_encode_code(format_item['fs'][0]['l'])
+                if t.endswith('mp4'):
+                    video_urls_info = format_item['flvs']
+
+            for segment_index, segment in enumerate(video_urls_info):
+                vl = segment['l']
+                if not vl.startswith('/'):
+                    vl = get_encode_code(vl)
+                key = get_path_key(
+                    vl.split('/')[-1].split('.')[0], format_id, segment_index)
+                filesize = segment['b']
+                base_url = data['vp']['du'].split('/')
+                base_url.insert(-1, key)
+                base_url = '/'.join(base_url)
+                param = {
+                    'su': _uuid,
+                    'qyid': uuid.uuid4().hex,
+                    'client': '',
+                    'z': '',
+                    'bt': '',
+                    'ct': '',
+                    'tn': str(int(time.time()))
+                }
+                api_video_url = base_url + vl + '?' + \
+                    compat_urllib_parse.urlencode(param)
+                js = self._download_json(
+                    api_video_url, video_id,
+                    note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
+                video_url = js['l']
+                video_urls.append(
+                    (video_url, filesize))
+
+            video_urls_dict[format_id] = video_urls
+        return video_urls_dict
+
+    def get_format(self, bid):
+        matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
+        return matched_format_ids[0] if len(matched_format_ids) else None
+
+    def get_bid(self, format_id):
+        matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
+        return matched_bids[0] if len(matched_bids) else None
+
+    def get_raw_data(self, tvid, video_id, enc_key, _uuid):
+        tm = str(int(time.time()))
+        param = {
+            'key': 'fvip',
+            'src': hashlib.md5(b'youtube-dl').hexdigest(),
+            'tvId': tvid,
+            'vid': video_id,
+            'vinfo': 1,
+            'tm': tm,
+            'enc': hashlib.md5(
+                (enc_key + tm + tvid).encode('utf8')).hexdigest(),
+            'qyid': _uuid,
+            'tn': random.random(),
+            'um': 0,
+            'authkey': hashlib.md5(
+                (tm + tvid).encode('utf8')).hexdigest()
+        }
+
+        api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
+            compat_urllib_parse.urlencode(param)
+        raw_data = self._download_json(api_url, video_id)
+        return raw_data
+
+    def get_enc_key(self, swf_url, video_id):
+        enc_key = '8e29ab5666d041c3a1ea76e06dabdffb'
+        return enc_key
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(
+            url, 'temp_id', note='download video page')
+        tvid = self._search_regex(
+            r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
+        video_id = self._search_regex(
+            r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
+        swf_url = self._search_regex(
+            r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
+        _uuid = uuid.uuid4().hex
+
+        enc_key = self.get_enc_key(swf_url, video_id)
+
+        raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
+
+        if raw_data['code'] != 'A000000':
+            raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
+
+        if not raw_data['data']['vp']['tkl']:
+            raise ExtractorError('No support iQiqy VIP video')
+
+        data = raw_data['data']
+
+        title = data['vi']['vn']
+
+        # generate video_urls_dict
+        video_urls_dict = self.construct_video_urls(
+            data, video_id, _uuid)
+
+        # construct info
+        entries = []
+        for format_id in video_urls_dict:
+            video_urls = video_urls_dict[format_id]
+            for i, video_url_info in enumerate(video_urls):
+                if len(entries) < i + 1:
+                    entries.append({'formats': []})
+                entries[i]['formats'].append(
+                    {
+                        'url': video_url_info[0],
+                        'filesize': video_url_info[-1],
+                        'format_id': format_id,
+                        'preference': int(self.get_bid(format_id))
+                    }
+                )
+
+        for i in range(len(entries)):
+            self._sort_formats(entries[i]['formats'])
+            entries[i].update(
+                {
+                    'id': '%s_part%d' % (video_id, i + 1),
+                    'title': title,
+                }
+            )
+
+        if len(entries) > 1:
+            info = {
+                '_type': 'multi_video',
+                'id': video_id,
+                'title': title,
+                'entries': entries,
+            }
+        else:
+            info = entries[0]
+            info['id'] = video_id
+            info['title'] = title
+
+        return info
index 99a1361f844c15520c842cd9fffa1e5c2e9b6974..bc226fa67c064b991674a510b1eba54d40dc67e0 100644 (file)
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     determine_ext,
     float_or_none,
 from ..utils import (
     determine_ext,
     float_or_none,
@@ -30,7 +31,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'pelikzzle',
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'pelikzzle',
-                'timestamp': 1404302298,
+                'timestamp': int,
                 'upload_date': '20140702',
                 'duration': 95.395,
                 'age_limit': 0,
                 'upload_date': '20140702',
                 'duration': 95.395,
                 'age_limit': 0,
@@ -46,7 +47,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
                 'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
-                'timestamp': 1163322193,
+                'timestamp': int,
                 'upload_date': '20061112',
                 'duration': 253.666,
                 'age_limit': 0,
                 'upload_date': '20061112',
                 'duration': 253.666,
                 'age_limit': 0,
@@ -67,9 +68,9 @@ class IzleseneIE(InfoExtractor):
 
         uploader = self._html_search_regex(
             r"adduserUsername\s*=\s*'([^']+)';",
 
         uploader = self._html_search_regex(
             r"adduserUsername\s*=\s*'([^']+)';",
-            webpage, 'uploader', fatal=False, default='')
+            webpage, 'uploader', fatal=False)
         timestamp = parse_iso8601(self._html_search_meta(
         timestamp = parse_iso8601(self._html_search_meta(
-            'uploadDate', webpage, 'upload date', fatal=False))
+            'uploadDate', webpage, 'upload date'))
 
         duration = float_or_none(self._html_search_regex(
             r'"videoduration"\s*:\s*"([^"]+)"',
 
         duration = float_or_none(self._html_search_regex(
             r'"videoduration"\s*:\s*"([^"]+)"',
@@ -86,8 +87,7 @@ class IzleseneIE(InfoExtractor):
 
         # Might be empty for some videos.
         streams = self._html_search_regex(
 
         # Might be empty for some videos.
         streams = self._html_search_regex(
-            r'"qualitylevel"\s*:\s*"([^"]+)"',
-            webpage, 'streams', fatal=False, default='')
+            r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
 
         formats = []
         if streams:
 
         formats = []
         if streams:
@@ -95,15 +95,15 @@ class IzleseneIE(InfoExtractor):
                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
                 formats.append({
                     'format_id': '%sp' % quality if quality else 'sd',
                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
                 formats.append({
                     'format_id': '%sp' % quality if quality else 'sd',
-                    'url': url,
+                    'url': compat_urllib_parse_unquote(url),
                     'ext': ext,
                 })
         else:
             stream_url = self._search_regex(
                     'ext': ext,
                 })
         else:
             stream_url = self._search_regex(
-                r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
+                r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
             formats.append({
                 'format_id': 'sd',
             formats.append({
                 'format_id': 'sd',
-                'url': stream_url,
+                'url': compat_urllib_parse_unquote(stream_url),
                 'ext': ext,
             })
 
                 'ext': ext,
             })
 
index d0720ff561c16e8c0816c5ff7ab333e54c297dbc..1df084d87ae4c712d9bcfa1aac6d6367641287b5 100644 (file)
@@ -8,9 +8,9 @@ from .common import InfoExtractor
 
 
 class JeuxVideoIE(InfoExtractor):
 
 
 class JeuxVideoIE(InfoExtractor):
-    _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
+    _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
         'info_dict': {
         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
         'info_dict': {
@@ -19,7 +19,10 @@ class JeuxVideoIE(InfoExtractor):
             'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
             'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
         },
             'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
             'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
         },
-    }
+    }, {
+        'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
index e3b43ff8dbfec5e065aa069a0fb140dcfb5822c9..06daf5a89ce3ffde4d71d7dc8ceee9441840b72b 100644 (file)
@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote_plus
 from ..utils import (
     js_to_json,
 )
 from ..utils import (
     js_to_json,
 )
@@ -24,7 +24,7 @@ class KaraoketvIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         page_video_url = self._og_search_video_url(webpage, video_id)
         webpage = self._download_webpage(url, video_id)
 
         page_video_url = self._og_search_video_url(webpage, video_id)
-        config_json = compat_urllib_parse.unquote_plus(self._search_regex(
+        config_json = compat_urllib_parse_unquote_plus(self._search_regex(
             r'config=(.*)', page_video_url, 'configuration'))
 
         urls_info_json = self._download_json(
             r'config=(.*)', page_video_url, 'configuration'))
 
         urls_info_json = self._download_json(
index 7d4b57056509383fdc082a68c1650f38dc258763..1d391e69ff7e0aba1b78ae5e32792b2dca839943 100644 (file)
@@ -28,6 +28,14 @@ class KickStarterIE(InfoExtractor):
             'uploader': 'Pebble Technology',
             'title': 'Pebble iOS Notifications',
         }
             'uploader': 'Pebble Technology',
             'title': 'Pebble iOS Notifications',
         }
+    }, {
+        'url': 'https://www.kickstarter.com/projects/1420158244/power-drive-2000/widget/video.html',
+        'info_dict': {
+            'id': '1420158244',
+            'ext': 'mp4',
+            'title': 'Power Drive 2000',
+        },
+        'expected_warnings': ['OpenGraph description'],
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
@@ -48,10 +56,15 @@ class KickStarterIE(InfoExtractor):
                 'title': title,
             }
 
                 'title': title,
             }
 
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+        if thumbnail is None:
+            thumbnail = self._html_search_regex(
+                r'<img[^>]+class="[^"]+\s*poster\s*[^"]+"[^>]+src="([^"]+)"',
+                webpage, 'thumbnail image', fatal=False)
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'description': self._og_search_description(webpage),
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': thumbnail,
         }
         }
diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py
new file mode 100644 (file)
index 0000000..1077846
--- /dev/null
@@ -0,0 +1,314 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    clean_html,
+    ExtractorError,
+    remove_start,
+)
+
+
+class KuwoBaseIE(InfoExtractor):
+    _FORMATS = [
+        {'format': 'ape', 'ext': 'ape', 'preference': 100},
+        {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
+        {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
+        {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
+        {'format': 'wma', 'ext': 'wma', 'preference': 20},
+        {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
+    ]
+
+    def _get_formats(self, song_id):
+        formats = []
+        for file_format in self._FORMATS:
+            song_url = self._download_webpage(
+                'http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url' %
+                (file_format['ext'], file_format.get('br', ''), song_id),
+                song_id, note='Download %s url info' % file_format['format'],
+            )
+            if song_url.startswith('http://') or song_url.startswith('https://'):
+                formats.append({
+                    'url': song_url,
+                    'format_id': file_format['format'],
+                    'format': file_format['format'],
+                    'preference': file_format['preference'],
+                    'abr': file_format.get('abr'),
+                })
+        self._sort_formats(formats)
+        return formats
+
+
+class KuwoIE(KuwoBaseIE):
+    IE_NAME = 'kuwo:song'
+    IE_DESC = '酷我音乐'
+    _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
+    _TESTS = [{
+        'url': 'http://www.kuwo.cn/yinyue/635632/',
+        'info_dict': {
+            'id': '635632',
+            'ext': 'ape',
+            'title': '爱我别走',
+            'creator': '张震岳',
+            'upload_date': '20080122',
+            'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
+        },
+    }, {
+        'url': 'http://www.kuwo.cn/yinyue/6446136/',
+        'info_dict': {
+            'id': '6446136',
+            'ext': 'mp3',
+            'title': '心',
+            'creator': 'IU',
+            'upload_date': '20150518',
+        },
+        'params': {
+            'format': 'mp3-320'
+        },
+    }]
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, song_id, note='Download song detail info',
+            errnote='Unable to get song detail info')
+
+        song_name = self._html_search_regex(
+            r'<h1[^>]+title="([^"]+)">', webpage, 'song name')
+        singer_name = self._html_search_regex(
+            r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
+            webpage, 'singer name', fatal=False)
+        lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
+        if lrc_content == '暂无':     # indicates no lyrics
+            lrc_content = None
+
+        formats = self._get_formats(song_id)
+
+        album_id = self._html_search_regex(
+            r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
+            webpage, 'album id', fatal=False)
+
+        publish_time = None
+        if album_id is not None:
+            album_info_page = self._download_webpage(
+                'http://www.kuwo.cn/album/%s/' % album_id, song_id,
+                note='Download album detail info',
+                errnote='Unable to get album detail info')
+
+            publish_time = self._html_search_regex(
+                r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page,
+                'publish time', fatal=False)
+            if publish_time:
+                publish_time = publish_time.replace('-', '')
+
+        return {
+            'id': song_id,
+            'title': song_name,
+            'creator': singer_name,
+            'upload_date': publish_time,
+            'description': lrc_content,
+            'formats': formats,
+        }
+
+
+class KuwoAlbumIE(InfoExtractor):
+    IE_NAME = 'kuwo:album'
+    IE_DESC = '酷我音乐 - 专辑'
+    _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+    _TEST = {
+        'url': 'http://www.kuwo.cn/album/502294/',
+        'info_dict': {
+            'id': '502294',
+            'title': 'M',
+            'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
+        },
+        'playlist_count': 2,
+    }
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, album_id, note='Download album info',
+            errnote='Unable to get album info')
+
+        album_name = self._html_search_regex(
+            r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
+            'album name')
+        album_intro = remove_start(
+            clean_html(get_element_by_id('intro', webpage)),
+            '%s简介:' % album_name)
+
+        entries = [
+            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
+                webpage)
+        ]
+        return self.playlist_result(entries, album_id, album_name, album_intro)
+
+
+class KuwoChartIE(InfoExtractor):
+    IE_NAME = 'kuwo:chart'
+    IE_DESC = '酷我音乐 - 排行榜'
+    _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
+    _TEST = {
+        'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
+        'info_dict': {
+            'id': '香港中文龙虎榜',
+            'title': '香港中文龙虎榜',
+            'description': 're:\d{4}第\d{2}期',
+        },
+        'playlist_mincount': 10,
+    }
+
+    def _real_extract(self, url):
+        chart_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, chart_id, note='Download chart info',
+            errnote='Unable to get chart info')
+
+        chart_name = self._html_search_regex(
+            r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
+
+        chart_desc = self._html_search_regex(
+            r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
+
+        entries = [
+            self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
+        ]
+        return self.playlist_result(entries, chart_id, chart_name, chart_desc)
+
+
+class KuwoSingerIE(InfoExtractor):
+    IE_NAME = 'kuwo:singer'
+    IE_DESC = '酷我音乐 - 歌手'
+    _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
+        'info_dict': {
+            'id': 'bruno+mars',
+            'title': 'Bruno Mars',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
+        'info_dict': {
+            'id': 'Ali',
+            'title': 'Ali',
+        },
+        'playlist_mincount': 95,
+    }]
+
+    def _real_extract(self, url):
+        singer_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, singer_id, note='Download singer info',
+            errnote='Unable to get singer info')
+
+        singer_name = self._html_search_regex(
+            r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
+        )
+
+        entries = []
+        first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
+        for page_num in itertools.count(1):
+            webpage = self._download_webpage(
+                'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
+                singer_id, note='Download song list page #%d' % page_num,
+                errnote='Unable to get song list page #%d' % page_num)
+
+            entries.extend([
+                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+                    r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
+                    webpage)
+            ][:10 if first_page_only else None])
+
+            if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
+                break
+
+        return self.playlist_result(entries, singer_id, singer_name)
+
+
+class KuwoCategoryIE(InfoExtractor):
+    IE_NAME = 'kuwo:category'
+    IE_DESC = '酷我音乐 - 分类'
+    _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
+    _TEST = {
+        'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
+        'info_dict': {
+            'id': '86375',
+            'title': '八十年代精选',
+            'description': '这些都是属于八十年代的回忆!',
+        },
+        'playlist_count': 30,
+    }
+
+    def _real_extract(self, url):
+        category_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, category_id, note='Download category info',
+            errnote='Unable to get category info')
+
+        category_name = self._html_search_regex(
+            r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
+
+        category_desc = remove_start(
+            get_element_by_id('intro', webpage).strip(),
+            '%s简介:' % category_name)
+
+        jsonm = self._parse_json(self._html_search_regex(
+            r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
+
+        entries = [
+            self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
+            for song in jsonm['musiclist']
+        ]
+        return self.playlist_result(entries, category_id, category_name, category_desc)
+
+
+class KuwoMvIE(KuwoBaseIE):
+    IE_NAME = 'kuwo:mv'
+    IE_DESC = '酷我音乐 - MV'
+    _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+    _TEST = {
+        'url': 'http://www.kuwo.cn/mv/6480076/',
+        'info_dict': {
+            'id': '6480076',
+            'ext': 'mkv',
+            'title': '我们家MV',
+            'creator': '2PM',
+        },
+    }
+    _FORMATS = KuwoBaseIE._FORMATS + [
+        {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
+        {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
+    ]
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, song_id, note='Download mv detail info: %s' % song_id,
+            errnote='Unable to get mv detail info: %s' % song_id)
+
+        mobj = re.search(
+            r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
+            webpage)
+        if mobj:
+            song_name = mobj.group('song')
+            singer_name = mobj.group('singer')
+        else:
+            raise ExtractorError('Unable to find song or singer names')
+
+        formats = self._get_formats(song_id)
+
+        return {
+            'id': song_id,
+            'title': song_name,
+            'creator': singer_name,
+            'formats': formats,
+        }
index da896caf160f6f0a0ae49167ae546cd9da4d45fa..ba2ae80853d36ce1b9a98d109c2580bcdde65d5a 100644 (file)
@@ -19,6 +19,7 @@ from ..utils import (
 
 
 class LetvIE(InfoExtractor):
 
 
 class LetvIE(InfoExtractor):
+    IE_DESC = '乐视网'
     _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
 
     _TESTS = [{
     _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
 
     _TESTS = [{
index 42cb6e35f821256e90c8eef4f176812e3e0f42d0..f8cbca7b36afab1890b71806d6761bbe67d7d924 100644 (file)
@@ -8,6 +8,7 @@ from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
     int_or_none,
 from ..utils import (
     determine_ext,
     int_or_none,
+    remove_end,
     unified_strdate,
     ExtractorError,
 )
     unified_strdate,
     ExtractorError,
 )
@@ -39,7 +40,6 @@ class LifeNewsIE(InfoExtractor):
             'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
             'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
             'upload_date': '20150402',
             'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
             'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
             'upload_date': '20150402',
-            'uploader': 'embed.life.ru',
         }
     }, {
         'url': 'http://lifenews.ru/news/153461',
         }
     }, {
         'url': 'http://lifenews.ru/news/153461',
@@ -50,7 +50,6 @@ class LifeNewsIE(InfoExtractor):
             'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
             'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
             'upload_date': '20150505',
             'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
             'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
             'upload_date': '20150505',
-            'uploader': 'embed.life.ru',
         }
     }, {
         'url': 'http://lifenews.ru/video/13035',
         }
     }, {
         'url': 'http://lifenews.ru/video/13035',
@@ -72,20 +71,20 @@ class LifeNewsIE(InfoExtractor):
         if not videos and not iframe_link:
             raise ExtractorError('No media links available for %s' % video_id)
 
         if not videos and not iframe_link:
             raise ExtractorError('No media links available for %s' % video_id)
 
-        title = self._og_search_title(webpage)
-        TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
-        if title.endswith(TITLE_SUFFIX):
-            title = title[:-len(TITLE_SUFFIX)]
+        title = remove_end(
+            self._og_search_title(webpage),
+            ' - Первый по срочным новостям — LIFE | NEWS')
 
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
             r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
 
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
             r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
+            r'=\'commentCount\'[^>]*>\s*(\d+)\s*<',
+            webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
 
         upload_date = self._html_search_regex(
-            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
+            r'<time[^>]*datetime=\'([^\']+)\'', webpage, 'upload date', fatal=False)
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
index 35822067f908f0567e8dcb8c9c8265df4d3421c2..857edfde263196d9bf2811568cc9f9de90eed92b 100644 (file)
@@ -40,6 +40,17 @@ class LiveLeakIE(InfoExtractor):
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,
         }
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,
         }
+    }, {
+        # Covers https://github.com/rg3/youtube-dl/pull/5983
+        'url': 'http://www.liveleak.com/view?i=801_1409392012',
+        'md5': '0b3bec2d888c20728ca2ad3642f0ef15',
+        'info_dict': {
+            'id': '801_1409392012',
+            'ext': 'mp4',
+            'description': "Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.",
+            'uploader': 'bony333',
+            'title': 'Crazy Hungarian tourist films close call waterspout in Croatia'
+        }
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
@@ -85,7 +96,10 @@ class LiveLeakIE(InfoExtractor):
             'url': s['file'],
         } for i, s in enumerate(sources)]
         for i, s in enumerate(sources):
             'url': s['file'],
         } for i, s in enumerate(sources)]
         for i, s in enumerate(sources):
-            orig_url = s['file'].replace('.h264_base.mp4', '')
+            # Removing '.h264_*.mp4' gives the raw video, which is essentially
+            # the same video without the LiveLeak logo at the top (see
+            # https://github.com/rg3/youtube-dl/pull/4768)
+            orig_url = re.sub(r'\.h264_.+?\.mp4', '', s['file'])
             if s['file'] != orig_url:
                 formats.append({
                     'format_id': 'original-%s' % i,
             if s['file'] != orig_url:
                 formats.append({
                     'format_id': 'original-%s' % i,
index cfd3b14f4bfd755a7600701e86900ece12b0c3ac..a00f6e5e5eb1d398ef0776d8b20dcb1dd51ec082 100644 (file)
@@ -30,13 +30,13 @@ class LyndaBaseIE(InfoExtractor):
             return
 
         login_form = {
             return
 
         login_form = {
-            'username': username,
-            'password': password,
+            'username': username.encode('utf-8'),
+            'password': password.encode('utf-8'),
             'remember': 'false',
             'stayPut': 'false'
         }
         request = compat_urllib_request.Request(
             'remember': 'false',
             'stayPut': 'false'
         }
         request = compat_urllib_request.Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
@@ -65,7 +65,7 @@ class LyndaBaseIE(InfoExtractor):
                     'stayPut': 'false',
                 }
                 request = compat_urllib_request.Request(
                     'stayPut': 'false',
                 }
                 request = compat_urllib_request.Request(
-                    self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form))
+                    self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8'))
                 login_page = self._download_webpage(
                     request, None,
                     'Confirming log in and log out from another device')
                 login_page = self._download_webpage(
                     request, None,
                     'Confirming log in and log out from another device')
index 0b85a59d1c644d7d04e573aae0bdd03ebd4f6c80..92511a671ae300287fe6eb57b91b9c708dba45c5 100644 (file)
@@ -2,9 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class MalemotionIE(InfoExtractor):
 
 
 class MalemotionIE(InfoExtractor):
@@ -24,7 +22,7 @@ class MalemotionIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        video_url = compat_urllib_parse.unquote(self._search_regex(
+        video_url = compat_urllib_parse_unquote(self._search_regex(
             r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)</title', webpage, 'title')
             r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)</title', webpage, 'title')
index 8bc333b0277e27e6fd8f3d4f11b3c9c7eabdd7d7..6e2e73a5162f10ea5818b636da579c932b4f2e7d 100644 (file)
@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
     compat_urllib_request,
 )
 from ..utils import (
@@ -155,7 +156,7 @@ class MetacafeIE(InfoExtractor):
         video_url = None
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
         video_url = None
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
-            mediaURL = compat_urllib_parse.unquote(mobj.group(1))
+            mediaURL = compat_urllib_parse_unquote(mobj.group(1))
             video_ext = mediaURL[-3:]
 
             # Extract gdaKey if available
             video_ext = mediaURL[-3:]
 
             # Extract gdaKey if available
index 7091f3335e8223ea0a089ba7cff127a983b12d7d..852d722664a3d63aafed0f8246949335b4150c09 100644 (file)
@@ -5,6 +5,7 @@ import json
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urlparse,
 )
 from ..utils import (
     compat_urlparse,
 )
 from ..utils import (
@@ -48,7 +49,7 @@ class MiTeleIE(InfoExtractor):
             domain = 'http://' + domain
         info_url = compat_urlparse.urljoin(
             domain,
             domain = 'http://' + domain
         info_url = compat_urlparse.urljoin(
             domain,
-            compat_urllib_parse.unquote(embed_data['flashvars']['host'])
+            compat_urllib_parse_unquote(embed_data['flashvars']['host'])
         )
         info_el = self._download_xml(info_url, episode).find('./video/info')
 
         )
         info_el = self._download_xml(info_url, episode).find('./video/info')
 
index 425a4ccf16fff96b1bface874748b93762d2194b..d47aecedae388829babaed8642611c5a6b7d29fe 100644 (file)
@@ -3,9 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     ExtractorError,
     HEADRequest,
 from ..utils import (
     ExtractorError,
     HEADRequest,
@@ -60,7 +58,7 @@ class MixcloudIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
-        track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
+        track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
 
         webpage = self._download_webpage(url, track_id)
 
 
         webpage = self._download_webpage(url, track_id)
 
index 2cec12d35ec1797dd7612ad49c5739e87f77e6c9..9bf99a54a98c4838c2b878db3ec165c867602110 100644 (file)
@@ -5,9 +5,9 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
-    compat_urllib_parse,
 )
 
 
 )
 
 
@@ -34,7 +34,7 @@ class MofosexIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
         webpage = self._download_webpage(req, video_id)
 
         video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
+        video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]
index 5b9b9fbcd0844897d6d63305ed00729e70c7f4fb..4557a2b13b3e47a75242ebd4a5c095bf17cbaacf 100644 (file)
@@ -35,7 +35,8 @@ class MySpassIE(InfoExtractor):
 
         # get metadata
         metadata_url = META_DATA_URL_TEMPLATE % video_id
 
         # get metadata
         metadata_url = META_DATA_URL_TEMPLATE % video_id
-        metadata = self._download_xml(metadata_url, video_id)
+        metadata = self._download_xml(
+            metadata_url, video_id, transform_source=lambda s: s.strip())
 
         # extract values from metadata
         url_flv_el = metadata.find('url_flv')
 
         # extract values from metadata
         url_flv_el = metadata.find('url_flv')
diff --git a/youtube_dl/extractor/myvi.py b/youtube_dl/extractor/myvi.py
new file mode 100644 (file)
index 0000000..4c65be1
--- /dev/null
@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .vimple import SprutoBaseIE
+
+
+class MyviIE(SprutoBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        myvi\.(?:ru/player|tv)/
+                            (?:
+                                (?:
+                                    embed/html|
+                                    flash|
+                                    api/Video/Get
+                                )/|
+                                content/preloader\.swf\?.*\bid=
+                            )
+                            (?P<id>[\da-zA-Z_-]+)
+                    '''
+    _TESTS = [{
+        'url': 'http://myvi.ru/player/embed/html/oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wObeRTZaCATzucDQIDph8hQU0',
+        'md5': '571bbdfba9f9ed229dc6d34cc0f335bf',
+        'info_dict': {
+            'id': 'f16b2bbd-cde8-481c-a981-7cd48605df43',
+            'ext': 'mp4',
+            'title': 'хозяин жизни',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 25,
+        },
+    }, {
+        'url': 'http://myvi.ru/player/content/preloader.swf?id=oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wOYf1WFpPfc_bWTKGVf_Zafr0',
+        'only_matching': True,
+    }, {
+        'url': 'http://myvi.ru/player/api/Video/Get/oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wObeRTZaCATzucDQIDph8hQU0',
+        'only_matching': True,
+    }, {
+        'url': 'http://myvi.tv/embed/html/oTGTNWdyz4Zwy_u1nraolwZ1odenTd9WkTnRfIL9y8VOgHYqOHApE575x4_xxS9Vn0?ap=0',
+        'only_matching': True,
+    }, {
+        'url': 'http://myvi.ru/player/flash/ocp2qZrHI-eZnHKQBK4cZV60hslH8LALnk0uBfKsB-Q4WnY26SeGoYPi8HWHxu0O30',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//myvi\.(?:ru/player|tv)/(?:embed/html|flash)/[^"]+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        spruto = self._download_json(
+            'http://myvi.ru/player/api/Video/Get/%s?sig' % video_id, video_id)['sprutoData']
+
+        return self._extract_spruto(spruto, video_id)
index 5e754fcffb6403cbd359b9b358ad3879ef279f53..c96f472a39e569c7dfb88682d36fad9ed6ce2c10 100644 (file)
@@ -10,6 +10,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_ord,
     compat_urllib_parse,
 from ..compat import (
     compat_ord,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
     compat_urllib_request,
 )
 from ..utils import (
@@ -107,7 +108,7 @@ class MyVideoIE(InfoExtractor):
             if not a == '_encxml':
                 params[a] = b
             else:
             if not a == '_encxml':
                 params[a] = b
             else:
-                encxml = compat_urllib_parse.unquote(b)
+                encxml = compat_urllib_parse_unquote(b)
         if not params.get('domain'):
             params['domain'] = 'www.myvideo.de'
         xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
         if not params.get('domain'):
             params['domain'] = 'www.myvideo.de'
         xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
@@ -135,7 +136,7 @@ class MyVideoIE(InfoExtractor):
         video_url = None
         mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
         if mobj:
         video_url = None
         mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
         if mobj:
-            video_url = compat_urllib_parse.unquote(mobj.group(1))
+            video_url = compat_urllib_parse_unquote(mobj.group(1))
             if 'myvideo2flash' in video_url:
                 self.report_warning(
                     'Rewriting URL to use unencrypted rtmp:// ...',
             if 'myvideo2flash' in video_url:
                 self.report_warning(
                     'Rewriting URL to use unencrypted rtmp:// ...',
@@ -147,10 +148,10 @@ class MyVideoIE(InfoExtractor):
             mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
             if mobj is None:
                 raise ExtractorError('unable to extract url')
             mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
             if mobj is None:
                 raise ExtractorError('unable to extract url')
-            video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
+            video_url = compat_urllib_parse_unquote(mobj.group(1)) + compat_urllib_parse_unquote(mobj.group(2))
 
         video_file = self._search_regex('source=\'(.*?)\'', dec_data, 'video file')
 
         video_file = self._search_regex('source=\'(.*?)\'', dec_data, 'video file')
-        video_file = compat_urllib_parse.unquote(video_file)
+        video_file = compat_urllib_parse_unquote(video_file)
 
         if not video_file.endswith('f4m'):
             ppath, prefix = video_file.split('.')
 
         if not video_file.endswith('f4m'):
             ppath, prefix = video_file.split('.')
@@ -159,7 +160,7 @@ class MyVideoIE(InfoExtractor):
             video_playpath = ''
 
         video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
             video_playpath = ''
 
         video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
-        video_swfobj = compat_urllib_parse.unquote(video_swfobj)
+        video_swfobj = compat_urllib_parse_unquote(video_swfobj)
 
         video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
                                               webpage, 'title')
 
         video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
                                               webpage, 'title')
index c18640c5a9f0093344475ad649643705522cddb9..f793b72f5c4398901d2c5faf8e2f283baef94cfc 100644 (file)
@@ -25,8 +25,11 @@ class NationalGeographicIE(InfoExtractor):
         name = url_basename(url)
 
         webpage = self._download_webpage(url, name)
         name = url_basename(url)
 
         webpage = self._download_webpage(url, name)
-        feed_url = self._search_regex(r'data-feed-url="([^"]+)"', webpage, 'feed url')
-        guid = self._search_regex(r'data-video-guid="([^"]+)"', webpage, 'guid')
+        feed_url = self._search_regex(
+            r'data-feed-url="([^"]+)"', webpage, 'feed url')
+        guid = self._search_regex(
+            r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
+            webpage, 'guid')
 
         feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name)
         content = feed.find('.//{http://search.yahoo.com/mrss/}content')
 
         feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name)
         content = feed.find('.//{http://search.yahoo.com/mrss/}content')
diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py
new file mode 100644 (file)
index 0000000..a8e0a64
--- /dev/null
@@ -0,0 +1,459 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from hashlib import md5
+from base64 import b64encode
+from datetime import datetime
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_request,
+    compat_urllib_parse,
+    compat_str,
+    compat_itertools_count,
+)
+
+
+class NetEaseMusicBaseIE(InfoExtractor):
+    _FORMATS = ['bMusic', 'mMusic', 'hMusic']
+    _NETEASE_SALT = '3go8&$8*3*3h0k(2)2'
+    _API_BASE = 'http://music.163.com/api/'
+
+    @classmethod
+    def _encrypt(cls, dfsid):
+        salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
+        string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
+        salt_len = len(salt_bytes)
+        for i in range(len(string_bytes)):
+            string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
+        m = md5()
+        m.update(bytes(string_bytes))
+        result = b64encode(m.digest()).decode('ascii')
+        return result.replace('/', '_').replace('+', '-')
+
+    @classmethod
+    def extract_formats(cls, info):
+        formats = []
+        for song_format in cls._FORMATS:
+            details = info.get(song_format)
+            if not details:
+                continue
+            formats.append({
+                'url': 'http://m1.music.126.net/%s/%s.%s' %
+                       (cls._encrypt(details['dfsId']), details['dfsId'],
+                        details['extension']),
+                'ext': details.get('extension'),
+                'abr': details.get('bitrate', 0) / 1000,
+                'format_id': song_format,
+                'filesize': details.get('size'),
+                'asr': details.get('sr')
+            })
+        return formats
+
+    @classmethod
+    def convert_milliseconds(cls, ms):
+        return int(round(ms / 1000.0))
+
+    def query_api(self, endpoint, video_id, note):
+        req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint))
+        req.add_header('Referer', self._API_BASE)
+        return self._download_json(req, video_id, note)
+
+
+class NetEaseMusicIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:song'
+    IE_DESC = '网易云音乐'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://music.163.com/#/song?id=32102397',
+        'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
+        'info_dict': {
+            'id': '32102397',
+            'ext': 'mp3',
+            'title': 'Bad Blood (feat. Kendrick Lamar)',
+            'creator': 'Taylor Swift / Kendrick Lamar',
+            'upload_date': '20150517',
+            'timestamp': 1431878400,
+            'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
+        },
+    }, {
+        'note': 'No lyrics translation.',
+        'url': 'http://music.163.com/#/song?id=29822014',
+        'info_dict': {
+            'id': '29822014',
+            'ext': 'mp3',
+            'title': '听见下雨的声音',
+            'creator': '周杰伦',
+            'upload_date': '20141225',
+            'timestamp': 1419523200,
+            'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
+        },
+    }, {
+        'note': 'No lyrics.',
+        'url': 'http://music.163.com/song?id=17241424',
+        'info_dict': {
+            'id': '17241424',
+            'ext': 'mp3',
+            'title': 'Opus 28',
+            'creator': 'Dustin O\'Halloran',
+            'upload_date': '20080211',
+            'timestamp': 1202745600,
+        },
+    }, {
+        'note': 'Has translated name.',
+        'url': 'http://music.163.com/#/song?id=22735043',
+        'info_dict': {
+            'id': '22735043',
+            'ext': 'mp3',
+            'title': '소원을 말해봐 (Genie)',
+            'creator': '少女时代',
+            'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184',
+            'upload_date': '20100127',
+            'timestamp': 1264608000,
+            'alt_title': '说出愿望吧(Genie)',
+        }
+    }]
+
+    def _process_lyrics(self, lyrics_info):
+        original = lyrics_info.get('lrc', {}).get('lyric')
+        translated = lyrics_info.get('tlyric', {}).get('lyric')
+
+        if not translated:
+            return original
+
+        lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
+        original_ts_texts = re.findall(lyrics_expr, original)
+        translation_ts_dict = dict(
+            (time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated)
+        )
+        lyrics = '\n'.join([
+            '%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, ''))
+            for time_stamp, text in original_ts_texts
+        ])
+        return lyrics
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+
+        params = {
+            'id': song_id,
+            'ids': '[%s]' % song_id
+        }
+        info = self.query_api(
+            'song/detail?' + compat_urllib_parse.urlencode(params),
+            song_id, 'Downloading song info')['songs'][0]
+
+        formats = self.extract_formats(info)
+        self._sort_formats(formats)
+
+        lyrics_info = self.query_api(
+            'song/lyric?id=%s&lv=-1&tv=-1' % song_id,
+            song_id, 'Downloading lyrics data')
+        lyrics = self._process_lyrics(lyrics_info)
+
+        alt_title = None
+        if info.get('transNames'):
+            alt_title = '/'.join(info.get('transNames'))
+
+        return {
+            'id': song_id,
+            'title': info['name'],
+            'alt_title': alt_title,
+            'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]),
+            'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')),
+            'thumbnail': info.get('album', {}).get('picUrl'),
+            'duration': self.convert_milliseconds(info.get('duration', 0)),
+            'description': lyrics,
+            'formats': formats,
+        }
+
+
+class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:album'
+    IE_DESC = '网易云音乐 - 专辑'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://music.163.com/#/album?id=220780',
+        'info_dict': {
+            'id': '220780',
+            'title': 'B\'day',
+        },
+        'playlist_count': 23,
+    }
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+
+        info = self.query_api(
+            'album/%s?id=%s' % (album_id, album_id),
+            album_id, 'Downloading album data')['album']
+
+        name = info['name']
+        desc = info.get('description')
+        entries = [
+            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+                            'NetEaseMusic', song['id'])
+            for song in info['songs']
+        ]
+        return self.playlist_result(entries, album_id, name, desc)
+
+
+class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:singer'
+    IE_DESC = '网易云音乐 - 歌手'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'note': 'Singer has aliases.',
+        'url': 'http://music.163.com/#/artist?id=10559',
+        'info_dict': {
+            'id': '10559',
+            'title': '张惠妹 - aMEI;阿密特',
+        },
+        'playlist_count': 50,
+    }, {
+        'note': 'Singer has translated name.',
+        'url': 'http://music.163.com/#/artist?id=124098',
+        'info_dict': {
+            'id': '124098',
+            'title': '李昇基 - 이승기',
+        },
+        'playlist_count': 50,
+    }]
+
+    def _real_extract(self, url):
+        singer_id = self._match_id(url)
+
+        info = self.query_api(
+            'artist/%s?id=%s' % (singer_id, singer_id),
+            singer_id, 'Downloading singer data')
+
+        name = info['artist']['name']
+        if info['artist']['trans']:
+            name = '%s - %s' % (name, info['artist']['trans'])
+        if info['artist']['alias']:
+            name = '%s - %s' % (name, ';'.join(info['artist']['alias']))
+
+        entries = [
+            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+                            'NetEaseMusic', song['id'])
+            for song in info['hotSongs']
+        ]
+        return self.playlist_result(entries, singer_id, name)
+
+
+class NetEaseMusicListIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:playlist'
+    IE_DESC = '网易云音乐 - 歌单'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://music.163.com/#/playlist?id=79177352',
+        'info_dict': {
+            'id': '79177352',
+            'title': 'Billboard 2007 Top 100',
+            'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
+        },
+        'playlist_count': 99,
+    }, {
+        'note': 'Toplist/Charts sample',
+        'url': 'http://music.163.com/#/discover/toplist?id=3733003',
+        'info_dict': {
+            'id': '3733003',
+            'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
+            'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
+        },
+        'playlist_count': 50,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        info = self.query_api(
+            'playlist/detail?id=%s&lv=-1&tv=-1' % list_id,
+            list_id, 'Downloading playlist data')['result']
+
+        name = info['name']
+        desc = info.get('description')
+
+        if info.get('specialType') == 10:  # is a chart/toplist
+            datestamp = datetime.fromtimestamp(
+                self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d')
+            name = '%s %s' % (name, datestamp)
+
+        entries = [
+            self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+                            'NetEaseMusic', song['id'])
+            for song in info['tracks']
+        ]
+        return self.playlist_result(entries, list_id, name, desc)
+
+
+class NetEaseMusicMvIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:mv'
+    IE_DESC = '网易云音乐 - MV'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://music.163.com/#/mv?id=415350',
+        'info_dict': {
+            'id': '415350',
+            'ext': 'mp4',
+            'title': '이럴거면 그러지말지',
+            'description': '白雅言自作曲唱甜蜜爱情',
+            'creator': '白雅言',
+            'upload_date': '20150520',
+        },
+    }
+
+    def _real_extract(self, url):
+        mv_id = self._match_id(url)
+
+        info = self.query_api(
+            'mv/detail?id=%s&type=mp4' % mv_id,
+            mv_id, 'Downloading mv info')['data']
+
+        formats = [
+            {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)}
+            for brs, mv_url in info['brs'].items()
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': mv_id,
+            'title': info['name'],
+            'description': info.get('desc') or info.get('briefDesc'),
+            'creator': info['artistName'],
+            'upload_date': info['publishTime'].replace('-', ''),
+            'formats': formats,
+            'thumbnail': info.get('cover'),
+            'duration': self.convert_milliseconds(info.get('duration', 0)),
+        }
+
+
+class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:program'
+    IE_DESC = '网易云音乐 - 电台节目'
+    _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://music.163.com/#/program?id=10109055',
+        'info_dict': {
+            'id': '10109055',
+            'ext': 'mp3',
+            'title': '不丹足球背后的故事',
+            'description': '喜马拉雅人的足球梦 ...',
+            'creator': '大话西藏',
+            'timestamp': 1434179342,
+            'upload_date': '20150613',
+            'duration': 900,
+        },
+    }, {
+        'note': 'This program has accompanying songs.',
+        'url': 'http://music.163.com/#/program?id=10141022',
+        'info_dict': {
+            'id': '10141022',
+            'title': '25岁,你是自在如风的少年<27°C>',
+            'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
+        },
+        'playlist_count': 4,
+    }, {
+        'note': 'This program has accompanying songs.',
+        'url': 'http://music.163.com/#/program?id=10141022',
+        'info_dict': {
+            'id': '10141022',
+            'ext': 'mp3',
+            'title': '25岁,你是自在如风的少年<27°C>',
+            'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
+            'timestamp': 1434450841,
+            'upload_date': '20150616',
+        },
+        'params': {
+            'noplaylist': True
+        }
+    }]
+
+    def _real_extract(self, url):
+        program_id = self._match_id(url)
+
+        info = self.query_api(
+            'dj/program/detail?id=%s' % program_id,
+            program_id, 'Downloading program info')['program']
+
+        name = info['name']
+        description = info['description']
+
+        if not info['songs'] or self._downloader.params.get('noplaylist'):
+            if info['songs']:
+                self.to_screen(
+                    'Downloading just the main audio %s because of --no-playlist'
+                    % info['mainSong']['id'])
+
+            formats = self.extract_formats(info['mainSong'])
+            self._sort_formats(formats)
+
+            return {
+                'id': program_id,
+                'title': name,
+                'description': description,
+                'creator': info['dj']['brand'],
+                'timestamp': self.convert_milliseconds(info['createTime']),
+                'thumbnail': info['coverUrl'],
+                'duration': self.convert_milliseconds(info.get('duration', 0)),
+                'formats': formats,
+            }
+
+        self.to_screen(
+            'Downloading playlist %s - add --no-playlist to just download the main audio %s'
+            % (program_id, info['mainSong']['id']))
+
+        song_ids = [info['mainSong']['id']]
+        song_ids.extend([song['id'] for song in info['songs']])
+        entries = [
+            self.url_result('http://music.163.com/#/song?id=%s' % song_id,
+                            'NetEaseMusic', song_id)
+            for song_id in song_ids
+        ]
+        return self.playlist_result(entries, program_id, name, description)
+
+
+class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
+    IE_NAME = 'netease:djradio'
+    IE_DESC = '网易云音乐 - 电台'
+    _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://music.163.com/#/djradio?id=42',
+        'info_dict': {
+            'id': '42',
+            'title': '声音蔓延',
+            'description': 'md5:766220985cbd16fdd552f64c578a6b15'
+        },
+        'playlist_mincount': 40,
+    }
+    _PAGE_SIZE = 1000
+
+    def _real_extract(self, url):
+        dj_id = self._match_id(url)
+
+        name = None
+        desc = None
+        entries = []
+        for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
+            info = self.query_api(
+                'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
+                % (self._PAGE_SIZE, dj_id, offset),
+                dj_id, 'Downloading dj programs - %d' % offset)
+
+            entries.extend([
+                self.url_result(
+                    'http://music.163.com/#/program?id=%s' % program['id'],
+                    'NetEaseMusicProgram', program['id'])
+                for program in info['programs']
+            ])
+
+            if name is None:
+                radio = info['programs'][0]['radio']
+                name = radio['name']
+                desc = radio['desc']
+
+            if not info['more']:
+                break
+
+        return self.playlist_result(entries, dj_id, name, desc)
index 85fcad06b51dc9ce87bdd563043c92a126cc8eea..5a9e73cd66a1b1224bdec848722f5e9d14f65c38 100644 (file)
@@ -31,7 +31,7 @@ class NewstubeIE(InfoExtractor):
         page = self._download_webpage(url, video_id, 'Downloading page')
 
         video_guid = self._html_search_regex(
         page = self._download_webpage(url, video_id, 'Downloading page')
 
         video_guid = self._html_search_regex(
-            r'<meta property="og:video" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            r'<meta property="og:video:url" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
             page, 'video GUID')
 
         player = self._download_xml(
             page, 'video GUID')
 
         player = self._download_xml(
index d1b7cff4cfbf30c76c52ae98ad247e8907be6abd..c10784f6b7321395e69c86ab06f91f8d3b37b655 100644 (file)
@@ -6,6 +6,7 @@ from ..utils import parse_iso8601
 
 
 class NextMediaIE(InfoExtractor):
 
 
 class NextMediaIE(InfoExtractor):
+    IE_DESC = '蘋果日報'
     _VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
     _VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
@@ -66,6 +67,7 @@ class NextMediaIE(InfoExtractor):
 
 
 class NextMediaActionNewsIE(NextMediaIE):
 
 
 class NextMediaActionNewsIE(NextMediaIE):
+    IE_DESC = '蘋果日報 - 動新聞'
     _VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
     _TESTS = [{
         'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
     _VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
     _TESTS = [{
         'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
@@ -90,6 +92,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 
 class AppleDailyIE(NextMediaIE):
 
 
 class AppleDailyIE(NextMediaIE):
+    IE_DESC = '臺灣蘋果日報'
     _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
     _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
index 2684dd250aa65e22903612f4a1780fc8f701296a..dc54634a58e440fc70ae9bcb3e7d5781981b2b1e 100644 (file)
@@ -19,7 +19,7 @@ class NFLIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
         (?:.+?/)*
     _VALID_URL = r'''(?x)https?://
         (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
         (?:.+?/)*
-        (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
+        (?P<id>(?:[a-z0-9]{16}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
     _TESTS = [
         {
             'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
     _TESTS = [
         {
             'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
@@ -58,6 +58,10 @@ class NFLIE(InfoExtractor):
                 'upload_date': '20150202',
             },
         },
                 'upload_date': '20150202',
             },
         },
+        {
+            'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
+            'only_matching': True,
+        }
     ]
 
     @staticmethod
     ]
 
     @staticmethod
index 3cecebf95a4acd0a388da5984aebc2822e79b32c..0f8aa5adad5b2247621ce00249f3bd03a33a104a 100644 (file)
@@ -182,7 +182,6 @@ class NiconicoIE(InfoExtractor):
         extension = xpath_text(video_info, './/movie_type')
         if not extension:
             extension = determine_ext(video_real_url)
         extension = xpath_text(video_info, './/movie_type')
         if not extension:
             extension = determine_ext(video_real_url)
-        video_format = extension.upper()
 
         thumbnail = (
             xpath_text(video_info, './/thumbnail_url') or
 
         thumbnail = (
             xpath_text(video_info, './/thumbnail_url') or
@@ -241,7 +240,7 @@ class NiconicoIE(InfoExtractor):
             'url': video_real_url,
             'title': title,
             'ext': extension,
             'url': video_real_url,
             'title': title,
             'ext': extension,
-            'format': video_format,
+            'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
             'thumbnail': thumbnail,
             'description': description,
             'uploader': uploader,
             'thumbnail': thumbnail,
             'description': description,
             'uploader': uploader,
index 664dc81d47ce7af613636022f4e540dffd67f8b6..a53e27b274eaa21ac15a1dc5077001d520832696 100644 (file)
@@ -166,6 +166,10 @@ class NocoIE(InfoExtractor):
         self._sort_formats(formats)
 
         timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
         self._sort_formats(formats)
 
         timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
+
+        if timestamp is not None and timestamp < 0:
+            timestamp = None
+
         uploader = show.get('partner_name')
         uploader_id = show.get('partner_key')
         duration = float_or_none(show.get('duration_ms'), 1000)
         uploader = show.get('partner_name')
         uploader_id = show.get('partner_key')
         duration = float_or_none(show.get('duration_ms'), 1000)
@@ -191,7 +195,7 @@ class NocoIE(InfoExtractor):
         if episode_number:
             title += ' #' + compat_str(episode_number)
         if episode:
         if episode_number:
             title += ' #' + compat_str(episode_number)
         if episode:
-            title += ' - ' + episode
+            title += ' - ' + compat_str(episode)
 
         description = show.get('show_resume') or show.get('family_resume')
 
 
         description = show.get('show_resume') or show.get('family_resume')
 
index 173e46cd8b78dfa0dcdf33b6d3c280bf40a70681..0b5ff47600559e50a2282b184b23d3fc7263d46d 100644 (file)
@@ -133,7 +133,7 @@ class NowTVIE(InfoExtractor):
         station = mobj.group('station')
 
         info = self._download_json(
         station = mobj.group('station')
 
         info = self._download_json(
-            'https://api.nowtv.de/v3/movies/%s?fields=*,format,files' % display_id,
+            'https://api.nowtv.de/v3/movies/%s?fields=id,title,free,geoblocked,articleLong,articleShort,broadcastStartDate,seoUrl,duration,format,files' % display_id,
             display_id)
 
         video_id = compat_str(info['id'])
             display_id)
 
         video_id = compat_str(info['id'])
index 5d84485714b9f360d47c8676710e9c3e6d9578c7..0c2d02c108ed425cf4688c34aa2a826ddaa400b4 100644 (file)
@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     fix_xml_ampersands,
 from .common import InfoExtractor
 from ..utils import (
     fix_xml_ampersands,
@@ -7,7 +9,6 @@ from ..utils import (
     qualities,
     strip_jsonp,
     unified_strdate,
     qualities,
     strip_jsonp,
     unified_strdate,
-    url_basename,
 )
 
 
 )
 
 
@@ -16,13 +17,42 @@ class NPOBaseIE(InfoExtractor):
         token_page = self._download_webpage(
             'http://ida.omroep.nl/npoplayer/i.js',
             video_id, note='Downloading token')
         token_page = self._download_webpage(
             'http://ida.omroep.nl/npoplayer/i.js',
             video_id, note='Downloading token')
-        return self._search_regex(
+        token = self._search_regex(
             r'npoplayer\.token = "(.+?)"', token_page, 'token')
             r'npoplayer\.token = "(.+?)"', token_page, 'token')
+        # Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
+        token_l = list(token)
+        first = second = None
+        for i in range(5, len(token_l) - 4):
+            if token_l[i].isdigit():
+                if first is None:
+                    first = i
+                elif second is None:
+                    second = i
+        if first is None or second is None:
+            first = 12
+            second = 13
+
+        token_l[first], token_l[second] = token_l[second], token_l[first]
+
+        return ''.join(token_l)
 
 
 class NPOIE(NPOBaseIE):
 
 
 class NPOIE(NPOBaseIE):
-    IE_NAME = 'npo.nl'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/(?!live|radio)[^/]+/[^/]+/(?P<id>[^/?]+)'
+    IE_NAME = 'npo'
+    IE_DESC = 'npo.nl and ntr.nl'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        npo:|
+                        https?://
+                            (?:www\.)?
+                            (?:
+                                npo\.nl/(?!live|radio)(?:[^/]+/){2}|
+                                ntr\.nl/(?:[^/]+/){2,}|
+                                omroepwnl\.nl/video/fragment/[^/]+__
+                            )
+                        )
+                        (?P<id>[^/?#]+)
+                '''
 
     _TESTS = [
         {
 
     _TESTS = [
         {
@@ -42,7 +72,7 @@ class NPOIE(NPOBaseIE):
             'info_dict': {
                 'id': 'VARA_101191800',
                 'ext': 'm4v',
             'info_dict': {
                 'id': 'VARA_101191800',
                 'ext': 'm4v',
-                'title': 'De Mega Mike & Mega Thomas show',
+                'title': 'De Mega Mike & Mega Thomas show: The best of.',
                 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
                 'upload_date': '20090227',
                 'duration': 2400,
                 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
                 'upload_date': '20090227',
                 'duration': 2400,
@@ -54,8 +84,8 @@ class NPOIE(NPOBaseIE):
             'info_dict': {
                 'id': 'VPWON_1169289',
                 'ext': 'm4v',
             'info_dict': {
                 'id': 'VPWON_1169289',
                 'ext': 'm4v',
-                'title': 'Tegenlicht',
-                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+                'title': 'Tegenlicht: De toekomst komt uit Afrika',
+                'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
                 'upload_date': '20130225',
                 'duration': 3000,
             },
                 'upload_date': '20130225',
                 'duration': 3000,
             },
@@ -84,6 +114,30 @@ class NPOIE(NPOBaseIE):
                 'title': 'Hoe gaat Europa verder na Parijs?',
             },
         },
                 'title': 'Hoe gaat Europa verder na Parijs?',
             },
         },
+        {
+            'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
+            'md5': '01c6a2841675995da1f0cf776f03a9c3',
+            'info_dict': {
+                'id': 'VPWON_1233944',
+                'ext': 'm4v',
+                'title': 'Aap, poot, pies',
+                'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
+                'upload_date': '20150508',
+                'duration': 599,
+            },
+        },
+        {
+            'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
+            'md5': 'd30cd8417b8b9bca1fdff27428860d08',
+            'info_dict': {
+                'id': 'POW_00996502',
+                'ext': 'm4v',
+                'title': '''"Dit is wel een 'landslide'..."''',
+                'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
+                'upload_date': '20150508',
+                'duration': 462,
+            },
+        }
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):
@@ -92,12 +146,24 @@ class NPOIE(NPOBaseIE):
 
     def _get_info(self, video_id):
         metadata = self._download_json(
 
     def _get_info(self, video_id):
         metadata = self._download_json(
-            'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
+            'http://e.omroep.nl/metadata/%s' % video_id,
             video_id,
             # We have to remove the javascript callback
             transform_source=strip_jsonp,
         )
 
             video_id,
             # We have to remove the javascript callback
             transform_source=strip_jsonp,
         )
 
+        # For some videos actual video id (prid) is different (e.g. for
+        # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
+        # video id is POMS_WNL_853698 but prid is POW_00996502)
+        video_id = metadata.get('prid') or video_id
+
+        # titel is too generic in some cases so utilize aflevering_titel as well
+        # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
+        title = metadata['titel']
+        sub_title = metadata.get('aflevering_titel')
+        if sub_title and sub_title != title:
+            title += ': %s' % sub_title
+
         token = self._get_token(video_id)
 
         formats = []
         token = self._get_token(video_id)
 
         formats = []
@@ -170,8 +236,8 @@ class NPOIE(NPOBaseIE):
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,
-            'title': metadata['titel'],
-            'description': metadata['info'],
+            'title': title,
+            'description': metadata.get('info'),
             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
             'upload_date': unified_strdate(metadata.get('gidsdatum')),
             'duration': parse_duration(metadata.get('tijdsduur')),
             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
             'upload_date': unified_strdate(metadata.get('gidsdatum')),
             'duration': parse_duration(metadata.get('tijdsduur')),
@@ -340,9 +406,8 @@ class NPORadioFragmentIE(InfoExtractor):
         }
 
 
         }
 
 
-class TegenlichtVproIE(NPOIE):
-    IE_NAME = 'tegenlicht.vpro.nl'
-    _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
+class VPROIE(NPOIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
 
     _TESTS = [
         {
 
     _TESTS = [
         {
@@ -351,17 +416,72 @@ class TegenlichtVproIE(NPOIE):
             'info_dict': {
                 'id': 'VPWON_1169289',
                 'ext': 'm4v',
             'info_dict': {
                 'id': 'VPWON_1169289',
                 'ext': 'm4v',
-                'title': 'Tegenlicht',
-                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+                'title': 'De toekomst komt uit Afrika',
+                'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
                 'upload_date': '20130225',
             },
         },
                 'upload_date': '20130225',
             },
         },
+        {
+            'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
+            'info_dict': {
+                'id': 'sergio-herman',
+                'title': 'Sergio Herman: Fucking perfect',
+            },
+            'playlist_count': 2,
+        },
+        {
+            # playlist with youtube embed
+            'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
+            'info_dict': {
+                'id': 'education-education',
+                'title': '2Doc',
+            },
+            'playlist_count': 2,
+        }
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):
-        name = url_basename(url)
-        webpage = self._download_webpage(url, name)
-        urn = self._html_search_meta('mediaurn', webpage)
-        info_page = self._download_json(
-            'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
-        return self._get_info(info_page['mid'])
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
+            for video_id in re.findall(r'data-media-id="([^"]+)"', webpage)
+        ]
+
+        playlist_title = self._search_regex(
+            r'<title>\s*([^>]+?)\s*-\s*Teledoc\s*-\s*VPRO\s*</title>',
+            webpage, 'playlist title', default=None) or self._og_search_title(webpage)
+
+        return self.playlist_result(entries, playlist_id, playlist_title)
+
+
+class WNLIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
+
+    _TEST = {
+        'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
+        'info_dict': {
+            'id': 'vandaag-de-dag-6-mei',
+            'title': 'Vandaag de Dag 6 mei',
+        },
+        'playlist_count': 4,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('npo:%s' % video_id, 'NPO')
+            for video_id, part in re.findall(
+                r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>(Deel \d+)', webpage)
+        ]
+
+        playlist_title = self._html_search_regex(
+            r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>',
+            webpage, 'playlist title')
+
+        return self.playlist_result(entries, playlist_id, playlist_title)
index cc70c295014f95fcb7e74f2f009889b5ca135663..d066a96db137ee3fb2c36f712803622e73b4aa40 100644 (file)
@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class NRKIE(InfoExtractor):
 
 
 class NRKIE(InfoExtractor):
-    _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
+    _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
 
     _TESTS = [
         {
 
     _TESTS = [
         {
@@ -76,7 +76,7 @@ class NRKIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
@@ -116,11 +116,12 @@ class NRKPlaylistIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
-    _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+    IE_DESC = 'NRK TV and NRK Radio'
+    _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
     _TESTS = [
         {
 
     _TESTS = [
         {
-            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
+            'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
@@ -132,7 +133,7 @@ class NRKTVIE(InfoExtractor):
             },
         },
         {
             },
         },
         {
-            'url': 'http://tv.nrk.no/program/mdfp15000514',
+            'url': 'https://tv.nrk.no/program/mdfp15000514',
             'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
             'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
@@ -145,7 +146,7 @@ class NRKTVIE(InfoExtractor):
         },
         {
             # single playlist video
         },
         {
             # single playlist video
-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
             'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
                 'id': 'MSPO40010515-part2',
             'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
                 'id': 'MSPO40010515-part2',
@@ -157,7 +158,7 @@ class NRKTVIE(InfoExtractor):
             'skip': 'Only works from Norway',
         },
         {
             'skip': 'Only works from Norway',
         },
         {
-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
             'playlist': [
                 {
                     'md5': '9480285eff92d64f06e02a5367970a7a',
             'playlist': [
                 {
                     'md5': '9480285eff92d64f06e02a5367970a7a',
@@ -188,6 +189,10 @@ class NRKTVIE(InfoExtractor):
                 'duration': 6947.5199999999995,
             },
             'skip': 'Only works from Norway',
                 'duration': 6947.5199999999995,
             },
             'skip': 'Only works from Norway',
+        },
+        {
+            'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
+            'only_matching': True,
         }
     ]
 
         }
     ]
 
@@ -206,7 +211,8 @@ class NRKTVIE(InfoExtractor):
         ]}
 
     def _extract_f4m(self, manifest_url, video_id):
         ]}
 
     def _extract_f4m(self, manifest_url, video_id):
-        return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
+        return self._extract_f4m_formats(
+            manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -268,7 +274,7 @@ class NRKTVIE(InfoExtractor):
 
         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:
 
         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
+            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))
         self._sort_formats(formats)
 
         subtitles_url = self._html_search_regex(
         self._sort_formats(formats)
 
         subtitles_url = self._html_search_regex(
index 6c7149fe3859732978d34356f8c18aca14e74f63..215ffe87b55db126300f0c18c98d9c5bfd920ed7 100644 (file)
@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     unified_strdate,
     int_or_none,
 from ..utils import (
     unified_strdate,
     int_or_none,
@@ -62,7 +62,7 @@ class OdnoklassnikiIE(InfoExtractor):
             metadata = self._parse_json(metadata, video_id)
         else:
             metadata = self._download_json(
             metadata = self._parse_json(metadata, video_id)
         else:
             metadata = self._download_json(
-                compat_urllib_parse.unquote(flashvars['metadataUrl']),
+                compat_urllib_parse_unquote(flashvars['metadataUrl']),
                 video_id, 'Downloading metadata JSON')
 
         movie = metadata['movie']
                 video_id, 'Downloading metadata JSON')
 
         movie = metadata['movie']
diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py
new file mode 100644 (file)
index 0000000..0f1f448
--- /dev/null
@@ -0,0 +1,76 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class OnionStudiosIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+
+    _TESTS = [{
+        'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
+        'md5': 'd4851405d31adfadf71cd7a487b765bb',
+        'info_dict': {
+            'id': '2937',
+            'ext': 'mp4',
+            'title': 'Hannibal charges forward, stops for a cocktail',
+            'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'The A.V. Club',
+            'uploader_id': 'TheAVClub',
+        },
+    }, {
+        'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
+
+        formats = []
+        for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
+            if determine_ext(src) != 'm3u8':  # m3u8 always results in 403
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
+            webpage, 'title', group='title')
+        description = self._search_regex(
+            r'share_description\s*=\s*(["\'])(?P<description>[^\1]+?)\1',
+            webpage, 'description', default=None, group='description')
+        thumbnail = self._search_regex(
+            r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
+            webpage, 'thumbnail', default=False, group='thumbnail')
+
+        uploader_id = self._search_regex(
+            r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
+            webpage, 'uploader id', fatal=False, group='uploader_id')
+        uploader = self._search_regex(
+            r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
+            webpage, 'uploader', default=False, group='uploader')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }
index 2249657eb1b796970c155f4baf3445fef9b60681..d2ceedd018fe1f0237aefa17330d5dbe3d94f68c 100644 (file)
@@ -3,9 +3,9 @@ from __future__ import unicode_literals
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote_plus
 from ..utils import (
     parse_iso8601,
 from ..utils import (
     parse_iso8601,
-    compat_urllib_parse,
     parse_age_limit,
     int_or_none,
 )
     parse_age_limit,
     int_or_none,
 )
@@ -37,7 +37,7 @@ class OpenFilmIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
 
         webpage = self._download_webpage(url, display_id)
 
-        player = compat_urllib_parse.unquote_plus(
+        player = compat_urllib_parse_unquote_plus(
             self._og_search_video_url(webpage))
 
         video = json.loads(self._search_regex(
             self._og_search_video_url(webpage))
 
         video = json.loads(self._search_regex(
index 143a7669639770e0cdfddc55e0b9395893301736..fec5d65ad94892ca0f40a9e49703c857d98b47a4 100644 (file)
@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re
@@ -35,6 +36,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                 'duration': 3190,
             },
                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                 'duration': 3190,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
@@ -46,6 +50,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                 'duration': 5050,
             },
                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                 'duration': 5050,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            }
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
@@ -68,7 +75,10 @@ class PBSIE(InfoExtractor):
                 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
@@ -82,7 +92,10 @@ class PBSIE(InfoExtractor):
                 'duration': 3172,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
                 'duration': 3172,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
@@ -90,6 +103,21 @@ class PBSIE(InfoExtractor):
                 'id': 'united-states-of-secrets',
             },
             'playlist_count': 2,
                 'id': 'united-states-of-secrets',
             },
             'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
+            'info_dict': {
+                'id': '2280706814',
+                'display_id': 'player',
+                'ext': 'mp4',
+                'title': 'Death and the Civil War',
+                'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+                'duration': 6705,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         }
     ]
 
         }
     ]
 
@@ -123,7 +151,7 @@ class PBSIE(InfoExtractor):
                 return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
                 return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
-                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 
@@ -196,6 +224,14 @@ class PBSIE(InfoExtractor):
             rating_str = rating_str.rpartition('-')[2]
         age_limit = US_RATINGS.get(rating_str)
 
             rating_str = rating_str.rpartition('-')[2]
         age_limit = US_RATINGS.get(rating_str)
 
+        subtitles = {}
+        closed_captions_url = info.get('closed_captions_url')
+        if closed_captions_url:
+            subtitles['en'] = [{
+                'ext': 'ttml',
+                'url': closed_captions_url,
+            }]
+
         return {
             'id': video_id,
             'display_id': display_id,
         return {
             'id': video_id,
             'display_id': display_id,
@@ -206,4 +242,5 @@ class PBSIE(InfoExtractor):
             'age_limit': age_limit,
             'upload_date': upload_date,
             'formats': formats,
             'age_limit': age_limit,
             'upload_date': upload_date,
             'formats': formats,
+            'subtitles': subtitles,
         }
         }
index c66db3cdc84e55a6a3a904ddf3ff7c09aaac9573..788411ccc18082f59588d40704900c26dba1fe21 100644 (file)
@@ -4,7 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote
 
 
 class PhotobucketIE(InfoExtractor):
 
 
 class PhotobucketIE(InfoExtractor):
@@ -34,7 +34,7 @@ class PhotobucketIE(InfoExtractor):
         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
                                        webpage, 'info json')
         info = json.loads(info_json)
         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
                                        webpage, 'info json')
         info = json.loads(info_json)
-        url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
+        url = compat_urllib_parse_unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
         return {
             'id': video_id,
             'url': url,
         return {
             'id': video_id,
             'url': url,
diff --git a/youtube_dl/extractor/pinkbike.py b/youtube_dl/extractor/pinkbike.py
new file mode 100644 (file)
index 0000000..a52210f
--- /dev/null
@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    remove_end,
+    remove_start,
+    str_to_int,
+    unified_strdate,
+)
+
+
+class PinkbikeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?pinkbike\.com/video/|es\.pinkbike\.org/i/kvid/kvid-y5\.swf\?id=)(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.pinkbike.com/video/402811/',
+        'md5': '4814b8ca7651034cd87e3361d5c2155a',
+        'info_dict': {
+            'id': '402811',
+            'ext': 'mp4',
+            'title': 'Brandon Semenuk - RAW 100',
+            'description': 'Official release: www.redbull.ca/rupertwalker',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 100,
+            'upload_date': '20150406',
+            'uploader': 'revelco',
+            'location': 'Victoria, British Columbia, Canada',
+            'view_count': int,
+            'comment_count': int,
+        }
+    }, {
+        'url': 'http://es.pinkbike.org/i/kvid/kvid-y5.swf?id=406629',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.pinkbike.com/video/%s' % video_id, video_id)
+
+        formats = []
+        for _, format_id, src in re.findall(
+                r'data-quality=((?:\\)?["\'])(.+?)\1[^>]+src=\1(.+?)\1', webpage):
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]$', format_id, 'height', default=None))
+            formats.append({
+                'url': src,
+                'format_id': format_id,
+                'height': height,
+            })
+        self._sort_formats(formats)
+
+        title = remove_end(self._og_search_title(webpage), ' Video - Pinkbike')
+        description = self._html_search_regex(
+            r'(?s)id="media-description"[^>]*>(.+?)<',
+            webpage, 'description', default=None) or remove_start(
+            self._og_search_description(webpage), title + '. ')
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration'))
+
+        uploader = self._search_regex(
+            r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+        upload_date = unified_strdate(self._search_regex(
+            r'class="fullTime"[^>]+title="([^"]+)"',
+            webpage, 'upload date', fatal=False))
+
+        location = self._html_search_regex(
+            r'(?s)<dt>Location</dt>\s*<dd>(.+?)<',
+            webpage, 'location', fatal=False)
+
+        def extract_count(webpage, label):
+            return str_to_int(self._search_regex(
+                r'<span[^>]+class="stat-num"[^>]*>([\d,.]+)</span>\s*<span[^>]+class="stat-label"[^>]*>%s' % label,
+                webpage, label, fatal=False))
+
+        view_count = extract_count(webpage, 'Views')
+        comment_count = extract_count(webpage, 'Comments')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'location': location,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'formats': formats
+        }
index 596c621d75067255f5be6e4eaf97ba897cc51fe5..06505e96fb9ac81224f03f71299eb80238c0921f 100644 (file)
@@ -18,7 +18,8 @@ class PlanetaPlayIE(InfoExtractor):
             'id': '3586',
             'ext': 'flv',
             'title': 'md5:e829428ee28b1deed00de90de49d1da1',
             'id': '3586',
             'ext': 'flv',
             'title': 'md5:e829428ee28b1deed00de90de49d1da1',
-        }
+        },
+        'skip': 'Not accessible from Travis CI server',
     }
 
     _SONG_FORMATS = {
     }
 
     _SONG_FORMATS = {
index 45716c75d9505c5fcb7e8c6d73ec4feaef298aee..8a1c296dda8b57611a0e464387be43ab0fc9a370 100644 (file)
@@ -38,9 +38,7 @@ class PlayedIE(InfoExtractor):
         if m_error:
             raise ExtractorError(m_error.group('msg'), expected=True)
 
         if m_error:
             raise ExtractorError(m_error.group('msg'), expected=True)
 
-        fields = re.findall(
-            r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
-        data = dict(fields)
+        data = self._hidden_inputs(orig_webpage)
 
         self._sleep(2, video_id)
 
 
         self._sleep(2, video_id)
 
index c3e667e9e72ea0aaf6e5db731f630816e6a2861d..2eb4fd96dcbc071c1c2ecfb596ab20c4526018bd 100644 (file)
@@ -4,7 +4,8 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
 )
 from ..utils import (
     clean_html,
 )
 from ..utils import (
     clean_html,
@@ -44,7 +45,7 @@ class PlayvidIE(InfoExtractor):
         flashvars = self._html_search_regex(
             r'flashvars="(.+?)"', webpage, 'flashvars')
 
         flashvars = self._html_search_regex(
             r'flashvars="(.+?)"', webpage, 'flashvars')
 
-        infos = compat_urllib_parse.unquote(flashvars).split(r'&')
+        infos = compat_urllib_parse_unquote(flashvars).split(r'&')
         for info in infos:
             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
             if videovars_match:
         for info in infos:
             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
             if videovars_match:
@@ -52,7 +53,7 @@ class PlayvidIE(InfoExtractor):
                 val = videovars_match.group(2)
 
                 if key == 'title':
                 val = videovars_match.group(2)
 
                 if key == 'title':
-                    video_title = compat_urllib_parse.unquote_plus(val)
+                    video_title = compat_urllib_parse_unquote_plus(val)
                 if key == 'duration':
                     try:
                         duration = int(val)
                 if key == 'duration':
                     try:
                         duration = int(val)
index daa284ea28be63f9677471f16a0b8102f32b560e..0b7886840fbced3d9fa6fb219050f40ac709c080 100644 (file)
@@ -5,7 +5,8 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
 )
     compat_urllib_parse_urlparse,
     compat_urllib_request,
 )
@@ -19,8 +20,8 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
 
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
+    _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
@@ -30,7 +31,17 @@ class PornHubIE(InfoExtractor):
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
-    }
+    }, {
+        'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(
@@ -39,7 +50,8 @@ class PornHubIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        req = compat_urllib_request.Request(url)
+        req = compat_urllib_request.Request(
+            'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
@@ -58,7 +70,7 @@ class PornHubIE(InfoExtractor):
             webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:
             webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:
-            thumbnail = compat_urllib_parse.unquote(thumbnail)
+            thumbnail = compat_urllib_parse_unquote(thumbnail)
 
         view_count = self._extract_count(
             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
 
         view_count = self._extract_count(
             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
@@ -69,9 +81,9 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
+        video_urls = list(map(compat_urllib_parse_unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
         if webpage.find('"encrypted":true') != -1:
         if webpage.find('"encrypted":true') != -1:
-            password = compat_urllib_parse.unquote_plus(
+            password = compat_urllib_parse_unquote_plus(
                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
index 9688ed94898de231e6c7f1c9dc28d3779da10311..eba4dfbb39576bff355b722c997dd31e07ce370f 100644 (file)
@@ -34,7 +34,7 @@ class PornoVoisinesIE(InfoExtractor):
             'duration': 120,
             'view_count': int,
             'average_rating': float,
             'duration': 120,
             'view_count': int,
             'average_rating': float,
-            'categories': ['Débutante', 'Scénario', 'Sodomie'],
+            'categories': ['Débutantes', 'Scénario', 'Sodomie'],
             'age_limit': 18,
         }
     }
             'age_limit': 18,
         }
     }
@@ -71,7 +71,7 @@ class PornoVoisinesIE(InfoExtractor):
         view_count = int_or_none(self._search_regex(
             r'(\d+) vues', webpage, 'view count', fatal=False))
         average_rating = self._search_regex(
         view_count = int_or_none(self._search_regex(
             r'(\d+) vues', webpage, 'view count', fatal=False))
         average_rating = self._search_regex(
-            r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
+            r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False)
         if average_rating:
             average_rating = float_or_none(average_rating.replace(',', '.'))
 
         if average_rating:
             average_rating = float_or_none(average_rating.replace(',', '.'))
 
index 01cc3d9ea3ff845476a7f7b306c3bfee25078b96..304359dc5b189b8ce27c967c2d369b26db334532 100644 (file)
@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
@@ -31,12 +29,7 @@ class PrimeShareTVIE(InfoExtractor):
         if '>File not exist<' in webpage:
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         if '>File not exist<' in webpage:
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
-            value="([^"]*)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
 
         headers = {
             'Referer': url,
 
         headers = {
             'Referer': url,
index f536e6e6cdfb3d71e21c98614e2baf117387493b..8190ed6766ce5c878fc82700524ec6d012d70a57 100644 (file)
@@ -35,10 +35,7 @@ class PromptFileIE(InfoExtractor):
             raise ExtractorError('Video %s does not exist' % video_id,
                                  expected=True)
 
             raise ExtractorError('Video %s does not exist' % video_id,
                                  expected=True)
 
-        fields = dict(re.findall(r'''(?x)type="hidden"\s+
-            name="(.+?)"\s+
-            value="(.*?)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
         post = compat_urllib_parse.urlencode(fields)
         req = compat_urllib_request.Request(url, post)
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         post = compat_urllib_parse.urlencode(fields)
         req = compat_urllib_request.Request(url, post)
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
index 255d4abc131519ec470ccdc2b1a64b7d38d9f44b..fec008ce7687a0360d2e54e3130425245f30b4fc 100644 (file)
@@ -9,8 +9,9 @@ from ..compat import (
     compat_urllib_parse,
 )
 from ..utils import (
     compat_urllib_parse,
 )
 from ..utils import (
-    unified_strdate,
+    determine_ext,
     int_or_none,
     int_or_none,
+    unified_strdate,
 )
 
 
 )
 
 
@@ -21,6 +22,11 @@ class ProSiebenSat1IE(InfoExtractor):
 
     _TESTS = [
         {
 
     _TESTS = [
         {
+            # Tests changes introduced in https://github.com/rg3/youtube-dl/pull/6242
+            # in response to fixing https://github.com/rg3/youtube-dl/issues/6215:
+            # - malformed f4m manifest support
+            # - proper handling of URLs starting with `https?://` in 2.0 manifests
+            # - recursive child f4m manifests extraction
             'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
             'info_dict': {
                 'id': '2104602',
             'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
             'info_dict': {
                 'id': '2104602',
@@ -177,6 +183,7 @@ class ProSiebenSat1IE(InfoExtractor):
         r'<header class="clearfix">\s*<h3>(.+?)</h3>',
         r'<!-- start video -->\s*<h1>(.+?)</h1>',
         r'<h1 class="att-name">\s*(.+?)</h1>',
         r'<header class="clearfix">\s*<h3>(.+?)</h3>',
         r'<!-- start video -->\s*<h1>(.+?)</h1>',
         r'<h1 class="att-name">\s*(.+?)</h1>',
+        r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',
@@ -206,8 +213,8 @@ class ProSiebenSat1IE(InfoExtractor):
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
 
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
 
-        access_token = 'testclient'
-        client_name = 'kolibri-1.2.5'
+        access_token = 'prosieben'
+        client_name = 'kolibri-2.0.19-splec4'
         client_location = url
 
         videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
         client_location = url
 
         videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
@@ -274,23 +281,30 @@ class ProSiebenSat1IE(InfoExtractor):
 
         for source in urls_sources:
             protocol = source['protocol']
 
         for source in urls_sources:
             protocol = source['protocol']
+            source_url = source['url']
             if protocol == 'rtmp' or protocol == 'rtmpe':
             if protocol == 'rtmp' or protocol == 'rtmpe':
-                mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url'])
+                mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
                 if not mobj:
                     continue
                 if not mobj:
                     continue
+                path = mobj.group('path')
+                mp4colon_index = path.rfind('mp4:')
+                app = path[:mp4colon_index]
+                play_path = path[mp4colon_index:]
                 formats.append({
                 formats.append({
-                    'url': mobj.group('url'),
-                    'app': mobj.group('app'),
-                    'play_path': mobj.group('playpath'),
+                    'url': '%s/%s' % (mobj.group('url'), app),
+                    'app': app,
+                    'play_path': play_path,
                     'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
                     'page_url': 'http://www.prosieben.de',
                     'vbr': fix_bitrate(source['bitrate']),
                     'ext': 'mp4',
                     'format_id': '%s_%s' % (source['cdn'], source['bitrate']),
                 })
                     'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
                     'page_url': 'http://www.prosieben.de',
                     'vbr': fix_bitrate(source['bitrate']),
                     'ext': 'mp4',
                     'format_id': '%s_%s' % (source['cdn'], source['bitrate']),
                 })
+            elif 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
+                formats.extend(self._extract_f4m_formats(source_url, clip_id))
             else:
                 formats.append({
             else:
                 formats.append({
-                    'url': source['url'],
+                    'url': source_url,
                     'vbr': fix_bitrate(source['bitrate']),
                 })
 
                     'vbr': fix_bitrate(source['bitrate']),
                 })
 
index f773332a895b1b147ae9609229700a0c887a362f..1654a641f00db6833056571394b4dbe0b2856150 100644 (file)
@@ -9,26 +9,48 @@ from .common import InfoExtractor
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
+    clean_html,
 )
 from ..compat import compat_urllib_request
 
 
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
 )
 from ..compat import compat_urllib_request
 
 
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
+    IE_DESC = 'QQ音乐'
     _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
     _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
-        'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
+        'md5': '9ce1c1c8445f561506d2e3cfb0255705',
         'info_dict': {
             'id': '004295Et37taLD',
         'info_dict': {
             'id': '004295Et37taLD',
-            'ext': 'm4a',
+            'ext': 'mp3',
             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
             'description': 'md5:d327722d0361576fde558f1ac68a7065',
             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
             'description': 'md5:d327722d0361576fde558f1ac68a7065',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'note': 'There is no mp3-320 version of this song.',
+        'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
+        'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
+        'info_dict': {
+            'id': '004MsGEo3DdNxV',
+            'ext': 'mp3',
+            'title': '如果',
+            'upload_date': '20050626',
+            'creator': '李季美',
+            'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }]
 
         }
     }]
 
+    _FORMATS = {
+        'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
+        'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
+        'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
+    }
+
     # Reference: m_r_GetRUin() in top_player.js
     # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
     @staticmethod
     # Reference: m_r_GetRUin() in top_player.js
     # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
     @staticmethod
@@ -62,21 +84,42 @@ class QQMusicIE(InfoExtractor):
         if lrc_content:
             lrc_content = lrc_content.replace('\\n', '\n')
 
         if lrc_content:
             lrc_content = lrc_content.replace('\\n', '\n')
 
+        thumbnail_url = None
+        albummid = self._search_regex(
+            [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
+            detail_info_page, 'album mid', default=None)
+        if albummid:
+            thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \
+                            % (albummid[-2:-1], albummid[-1], albummid)
+
         guid = self.m_r_get_ruin()
 
         vkey = self._download_json(
             'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
             mid, note='Retrieve vkey', errnote='Unable to get vkey',
             transform_source=strip_jsonp)['key']
         guid = self.m_r_get_ruin()
 
         vkey = self._download_json(
             'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
             mid, note='Retrieve vkey', errnote='Unable to get vkey',
             transform_source=strip_jsonp)['key']
-        song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
+
+        formats = []
+        for format_id, details in self._FORMATS.items():
+            formats.append({
+                'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
+                       % (details['prefix'], mid, details['ext'], vkey, guid),
+                'format': format_id,
+                'format_id': format_id,
+                'preference': details['preference'],
+                'abr': details.get('abr'),
+            })
+        self._check_formats(formats, mid)
+        self._sort_formats(formats)
 
         return {
             'id': mid,
 
         return {
             'id': mid,
-            'url': song_url,
+            'formats': formats,
             'title': song_name,
             'upload_date': publish_time,
             'creator': singer,
             'description': lrc_content,
             'title': song_name,
             'upload_date': publish_time,
             'creator': singer,
             'description': lrc_content,
+            'thumbnail': thumbnail_url,
         }
 
 
         }
 
 
@@ -100,6 +143,7 @@ class QQPlaylistBaseIE(InfoExtractor):
 
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
 
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
+    IE_DESC = 'QQ音乐 - 歌手'
     _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
     _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
@@ -144,39 +188,50 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
 
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
+    IE_DESC = 'QQ音乐 - 专辑'
     _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 
     _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 
-    _TEST = {
-        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
         'info_dict': {
             'id': '000gXCTb2AhRR1',
             'title': '我们都是这样长大的',
         'info_dict': {
             'id': '000gXCTb2AhRR1',
             'title': '我们都是这样长大的',
-            'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+            'description': 'md5:179c5dce203a5931970d306aa9607ea6',
         },
         'playlist_count': 4,
         },
         'playlist_count': 4,
-    }
+    }, {
+        'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
+        'info_dict': {
+            'id': '002Y5a3b3AlCu3',
+            'title': '그리고...',
+            'description': 'md5:a48823755615508a95080e81b51ba729',
+        },
+        'playlist_count': 8,
+    }]
 
     def _real_extract(self, url):
         mid = self._match_id(url)
 
 
     def _real_extract(self, url):
         mid = self._match_id(url)
 
-        album_page = self._download_webpage(
-            self.qq_static_url('album', mid), mid, 'Download album page')
-
-        entries = self.get_entries_from_page(album_page)
+        album = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
+            mid, 'Download album page')['data']
 
 
-        album_name = self._html_search_regex(
-            r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
-            default=None)
-
-        album_detail = self._html_search_regex(
-            r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
-            album_page, 'album details', default=None)
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in album['list']
+        ]
+        album_name = album.get('name')
+        album_detail = album.get('desc')
+        if album_detail is not None:
+            album_detail = album_detail.strip()
 
         return self.playlist_result(entries, mid, album_name, album_detail)
 
 
 class QQMusicToplistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:toplist'
 
         return self.playlist_result(entries, mid, album_name, album_detail)
 
 
 class QQMusicToplistIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:toplist'
+    IE_DESC = 'QQ音乐 - 排行榜'
     _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
 
     _TESTS = [{
     _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
 
     _TESTS = [{
@@ -226,3 +281,37 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
         list_name = topinfo.get('ListName')
         list_description = topinfo.get('info')
         return self.playlist_result(entries, list_id, list_name, list_description)
         list_name = topinfo.get('ListName')
         list_description = topinfo.get('info')
         return self.playlist_result(entries, list_id, list_name, list_description)
+
+
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:playlist'
+    IE_DESC = 'QQ音乐 - 歌单'
+    _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://y.qq.com/#type=taoge&id=3462654915',
+        'info_dict': {
+            'id': '3462654915',
+            'title': '韩国5月新歌精选下旬',
+            'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
+        },
+        'playlist_count': 40,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        list_json = self._download_json(
+            'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
+            % list_id, list_id, 'Download list page',
+            transform_source=strip_jsonp)['cdlist'][0]
+
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in list_json['songlist']
+        ]
+
+        list_name = list_json.get('dissname')
+        list_description = clean_html(unescapeHTML(list_json.get('desc')))
+        return self.playlist_result(entries, list_id, list_name, list_description)
index af7d76cf47e575277de3ffe480fdb8e1eb48b43c..f414e2384e619e8faccab280bdb9e8a9518819c9 100644 (file)
@@ -24,6 +24,7 @@ class QuickVidIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
             'view_count': int,
         },
             'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
             'view_count': int,
         },
+        'skip': 'Not accessible from Travis CI server',
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):
diff --git a/youtube_dl/extractor/rds.py b/youtube_dl/extractor/rds.py
new file mode 100644 (file)
index 0000000..796adfd
--- /dev/null
@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class RDSIE(InfoExtractor):
+    IE_DESC = 'RDS.ca'
+    _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<display_id>[^/]+)-(?P<id>\d+\.\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799',
+        'info_dict': {
+            'id': '3.1132799',
+            'display_id': 'fowler-jr-prend-la-direction-de-jacksonville',
+            'ext': 'mp4',
+            'title': 'Fowler Jr. prend la direction de Jacksonville',
+            'description': 'Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ',
+            'timestamp': 1430397346,
+            'upload_date': '20150430',
+            'duration': 154.354,
+            'age_limit': 0,
+        }
+    }, {
+        'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        # TODO: extract f4m from 9c9media.com
+        video_url = self._search_regex(
+            r'<span[^>]+itemprop="contentURL"[^>]+content="([^"]+)"',
+            webpage, 'video url')
+
+        title = self._og_search_title(webpage) or self._html_search_meta(
+            'title', webpage, 'title', fatal=True)
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage, 'description')
+        thumbnail = self._og_search_thumbnail(webpage) or self._search_regex(
+            [r'<link[^>]+itemprop="thumbnailUrl"[^>]+href="([^"]+)"',
+             r'<span[^>]+itemprop="thumbnailUrl"[^>]+content="([^"]+)"'],
+            webpage, 'thumbnail', fatal=False)
+        timestamp = parse_iso8601(self._search_regex(
+            r'<span[^>]+itemprop="uploadDate"[^>]+content="([^"]+)"',
+            webpage, 'upload date', fatal=False))
+        duration = parse_duration(self._search_regex(
+            r'<span[^>]+itemprop="duration"[^>]+content="([^"]+)"',
+            webpage, 'duration', fatal=False))
+        age_limit = self._family_friendly_search(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'age_limit': age_limit,
+        }
index 5a381d9ced41516db44d7e17120b29948a1957cb..e4215d546219bb95fe79abfb184da149148962db 100644 (file)
@@ -21,6 +21,13 @@ class RTBFIE(InfoExtractor):
         }
     }
 
         }
     }
 
+    _QUALITIES = [
+        ('mobile', 'mobile'),
+        ('web', 'SD'),
+        ('url', 'MD'),
+        ('high', 'HD'),
+    ]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -32,14 +39,21 @@ class RTBFIE(InfoExtractor):
                 r'data-video="([^"]+)"', webpage, 'data video')),
             video_id)
 
                 r'data-video="([^"]+)"', webpage, 'data video')),
             video_id)
 
-        video_url = data.get('downloadUrl') or data.get('url')
-
         if data.get('provider').lower() == 'youtube':
         if data.get('provider').lower() == 'youtube':
+            video_url = data.get('downloadUrl') or data.get('url')
             return self.url_result(video_url, 'Youtube')
             return self.url_result(video_url, 'Youtube')
+        formats = []
+        for key, format_id in self._QUALITIES:
+            format_url = data['sources'].get(key)
+            if format_url:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                })
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),
             'thumbnail': data.get('thumbnail'),
             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),
             'thumbnail': data.get('thumbnail'),
index cfce4550ada568cfe13fae859a2bb745671074b5..e0c530d64a97500eaa1b653599f92c9420518c77 100644 (file)
@@ -12,10 +12,10 @@ class RtlNlIE(InfoExtractor):
     IE_NAME = 'rtl.nl'
     IE_DESC = 'rtl.nl and rtlxl.nl'
     _VALID_URL = r'''(?x)
     IE_NAME = 'rtl.nl'
     IE_DESC = 'rtl.nl and rtlxl.nl'
     _VALID_URL = r'''(?x)
-        https?://(www\.)?
+        https?://(?:www\.)?
         (?:
             rtlxl\.nl/\#!/[^/]+/|
         (?:
             rtlxl\.nl/\#!/[^/]+/|
-            rtl\.nl/system/videoplayer/[^?#]+?/video_embed\.html\#uuid=
+            rtl\.nl/system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html\b.+?\buuid=
         )
         (?P<id>[0-9a-f-]+)'''
 
         )
         (?P<id>[0-9a-f-]+)'''
 
@@ -43,22 +43,51 @@ class RtlNlIE(InfoExtractor):
             'upload_date': '20150215',
             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
         }
             'upload_date': '20150215',
             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
         }
+    }, {
+        # empty synopsis and missing episodes (see https://github.com/rg3/youtube-dl/issues/6275)
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a/autoplay=false',
+        'info_dict': {
+            'id': 'f536aac0-1dc3-4314-920e-3bd1c5b3811a',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws - Meer beelden van overval juwelier',
+            'thumbnail': 're:^https?://screenshots\.rtl\.nl/system/thumb/sz=[0-9]+x[0-9]+/uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a$',
+            'timestamp': 1437233400,
+            'upload_date': '20150718',
+            'duration': 30.474,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # encrypted m3u8 streams, georestricted
+        'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         uuid = self._match_id(url)
         info = self._download_json(
     }]
 
     def _real_extract(self, url):
         uuid = self._match_id(url)
         info = self._download_json(
-            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
             uuid)
 
         material = info['material'][0]
             uuid)
 
         material = info['material'][0]
-        progname = info['abstracts'][0]['name']
-        subtitle = material['title'] or info['episodes'][0]['name']
-        description = material.get('synopsis') or info['episodes'][0]['synopsis']
+        title = info['abstracts'][0]['name']
+        subtitle = material.get('title')
+        if subtitle:
+            title += ' - %s' % subtitle
+        description = material.get('synopsis')
+
+        meta = info.get('meta', {})
 
         # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
 
         # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
-        videopath = material['videopath'].replace('.f4m', '.m3u8')
-        m3u8_url = 'http://manifest.us.rtl.nl' + videopath
+        # NB: nowadays, recent ffmpeg and avconv can handle these encrypted streams, so
+        # this adaptive -> flash workaround is not required in general, but it also
+        # allows bypassing georestriction therefore is retained for now.
+        videopath = material['videopath'].replace('/adaptive/', '/flash/')
+        m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
 
         formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
 
 
         formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
 
@@ -79,7 +108,7 @@ class RtlNlIE(InfoExtractor):
         self._sort_formats(formats)
 
         thumbnails = []
         self._sort_formats(formats)
 
         thumbnails = []
-        meta = info.get('meta', {})
+
         for p in ('poster_base_url', '"thumb_base_url"'):
             if not meta.get(p):
                 continue
         for p in ('poster_base_url', '"thumb_base_url"'):
             if not meta.get(p):
                 continue
@@ -95,7 +124,7 @@ class RtlNlIE(InfoExtractor):
 
         return {
             'id': uuid,
 
         return {
             'id': uuid,
-            'title': '%s - %s' % (progname, subtitle),
+            'title': title,
             'formats': formats,
             'timestamp': material['original_date'],
             'description': description,
             'formats': formats,
             'timestamp': material['original_date'],
             'description': description,
diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py
new file mode 100644 (file)
index 0000000..4e22628
--- /dev/null
@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    xpath_text,
+)
+
+
+class RuutuIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
+    _TESTS = [
+        {
+            'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+            'md5': 'ab2093f39be1ca8581963451b3c0234f',
+            'info_dict': {
+                'id': '2058907',
+                'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+                'ext': 'mp4',
+                'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
+                'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 114,
+                'age_limit': 0,
+            },
+        },
+        {
+            'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa',
+            'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
+            'info_dict': {
+                'id': '2057306',
+                'display_id': 'superpesis-katso-koko-kausi-ruudussa',
+                'ext': 'mp4',
+                'title': 'Superpesis: katso koko kausi Ruudussa',
+                'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 40,
+                'age_limit': 0,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'data-media-id="(\d+)"', webpage, 'media id')
+
+        video_xml_url = None
+
+        media_data = self._search_regex(
+            r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage,
+            'media data', default=None)
+        if media_data:
+            media_json = self._parse_json(media_data, display_id, fatal=False)
+            if media_json:
+                xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl')
+                if xml_url:
+                    video_xml_url = xml_url.replace('{ID}', video_id)
+
+        if not video_xml_url:
+            video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id
+
+        video_xml = self._download_xml(video_xml_url, video_id)
+
+        formats = []
+        processed_urls = []
+
+        def extract_formats(node):
+            for child in node:
+                if child.tag.endswith('Files'):
+                    extract_formats(child)
+                elif child.tag.endswith('File'):
+                    video_url = child.text
+                    if not video_url or video_url in processed_urls or 'NOT_USED' in video_url:
+                        return
+                    processed_urls.append(video_url)
+                    ext = determine_ext(video_url)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', m3u8_id='hls'))
+                    elif ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            video_url, video_id, f4m_id='hds'))
+                    else:
+                        proto = compat_urllib_parse_urlparse(video_url).scheme
+                        if not child.tag.startswith('HTTP') and proto != 'rtmp':
+                            continue
+                        preference = -1 if proto == 'rtmp' else 1
+                        label = child.get('label')
+                        tbr = int_or_none(child.get('bitrate'))
+                        width, height = [int_or_none(x) for x in child.get('resolution', '').split('x')]
+                        formats.append({
+                            'format_id': '%s-%s' % (proto, label if label else tbr),
+                            'url': video_url,
+                            'width': width,
+                            'height': height,
+                            'tbr': tbr,
+                            'preference': preference,
+                        })
+
+        extract_formats(video_xml.find('./Clip'))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
+            'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
+            'formats': formats,
+        }
index 10251f29e033ef241618ed7985e214dc0e76cd51..f3c80708c86ab2fc29fbd029b245bbe894af2dfb 100644 (file)
@@ -83,7 +83,7 @@ class SafariIE(SafariBaseIE):
                                     library/view/[^/]+|
                                     api/v1/book
                                 )/
                                     library/view/[^/]+|
                                     api/v1/book
                                 )/
-                                (?P<course_id>\d+)/
+                                (?P<course_id>[^/]+)/
                                     (?:chapter(?:-content)?/)?
                                 (?P<part>part\d+)\.html
     '''
                                     (?:chapter(?:-content)?/)?
                                 (?P<part>part\d+)\.html
     '''
@@ -100,6 +100,10 @@ class SafariIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
         'only_matching': True,
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
         'only_matching': True,
+    }, {
+        # non-digits in course id
+        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
@@ -122,7 +126,7 @@ class SafariCourseIE(SafariBaseIE):
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
index d4bd1a0d72624e65bc9a5890f371b492451a9486..d6ee2d9e2245475d236c12fb6967af68558d8598 100644 (file)
@@ -1,17 +1,12 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
 from .common import InfoExtractor
 from .common import InfoExtractor
-from ..utils import (
-    js_to_json,
-    remove_end,
-)
 
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
 
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
-    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
@@ -21,39 +16,36 @@ class SBSIE(InfoExtractor):
         'info_dict': {
             'id': '320403011771',
             'ext': 'mp4',
         'info_dict': {
             'id': '320403011771',
             'ext': 'mp4',
-            'title': 'Dingo Conservation',
-            'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
+            'title': 'Dingo Conservation (The Feed)',
+            'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
             'thumbnail': 're:http://.*\.jpg',
             'thumbnail': 're:http://.*\.jpg',
+            'duration': 308,
         },
         },
-        'add_ies': ['generic'],
     }, {
         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
         'only_matching': True,
     }, {
         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
         'only_matching': True,
+    }, {
+        'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        player = self._search_regex(
-            r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
-            webpage, 'player')
-        player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
-
-        release_urls = self._parse_json(js_to_json(player), video_id)
+        webpage = self._download_webpage(
+            'http://www.sbs.com.au/ondemand/video/single/%s?context=web' % video_id, video_id)
 
 
-        theplatform_url = release_urls.get('progressive') or release_urls['standard']
+        player_params = self._parse_json(
+            self._search_regex(
+                r'(?s)var\s+playerParams\s*=\s*({.+?});', webpage, 'playerParams'),
+            video_id)
 
 
-        title = remove_end(self._og_search_title(webpage), ' (The Feed)')
-        description = self._html_search_meta('description', webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        urls = player_params['releaseUrls']
+        theplatform_url = (urls.get('progressive') or urls.get('standard') or
+                           urls.get('html') or player_params['relatedItemsURL'])
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
             'url': theplatform_url,
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
             'url': theplatform_url,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
         }
         }
index 9f3e944e73532a92c5213ce95e7633fe6bc4c212..a07677686a4ecc2923b310c3aeeeaab610bb0868 100644 (file)
@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import re
 import base64
 
 from .common import InfoExtractor
 import base64
 
 from .common import InfoExtractor
@@ -35,8 +34,7 @@ class SharedIE(InfoExtractor):
             raise ExtractorError(
                 'Video %s does not exist' % video_id, expected=True)
 
             raise ExtractorError(
                 'Video %s does not exist' % video_id, expected=True)
 
-        download_form = dict(re.findall(
-            r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+        download_form = self._hidden_inputs(webpage)
         request = compat_urllib_request.Request(
             url, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         request = compat_urllib_request.Request(
             url, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
index 24746a09a0c2183e8a0bd8e239cb59291b41f19a..93a7cfe15cc764bc61b912dd2e3283d950790565 100644 (file)
@@ -53,7 +53,7 @@ class SmotriIE(InfoExtractor):
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
-        # video-password
+        # video-password, not approved by moderator
         {
             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
             'md5': 'f6331cef33cad65a0815ee482a54440b',
         {
             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
             'md5': 'f6331cef33cad65a0815ee482a54440b',
@@ -71,7 +71,24 @@ class SmotriIE(InfoExtractor):
             },
             'skip': 'Video is not approved by moderator',
         },
             },
             'skip': 'Video is not approved by moderator',
         },
-        # age limit + video-password
+        # video-password
+        {
+            'url': 'http://smotri.com/video/view/?id=v6984858774#',
+            'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
+            'info_dict': {
+                'id': 'v6984858774',
+                'ext': 'mp4',
+                'title': 'Дача Солженицина ПАРОЛЬ 223322',
+                'uploader': 'psavari1',
+                'uploader_id': 'psavari1',
+                'upload_date': '20081103',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'videopassword': '223322',
+            },
+        },
+        # age limit + video-password, not approved by moderator
         {
             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
             'md5': '91e909c9f0521adf5ee86fbe073aad70',
         {
             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
             'md5': '91e909c9f0521adf5ee86fbe073aad70',
@@ -90,19 +107,22 @@ class SmotriIE(InfoExtractor):
             },
             'skip': 'Video is not approved by moderator',
         },
             },
             'skip': 'Video is not approved by moderator',
         },
-        # not approved by moderator, but available
+        # age limit + video-password
         {
         {
-            'url': 'http://smotri.com/video/view/?id=v28888533b73',
-            'md5': 'f44bc7adac90af518ef1ecf04893bb34',
+            'url': 'http://smotri.com/video/view/?id=v7780025814',
+            'md5': 'b4599b068422559374a59300c5337d72',
             'info_dict': {
             'info_dict': {
-                'id': 'v28888533b73',
+                'id': 'v7780025814',
                 'ext': 'mp4',
                 'ext': 'mp4',
-                'title': 'Russian Spies Killed By ISIL Child Soldier',
-                'uploader': 'Mopeder',
-                'uploader_id': 'mopeder',
-                'duration': 71,
-                'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
-                'upload_date': '20150114',
+                'title': 'Sexy Beach (пароль 123)',
+                'uploader': 'вАся',
+                'uploader_id': 'asya_prosto',
+                'upload_date': '20081218',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'age_limit': 18,
+            },
+            'params': {
+                'videopassword': '123'
             },
         },
         # swf player
             },
         },
         # swf player
@@ -152,6 +172,10 @@ class SmotriIE(InfoExtractor):
             'getvideoinfo': '1',
         }
 
             'getvideoinfo': '1',
         }
 
+        video_password = self._downloader.params.get('videopassword', None)
+        if video_password:
+            video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
+
         request = compat_urllib_request.Request(
             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         request = compat_urllib_request.Request(
             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -161,13 +185,18 @@ class SmotriIE(InfoExtractor):
         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 
         if not video_url:
         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 
         if not video_url:
-            if video.get('_moderate_no') or not video.get('moderated'):
+            if video.get('_moderate_no'):
                 raise ExtractorError(
                     'Video %s has not been approved by moderator' % video_id, expected=True)
 
             if video.get('error'):
                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
                 raise ExtractorError(
                     'Video %s has not been approved by moderator' % video_id, expected=True)
 
             if video.get('error'):
                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
+            if video.get('_pass_protected') == 1:
+                msg = ('Invalid video password' if video_password
+                       else 'This video is protected by a password, use the --video-password option')
+                raise ExtractorError(msg, expected=True)
+
         title = video['title']
         thumbnail = video['_imgURL']
         upload_date = unified_strdate(video['added'])
         title = video['title']
         thumbnail = video['_imgURL']
         upload_date = unified_strdate(video['added'])
diff --git a/youtube_dl/extractor/snagfilms.py b/youtube_dl/extractor/snagfilms.py
new file mode 100644 (file)
index 0000000..cf495f3
--- /dev/null
@@ -0,0 +1,171 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    parse_duration,
+)
+
+
+class SnagFilmsEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
+    _TESTS = [{
+        'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
+        'md5': '2924e9215c6eff7a55ed35b72276bd93',
+        'info_dict': {
+            'id': '74849a00-85a9-11e1-9660-123139220831',
+            'ext': 'mp4',
+            'title': '#whilewewatch',
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        if '>This film is not playable in your area.<' in webpage:
+            raise ExtractorError(
+                'Film %s is not playable in your area.' % video_id, expected=True)
+
+        formats = []
+        for source in self._parse_json(js_to_json(self._search_regex(
+                r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
+            file_ = source.get('file')
+            if not file_:
+                continue
+            type_ = source.get('type')
+            format_id = source.get('label')
+            ext = determine_ext(file_)
+            if any(_ == 'm3u8' for _ in (type_, ext)):
+                formats.extend(self._extract_m3u8_formats(
+                    file_, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                bitrate = int_or_none(self._search_regex(
+                    r'(\d+)kbps', file_, 'bitrate', default=None))
+                height = int_or_none(self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None))
+                formats.append({
+                    'url': file_,
+                    'format_id': format_id,
+                    'tbr': bitrate,
+                    'height': height,
+                })
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
+            webpage, 'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+
+class SnagFilmsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.snagfilms.com/films/title/lost_for_life',
+        'md5': '19844f897b35af219773fd63bdec2942',
+        'info_dict': {
+            'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
+            'display_id': 'lost_for_life',
+            'ext': 'mp4',
+            'title': 'Lost for Life',
+            'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 4489,
+            'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
+        'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
+        'info_dict': {
+            'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
+            'display_id': 'the_world_cut_project/india',
+            'ext': 'mp4',
+            'title': 'India',
+            'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 979,
+            'categories': ['Documentary', 'Sports', 'Politics']
+        }
+    }, {
+        # Film is not playable in your area.
+        'url': 'http://www.snagfilms.com/films/title/inside_mecca',
+        'only_matching': True,
+    }, {
+        # Film is not available.
+        'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        if ">Sorry, the Film you're looking for is not available.<" in webpage:
+            raise ExtractorError(
+                'Film %s is not available.' % display_id, expected=True)
+
+        film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
+
+        snag = self._parse_json(
+            self._search_regex(
+                'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
+            display_id)
+
+        for item in snag:
+            if item.get('data', {}).get('film', {}).get('id') == film_id:
+                data = item['data']['film']
+                title = data['title']
+                description = clean_html(data.get('synopsis'))
+                thumbnail = data.get('image')
+                duration = int_or_none(data.get('duration') or data.get('runtime'))
+                categories = [
+                    category['title'] for category in data.get('categories', [])
+                    if category.get('title')]
+                break
+        else:
+            title = self._search_regex(
+                r'itemprop="title">([^<]+)<', webpage, 'title')
+            description = self._html_search_regex(
+                r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
+                webpage, 'description', default=None) or self._og_search_description(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
+            duration = parse_duration(self._search_regex(
+                r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
+                webpage, 'duration', fatal=False))
+            categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
+            'id': film_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'categories': categories,
+        }
index 29bd9ce6f76247b5ac997050075c7e720d8a3b2b..ba2d5e19bc0d1de322b4b12ed5b8c0dc31157f7f 100644 (file)
@@ -6,9 +6,12 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_request
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+from ..utils import (
+    ExtractorError,
 )
 )
-from ..utils import ExtractorError
 
 
 class SohuIE(InfoExtractor):
 
 
 class SohuIE(InfoExtractor):
@@ -26,7 +29,7 @@ class SohuIE(InfoExtractor):
         'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
         'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
-        'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
+        'md5': '699060e75cf58858dd47fb9c03c42cfb',
         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',
         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',
@@ -34,7 +37,7 @@ class SohuIE(InfoExtractor):
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
-        'md5': '49308ff6dafde5ece51137d04aec311e',
+        'md5': '9bf34be48f2f4dadcb226c74127e203c',
         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',
         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',
@@ -48,7 +51,7 @@ class SohuIE(InfoExtractor):
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
-            'md5': '492923eac023ba2f13ff69617c32754a',
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',
@@ -56,7 +59,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',
@@ -64,7 +67,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': '93584716ee0657c0b205b8aa3d27aa13',
+            'md5': '8407e634175fdac706766481b9443450',
             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',
@@ -139,21 +142,42 @@ class SohuIE(InfoExtractor):
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():
+                allot = format_data['allot']
+
                 data = format_data['data']
                 data = format_data['data']
+                clips_url = data['clipsURL']
+                su = data['su']
 
 
-                # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
-                # so retry until got a working URL
                 video_url = 'newflv.sohu.ccgslb.net'
                 video_url = 'newflv.sohu.ccgslb.net'
+                cdnId = None
                 retries = 0
                 retries = 0
-                while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
-                    download_note = 'Download information from CDN gateway for format ' + format_id
+
+                while 'newflv.sohu.ccgslb.net' in video_url:
+                    params = {
+                        'prot': 9,
+                        'file': clips_url[i],
+                        'new': su[i],
+                        'prod': 'flash',
+                    }
+
+                    if cdnId is not None:
+                        params['idc'] = cdnId
+
+                    download_note = 'Downloading %s video URL part %d of %d' % (
+                        format_id, i + 1, part_count)
+
                     if retries > 0:
                         download_note += ' (retry #%d)' % retries
                     if retries > 0:
                         download_note += ' (retry #%d)' % retries
+                    part_info = self._parse_json(self._download_webpage(
+                        'http://%s/?%s' % (allot, compat_urllib_parse.urlencode(params)),
+                        video_id, download_note), video_id)
+
+                    video_url = part_info['url']
+                    cdnId = part_info.get('nid')
+
                     retries += 1
                     retries += 1
-                    cdn_info = self._download_json(
-                        'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
-                        video_id, download_note)
-                    video_url = cdn_info['url']
+                    if retries > 5:
+                        raise ExtractorError('Failed to get video URL')
 
                 formats.append({
                     'url': video_url,
 
                 formats.append({
                     'url': video_url,
index c23c5ee0fb853f86e4662ad574b587610456159c..118ca483265cfda0a4419d93e8ce2fd174148be4 100644 (file)
@@ -29,7 +29,7 @@ class SoundcloudIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
     _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
-                            (?!sets/|likes/?(?:$|[?#]))
+                            (?!sets/|(?:likes|tracks)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -307,6 +307,9 @@ class SoundcloudUserIE(SoundcloudIE):
             'title': 'The Royal Concept',
         },
         'playlist_mincount': 1,
             'title': 'The Royal Concept',
         },
         'playlist_mincount': 1,
+    }, {
+        'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
index 06d6e6640637f2ff3507c3fa1c68339fbb8d98b4..5fa6faf18b738aa32e384972bf65ad56188ad9b4 100644 (file)
@@ -4,7 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
 )
     compat_urllib_parse_urlparse,
     compat_urllib_request,
 )
@@ -27,7 +27,7 @@ class SpankwireIE(InfoExtractor):
             'description': 'Crazy Bitch X rated music video.',
             'uploader': 'oreusz',
             'uploader_id': '124697',
             'description': 'Crazy Bitch X rated music video.',
             'uploader': 'oreusz',
             'uploader_id': '124697',
-            'upload_date': '20070508',
+            'upload_date': '20070507',
             'age_limit': 18,
         }
     }
             'age_limit': 18,
         }
     }
@@ -44,7 +44,7 @@ class SpankwireIE(InfoExtractor):
         title = self._html_search_regex(
             r'<h1>([^<]+)', webpage, 'title')
         description = self._html_search_regex(
         title = self._html_search_regex(
             r'<h1>([^<]+)', webpage, 'title')
         description = self._html_search_regex(
-            r'<div\s+id="descriptionContent">([^<]+)<',
+            r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
             webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
             webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
@@ -64,12 +64,12 @@ class SpankwireIE(InfoExtractor):
             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._html_search_regex(
             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._html_search_regex(
-            r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
+            r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
             webpage, 'comment count', fatal=False))
 
         video_urls = list(map(
             webpage, 'comment count', fatal=False))
 
         video_urls = list(map(
-            compat_urllib_parse.unquote,
-            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
+            compat_urllib_parse_unquote,
+            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
             password = self._search_regex(
                 r'flashvars\.video_title = "([^"]+)',
         if webpage.find('flashvars\.encrypted = "true"') != -1:
             password = self._search_regex(
                 r'flashvars\.video_title = "([^"]+)',
index 359722ad697a7948bea484e7c8f8f77a924544f8..27f4033c547a9700db6af520c4fe4a957e3755c0 100644 (file)
@@ -2,7 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
+    determine_ext,
+    float_or_none,
+)
 
 
 class SpiegeltvIE(InfoExtractor):
 
 
 class SpiegeltvIE(InfoExtractor):
@@ -17,7 +21,7 @@ class SpiegeltvIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg$',
         },
         'params': {
             'thumbnail': 're:http://.*\.jpg$',
         },
         'params': {
-            # rtmp download
+            # m3u8 download
             'skip_download': True,
         }
     }, {
             'skip_download': True,
         }
     }, {
@@ -53,7 +57,37 @@ class SpiegeltvIE(InfoExtractor):
         server_json = self._download_json(
             'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json',
             video_id, note='Downloading server information')
         server_json = self._download_json(
             'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json',
             video_id, note='Downloading server information')
-        server = server_json['streamingserver'][0]['endpoint']
+
+        format = '16x9' if is_wide else '4x3'
+
+        formats = []
+        for streamingserver in server_json['streamingserver']:
+            endpoint = streamingserver.get('endpoint')
+            if not endpoint:
+                continue
+            play_path = 'mp4:%s_spiegeltv_0500_%s.m4v' % (uuid, format)
+            if endpoint.startswith('rtmp'):
+                formats.append({
+                    'url': endpoint,
+                    'format_id': 'rtmp',
+                    'app': compat_urllib_parse_urlparse(endpoint).path[1:],
+                    'play_path': play_path,
+                    'player_path': 'http://prod-static.spiegel.tv/frontend-076.swf',
+                    'ext': 'flv',
+                    'rtmp_live': True,
+                })
+            elif determine_ext(endpoint) == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    endpoint.replace('[video]', play_path),
+                    video_id, 'm4v',
+                    preference=1,  # Prefer hls since it allows to workaround georestriction
+                    m3u8_id='hls', fatal=False)
+                if m3u8_formats is not False:
+                    formats.extend(m3u8_formats)
+            else:
+                formats.append({
+                    'url': endpoint,
+                })
 
         thumbnails = []
         for image in media_json['images']:
 
         thumbnails = []
         for image in media_json['images']:
@@ -65,17 +99,12 @@ class SpiegeltvIE(InfoExtractor):
 
         description = media_json['subtitle']
         duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
 
         description = media_json['subtitle']
         duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
-        format = '16x9' if is_wide else '4x3'
-
-        url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
 
         return {
             'id': video_id,
             'title': title,
 
         return {
             'id': video_id,
             'title': title,
-            'url': url,
-            'ext': 'm4v',
             'description': description,
             'duration': duration,
             'thumbnails': thumbnails,
             'description': description,
             'duration': duration,
             'thumbnails': thumbnails,
-            'rtmp_live': True,
+            'formats': formats,
         }
         }
index 854d01beeb5cefd1f82d7991ee2c0ce75ad33dfa..e527aa97188b1860e054f8af7c7bd7a33301729e 100644 (file)
@@ -44,7 +44,7 @@ class SunPornoIE(InfoExtractor):
             webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(
             webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(
-            r'class="views">\s*(\d+)\s*<',
+            r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'(\d+)</b> Comments?',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'(\d+)</b> Comments?',
index bfe07b02417a2a44f23a09c10c25d48ec18b5535..cf1b37a7533f3af05022cd2fa2a7f908e8edb9a0 100644 (file)
@@ -11,13 +11,13 @@ class TagesschauIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html'
 
     _TESTS = [{
     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html'
 
     _TESTS = [{
-        'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
-        'md5': 'bcdeac2194fb296d599ce7929dfa4009',
+        'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
+        'md5': '917a228bc7df7850783bc47979673a09',
         'info_dict': {
         'info_dict': {
-            'id': '1399128',
+            'id': '102143',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
-            'description': 'md5:69da3c61275b426426d711bde96463ab',
+            'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
+            'description': 'md5:171feccd9d9b3dd54d05d501568f6359',
             'thumbnail': 're:^http:.*\.jpg$',
         },
     }, {
             'thumbnail': 're:^http:.*\.jpg$',
         },
     }, {
index b2a4b1fc05430558ad9b33a9aa3ce834107dc6e3..d1b7264b4ca4a0cb72e491da26d7f5bbc1cc66b7 100644 (file)
@@ -51,6 +51,17 @@ class TeamcocoIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # m3u8 downloads
             }
             'params': {
                 'skip_download': True,  # m3u8 downloads
             }
+        }, {
+            'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9',
+            'info_dict': {
+                'id': '89341',
+                'ext': 'mp4',
+                'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+                'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+            },
+            'params': {
+                'skip_download': True,  # m3u8 downloads
+            }
         }
     ]
     _VIDEO_ID_REGEXES = (
         }
     ]
     _VIDEO_ID_REGEXES = (
@@ -110,9 +121,23 @@ class TeamcocoIE(InfoExtractor):
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
             if determine_ext(filed['url']) == 'm3u8':
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
             if determine_ext(filed['url']) == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    filed['url'], video_id, ext='mp4'))
+                # compat_urllib_parse.urljoin does not work here
+                if filed['url'].startswith('/'):
+                    m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url']
+                else:
+                    m3u8_url = filed['url']
+                m3u8_formats = self._extract_m3u8_formats(
+                    m3u8_url, video_id, ext='mp4')
+                for m3u8_format in m3u8_formats:
+                    if m3u8_format not in formats:
+                        formats.append(m3u8_format)
+            elif determine_ext(filed['url']) == 'f4m':
+                # TODO Correct f4m extraction
+                continue
             else:
             else:
+                if filed['url'].startswith('/mp4:protected/'):
+                    # TODO Correct extraction for these files
+                    continue
                 m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
                 if m_format is not None:
                     format_id = m_format.group(1)
                 m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
                 if m_format is not None:
                     format_id = m_format.group(1)
index 92731ad3d7e8dcc3167b50ce1a15e3b035fb7721..83d833e30dbeb60caa43aa272bfd4d35f4507a53 100644 (file)
@@ -26,7 +26,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language
 class ThePlatformIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
 class ThePlatformIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
-           (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
+           (?:(?P<media>(?:[^/]+/)+select/media/)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
          |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TESTS = [{
          |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TESTS = [{
@@ -56,6 +56,17 @@ class ThePlatformIE(InfoExtractor):
             # rtmp download
             'skip_download': True,
         }
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://player.theplatform.com/p/D6x-PC/pulse_preview/embed/select/media/yMBg9E8KFxZD',
+        'info_dict': {
+            'id': 'yMBg9E8KFxZD',
+            'ext': 'mp4',
+            'description': 'md5:644ad9188d655b742f942bf2e06b002d',
+            'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
+        }
+    }, {
+        'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
+        'only_matching': True,
     }]
 
     @staticmethod
     }]
 
     @staticmethod
@@ -85,6 +96,11 @@ class ThePlatformIE(InfoExtractor):
         if not provider_id:
             provider_id = 'dJ5BDC'
 
         if not provider_id:
             provider_id = 'dJ5BDC'
 
+        path = provider_id
+        if mobj.group('media'):
+            path += '/media'
+        path += '/' + video_id
+
         if smuggled_data.get('force_smil_url', False):
             smil_url = url
         elif mobj.group('config'):
         if smuggled_data.get('force_smil_url', False):
             smil_url = url
         elif mobj.group('config'):
@@ -94,8 +110,7 @@ class ThePlatformIE(InfoExtractor):
             config = self._download_json(config_url, video_id, 'Downloading config')
             smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
         else:
             config = self._download_json(config_url, video_id, 'Downloading config')
             smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
         else:
-            smil_url = ('http://link.theplatform.com/s/{0}/{1}/meta.smil?'
-                        'format=smil&mbr=true'.format(provider_id, video_id))
+            smil_url = 'http://link.theplatform.com/s/%s/meta.smil?format=smil&mbr=true' % path
 
         sig = smuggled_data.get('sig')
         if sig:
 
         sig = smuggled_data.get('sig')
         if sig:
@@ -112,7 +127,7 @@ class ThePlatformIE(InfoExtractor):
         else:
             raise ExtractorError(error_msg, expected=True)
 
         else:
             raise ExtractorError(error_msg, expected=True)
 
-        info_url = 'http://link.theplatform.com/s/{0}/{1}?format=preview'.format(provider_id, video_id)
+        info_url = 'http://link.theplatform.com/s/%s?format=preview' % path
         info_json = self._download_webpage(info_url, video_id)
         info = json.loads(info_json)
 
         info_json = self._download_webpage(info_url, video_id)
         info = json.loads(info_json)
 
index a77c6a2fc9f2838305145c97e9920d09635ceba7..5d09eb9a8b28cdd2f8bea0743d947f98415564a2 100644 (file)
@@ -1,9 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..utils import unified_strdate
 
 from .common import InfoExtractor
 from ..utils import unified_strdate
 
@@ -17,7 +14,7 @@ class TheSixtyOneIE(InfoExtractor):
             song
         )/(?P<id>[A-Za-z0-9]+)/?$'''
     _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
             song
         )/(?P<id>[A-Za-z0-9]+)/?$'''
     _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
-    _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream'
+    _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
     _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
     _TESTS = [
         {
     _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
     _TESTS = [
         {
@@ -70,14 +67,19 @@ class TheSixtyOneIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group('id')
+        song_id = self._match_id(url)
 
         webpage = self._download_webpage(
             self._SONG_URL_TEMPLATE.format(song_id), song_id)
 
 
         webpage = self._download_webpage(
             self._SONG_URL_TEMPLATE.format(song_id), song_id)
 
-        song_data = json.loads(self._search_regex(
-            r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'))
+        song_data = self._parse_json(self._search_regex(
+            r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'), song_id)
+
+        if self._search_regex(r'(t61\.s3_audio_load\s*=\s*1\.0;)', webpage, 's3_audio_load marker', default=None):
+            song_data['audio_server'] = 's3.amazonaws.com'
+        else:
+            song_data['audio_server'] = song_data['audio_server'] + '.thesixtyone.com'
+
         keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
         url = self._SONG_FILE_URL_TEMPLATE.format(
             "".join(reversed(keys)), **song_data)
         keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
         url = self._SONG_FILE_URL_TEMPLATE.format(
             "".join(reversed(keys)), **song_data)
diff --git a/youtube_dl/extractor/thisamericanlife.py b/youtube_dl/extractor/thisamericanlife.py
new file mode 100644 (file)
index 0000000..36493a5
--- /dev/null
@@ -0,0 +1,40 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ThisAmericanLifeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/(?:radio-archives/episode/|play_full\.php\?play=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
+        'md5': '8f7d2da8926298fdfca2ee37764c11ce',
+        'info_dict': {
+            'id': '487',
+            'ext': 'm4a',
+            'title': '487: Harper High School, Part One',
+            'description': 'md5:ee40bdf3fb96174a9027f76dbecea655',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.thisamericanlife.org/play_full.php?play=487',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.thisamericanlife.org/radio-archives/episode/%s' % video_id, video_id)
+
+        return {
+            'id': video_id,
+            'url': 'http://stream.thisamericanlife.org/{0}/stream/{0}_64k.m3u8'.format(video_id),
+            'protocol': 'm3u8_native',
+            'ext': 'm4a',
+            'acodec': 'aac',
+            'vcodec': 'none',
+            'abr': 64,
+            'title': self._html_search_meta(r'twitter:title', webpage, 'title', fatal=True),
+            'description': self._html_search_meta(r'description', webpage, 'description'),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }
index 9f9e388c50948d658d1022f8514122643b623a03..13263614cc06b099d929ee71564899ac3620f76a 100644 (file)
@@ -12,17 +12,22 @@ class TlcIE(DiscoveryIE):
     IE_NAME = 'tlc.com'
     _VALID_URL = r'http://www\.tlc\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
 
     IE_NAME = 'tlc.com'
     _VALID_URL = r'http://www\.tlc\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
 
-    _TEST = {
+    # DiscoveryIE has _TESTS
+    _TESTS = [{
         'url': 'http://www.tlc.com/tv-shows/cake-boss/videos/too-big-to-fly.htm',
         'url': 'http://www.tlc.com/tv-shows/cake-boss/videos/too-big-to-fly.htm',
-        'md5': 'c4038f4a9b44d0b5d74caaa64ed2a01a',
         'info_dict': {
         'info_dict': {
-            'id': '853232',
+            'id': '104493',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'Cake Boss: Too Big to Fly',
+            'title': 'Too Big to Fly',
             'description': 'Buddy has taken on a high flying task.',
             'duration': 119,
             'description': 'Buddy has taken on a high flying task.',
             'duration': 119,
+            'timestamp': 1393365060,
+            'upload_date': '20140225',
         },
         },
-    }
+        'params': {
+            'skip_download': True,  # requires ffmpef
+        },
+    }]
 
 
 class TlcDeIE(InfoExtractor):
 
 
 class TlcDeIE(InfoExtractor):
index c282865b2517d8cbd62df6f2dee0540146baae48..49516abca690721a83dee5044bb2cdd6540d4a07 100644 (file)
@@ -3,39 +3,70 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
 from ..utils import (
-    parse_duration,
     fix_xml_ampersands,
     fix_xml_ampersands,
+    float_or_none,
+    int_or_none,
+    parse_duration,
+    str_to_int,
+    xpath_text,
 )
 
 
 )
 
 
-class TNAFlixIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
-
-    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
-    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
-            'md5': 'ecf3498417d09216374fc5907f9c6ec0',
-            'info_dict': {
-                'id': '553878',
-                'display_id': 'Carmella-Decesare-striptease',
-                'ext': 'mp4',
-                'title': 'Carmella Decesare - striptease',
-                'description': '',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'duration': 91,
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
-            'only_matching': True,
-        }
+class TNAFlixNetworkBaseIE(InfoExtractor):
+    # May be overridden in descendants if necessary
+    _CONFIG_REGEX = [
+        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
+        r'<input[^>]+name="config\d?" value="([^"]+)"',
     ]
     ]
+    _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
+    _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
+    _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
+    _VIEW_COUNT_REGEX = None
+    _COMMENT_COUNT_REGEX = None
+    _AVERAGE_RATING_REGEX = None
+    _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
+
+    def _extract_thumbnails(self, flix_xml):
+
+        def get_child(elem, names):
+            for name in names:
+                child = elem.find(name)
+                if child is not None:
+                    return child
+
+        timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
+        if timeline is None:
+            return
+
+        pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
+        if pattern_el is None or not pattern_el.text:
+            return
+
+        first_el = get_child(timeline, ['imageFirst', 'first'])
+        last_el = get_child(timeline, ['imageLast', 'last'])
+        if first_el is None or last_el is None:
+            return
+
+        first_text = first_el.text
+        last_text = last_el.text
+        if not first_text.isdigit() or not last_text.isdigit():
+            return
+
+        first = int(first_text)
+        last = int(last_text)
+        if first > last:
+            return
+
+        width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
+        height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
+
+        return [{
+            'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
+            'width': width,
+            'height': height,
+        } for i in range(first, last + 1)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -44,47 +75,195 @@ class TNAFlixIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._html_search_regex(
-            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
-        description = self._html_search_regex(
-            self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
-
-        age_limit = self._rta_search(webpage)
-
-        duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration', default=None))
-
         cfg_url = self._proto_relative_url(self._html_search_regex(
             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
 
         cfg_xml = self._download_xml(
         cfg_url = self._proto_relative_url(self._html_search_regex(
             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
 
         cfg_xml = self._download_xml(
-            cfg_url, display_id, note='Downloading metadata',
+            cfg_url, display_id, 'Downloading metadata',
             transform_source=fix_xml_ampersands)
 
             transform_source=fix_xml_ampersands)
 
-        thumbnail = self._proto_relative_url(
-            cfg_xml.find('./startThumb').text, 'http:')
-
         formats = []
         formats = []
+
+        def extract_video_url(vl):
+            return re.sub('speed=\d+', 'speed=', vl.text)
+
+        video_link = cfg_xml.find('./videoLink')
+        if video_link is not None:
+            formats.append({
+                'url': extract_video_url(video_link),
+                'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
+            })
+
         for item in cfg_xml.findall('./quality/item'):
         for item in cfg_xml.findall('./quality/item'):
-            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
-            format_id = item.find('res').text
-            fmt = {
-                'url': self._proto_relative_url(video_url, 'http:'),
+            video_link = item.find('./videoLink')
+            if video_link is None:
+                continue
+            res = item.find('res')
+            format_id = None if res is None else res.text
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]', format_id, 'height', default=None))
+            formats.append({
+                'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
                 'format_id': format_id,
                 'format_id': format_id,
-            }
-            m = re.search(r'^(\d+)', format_id)
-            if m:
-                fmt['height'] = int(m.group(1))
-            formats.append(fmt)
+                'height': height,
+            })
+
         self._sort_formats(formats)
 
         self._sort_formats(formats)
 
+        thumbnail = self._proto_relative_url(
+            xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
+        thumbnails = self._extract_thumbnails(cfg_xml)
+
+        title = self._html_search_regex(
+            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+
+        age_limit = self._rta_search(webpage)
+
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration', default=None))
+
+        def extract_field(pattern, name):
+            return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
+
+        description = extract_field(self._DESCRIPTION_REGEX, 'description')
+        uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
+        view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
+        comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
+        average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
+
+        categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
+        categories = categories_str.split(', ') if categories_str is not None else []
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'duration': duration,
             'age_limit': age_limit,
             'duration': duration,
             'age_limit': age_limit,
+            'uploader': uploader,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'average_rating': average_rating,
+            'categories': categories,
             'formats': formats,
         }
             'formats': formats,
         }
+
+
+class TNAFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
+
+    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
+
+    _TESTS = [{
+        # anonymous uploader, no categories
+        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'info_dict': {
+            'id': '553878',
+            'display_id': 'Carmella-Decesare-striptease',
+            'ext': 'mp4',
+            'title': 'Carmella Decesare - striptease',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 91,
+            'age_limit': 18,
+            'uploader': 'Anonymous',
+            'categories': [],
+        }
+    }, {
+        # non-anonymous uploader, categories
+        'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
+        'md5': '0f5d4d490dbfd117b8607054248a07c0',
+        'info_dict': {
+            'id': '6538',
+            'display_id': 'Educational-xxx-video',
+            'ext': 'mp4',
+            'title': 'Educational xxx video',
+            'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 164,
+            'age_limit': 18,
+            'uploader': 'bobwhite39',
+            'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
+        }
+    }, {
+        'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+        'only_matching': True,
+    }]
+
+
+class EMPFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+
+    _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
+
+    _TESTS = [{
+        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+        'info_dict': {
+            'id': '33051',
+            'display_id': 'Amateur-Finger-Fuck',
+            'ext': 'mp4',
+            'title': 'Amateur Finger Fuck',
+            'description': 'Amateur solo finger fucking.',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 83,
+            'age_limit': 18,
+            'uploader': 'cwbike',
+            'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
+        }
+    }, {
+        'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+        'only_matching': True,
+    }]
+
+
+class MovieFapIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
+
+    _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
+    _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
+    _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
+    _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
+
+    _TESTS = [{
+        # normal, multi-format video
+        'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
+        'md5': '26624b4e2523051b550067d547615906',
+        'info_dict': {
+            'id': 'be9867c9416c19f54a4a',
+            'display_id': 'experienced-milf-amazing-handjob',
+            'ext': 'mp4',
+            'title': 'Experienced MILF Amazing Handjob',
+            'description': 'Experienced MILF giving an Amazing Handjob',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'darvinfred06',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
+        }
+    }, {
+        # quirky single-format case where the extension is given as fid, but the video is really an flv
+        'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
+        'md5': 'fa56683e291fc80635907168a743c9ad',
+        'info_dict': {
+            'id': 'e5da0d3edce5404418f5',
+            'display_id': 'jeune-couple-russe',
+            'ext': 'flv',
+            'title': 'Jeune Couple Russe',
+            'description': 'Amateur',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'whiskeyjar',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Teen'],
+        }
+    }]
index 6ca8840b0869f1490c06c7df0905c28e38ba1fee..c9cb69333f7da0a9f4fe009e79b06433bca83726 100644 (file)
@@ -47,7 +47,7 @@ class Tube8IE(InfoExtractor):
         webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
         webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
-            r'flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
+            r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'))
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
index e6218808f29116e8d2d0d39f2a61342eef1bc823..3d3b635e4cb362515b365ccd8f9321e5124aadeb 100644 (file)
@@ -39,6 +39,17 @@ class TumblrIE(InfoExtractor):
             'timestamp': 1430931613,
         },
         'add_ie': ['Vidme'],
             'timestamp': 1430931613,
         },
         'add_ie': ['Vidme'],
+    }, {
+        'url': 'http://camdamage.tumblr.com/post/98846056295/',
+        'md5': 'a9e0c8371ea1ca306d6554e3fecf50b6',
+        'info_dict': {
+            'id': '105463834',
+            'ext': 'mp4',
+            'title': 'Cam Damage-HD 720p',
+            'uploader': 'John Moyer',
+            'uploader_id': 'user32021558',
+        },
+        'add_ie': ['Vimeo'],
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
@@ -47,18 +58,16 @@ class TumblrIE(InfoExtractor):
         blog = m_url.group('blog_name')
 
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
         blog = m_url.group('blog_name')
 
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
-        webpage = self._download_webpage(url, video_id)
-
-        vid_me_embed_url = self._search_regex(
-            r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
-            webpage, 'vid.me embed', default=None)
-        if vid_me_embed_url is not None:
-            return self.url_result(vid_me_embed_url, 'Vidme')
+        webpage, urlh = self._download_webpage_handle(url, video_id)
 
         iframe_url = self._search_regex(
             r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
 
         iframe_url = self._search_regex(
             r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
-            webpage, 'iframe url')
-        iframe = self._download_webpage(iframe_url, video_id)
+            webpage, 'iframe url', default=None)
+        if iframe_url is None:
+            return self.url_result(urlh.geturl(), 'Generic')
+
+        iframe = self._download_webpage(iframe_url, video_id,
+                                        'Downloading iframe page')
         video_url = self._search_regex(r'<source src="([^"]+)"',
                                        iframe, 'video url')
 
         video_url = self._search_regex(r'<source src="([^"]+)"',
                                        iframe, 'video url')
 
index 29703a8a9a6ddf0981642c28cd2f1f68cc07c7b7..7ae63a4992a74368ec8b5f6a266a298cb6776b79 100644 (file)
@@ -23,7 +23,7 @@ class TurboIE(InfoExtractor):
             'ext': 'mp4',
             'duration': 3715,
             'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
             'ext': 'mp4',
             'duration': 3715,
             'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
-            'description': 'Retrouvez dans cette rubrique toutes les vidéos de l\'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
+            'description': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia...',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
@@ -42,7 +42,7 @@ class TurboIE(InfoExtractor):
         title = xpath_text(item, './title', 'title')
         duration = int_or_none(xpath_text(item, './durate', 'duration'))
         thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
         title = xpath_text(item, './title', 'title')
         duration = int_or_none(xpath_text(item, './durate', 'duration'))
         thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
-        description = self._og_search_description(webpage)
+        description = self._html_search_meta('description', webpage)
 
         formats = []
         get_quality = qualities(['3g', 'sd', 'hq'])
 
         formats = []
         get_quality = qualities(['3g', 'sd', 'hq'])
diff --git a/youtube_dl/extractor/tvc.py b/youtube_dl/extractor/tvc.py
new file mode 100644 (file)
index 0000000..3a4f393
--- /dev/null
@@ -0,0 +1,109 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+)
+
+
+class TVCIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702',
+        'md5': 'bbc5ff531d1e90e856f60fc4b3afd708',
+        'info_dict': {
+            'id': '74622',
+            'ext': 'mp4',
+            'title': 'События. "События". Эфир от 22.05.2015 14:30',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1122,
+        },
+    }
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:http:)?//(?:www\.)?tvc\.ru/video/iframe/id/[^"]+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://www.tvc.ru/video/json/id/%s' % video_id, video_id)
+
+        formats = []
+        for info in video.get('path', {}).get('quality', []):
+            video_url = info.get('url')
+            if not video_url:
+                continue
+            format_id = self._search_regex(
+                r'cdnvideo/([^/]+?)(?:-[^/]+?)?/', video_url,
+                'format id', default=None)
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+                'width': int_or_none(info.get('width')),
+                'height': int_or_none(info.get('height')),
+                'tbr': int_or_none(info.get('bitrate')),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video['title'],
+            'thumbnail': video.get('picture'),
+            'duration': int_or_none(video.get('duration')),
+            'formats': formats,
+        }
+
+
+class TVCArticleIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/',
+        'info_dict': {
+            'id': '74622',
+            'ext': 'mp4',
+            'title': 'События. "События". Эфир от 22.05.2015 14:30',
+            'description': 'md5:ad7aa7db22903f983e687b8a3e98c6dd',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1122,
+        },
+    }, {
+        'url': 'http://www.tvc.ru/news/show/id/69944',
+        'info_dict': {
+            'id': '75399',
+            'ext': 'mp4',
+            'title': 'Эксперты: в столице встал вопрос о максимально безопасных остановках',
+            'description': 'md5:f2098f71e21f309e89f69b525fd9846e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 278,
+        },
+    }, {
+        'url': 'http://www.tvc.ru/channel/brand/id/47/show/episodes#',
+        'info_dict': {
+            'id': '2185',
+            'ext': 'mp4',
+            'title': 'Ещё не поздно. Эфир от 03.08.2013',
+            'description': 'md5:51fae9f3f8cfe67abce014e428e5b027',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 3316,
+        },
+    }]
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, self._match_id(url))
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'TVC',
+            'url': self._og_search_video_url(webpage),
+            'title': clean_html(self._og_search_title(webpage)),
+            'description': clean_html(self._og_search_description(webpage)),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }
index e83e31a31640fa32e4a19a48a745d279a14d3753..79863e781fd41101c76659ab3b43a85433d25665 100644 (file)
@@ -26,6 +26,7 @@ class TVPlayIE(InfoExtractor):
            viasat4play\.no/programmer|
            tv6play\.no/programmer|
            tv3play\.dk/programmer|
            viasat4play\.no/programmer|
            tv6play\.no/programmer|
            tv3play\.dk/programmer|
+           play\.novatv\.bg/programi
         )/[^/]+/(?P<id>\d+)
         '''
     _TESTS = [
         )/[^/]+/(?P<id>\d+)
         '''
     _TESTS = [
@@ -173,6 +174,22 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
+            'info_dict': {
+                'id': '624952',
+                'ext': 'flv',
+                'title': 'Здравей, България (12.06.2015 г.) ',
+                'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
+                'duration': 8838,
+                'timestamp': 1434100372,
+                'upload_date': '20150612',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):
index 94bd6345da18815a50b72502a8b91ae4e30ae2b5..73ce335b7f0a5b5790f8dd65e3ac170e9791b7d8 100644 (file)
@@ -22,8 +22,8 @@ class TwitchBaseIE(InfoExtractor):
 
     _API_BASE = 'https://api.twitch.tv'
     _USHER_BASE = 'http://usher.twitch.tv'
 
     _API_BASE = 'https://api.twitch.tv'
     _USHER_BASE = 'http://usher.twitch.tv'
-    _LOGIN_URL = 'https://secure.twitch.tv/user/login'
-    _LOGIN_POST_URL = 'https://secure-login.twitch.tv/login'
+    _LOGIN_URL = 'https://secure.twitch.tv/login'
+    _LOGIN_POST_URL = 'https://passport.twitch.tv/authorize'
     _NETRC_MACHINE = 'twitch'
 
     def _handle_error(self, response):
     _NETRC_MACHINE = 'twitch'
 
     def _handle_error(self, response):
@@ -59,20 +59,12 @@ class TwitchBaseIE(InfoExtractor):
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
-        authenticity_token = self._search_regex(
-            r'<input name="authenticity_token" type="hidden" value="([^"]+)"',
-            login_page, 'authenticity token')
-
-        login_form = {
-            'utf8': '✓'.encode('utf-8'),
-            'authenticity_token': authenticity_token,
-            'redirect_on_login': '',
-            'embed_form': 'false',
-            'mp_source_action': 'login-button',
-            'follow': '',
-            'login': username,
-            'password': password,
-        }
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'login': username.encode('utf-8'),
+            'password': password.encode('utf-8'),
+        })
 
         request = compat_urllib_request.Request(
             self._LOGIN_POST_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
 
         request = compat_urllib_request.Request(
             self._LOGIN_POST_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
@@ -80,11 +72,15 @@ class TwitchBaseIE(InfoExtractor):
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
-        m = re.search(
-            r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response)
-        if m:
+        error_message = self._search_regex(
+            r'<div[^>]+class="subwindow_notice"[^>]*>([^<]+)</div>',
+            response, 'error message', default=None)
+        if error_message:
             raise ExtractorError(
             raise ExtractorError(
-                'Unable to login: %s' % m.group('msg').strip(), expected=True)
+                'Unable to login. Twitch said: %s' % error_message, expected=True)
+
+        if '>Reset your password<' in response:
+            self.report_warning('Twitch asks you to reset your password, go to https://secure.twitch.tv/reset/submit')
 
     def _prefer_source(self, formats):
         try:
 
     def _prefer_source(self, formats):
         try:
@@ -189,17 +185,17 @@ class TwitchVodIE(TwitchItemBaseIE):
     _ITEM_SHORTCUT = 'v'
 
     _TEST = {
     _ITEM_SHORTCUT = 'v'
 
     _TEST = {
-        'url': 'http://www.twitch.tv/ksptv/v/3622000',
+        'url': 'http://www.twitch.tv/riotgames/v/6528877',
         'info_dict': {
         'info_dict': {
-            'id': 'v3622000',
+            'id': 'v6528877',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': '''KSPTV: Squadcast: "Everyone's on vacation so here's Dahud" Edition!''',
+            'title': 'LCK Summer Split - Week 6 Day 1',
             'thumbnail': 're:^https?://.*\.jpg$',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'duration': 6951,
-            'timestamp': 1419028564,
-            'upload_date': '20141219',
-            'uploader': 'KSPTV',
-            'uploader_id': 'ksptv',
+            'duration': 17208,
+            'timestamp': 1435131709,
+            'upload_date': '20150624',
+            'uploader': 'Riot Games',
+            'uploader_id': 'riotgames',
             'view_count': int,
         },
         'params': {
             'view_count': int,
         },
         'params': {
@@ -215,7 +211,7 @@ class TwitchVodIE(TwitchItemBaseIE):
             '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
             'Downloading %s access token' % self._ITEM_TYPE)
         formats = self._extract_m3u8_formats(
             '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
             'Downloading %s access token' % self._ITEM_TYPE)
         formats = self._extract_m3u8_formats(
-            '%s/vod/%s?nauth=%s&nauthsig=%s'
+            '%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true'
             % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
             item_id, 'mp4')
         self._prefer_source(formats)
             % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
             item_id, 'mp4')
         self._prefer_source(formats)
@@ -314,9 +310,9 @@ class TwitchBookmarksIE(TwitchPlaylistBaseIE):
 
 class TwitchStreamIE(TwitchBaseIE):
     IE_NAME = 'twitch:stream'
 
 class TwitchStreamIE(TwitchBaseIE):
     IE_NAME = 'twitch:stream'
-    _VALID_URL = r'%s/(?P<id>[^/]+)/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
+    _VALID_URL = r'%s/(?P<id>[^/#?]+)/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
 
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.twitch.tv/shroomztv',
         'info_dict': {
             'id': '12772022048',
         'url': 'http://www.twitch.tv/shroomztv',
         'info_dict': {
             'id': '12772022048',
@@ -335,7 +331,10 @@ class TwitchStreamIE(TwitchBaseIE):
             # m3u8 download
             'skip_download': True,
         },
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.twitch.tv/miracle_doto#profile-0',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         channel_id = self._match_id(url)
 
     def _real_extract(self, url):
         channel_id = self._match_id(url)
@@ -350,6 +349,12 @@ class TwitchStreamIE(TwitchBaseIE):
                 'http://www.twitch.tv/%s/profile' % channel_id,
                 'TwitchProfile', channel_id)
 
                 'http://www.twitch.tv/%s/profile' % channel_id,
                 'TwitchProfile', channel_id)
 
+        # Channel name may be typed if different case than the original channel name
+        # (e.g. http://www.twitch.tv/TWITCHPLAYSPOKEMON) that will lead to constructing
+        # an invalid m3u8 URL. Working around by use of original channel name from stream
+        # JSON and fallback to lowercase if it's not available.
+        channel_id = stream.get('channel', {}).get('name') or channel_id.lower()
+
         access_token = self._download_json(
             '%s/api/channels/%s/access_token' % (self._API_BASE, channel_id), channel_id,
             'Downloading channel access token')
         access_token = self._download_json(
             '%s/api/channels/%s/access_token' % (self._API_BASE, channel_id), channel_id,
             'Downloading channel access token')
diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py
new file mode 100644 (file)
index 0000000..1aaa063
--- /dev/null
@@ -0,0 +1,72 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import (
+    float_or_none,
+    unescapeHTML,
+)
+
+
+class TwitterCardIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
+        'md5': 'a74f50b310c83170319ba16de6955192',
+        'info_dict': {
+            'id': '560070183650213889',
+            'ext': 'mp4',
+            'title': 'TwitterCard',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 30.033,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        # Different formats served for different User-Agents
+        USER_AGENTS = [
+            'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)',  # mp4
+            'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0',  # webm
+        ]
+
+        config = None
+        formats = []
+        for user_agent in USER_AGENTS:
+            request = compat_urllib_request.Request(url)
+            request.add_header('User-Agent', user_agent)
+            webpage = self._download_webpage(request, video_id)
+
+            config = self._parse_json(
+                unescapeHTML(self._search_regex(
+                    r'data-player-config="([^"]+)"', webpage, 'data player config')),
+                video_id)
+
+            video_url = config['playlist'][0]['source']
+
+            f = {
+                'url': video_url,
+            }
+
+            m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
+            if m:
+                f.update({
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                })
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = config.get('posterImageUrl')
+        duration = float_or_none(config.get('duration'))
+
+        return {
+            'id': video_id,
+            'title': 'TwitterCard',
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
index 4667ed83b71f4aec5f081741834e2c9cca010e82..e2bab52fef3451596ec1cf0de19e3131e378b5dd 100644 (file)
@@ -15,7 +15,8 @@ from ..utils import (
 class UdemyIE(InfoExtractor):
     IE_NAME = 'udemy'
     _VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
 class UdemyIE(InfoExtractor):
     IE_NAME = 'udemy'
     _VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
-    _LOGIN_URL = 'https://www.udemy.com/join/login-submit/'
+    _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
+    _ORIGIN_URL = 'https://www.udemy.com'
     _NETRC_MACHINE = 'udemy'
 
     _TESTS = [{
     _NETRC_MACHINE = 'udemy'
 
     _TESTS = [{
@@ -74,29 +75,33 @@ class UdemyIE(InfoExtractor):
                 expected=True)
 
         login_popup = self._download_webpage(
                 expected=True)
 
         login_popup = self._download_webpage(
-            'https://www.udemy.com/join/login-popup?displayType=ajax&showSkipButton=1', None,
-            'Downloading login popup')
+            self._LOGIN_URL, None, 'Downloading login popup')
 
         if login_popup == '<div class="run-command close-popup redirect" data-url="https://www.udemy.com/"></div>':
             return
 
 
         if login_popup == '<div class="run-command close-popup redirect" data-url="https://www.udemy.com/"></div>':
             return
 
-        csrf = self._html_search_regex(
-            r'<input type="hidden" name="csrf" value="(.+?)"',
-            login_popup, 'csrf token')
+        login_form = self._form_hidden_inputs('login-form', login_popup)
+
+        login_form.update({
+            'email': username.encode('utf-8'),
+            'password': password.encode('utf-8'),
+        })
 
 
-        login_form = {
-            'email': username,
-            'password': password,
-            'csrf': csrf,
-            'displayType': 'json',
-            'isSubmitted': '1',
-        }
         request = compat_urllib_request.Request(
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         request = compat_urllib_request.Request(
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
-        response = self._download_json(
+        request.add_header('Referer', self._ORIGIN_URL)
+        request.add_header('Origin', self._ORIGIN_URL)
+
+        response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
             request, None, 'Logging in as %s' % username)
 
-        if 'returnUrl' not in response:
+        if all(logout_pattern not in response
+               for logout_pattern in ['href="https://www.udemy.com/user/logout/', '>Logout<']):
+            error = self._html_search_regex(
+                r'(?s)<div[^>]+class="form-errors[^"]*">(.+?)</div>',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
             raise ExtractorError('Unable to log in')
 
     def _real_extract(self, url):
             raise ExtractorError('Unable to log in')
 
     def _real_extract(self, url):
index c08428acfab446dff6157035ef032ae326199ebf..2151f83382d6b3185722b54de2d0eab2a988c6ae 100644 (file)
@@ -11,6 +11,7 @@ from ..compat import compat_urlparse
 
 
 class UDNEmbedIE(InfoExtractor):
 
 
 class UDNEmbedIE(InfoExtractor):
+    IE_DESC = '聯合影音'
     _VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://video.udn.com/embed/news/300040',
     _VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://video.udn.com/embed/news/300040',
index dd026748dcbb536f9f49181b0d211bf0a9157777..722eb52368825b92c88506ff33d79bf1f2f91a32 100644 (file)
@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
 )
 from ..utils import (
     ExtractorError,
@@ -26,11 +27,21 @@ class Vbox7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';',
-                                          redirect_page, 'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id,
+        # need to get the page 3 times for the correct jsSecretToken cookie
+        # which is necessary for the correct title
+        def get_session_id():
+            redirect_page = self._download_webpage(url, video_id)
+            session_id_url = self._search_regex(
+                r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
+                'session id url')
+            self._download_webpage(
+                compat_urlparse.urljoin(url, session_id_url), video_id,
+                'Getting session id')
+
+        get_session_id()
+        get_session_id()
+
+        webpage = self._download_webpage(url, video_id,
                                          'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',
                                          'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',
index 346edf485998e973f4a56f8dee3213093f90aae1..0d8d832cc0890a8cb99c8388b1b9fc1964396d23 100644 (file)
@@ -5,6 +5,7 @@ import json
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_parse_unquote,
     compat_urlparse,
 )
 from ..utils import (
     compat_urlparse,
 )
 from ..utils import (
@@ -76,7 +77,7 @@ class VeeHDIE(InfoExtractor):
 
         if config_json:
             config = json.loads(config_json)
 
         if config_json:
             config = json.loads(config_json)
-            video_url = compat_urlparse.unquote(config['clip']['url'])
+            video_url = compat_urllib_parse_unquote(config['clip']['url'])
 
         if not video_url:
             video_url = self._html_search_regex(
 
         if not video_url:
             video_url = self._html_search_regex(
index 04e2b0ba7849adee473a42e471d77ced7df0652c..01af7a99574401b38e487b01dd5104e674740bbc 100644 (file)
@@ -1,5 +1,4 @@
 from __future__ import unicode_literals
 from __future__ import unicode_literals
-import re
 
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
 
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
@@ -7,25 +6,29 @@ from ..utils import ExtractorError
 
 
 class ViceIE(InfoExtractor):
 
 
 class ViceIE(InfoExtractor):
-    _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)'
 
 
-    _TEST = {
-        'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
-        'info_dict': {
-            'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
-            'ext': 'mp4',
-            'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
-        },
-        'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            'skip_download': True,
-        },
-    }
+    _TESTS = [
+        {
+            'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
+            'info_dict': {
+                'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
+                'ext': 'mp4',
+                'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+            },
+            'params': {
+                # Requires ffmpeg (m3u8 manifest)
+                'skip_download': True,
+            },
+        }, {
+            'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
+            'only_matching': True,
+        }
+    ]
 
     def _real_extract(self, url):
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
         try:
             embed_code = self._search_regex(
                 r'embedCode=([^&\'"]+)', webpage,
         try:
             embed_code = self._search_regex(
                 r'embedCode=([^&\'"]+)', webpage,
index eb309a7cdf99b3ebc4bde755fe09d47505516f28..78ff6310a07f6864abda658ca1e804e26594460b 100644 (file)
@@ -8,20 +8,23 @@ from ..compat import compat_urllib_request
 
 
 class VideoMegaIE(InfoExtractor):
 
 
 class VideoMegaIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://
-        (?:www\.)?videomega\.tv/
-        (?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
-        '''
-    _TEST = {
-        'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4',
-        'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
+    _VALID_URL = r'(?:videomega:|https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=)(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA',
+        'md5': 'cc1920a58add3f05c6a93285b84fb3aa',
         'info_dict': {
         'info_dict': {
-            'id': '4GNA688SU99US886ANG4',
+            'id': 'AOSQBJYKIDDIKYJBQSOA',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'BigBuckBunny_320x180',
+            'title': '1254207',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
             'thumbnail': 're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA&width=1070&height=600',
+        'only_matching': True,
+    }, {
+        'url': 'http://videomega.tv/view.php?ref=090051111052065112106089103052052103089106112065052111051090',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -29,12 +32,13 @@ class VideoMegaIE(InfoExtractor):
         iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
         req = compat_urllib_request.Request(iframe_url)
         req.add_header('Referer', url)
         iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
         req = compat_urllib_request.Request(iframe_url)
         req.add_header('Referer', url)
+        req.add_header('Cookie', 'noadvtday=0')
         webpage = self._download_webpage(req, video_id)
 
         title = self._html_search_regex(
         webpage = self._download_webpage(req, video_id)
 
         title = self._html_search_regex(
-            r'<title>(.*?)</title>', webpage, 'title')
+            r'<title>(.+?)</title>', webpage, 'title')
         title = re.sub(
         title = re.sub(
-            r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title)
+            r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s*|\s*-\svideomega\.tv$)', '', title)
         thumbnail = self._search_regex(
             r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
         video_url = self._search_regex(
         thumbnail = self._search_regex(
             r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
         video_url = self._search_regex(
index 7f2fb1ca8896e29e48a41a9efddaded987ba1e96..51cdc6b65143aaf4a0d2823ffa8c859c96e25972 100644 (file)
@@ -1,5 +1,7 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
+import json
 import time
 import hmac
 import hashlib
 import time
 import hmac
 import hashlib
@@ -11,6 +13,7 @@ from ..utils import (
     parse_age_limit,
     parse_iso8601,
 )
     parse_age_limit,
     parse_iso8601,
 )
+from ..compat import compat_urllib_request
 from .common import InfoExtractor
 
 
 from .common import InfoExtractor
 
 
@@ -23,27 +26,35 @@ class VikiBaseIE(InfoExtractor):
     _APP_VERSION = '2.2.5.1428709186'
     _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
 
     _APP_VERSION = '2.2.5.1428709186'
     _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
 
-    def _prepare_call(self, path, timestamp=None):
+    _NETRC_MACHINE = 'viki'
+
+    _token = None
+
+    def _prepare_call(self, path, timestamp=None, post_data=None):
         path += '?' if '?' not in path else '&'
         if not timestamp:
             timestamp = int(time.time())
         query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
         path += '?' if '?' not in path else '&'
         if not timestamp:
             timestamp = int(time.time())
         query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
+        if self._token:
+            query += '&token=%s' % self._token
         sig = hmac.new(
             self._APP_SECRET.encode('ascii'),
             query.encode('ascii'),
             hashlib.sha1
         ).hexdigest()
         sig = hmac.new(
             self._APP_SECRET.encode('ascii'),
             query.encode('ascii'),
             hashlib.sha1
         ).hexdigest()
-        return self._API_URL_TEMPLATE % (query, sig)
+        url = self._API_URL_TEMPLATE % (query, sig)
+        return compat_urllib_request.Request(
+            url, json.dumps(post_data).encode('utf-8')) if post_data else url
 
 
-    def _call_api(self, path, video_id, note, timestamp=None):
+    def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
         resp = self._download_json(
         resp = self._download_json(
-            self._prepare_call(path, timestamp), video_id, note)
+            self._prepare_call(path, timestamp, post_data), video_id, note)
 
         error = resp.get('error')
         if error:
             if error == 'invalid timestamp':
                 resp = self._download_json(
 
         error = resp.get('error')
         if error:
             if error == 'invalid timestamp':
                 resp = self._download_json(
-                    self._prepare_call(path, int(resp['current_timestamp'])),
+                    self._prepare_call(path, int(resp['current_timestamp']), post_data),
                     video_id, '%s (retry)' % note)
                 error = resp.get('error')
             if error:
                     video_id, '%s (retry)' % note)
                 error = resp.get('error')
             if error:
@@ -56,6 +67,27 @@ class VikiBaseIE(InfoExtractor):
             '%s returned error: %s' % (self.IE_NAME, error),
             expected=True)
 
             '%s returned error: %s' % (self.IE_NAME, error),
             expected=True)
 
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'login_id': username,
+            'password': password,
+        }
+
+        login = self._call_api(
+            'sessions.json', None,
+            'Logging in as %s' % username, post_data=login_form)
+
+        self._token = login.get('token')
+        if not self._token:
+            self.report_warning('Unable to get session token, login has probably failed')
+
 
 class VikiIE(VikiBaseIE):
     IE_NAME = 'viki'
 
 class VikiIE(VikiBaseIE):
     IE_NAME = 'viki'
index f300c7ca40eeba75f872bbd6cd79c3f0720e0955..10d6745af703e00d6962d3e14c8b01f2419ad955 100644 (file)
@@ -22,6 +22,7 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     urlencode_postdata,
     unified_strdate,
     unsmuggle_url,
     urlencode_postdata,
+    unescapeHTML,
 )
 
 
 )
 
 
@@ -173,6 +174,21 @@ class VimeoIE(VimeoBaseInfoExtractor):
         },
     ]
 
         },
     ]
 
+    @staticmethod
+    def _extract_vimeo_url(url, webpage):
+        # Look for embedded (iframe) Vimeo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
+        if mobj:
+            player_url = unescapeHTML(mobj.group('url'))
+            surl = smuggle_url(player_url, {'Referer': url})
+            return surl
+        # Look for embedded (swf embed) Vimeo player
+        mobj = re.search(
+            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+        if mobj:
+            return mobj.group(1)
+
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
@@ -436,11 +452,7 @@ class VimeoChannelIE(InfoExtractor):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
         password = self._downloader.params.get('videopassword', None)
         if password is None:
             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            value="([^"]*)"
-            ''', login_form))
+        fields = self._hidden_inputs(login_form)
         token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
         fields['token'] = token
         fields['password'] = password
         token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
         fields['token'] = token
         fields['password'] = password
index aa3d6ddfd2420524fd87f85819d2611225224e79..92321d66e369626c0adfeda6cb4fae282a6f7abb 100644 (file)
@@ -4,7 +4,29 @@ from .common import InfoExtractor
 from ..utils import int_or_none
 
 
 from ..utils import int_or_none
 
 
-class VimpleIE(InfoExtractor):
+class SprutoBaseIE(InfoExtractor):
+    def _extract_spruto(self, spruto, video_id):
+        playlist = spruto['playlist'][0]
+        title = playlist['title']
+        video_id = playlist.get('videoId') or video_id
+        thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
+        duration = int_or_none(playlist.get('duration'))
+
+        formats = [{
+            'url': f['url'],
+        } for f in playlist['video']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class VimpleIE(SprutoBaseIE):
     IE_DESC = 'Vimple - one-click video hosting'
     _VALID_URL = r'https?://(?:player\.vimple\.ru/iframe|vimple\.ru)/(?P<id>[\da-f-]{32,36})'
     _TESTS = [
     IE_DESC = 'Vimple - one-click video hosting'
     _VALID_URL = r'https?://(?:player\.vimple\.ru/iframe|vimple\.ru)/(?P<id>[\da-f-]{32,36})'
     _TESTS = [
@@ -30,25 +52,9 @@ class VimpleIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://player.vimple.ru/iframe/%s' % video_id, video_id)
 
         webpage = self._download_webpage(
             'http://player.vimple.ru/iframe/%s' % video_id, video_id)
 
-        playlist = self._parse_json(
+        spruto = self._parse_json(
             self._search_regex(
                 r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
             self._search_regex(
                 r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
-            video_id)['playlist'][0]
-
-        title = playlist['title']
-        video_id = playlist.get('videoId') or video_id
-        thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
-        duration = int_or_none(playlist.get('duration'))
-
-        formats = [{
-            'url': f['url'],
-        } for f in playlist['video']]
-        self._sort_formats(formats)
+            video_id)
 
 
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-        }
+        return self._extract_spruto(spruto, video_id)
index cc384adbf9837f35f90c64d0e8dc0396b0b601ec..c30c5a8e524324a29d7c4a2dad49d5b9d50dda30 100644 (file)
@@ -13,14 +13,26 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     orderedSet,
 from ..utils import (
     ExtractorError,
     orderedSet,
+    str_to_int,
     unescapeHTML,
     unified_strdate,
 )
 
 
 class VKIE(InfoExtractor):
     unescapeHTML,
     unified_strdate,
 )
 
 
 class VKIE(InfoExtractor):
-    IE_NAME = 'vk.com'
-    _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
+    IE_NAME = 'vk'
+    IE_DESC = 'VK'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
+                            (?:
+                                (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
+                                (?:www\.)?biqle\.ru/watch/
+                            )
+                            (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
+                        )
+                    '''
     _NETRC_MACHINE = 'vk'
 
     _TESTS = [
     _NETRC_MACHINE = 'vk'
 
     _TESTS = [
@@ -34,6 +46,7 @@ class VKIE(InfoExtractor):
                 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
                 'duration': 195,
                 'upload_date': '20120212',
                 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
                 'duration': 195,
                 'upload_date': '20120212',
+                'view_count': int,
             },
         },
         {
             },
         },
         {
@@ -45,7 +58,8 @@ class VKIE(InfoExtractor):
                 'uploader': 'Tom Cruise',
                 'title': 'No name',
                 'duration': 9,
                 'uploader': 'Tom Cruise',
                 'title': 'No name',
                 'duration': 9,
-                'upload_date': '20130721'
+                'upload_date': '20130721',
+                'view_count': int,
             }
         },
         {
             }
         },
         {
@@ -59,6 +73,7 @@ class VKIE(InfoExtractor):
                 'title': 'Lin Dan',
                 'duration': 101,
                 'upload_date': '20120730',
                 'title': 'Lin Dan',
                 'duration': 101,
                 'upload_date': '20120730',
+                'view_count': int,
             }
         },
         {
             }
         },
         {
@@ -73,7 +88,8 @@ class VKIE(InfoExtractor):
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
-                'upload_date': '20121218'
+                'upload_date': '20121218',
+                'view_count': int,
             },
             'skip': 'Requires vk account credentials',
         },
             },
             'skip': 'Requires vk account credentials',
         },
@@ -100,14 +116,54 @@ class VKIE(InfoExtractor):
                 'title': 'Книга Илая',
                 'duration': 6771,
                 'upload_date': '20140626',
                 'title': 'Книга Илая',
                 'duration': 6771,
                 'upload_date': '20140626',
+                'view_count': int,
             },
             'skip': 'Only works from Russia',
         },
             },
             'skip': 'Only works from Russia',
         },
+        {
+            # video (removed?) only available with list id
+            'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
+            'md5': '091287af5402239a1051c37ec7b92913',
+            'info_dict': {
+                'id': '171201961',
+                'ext': 'mp4',
+                'title': 'ТюменцевВВ_09.07.2015',
+                'uploader': 'Anton Ivanov',
+                'duration': 109,
+                'upload_date': '20150709',
+                'view_count': int,
+            },
+        },
+        {
+            # youtube embed
+            'url': 'https://vk.com/video276849682_170681728',
+            'info_dict': {
+                'id': 'V3K4mi0SYkc',
+                'ext': 'mp4',
+                'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
+                'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
+                'duration': 179,
+                'upload_date': '20130116',
+                'uploader': "Children's Joy Foundation",
+                'uploader_id': 'thecjf',
+                'view_count': int,
+            },
+        },
         {
             # removed video, just testing that we match the pattern
             'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
             'only_matching': True,
         },
         {
             # removed video, just testing that we match the pattern
             'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
             'only_matching': True,
         },
+        {
+            # age restricted video, requires vk account credentials
+            'url': 'https://vk.com/video205387401_164765225',
+            'only_matching': True,
+        },
+        {
+            # vk wrapper
+            'url': 'http://www.biqle.ru/watch/847655_160197695',
+            'only_matching': True,
+        }
     ]
 
     def _login(self):
     ]
 
     def _login(self):
@@ -115,20 +171,25 @@ class VKIE(InfoExtractor):
         if username is None:
             return
 
         if username is None:
             return
 
-        login_form = {
-            'act': 'login',
-            'role': 'al_frame',
-            'expire': '1',
-            'email': username,
-            'pass': password,
-        }
+        login_page = self._download_webpage(
+            'https://vk.com', None, 'Downloading login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'email': username.encode('cp1251'),
+            'pass': password.encode('cp1251'),
+        })
 
 
-        request = compat_urllib_request.Request('https://login.vk.com/?act=login',
-                                                compat_urllib_parse.urlencode(login_form).encode('utf-8'))
-        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+        request = compat_urllib_request.Request(
+            'https://login.vk.com/?act=login',
+            compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        login_page = self._download_webpage(
+            request, None, note='Logging in as %s' % username)
 
         if re.search(r'onLoginFailed', login_page):
 
         if re.search(r'onLoginFailed', login_page):
-            raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
+            raise ExtractorError(
+                'Unable to login, incorrect username and/or password', expected=True)
 
     def _real_initialize(self):
         self._login()
 
     def _real_initialize(self):
         self._login()
@@ -140,9 +201,26 @@ class VKIE(InfoExtractor):
         if not video_id:
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
         if not video_id:
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
-        info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+        info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+
+        # Some videos (removed?) can only be downloaded with list id specified
+        list_id = mobj.group('list_id')
+        if list_id:
+            info_url += '&list=%s' % list_id
+
         info_page = self._download_webpage(info_url, video_id)
 
         info_page = self._download_webpage(info_url, video_id)
 
+        error_message = self._html_search_regex(
+            r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
+            info_page, 'error message', default=None)
+        if error_message:
+            raise ExtractorError(error_message, expected=True)
+
+        if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
+            raise ExtractorError(
+                'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
+                expected=True)
+
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
             'Video %s has been removed from public access due to rightholder complaint.',
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
             'Video %s has been removed from public access due to rightholder complaint.',
@@ -156,16 +234,20 @@ class VKIE(InfoExtractor):
 
             r'<!>Видео временно недоступно':
             'Video %s is temporarily unavailable.',
 
             r'<!>Видео временно недоступно':
             'Video %s is temporarily unavailable.',
+
+            r'<!>Access denied':
+            'Access denied to video %s.',
         }
 
         for error_re, error_msg in ERRORS.items():
             if re.search(error_re, info_page):
                 raise ExtractorError(error_msg % video_id, expected=True)
 
         }
 
         for error_re, error_msg in ERRORS.items():
             if re.search(error_re, info_page):
                 raise ExtractorError(error_msg % video_id, expected=True)
 
-        m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
-        if m_yt is not None:
-            self.to_screen('Youtube video detected')
-            return self.url_result(m_yt.group(1), 'Youtube')
+        youtube_url = self._search_regex(
+            r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
+            info_page, 'youtube iframe', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, 'Youtube')
 
         m_rutube = re.search(
             r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
 
         m_rutube = re.search(
             r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
@@ -175,25 +257,29 @@ class VKIE(InfoExtractor):
                 m_rutube.group(1).replace('\\', ''))
             return self.url_result(rutube_url)
 
                 m_rutube.group(1).replace('\\', ''))
             return self.url_result(rutube_url)
 
-        m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
+        m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
         if m_opts:
         if m_opts:
-            m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
+            m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
             if m_opts_url:
                 opts_url = m_opts_url.group(1)
                 if opts_url.startswith('//'):
                     opts_url = 'http:' + opts_url
                 return self.url_result(opts_url)
 
             if m_opts_url:
                 opts_url = m_opts_url.group(1)
                 if opts_url.startswith('//'):
                     opts_url = 'http:' + opts_url
                 return self.url_result(opts_url)
 
-        data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
+        data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
         data = json.loads(data_json)
 
         # Extract upload date
         upload_date = None
         data = json.loads(data_json)
 
         # Extract upload date
         upload_date = None
-        mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
+        mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
         if mobj is not None:
             mobj.group(1) + ' ' + mobj.group(2)
             upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
 
         if mobj is not None:
             mobj.group(1) + ' ' + mobj.group(2)
             upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
 
+        view_count = str_to_int(self._search_regex(
+            r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
+            info_page, 'view count', fatal=False))
+
         formats = [{
             'format_id': k,
             'url': v,
         formats = [{
             'format_id': k,
             'url': v,
@@ -210,29 +296,39 @@ class VKIE(InfoExtractor):
             'uploader': data.get('md_author'),
             'duration': data.get('duration'),
             'upload_date': upload_date,
             'uploader': data.get('md_author'),
             'duration': data.get('duration'),
             'upload_date': upload_date,
+            'view_count': view_count,
         }
 
 
 class VKUserVideosIE(InfoExtractor):
         }
 
 
 class VKUserVideosIE(InfoExtractor):
-    IE_NAME = 'vk.com:user-videos'
-    IE_DESC = 'vk.com:All of a user\'s videos'
-    _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
+    IE_NAME = 'vk:uservideos'
+    IE_DESC = "VK - User's Videos"
+    _VALID_URL = r'https?://vk\.com/videos(?P<id>-?[0-9]+)$'
     _TEMPLATE_URL = 'https://vk.com/videos'
     _TEMPLATE_URL = 'https://vk.com/videos'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://vk.com/videos205387401',
         'info_dict': {
             'id': '205387401',
         'url': 'http://vk.com/videos205387401',
         'info_dict': {
             'id': '205387401',
+            'title': "Tom Cruise's Videos",
         },
         'playlist_mincount': 4,
         },
         'playlist_mincount': 4,
-    }
+    }, {
+        'url': 'http://vk.com/videos-77521',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
-        page = self._download_webpage(url, page_id)
-        video_ids = orderedSet(
-            m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
-        url_entries = [
+
+        webpage = self._download_webpage(url, page_id)
+
+        entries = [
             self.url_result(
                 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
             self.url_result(
                 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
-            for video_id in video_ids]
-        return self.playlist_result(url_entries, page_id)
+            for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
+
+        title = unescapeHTML(self._search_regex(
+            r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
+            webpage, 'title', default=page_id))
+
+        return self.playlist_result(entries, page_id, title)
index 1c0966a793511a2ec3a9d147bd75ff22e8fb7209..ccf1928b5d323f277b4e8a47bd4d008e821b147c 100644 (file)
@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
@@ -28,12 +26,7 @@ class VodlockerIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
-            value="([^"]*)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':
             self._sleep(3, video_id)  # they do detect when requests happen too fast!
 
         if fields['op'] == 'download1':
             self._sleep(3, video_id)  # they do detect when requests happen too fast!
index 405cb9db49f41a144a4c842d8f99aeb1c2023da9..149e364677fcab4d0374479c4b96ff741277b17e 100644 (file)
@@ -36,6 +36,7 @@ class VubeIE(InfoExtractor):
                 'comment_count': int,
                 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
             },
                 'comment_count': int,
                 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
             },
+            'skip': 'Not accessible from Travis CI server',
         }, {
             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
             'md5': 'db7aba89d4603dadd627e9d1973946fe',
         }, {
             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
             'md5': 'db7aba89d4603dadd627e9d1973946fe',
index 73077a312549f6b883fdf549a2b364f6de35db9f..2037d9b3d57cd5876d85e9552ffcc9f387fcc975 100644 (file)
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import int_or_none
 
 from .common import InfoExtractor
 from ..utils import int_or_none
 
@@ -98,3 +100,42 @@ class WebOfStoriesIE(InfoExtractor):
             'description': description,
             'duration': duration,
         }
             'description': description,
             'duration': duration,
         }
+
+
+class WebOfStoriesPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.webofstories.com/playAll/donald.knuth',
+        'info_dict': {
+            'id': 'donald.knuth',
+            'title': 'Donald Knuth (Scientist)',
+        },
+        'playlist_mincount': 97,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories')
+            for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage))
+        ]
+
+        title = self._search_regex(
+            r'<div id="speakerName">\s*<span>([^<]+)</span>',
+            webpage, 'speaker', default=None)
+        if title:
+            field = self._search_regex(
+                r'<span id="primaryField">([^<]+)</span>',
+                webpage, 'field', default=None)
+            if field:
+                title += ' (%s)' % field
+
+        if not title:
+            title = self._search_regex(
+                r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
+                webpage, 'title')
+
+        return self.playlist_result(entries, playlist_id, title)
index 80c48c37d32c0849e689d626811ee34c5b414ee0..4ff99e5ca37fb8f4f0b663cc99761c31e75f1cf4 100644 (file)
@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class XBefIE(InfoExtractor):
 
 
 class XBefIE(InfoExtractor):
@@ -30,7 +28,7 @@ class XBefIE(InfoExtractor):
         config_url_enc = self._download_webpage(
             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
             note='Retrieving config URL')
         config_url_enc = self._download_webpage(
             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
             note='Retrieving config URL')
-        config_url = compat_urllib_parse.unquote(config_url_enc)
+        config_url = compat_urllib_parse_unquote(config_url_enc)
         config = self._download_xml(
             config_url, video_id, note='Retrieving config')
 
         config = self._download_xml(
             config_url, video_id, note='Retrieving config')
 
index 4527567f8fc26c45b091aa868dc77b159576b56c..b4ad513a0d18ecbae558deceb6234efaa5ce5415 100644 (file)
@@ -13,7 +13,6 @@ from ..utils import (
 
 
 class XHamsterIE(InfoExtractor):
 
 
 class XHamsterIE(InfoExtractor):
-    """Information Extractor for xHamster"""
     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [
         {
     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [
         {
@@ -133,3 +132,36 @@ class XHamsterIE(InfoExtractor):
             'age_limit': age_limit,
             'formats': formats,
         }
             'age_limit': age_limit,
             'formats': formats,
         }
+
+
+class XHamsterEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://xhamster.com/xembed.php?video=3328539',
+        'info_dict': {
+            'id': '3328539',
+            'ext': 'mp4',
+            'title': 'Pen Masturbation',
+            'upload_date': '20140728',
+            'uploader_id': 'anonymous',
+            'duration': 5,
+            'age_limit': 18,
+        }
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
+            webpage, 'xhamster url')
+
+        return self.url_result(video_url, 'XHamster')
index 79ed6c744242bf132afd033ae35949cc1e2263b5..5a41f8ffa0c5a46a3d0431a6aac8e93ba8ca1cb9 100644 (file)
@@ -2,9 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class XNXXIE(InfoExtractor):
 
 
 class XNXXIE(InfoExtractor):
@@ -26,7 +24,7 @@ class XNXXIE(InfoExtractor):
 
         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
                                        webpage, 'video URL')
 
         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
                                        webpage, 'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        video_url = compat_urllib_parse_unquote(video_url)
 
         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
                                               webpage, 'title')
 
         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
                                               webpage, 'title')
index 1644f53c876329f053406be3d3dc1aa463cddc1b..779e4f46a1dd5315c6a9be3dad09e65c07a205b2 100644 (file)
@@ -5,7 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
 )
 from ..utils import (
     parse_duration,
 )
 from ..utils import (
     parse_duration,
@@ -59,7 +59,7 @@ class XTubeIE(InfoExtractor):
         for format_id, video_url in re.findall(
                 r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
             fmt = {
         for format_id, video_url in re.findall(
                 r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
             fmt = {
-                'url': compat_urllib_parse.unquote(video_url),
+                'url': compat_urllib_parse_unquote(video_url),
                 'format_id': format_id,
             }
             m = re.search(r'^(?P<height>\d+)[pP]', format_id)
                 'format_id': format_id,
             }
             m = re.search(r'^(?P<height>\d+)[pP]', format_id)
@@ -68,7 +68,7 @@ class XTubeIE(InfoExtractor):
             formats.append(fmt)
 
         if not formats:
             formats.append(fmt)
 
         if not formats:
-            video_url = compat_urllib_parse.unquote(self._search_regex(
+            video_url = compat_urllib_parse_unquote(self._search_regex(
                 r'flashvars\.video_url\s*=\s*"([^"]+)"',
                 webpage, 'video URL'))
             formats.append({'url': video_url})
                 r'flashvars\.video_url\s*=\s*"([^"]+)"',
                 webpage, 'video URL'))
             formats.append({'url': video_url})
index 81d885fdcee1cf788c217e862629df58f386d73c..5aac8adb36e2ad12e798cb4f0c77e5b204c7b91b 100644 (file)
@@ -13,6 +13,7 @@ from ..utils import (
 
 
 class XuiteIE(InfoExtractor):
 
 
 class XuiteIE(InfoExtractor):
+    IE_DESC = '隨意窩Xuite影音'
     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
     _TESTS = [{
     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
     _TESTS = [{
index 2a45dc574263f7e651020e591fcc40bdf987367d..5dcf2fdd12f9140f0bd373fd5db41c93f4b18b38 100644 (file)
@@ -4,11 +4,13 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urllib_request,
 )
 from ..utils import (
     clean_html,
     ExtractorError,
 )
 from ..utils import (
     clean_html,
     ExtractorError,
+    determine_ext,
 )
 
 
 )
 
 
@@ -25,6 +27,8 @@ class XVideosIE(InfoExtractor):
         }
     }
 
         }
     }
 
+    _ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -33,16 +37,37 @@ class XVideosIE(InfoExtractor):
         if mobj:
             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
 
         if mobj:
             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
 
-        video_url = compat_urllib_parse.unquote(
+        video_url = compat_urllib_parse_unquote(
             self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 
             self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 
+        formats = [{
+            'url': video_url,
+        }]
+
+        android_req = compat_urllib_request.Request(url)
+        android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
+        android_webpage = self._download_webpage(android_req, video_id, fatal=False)
+
+        if android_webpage is not None:
+            player_params_str = self._search_regex(
+                'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
+                android_webpage, 'player parameters', default='')
+            player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
+            if player_params:
+                formats.extend([{
+                    'url': param,
+                    'preference': -10,
+                } for param in player_params if determine_ext(param) == 'mp4'])
+
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': video_title,
             'ext': 'flv',
             'thumbnail': video_thumbnail,
             'title': video_title,
             'ext': 'flv',
             'thumbnail': video_thumbnail,
index 9d851bae3b779d8ce434742d6f5ef70d3f423936..001ee17b6f93d457bdc2fbdaf802b61ef19e1b41 100644 (file)
@@ -14,6 +14,7 @@ from ..utils import (
 
 
 class YamIE(InfoExtractor):
 
 
 class YamIE(InfoExtractor):
+    IE_DESC = '蕃薯藤yam天空部落'
     _VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
 
     _TESTS = [{
     _VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
 
     _TESTS = [{
diff --git a/youtube_dl/extractor/yinyuetai.py b/youtube_dl/extractor/yinyuetai.py
new file mode 100644 (file)
index 0000000..834d860
--- /dev/null
@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class YinYueTaiIE(InfoExtractor):
+    IE_NAME = 'yinyuetai:video'
+    IE_DESC = '音悦Tai'
+    _VALID_URL = r'https?://v\.yinyuetai\.com/video(?:/h5)?/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://v.yinyuetai.com/video/2322376',
+        'md5': '6e3abe28d38e3a54b591f9f040595ce0',
+        'info_dict': {
+            'id': '2322376',
+            'ext': 'mp4',
+            'title': '少女时代_PARTY_Music Video Teaser',
+            'creator': '少女时代',
+            'duration': 25,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://v.yinyuetai.com/video/h5/2322376',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        info = self._download_json(
+            'http://ext.yinyuetai.com/main/get-h-mv-info?json=true&videoId=%s' % video_id, video_id,
+            'Downloading mv info')['videoInfo']['coreVideoInfo']
+
+        if info['error']:
+            raise ExtractorError(info['errorMsg'], expected=True)
+
+        formats = [{
+            'url': format_info['videoUrl'],
+            'format_id': format_info['qualityLevel'],
+            'format': format_info.get('qualityLevelName'),
+            'filesize': format_info.get('fileSize'),
+            # though URLs ends with .flv, the downloaded files are in fact mp4
+            'ext': 'mp4',
+            'tbr': format_info.get('bitrate'),
+        } for format_info in info['videoUrlModels']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': info['videoName'],
+            'thumbnail': info.get('bigHeadImage'),
+            'creator': info.get('artistNames'),
+            'duration': info.get('duration'),
+            'formats': formats,
+        }
index 894678a23dac9d1b03e07f0cd9b2eecc7e690e18..869f3e8190ca0b751366a85f142a0b49fe294fa1 100644 (file)
@@ -5,7 +5,7 @@ import re
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote_plus
 
 
 class YnetIE(InfoExtractor):
 
 
 class YnetIE(InfoExtractor):
@@ -34,7 +34,7 @@ class YnetIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
+        content = compat_urllib_parse_unquote_plus(self._og_search_video_url(webpage))
         config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
         f4m_url = config['clip']['url']
         title = self._og_search_title(webpage)
         config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
         f4m_url = config['clip']['url']
         title = self._og_search_title(webpage)
index 97b98bbe88715f644da6bec1709d697af2c8e0e0..78caeb8b36e0be8cf4e97365d9e28251723059b7 100644 (file)
 # coding: utf-8
 # coding: utf-8
-
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-import math
-import random
-import re
-import time
+import base64
 
 from .common import InfoExtractor
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..utils import ExtractorError
+
+from ..compat import (
+    compat_urllib_parse,
+    compat_ord,
+    compat_urllib_request,
 )
 
 
 class YoukuIE(InfoExtractor):
 )
 
 
 class YoukuIE(InfoExtractor):
+    IE_NAME = 'youku'
+    IE_DESC = '优酷'
     _VALID_URL = r'''(?x)
         (?:
             http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
     '''
     _VALID_URL = r'''(?x)
         (?:
             http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
     '''
-    _TEST = {
-        'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
-        'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
-        'params': {
-            'test': False
+
+    _TESTS = [{
+        'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
+        'md5': '5f3af4192eabacc4501508d54a8cabd7',
+        'info_dict': {
+            'id': 'XMTc1ODE5Njcy_part1',
+            'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
+            'ext': 'flv'
+        }
+    }, {
+        'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
+        'only_matching': True,
+    }, {
+        'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
+        'info_dict': {
+            'id': 'XODgxNjg1Mzk2',
+            'title': '武媚娘传奇 85',
         },
         },
+        'playlist_count': 11,
+    }, {
+        'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
         'info_dict': {
         'info_dict': {
-            'id': 'XNDgyMDQ2NTQw_part00',
-            'ext': 'flv',
-            'title': 'youtube-dl test video "\'/\\ä↭𝕐'
+            'id': 'XMTI1OTczNDM5Mg',
+            'title': '花千骨 04',
+        },
+        'playlist_count': 13,
+        'skip': 'Available in China only',
+    }]
+
+    def construct_video_urls(self, data1, data2):
+        # get sid, token
+        def yk_t(s1, s2):
+            ls = list(range(256))
+            t = 0
+            for i in range(256):
+                t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
+                ls[i], ls[t] = ls[t], ls[i]
+            s = bytearray()
+            x, y = 0, 0
+            for i in range(len(s2)):
+                y = (y + 1) % 256
+                x = (x + ls[y]) % 256
+                ls[x], ls[y] = ls[y], ls[x]
+                s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
+            return bytes(s)
+
+        sid, token = yk_t(
+            b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
+        ).decode('ascii').split('_')
+
+        # get oip
+        oip = data2['ip']
+
+        # get fileid
+        string_ls = list(
+            'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
+        shuffled_string_ls = []
+        seed = data1['seed']
+        N = len(string_ls)
+        for ii in range(N):
+            seed = (seed * 0xd3 + 0x754f) % 0x10000
+            idx = seed * len(string_ls) // 0x10000
+            shuffled_string_ls.append(string_ls[idx])
+            del string_ls[idx]
+
+        fileid_dict = {}
+        for format in data1['streamtypes']:
+            streamfileid = [
+                int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
+            fileid = ''.join(
+                [shuffled_string_ls[i] for i in streamfileid])
+            fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
+
+        def get_fileid(format, n):
+            fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+            return fileid
+
+        # get ep
+        def generate_ep(format, n):
+            fileid = get_fileid(format, n)
+            ep_t = yk_t(
+                b'bf7e5f01',
+                ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
+            )
+            ep = base64.b64encode(ep_t).decode('ascii')
+            return ep
+
+        # generate video_urls
+        video_urls_dict = {}
+        for format in data1['streamtypes']:
+            video_urls = []
+            for dt in data1['segs'][format]:
+                n = str(int(dt['no']))
+                param = {
+                    'K': dt['k'],
+                    'hd': self.get_hd(format),
+                    'myp': 0,
+                    'ts': dt['seconds'],
+                    'ypp': 0,
+                    'ctype': 12,
+                    'ev': 1,
+                    'token': token,
+                    'oip': oip,
+                    'ep': generate_ep(format, n)
+                }
+                video_url = \
+                    'http://k.youku.com/player/getFlvPath/' + \
+                    'sid/' + sid + \
+                    '_' + str(int(n) + 1).zfill(2) + \
+                    '/st/' + self.parse_ext_l(format) + \
+                    '/fileid/' + get_fileid(format, n) + '?' + \
+                    compat_urllib_parse.urlencode(param)
+                video_urls.append(video_url)
+            video_urls_dict[format] = video_urls
+
+        return video_urls_dict
+
+    def get_hd(self, fm):
+        hd_id_dict = {
+            'flv': '0',
+            'mp4': '1',
+            'hd2': '2',
+            'hd3': '3',
+            '3gp': '0',
+            '3gphd': '1'
         }
         }
-    }
-
-    def _gen_sid(self):
-        nowTime = int(time.time() * 1000)
-        random1 = random.randint(1000, 1998)
-        random2 = random.randint(1000, 9999)
-
-        return "%d%d%d" % (nowTime, random1, random2)
-
-    def _get_file_ID_mix_string(self, seed):
-        mixed = []
-        source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
-        seed = float(seed)
-        for i in range(len(source)):
-            seed = (seed * 211 + 30031) % 65536
-            index = math.floor(seed / 65536 * len(source))
-            mixed.append(source[int(index)])
-            source.remove(source[int(index)])
-        # return ''.join(mixed)
-        return mixed
-
-    def _get_file_id(self, fileId, seed):
-        mixed = self._get_file_ID_mix_string(seed)
-        ids = fileId.split('*')
-        realId = []
-        for ch in ids:
-            if ch:
-                realId.append(mixed[int(ch)])
-        return ''.join(realId)
+        return hd_id_dict[fm]
+
+    def parse_ext_l(self, fm):
+        ext_dict = {
+            'flv': 'flv',
+            'mp4': 'mp4',
+            'hd2': 'flv',
+            'hd3': 'flv',
+            '3gp': 'flv',
+            '3gphd': 'mp4'
+        }
+        return ext_dict[fm]
+
+    def get_format_name(self, fm):
+        _dict = {
+            '3gp': 'h6',
+            '3gphd': 'h5',
+            'flv': 'h4',
+            'mp4': 'h3',
+            'hd2': 'h2',
+            'hd3': 'h1'
+        }
+        return _dict[fm]
 
     def _real_extract(self, url):
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+        video_id = self._match_id(url)
 
 
-        config = self._download_json(info_url, video_id)
+        def retrieve_data(req_url, note):
+            req = compat_urllib_request.Request(req_url)
 
 
-        error_code = config['data'][0].get('error_code')
-        if error_code:
-            # -8 means blocked outside China.
-            error = config['data'][0].get('error')  # Chinese and English, separated by newline.
-            raise ExtractorError(error or 'Server reported error %i' % error_code,
-                                 expected=True)
+            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+            if cn_verification_proxy:
+                req.add_header('Ytdl-request-proxy', cn_verification_proxy)
 
 
-        video_title = config['data'][0]['title']
-        seed = config['data'][0]['seed']
+            raw_data = self._download_json(req, video_id, note=note)
+            return raw_data['data'][0]
 
 
-        format = self._downloader.params.get('format', None)
-        supported_format = list(config['data'][0]['streamfileids'].keys())
+        # request basic data
+        data1 = retrieve_data(
+            'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
+            'Downloading JSON metadata 1')
+        data2 = retrieve_data(
+            'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
+            'Downloading JSON metadata 2')
 
 
-        # TODO proper format selection
-        if format is None or format == 'best':
-            if 'hd2' in supported_format:
-                format = 'hd2'
+        error_code = data1.get('error_code')
+        if error_code:
+            error = data1.get('error')
+            if error is not None and '因版权原因无法观看此视频' in error:
+                raise ExtractorError(
+                    'Youku said: Sorry, this video is available in China only', expected=True)
             else:
             else:
-                format = 'flv'
-            ext = 'flv'
-        elif format == 'worst':
-            format = 'mp4'
-            ext = 'mp4'
-        else:
-            format = 'flv'
-            ext = 'flv'
-
-        fileid = config['data'][0]['streamfileids'][format]
-        keys = [s['k'] for s in config['data'][0]['segs'][format]]
-        # segs is usually a dictionary, but an empty *list* if an error occured.
-
-        files_info = []
-        sid = self._gen_sid()
-        fileid = self._get_file_id(fileid, seed)
-
-        # column 8,9 of fileid represent the segment number
-        # fileid[7:9] should be changed
-        for index, key in enumerate(keys):
-            temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
-            download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
-
-            info = {
-                'id': '%s_part%02d' % (video_id, index),
-                'url': download_url,
-                'uploader': None,
-                'upload_date': None,
-                'title': video_title,
-                'ext': ext,
-            }
-            files_info.append(info)
-
-        return files_info
+                msg = 'Youku server reported error %i' % error_code
+                if error is not None:
+                    msg += ': ' + error
+                raise ExtractorError(msg)
+
+        title = data1['title']
+
+        # generate video_urls_dict
+        video_urls_dict = self.construct_video_urls(data1, data2)
+
+        # construct info
+        entries = [{
+            'id': '%s_part%d' % (video_id, i + 1),
+            'title': title,
+            'formats': [],
+            # some formats are not available for all parts, we have to detect
+            # which one has all
+        } for i in range(max(len(v) for v in data1['segs'].values()))]
+        for fm in data1['streamtypes']:
+            video_urls = video_urls_dict[fm]
+            for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
+                entry['formats'].append({
+                    'url': video_url,
+                    'format_id': self.get_format_name(fm),
+                    'ext': self.parse_ext_l(fm),
+                    'filesize': int(seg['size']),
+                })
+
+        return {
+            '_type': 'multi_video',
+            'id': video_id,
+            'title': title,
+            'entries': entries,
+        }
index aacb999ce9044ba07af7597d03b34e1aa37ebddd..3d8b31f9830b218e02021b41214010b4f61d29a9 100644 (file)
@@ -17,6 +17,8 @@ from ..compat import (
     compat_chr,
     compat_parse_qs,
     compat_urllib_parse,
     compat_chr,
     compat_parse_qs,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
     compat_urllib_request,
     compat_urlparse,
     compat_str,
     compat_urllib_request,
     compat_urlparse,
     compat_str,
@@ -29,9 +31,11 @@ from ..utils import (
     get_element_by_id,
     int_or_none,
     orderedSet,
     get_element_by_id,
     int_or_none,
     orderedSet,
+    str_to_int,
     unescapeHTML,
     unified_strdate,
     uppercase_escape,
     unescapeHTML,
     unified_strdate,
     uppercase_escape,
+    ISO3166Utils,
 )
 
 
 )
 
 
@@ -234,6 +238,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '44': {'ext': 'webm', 'width': 854, 'height': 480},
         '45': {'ext': 'webm', 'width': 1280, 'height': 720},
         '46': {'ext': 'webm', 'width': 1920, 'height': 1080},
         '44': {'ext': 'webm', 'width': 854, 'height': 480},
         '45': {'ext': 'webm', 'width': 1280, 'height': 720},
         '46': {'ext': 'webm', 'width': 1920, 'height': 1080},
+        '59': {'ext': 'mp4', 'width': 854, 'height': 480},
+        '78': {'ext': 'mp4', 'width': 854, 'height': 480},
 
 
         # 3d videos
 
 
         # 3d videos
@@ -516,6 +522,38 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'skip_download': 'requires avconv',
             }
         },
                 'skip_download': 'requires avconv',
             }
         },
+        # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
+        {
+            'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
+            'info_dict': {
+                'id': 'FIl7x6_3R5Y',
+                'ext': 'mp4',
+                'title': 'md5:7b81415841e02ecd4313668cde88737a',
+                'description': 'md5:116377fd2963b81ec4ce64b542173306',
+                'upload_date': '20150625',
+                'uploader_id': 'dorappi2000',
+                'uploader': 'dorappi2000',
+                'formats': 'mincount:33',
+            },
+        },
+        # DASH manifest with segment_list
+        {
+            'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
+            'md5': '8ce563a1d667b599d21064e982ab9e31',
+            'info_dict': {
+                'id': 'CsmdDsKjzN8',
+                'ext': 'mp4',
+                'upload_date': '20150501',  # According to '<meta itemprop="datePublished"', but in other places it's 20150510
+                'uploader': 'Airtek',
+                'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
+                'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
+                'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
+            },
+            'params': {
+                'youtube_include_dash_manifest': True,
+                'format': '135',  # bestvideo
+            }
+        },
     ]
 
     def __init__(self, *args, **kwargs):
     ]
 
     def __init__(self, *args, **kwargs):
@@ -780,16 +818,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
 
     def _parse_dash_manifest(
         return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
 
     def _parse_dash_manifest(
-            self, video_id, dash_manifest_url, player_url, age_gate):
+            self, video_id, dash_manifest_url, player_url, age_gate, fatal=True):
         def decrypt_sig(mobj):
             s = mobj.group(1)
             dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
             return '/signature/%s' % dec_s
         def decrypt_sig(mobj):
             s = mobj.group(1)
             dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
             return '/signature/%s' % dec_s
-        dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
+        dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url)
         dash_doc = self._download_xml(
             dash_manifest_url, video_id,
             note='Downloading DASH manifest',
         dash_doc = self._download_xml(
             dash_manifest_url, video_id,
             note='Downloading DASH manifest',
-            errnote='Could not download DASH manifest')
+            errnote='Could not download DASH manifest',
+            fatal=fatal)
+
+        if dash_doc is False:
+            return []
 
         formats = []
         for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
 
         formats = []
         for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
@@ -802,6 +844,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     # TODO implement WebVTT downloading
                     pass
                 elif mime_type.startswith('audio/') or mime_type.startswith('video/'):
                     # TODO implement WebVTT downloading
                     pass
                 elif mime_type.startswith('audio/') or mime_type.startswith('video/'):
+                    segment_list = r.find('{urn:mpeg:DASH:schema:MPD:2011}SegmentList')
                     format_id = r.attrib['id']
                     video_url = url_el.text
                     filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
                     format_id = r.attrib['id']
                     video_url = url_el.text
                     filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
@@ -815,6 +858,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         'filesize': filesize,
                         'fps': int_or_none(r.attrib.get('frameRate')),
                     }
                         'filesize': filesize,
                         'fps': int_or_none(r.attrib.get('frameRate')),
                     }
+                    if segment_list is not None:
+                        f.update({
+                            'initialization_url': segment_list.find('{urn:mpeg:DASH:schema:MPD:2011}Initialization').attrib['sourceURL'],
+                            'segment_urls': [segment.attrib.get('media') for segment in segment_list.findall('{urn:mpeg:DASH:schema:MPD:2011}SegmentURL')],
+                            'protocol': 'http_dash_segments',
+                        })
                     try:
                         existing_format = next(
                             fo for fo in formats
                     try:
                         existing_format = next(
                             fo for fo in formats
@@ -822,6 +871,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     except StopIteration:
                         full_info = self._formats.get(format_id, {}).copy()
                         full_info.update(f)
                     except StopIteration:
                         full_info = self._formats.get(format_id, {}).copy()
                         full_info.update(f)
+                        codecs = r.attrib.get('codecs')
+                        if codecs:
+                            if full_info.get('acodec') == 'none' and 'vcodec' not in full_info:
+                                full_info['vcodec'] = codecs
+                            elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info:
+                                full_info['acodec'] = codecs
                         formats.append(full_info)
                     else:
                         existing_format.update(f)
                         formats.append(full_info)
                     else:
                         existing_format.update(f)
@@ -837,7 +892,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # Extract original video URL from URL with redirection, like age verification, using next_url parameter
         mobj = re.search(self._NEXT_URL_RE, url)
         if mobj:
         # Extract original video URL from URL with redirection, like age verification, using next_url parameter
         mobj = re.search(self._NEXT_URL_RE, url)
         if mobj:
-            url = proto + '://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
+            url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
         video_id = self.extract_id(url)
 
         # Get video webpage
         video_id = self.extract_id(url)
 
         # Get video webpage
@@ -851,8 +906,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             player_url = None
 
         else:
             player_url = None
 
+        dash_mpds = []
+
+        def add_dash_mpd(video_info):
+            dash_mpd = video_info.get('dashmpd')
+            if dash_mpd and dash_mpd[0] not in dash_mpds:
+                dash_mpds.append(dash_mpd[0])
+
         # Get video info
         embed_webpage = None
         # Get video info
         embed_webpage = None
+        is_live = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
@@ -871,24 +934,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 note='Refetching age-gated info webpage',
                 errnote='unable to download video info webpage')
             video_info = compat_parse_qs(video_info_webpage)
                 note='Refetching age-gated info webpage',
                 errnote='unable to download video info webpage')
             video_info = compat_parse_qs(video_info_webpage)
+            add_dash_mpd(video_info)
         else:
             age_gate = False
         else:
             age_gate = False
-            try:
-                # Try looking directly into the video webpage
-                mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
-                if not mobj:
-                    raise ValueError('Could not find ytplayer.config')  # caught below
+            video_info = None
+            # Try looking directly into the video webpage
+            mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
+            if mobj:
                 json_code = uppercase_escape(mobj.group(1))
                 ytplayer_config = json.loads(json_code)
                 args = ytplayer_config['args']
                 json_code = uppercase_escape(mobj.group(1))
                 ytplayer_config = json.loads(json_code)
                 args = ytplayer_config['args']
-                # Convert to the same format returned by compat_parse_qs
-                video_info = dict((k, [v]) for k, v in args.items())
-                if not args.get('url_encoded_fmt_stream_map'):
-                    raise ValueError('No stream_map present')  # caught below
-            except ValueError:
-                # We fallback to the get_video_info pages (used by the embed page)
+                if args.get('url_encoded_fmt_stream_map'):
+                    # Convert to the same format returned by compat_parse_qs
+                    video_info = dict((k, [v]) for k, v in args.items())
+                    add_dash_mpd(video_info)
+                if args.get('livestream') == '1' or args.get('live_playback') == 1:
+                    is_live = True
+            if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
+                # We also try looking in get_video_info since it may contain different dashmpd
+                # URL that points to a DASH manifest with possibly different itag set (some itags
+                # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
+                # manifest pointed by get_video_info's dashmpd).
+                # The general idea is to take a union of itags of both DASH manifests (for example
+                # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
                 self.report_video_info_webpage_download(video_id)
                 self.report_video_info_webpage_download(video_id)
-                for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+                for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
                     video_info_url = (
                         '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
                         % (proto, video_id, el_type))
                     video_info_url = (
                         '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
                         % (proto, video_id, el_type))
@@ -896,11 +966,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         video_info_url,
                         video_id, note=False,
                         errnote='unable to download video info webpage')
                         video_info_url,
                         video_id, note=False,
                         errnote='unable to download video info webpage')
-                    video_info = compat_parse_qs(video_info_webpage)
-                    if 'token' in video_info:
+                    get_video_info = compat_parse_qs(video_info_webpage)
+                    add_dash_mpd(get_video_info)
+                    if not video_info:
+                        video_info = get_video_info
+                    if 'token' in get_video_info:
                         break
         if 'token' not in video_info:
             if 'reason' in video_info:
                         break
         if 'token' not in video_info:
             if 'reason' in video_info:
+                if 'The uploader has not made this video available in your country.' in video_info['reason']:
+                    regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
+                    if regions_allowed is not None:
+                        raise ExtractorError('YouTube said: This video is available in %s only' % (
+                            ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
+                            expected=True)
                 raise ExtractorError(
                     'YouTube said: %s' % video_info['reason'][0],
                     expected=True, video_id=video_id)
                 raise ExtractorError(
                     'YouTube said: %s' % video_info['reason'][0],
                     expected=True, video_id=video_id)
@@ -924,7 +1003,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # uploader
         if 'author' not in video_info:
             raise ExtractorError('Unable to extract uploader name')
         # uploader
         if 'author' not in video_info:
             raise ExtractorError('Unable to extract uploader name')
-        video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
+        video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
 
         # uploader_id
         video_uploader_id = None
 
         # uploader_id
         video_uploader_id = None
@@ -951,18 +1030,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             self._downloader.report_warning('unable to extract video thumbnail')
             video_thumbnail = None
         else:   # don't panic if we can't find it
             self._downloader.report_warning('unable to extract video thumbnail')
             video_thumbnail = None
         else:   # don't panic if we can't find it
-            video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
+            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
 
         # upload date
 
         # upload date
-        upload_date = None
-        mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage)
-        if mobj is None:
-            mobj = re.search(
-                r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>',
-                video_webpage)
-        if mobj is not None:
-            upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
-            upload_date = unified_strdate(upload_date)
+        upload_date = self._html_search_meta(
+            'datePublished', video_webpage, 'upload date', default=None)
+        if not upload_date:
+            upload_date = self._search_regex(
+                [r'(?s)id="eow-date.*?>(.*?)</span>',
+                 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+                video_webpage, 'upload date', default=None)
+            if upload_date:
+                upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+        upload_date = unified_strdate(upload_date)
 
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
 
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
@@ -996,12 +1076,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 video_description = ''
 
         def _extract_count(count_name):
                 video_description = ''
 
         def _extract_count(count_name):
-            count = self._search_regex(
-                r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name),
-                video_webpage, count_name, default=None)
-            if count is not None:
-                return int(count.replace(',', ''))
-            return None
+            return str_to_int(self._search_regex(
+                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
+                % re.escape(count_name),
+                video_webpage, count_name, default=None))
+
         like_count = _extract_count('like')
         dislike_count = _extract_count('dislike')
 
         like_count = _extract_count('like')
         dislike_count = _extract_count('dislike')
 
@@ -1013,7 +1092,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             self._downloader.report_warning('unable to extract video duration')
             video_duration = None
         else:
             self._downloader.report_warning('unable to extract video duration')
             video_duration = None
         else:
-            video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]))
+            video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
 
         # annotations
         video_annotations = None
 
         # annotations
         video_annotations = None
@@ -1116,24 +1195,32 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # Look for the DASH manifest
         if self._downloader.params.get('youtube_include_dash_manifest', True):
 
         # Look for the DASH manifest
         if self._downloader.params.get('youtube_include_dash_manifest', True):
-            dash_mpd = video_info.get('dashmpd')
-            if dash_mpd:
-                dash_manifest_url = dash_mpd[0]
+            dash_mpd_fatal = True
+            for dash_manifest_url in dash_mpds:
+                dash_formats = {}
                 try:
                 try:
-                    dash_formats = self._parse_dash_manifest(
-                        video_id, dash_manifest_url, player_url, age_gate)
+                    for df in self._parse_dash_manifest(
+                            video_id, dash_manifest_url, player_url, age_gate, dash_mpd_fatal):
+                        # Do not overwrite DASH format found in some previous DASH manifest
+                        if df['format_id'] not in dash_formats:
+                            dash_formats[df['format_id']] = df
+                        # Additional DASH manifests may end up in HTTP Error 403 therefore
+                        # allow them to fail without bug report message if we already have
+                        # some DASH manifest succeeded. This is temporary workaround to reduce
+                        # burst of bug reports until we figure out the reason and whether it
+                        # can be fixed at all.
+                        dash_mpd_fatal = False
                 except (ExtractorError, KeyError) as e:
                     self.report_warning(
                         'Skipping DASH manifest: %r' % e, video_id)
                 except (ExtractorError, KeyError) as e:
                     self.report_warning(
                         'Skipping DASH manifest: %r' % e, video_id)
-                else:
+                if dash_formats:
                     # Remove the formats we found through non-DASH, they
                     # contain less info and it can be wrong, because we use
                     # fixed values (for example the resolution). See
                     # https://github.com/rg3/youtube-dl/issues/5774 for an
                     # example.
                     # Remove the formats we found through non-DASH, they
                     # contain less info and it can be wrong, because we use
                     # fixed values (for example the resolution). See
                     # https://github.com/rg3/youtube-dl/issues/5774 for an
                     # example.
-                    dash_keys = set(df['format_id'] for df in dash_formats)
-                    formats = [f for f in formats if f['format_id'] not in dash_keys]
-                    formats.extend(dash_formats)
+                    formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
+                    formats.extend(dash_formats.values())
 
         # Check for malformed aspect ratio
         stretched_m = re.search(
 
         # Check for malformed aspect ratio
         stretched_m = re.search(
@@ -1167,6 +1254,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'dislike_count': dislike_count,
             'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
             'formats': formats,
             'dislike_count': dislike_count,
             'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
             'formats': formats,
+            'is_live': is_live,
         }
 
 
         }
 
 
@@ -1290,7 +1378,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     def _extract_playlist(self, playlist_id):
         url = self._TEMPLATE_URL % playlist_id
         page = self._download_webpage(url, playlist_id)
     def _extract_playlist(self, playlist_id):
         url = self._TEMPLATE_URL % playlist_id
         page = self._download_webpage(url, playlist_id)
-        more_widget_html = content_html = page
 
         for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
             match = match.strip()
 
         for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
             match = match.strip()
@@ -1310,36 +1397,36 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                 self.report_warning('Youtube gives an alert message: ' + match)
 
         # Extract the video ids from the playlist pages
                 self.report_warning('Youtube gives an alert message: ' + match)
 
         # Extract the video ids from the playlist pages
-        ids = []
-
-        for page_num in itertools.count(1):
-            matches = re.finditer(self._VIDEO_RE, content_html)
-            # We remove the duplicates and the link with index 0
-            # (it's not the first video of the playlist)
-            new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
-            ids.extend(new_ids)
-
-            mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
-            if not mobj:
-                break
+        def _entries():
+            more_widget_html = content_html = page
+            for page_num in itertools.count(1):
+                matches = re.finditer(self._VIDEO_RE, content_html)
+                # We remove the duplicates and the link with index 0
+                # (it's not the first video of the playlist)
+                new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
+                for vid_id in new_ids:
+                    yield self.url_result(vid_id, 'Youtube', video_id=vid_id)
+
+                mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+                if not mobj:
+                    break
 
 
-            more = self._download_json(
-                'https://youtube.com/%s' % mobj.group('more'), playlist_id,
-                'Downloading page #%s' % page_num,
-                transform_source=uppercase_escape)
-            content_html = more['content_html']
-            if not content_html.strip():
-                # Some webpages show a "Load more" button but they don't
-                # have more videos
-                break
-            more_widget_html = more['load_more_widget_html']
+                more = self._download_json(
+                    'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                    'Downloading page #%s' % page_num,
+                    transform_source=uppercase_escape)
+                content_html = more['content_html']
+                if not content_html.strip():
+                    # Some webpages show a "Load more" button but they don't
+                    # have more videos
+                    break
+                more_widget_html = more['load_more_widget_html']
 
         playlist_title = self._html_search_regex(
             r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
             page, 'title')
 
 
         playlist_title = self._html_search_regex(
             r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
             page, 'title')
 
-        url_results = self._ids_to_results(ids)
-        return self.playlist_result(url_results, playlist_id, playlist_title)
+        return self.playlist_result(_entries(), playlist_id, playlist_title)
 
     def _real_extract(self, url):
         # Extract playlist id
 
     def _real_extract(self, url):
         # Extract playlist id
@@ -1406,10 +1493,12 @@ class YoutubeChannelIE(InfoExtractor):
         channel_page = self._download_webpage(
             url + '?view=57', channel_id,
             'Downloading channel page', fatal=False)
         channel_page = self._download_webpage(
             url + '?view=57', channel_id,
             'Downloading channel page', fatal=False)
-        channel_playlist_id = self._search_regex(
-            [r'<meta itemprop="channelId" content="([^"]+)">',
-             r'data-channel-external-id="([^"]+)"'],
-            channel_page, 'channel id', default=None)
+        channel_playlist_id = self._html_search_meta(
+            'channelId', channel_page, 'channel id', default=None)
+        if not channel_playlist_id:
+            channel_playlist_id = self._search_regex(
+                r'data-channel-external-id="([^"]+)"',
+                channel_page, 'channel id', default=None)
         if channel_playlist_id and channel_playlist_id.startswith('UC'):
             playlist_id = 'UU' + channel_playlist_id[2:]
             return self.url_result(
         if channel_playlist_id and channel_playlist_id.startswith('UC'):
             playlist_id = 'UU' + channel_playlist_id[2:]
             return self.url_result(
@@ -1503,7 +1592,7 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
 
         for pagenum in itertools.count(1):
             url_query = {
 
         for pagenum in itertools.count(1):
             url_query = {
-                'search_query': query,
+                'search_query': query.encode('utf-8'),
                 'page': pagenum,
                 'spf': 'navigate',
             }
                 'page': pagenum,
                 'spf': 'navigate',
             }
@@ -1551,7 +1640,7 @@ class YoutubeSearchURLIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        query = compat_urllib_parse.unquote_plus(mobj.group('query'))
+        query = compat_urllib_parse_unquote_plus(mobj.group('query'))
 
         webpage = self._download_webpage(url, query)
         result_code = self._search_regex(
 
         webpage = self._download_webpage(url, query)
         result_code = self._search_regex(
index 5a2315bd96ce0c6abfdf4a8bea65aa68e6fa370b..9016e34983d3fed5e0fab72e9a8626124cdee859 100644 (file)
@@ -145,11 +145,15 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--list-extractors',
         action='store_true', dest='list_extractors', default=False,
     general.add_option(
         '--list-extractors',
         action='store_true', dest='list_extractors', default=False,
-        help='List all supported extractors and the URLs they would handle')
+        help='List all supported extractors')
     general.add_option(
         '--extractor-descriptions',
         action='store_true', dest='list_extractor_descriptions', default=False,
         help='Output descriptions of all supported extractors')
     general.add_option(
         '--extractor-descriptions',
         action='store_true', dest='list_extractor_descriptions', default=False,
         help='Output descriptions of all supported extractors')
+    general.add_option(
+        '--force-generic-extractor',
+        action='store_true', dest='force_generic_extractor', default=False,
+        help='Force extraction to use the generic extractor')
     general.add_option(
         '--default-search',
         dest='default_search', metavar='PREFIX',
     general.add_option(
         '--default-search',
         dest='default_search', metavar='PREFIX',
@@ -215,7 +219,7 @@ def parseOpts(overrideArguments=None):
     selection.add_option(
         '--playlist-items',
         dest='playlist_items', metavar='ITEM_SPEC', default=None,
     selection.add_option(
         '--playlist-items',
         dest='playlist_items', metavar='ITEM_SPEC', default=None,
-        help='Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.')
+        help='Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.')
     selection.add_option(
         '--match-title',
         dest='matchtitle', metavar='REGEX',
     selection.add_option(
         '--match-title',
         dest='matchtitle', metavar='REGEX',
@@ -342,12 +346,13 @@ def parseOpts(overrideArguments=None):
     video_format.add_option(
         '--youtube-skip-dash-manifest',
         action='store_false', dest='youtube_include_dash_manifest',
     video_format.add_option(
         '--youtube-skip-dash-manifest',
         action='store_false', dest='youtube_include_dash_manifest',
-        help='Do not download the DASH manifest on YouTube videos')
+        help='Do not download the DASH manifests and related data on YouTube videos')
     video_format.add_option(
         '--merge-output-format',
         action='store', dest='merge_output_format', metavar='FORMAT', default=None,
         help=(
     video_format.add_option(
         '--merge-output-format',
         action='store', dest='merge_output_format', metavar='FORMAT', default=None,
         help=(
-            'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.'
+            'If a merge is required (e.g. bestvideo+bestaudio), '
+            'output to given container format. One of mkv, mp4, ogg, webm, flv. '
             'Ignored if no merge is required'))
 
     subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
             'Ignored if no merge is required'))
 
     subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
@@ -686,7 +691,11 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--recode-video',
         metavar='FORMAT', dest='recodevideo', default=None,
     postproc.add_option(
         '--recode-video',
         metavar='FORMAT', dest='recodevideo', default=None,
-        help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)')
+        help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)')
+    postproc.add_option(
+        '--postprocessor-args',
+        dest='postprocessor_args', metavar='ARGS',
+        help='Give these arguments to the postprocessor')
     postproc.add_option(
         '-k', '--keep-video',
         action='store_true', dest='keepvideo', default=False,
     postproc.add_option(
         '-k', '--keep-video',
         action='store_true', dest='keepvideo', default=False,
@@ -725,7 +734,7 @@ def parseOpts(overrideArguments=None):
         metavar='POLICY', dest='fixup', default='detect_or_warn',
         help='Automatically correct known faults of the file. '
              'One of never (do nothing), warn (only emit a warning), '
         metavar='POLICY', dest='fixup', default='detect_or_warn',
         help='Automatically correct known faults of the file. '
              'One of never (do nothing), warn (only emit a warning), '
-             'detect_or_warn(the default; fix file if we can, warn otherwise)')
+             'detect_or_warn (the default; fix file if we can, warn otherwise)')
     postproc.add_option(
         '--prefer-avconv',
         action='store_false', dest='prefer_ffmpeg',
     postproc.add_option(
         '--prefer-avconv',
         action='store_false', dest='prefer_ffmpeg',
index 3b0e8ddd8bfed92f2e9043b0adea2655a9e5f67b..4191d040bb1da468e248d57b78df1afdacf64cd0 100644 (file)
@@ -23,6 +23,9 @@ class PostProcessor(object):
 
     PostProcessor objects follow a "mutual registration" process similar
     to InfoExtractor objects.
 
     PostProcessor objects follow a "mutual registration" process similar
     to InfoExtractor objects.
+
+    Optionally PostProcessor can use a list of additional command-line arguments
+    with self._configuration_args.
     """
 
     _downloader = None
     """
 
     _downloader = None
@@ -57,6 +60,13 @@ class PostProcessor(object):
         except Exception:
             self._downloader.report_warning(errnote)
 
         except Exception:
             self._downloader.report_warning(errnote)
 
+    def _configuration_args(self, default=[]):
+        pp_args = self._downloader.params.get('postprocessor_args')
+        if pp_args is None:
+            return default
+        assert isinstance(pp_args, list)
+        return pp_args
+
 
 class AudioConversionError(PostProcessingError):
     pass
 
 class AudioConversionError(PostProcessingError):
     pass
index 774494efd1dbc9af1901bf67d1453689e846b780..e19dbf73d5fe36c602d9ffb83cd2d02ab39cb5e1 100644 (file)
@@ -35,6 +35,11 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
 
         thumbnail_filename = info['thumbnails'][-1]['filename']
 
 
         thumbnail_filename = info['thumbnails'][-1]['filename']
 
+        if not os.path.exists(encodeFilename(thumbnail_filename)):
+            self._downloader.report_warning(
+                'Skipping embedding the thumbnail because the file is missing.')
+            return [], info
+
         if info['ext'] == 'mp3':
             options = [
                 '-c', 'copy', '-map', '0', '-map', '1',
         if info['ext'] == 'mp3':
             options = [
                 '-c', 'copy', '-map', '0', '-map', '1',
index cc65b34e71a28cfb0947b9441d5dcc006baf47ba..1f723908be8d4ff0247affc5aed9ffc44e777602 100644 (file)
@@ -21,6 +21,7 @@ from ..utils import (
     shell_quote,
     subtitles_filename,
     dfxp2srt,
     shell_quote,
     subtitles_filename,
     dfxp2srt,
+    ISO639Utils,
 )
 
 
 )
 
 
@@ -130,6 +131,8 @@ class FFmpegPostProcessor(PostProcessor):
         oldest_mtime = min(
             os.stat(encodeFilename(path)).st_mtime for path in input_paths)
 
         oldest_mtime = min(
             os.stat(encodeFilename(path)).st_mtime for path in input_paths)
 
+        opts += self._configuration_args()
+
         files_cmd = []
         for path in input_paths:
             files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)])
         files_cmd = []
         for path in input_paths:
             files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)])
@@ -262,7 +265,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
         if (new_path == path or
                 (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
         # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
         if (new_path == path or
                 (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
-            self._downloader.to_screen('[youtube] Post-process file %s exists, skipping' % new_path)
+            self._downloader.to_screen('[ffmpeg] Post-process file %s exists, skipping' % new_path)
             return [], information
 
         try:
             return [], information
 
         try:
@@ -293,13 +296,16 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
 
     def run(self, information):
         path = information['filepath']
 
     def run(self, information):
         path = information['filepath']
-        prefix, sep, ext = path.rpartition('.')
-        outpath = prefix + sep + self._preferedformat
         if information['ext'] == self._preferedformat:
             self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
             return [], information
         if information['ext'] == self._preferedformat:
             self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
             return [], information
+        options = []
+        if self._preferedformat == 'avi':
+            options.extend(['-c:v', 'libxvid', '-vtag', 'XVID'])
+        prefix, sep, ext = path.rpartition('.')
+        outpath = prefix + sep + self._preferedformat
         self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
         self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
-        self.run_ffmpeg(path, outpath, [])
+        self.run_ffmpeg(path, outpath, options)
         information['filepath'] = outpath
         information['format'] = self._preferedformat
         information['ext'] = self._preferedformat
         information['filepath'] = outpath
         information['format'] = self._preferedformat
         information['ext'] = self._preferedformat
@@ -307,199 +313,6 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
 
 
 class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
 
 
 class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
-    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
-    _lang_map = {
-        'aa': 'aar',
-        'ab': 'abk',
-        'ae': 'ave',
-        'af': 'afr',
-        'ak': 'aka',
-        'am': 'amh',
-        'an': 'arg',
-        'ar': 'ara',
-        'as': 'asm',
-        'av': 'ava',
-        'ay': 'aym',
-        'az': 'aze',
-        'ba': 'bak',
-        'be': 'bel',
-        'bg': 'bul',
-        'bh': 'bih',
-        'bi': 'bis',
-        'bm': 'bam',
-        'bn': 'ben',
-        'bo': 'bod',
-        'br': 'bre',
-        'bs': 'bos',
-        'ca': 'cat',
-        'ce': 'che',
-        'ch': 'cha',
-        'co': 'cos',
-        'cr': 'cre',
-        'cs': 'ces',
-        'cu': 'chu',
-        'cv': 'chv',
-        'cy': 'cym',
-        'da': 'dan',
-        'de': 'deu',
-        'dv': 'div',
-        'dz': 'dzo',
-        'ee': 'ewe',
-        'el': 'ell',
-        'en': 'eng',
-        'eo': 'epo',
-        'es': 'spa',
-        'et': 'est',
-        'eu': 'eus',
-        'fa': 'fas',
-        'ff': 'ful',
-        'fi': 'fin',
-        'fj': 'fij',
-        'fo': 'fao',
-        'fr': 'fra',
-        'fy': 'fry',
-        'ga': 'gle',
-        'gd': 'gla',
-        'gl': 'glg',
-        'gn': 'grn',
-        'gu': 'guj',
-        'gv': 'glv',
-        'ha': 'hau',
-        'he': 'heb',
-        'hi': 'hin',
-        'ho': 'hmo',
-        'hr': 'hrv',
-        'ht': 'hat',
-        'hu': 'hun',
-        'hy': 'hye',
-        'hz': 'her',
-        'ia': 'ina',
-        'id': 'ind',
-        'ie': 'ile',
-        'ig': 'ibo',
-        'ii': 'iii',
-        'ik': 'ipk',
-        'io': 'ido',
-        'is': 'isl',
-        'it': 'ita',
-        'iu': 'iku',
-        'ja': 'jpn',
-        'jv': 'jav',
-        'ka': 'kat',
-        'kg': 'kon',
-        'ki': 'kik',
-        'kj': 'kua',
-        'kk': 'kaz',
-        'kl': 'kal',
-        'km': 'khm',
-        'kn': 'kan',
-        'ko': 'kor',
-        'kr': 'kau',
-        'ks': 'kas',
-        'ku': 'kur',
-        'kv': 'kom',
-        'kw': 'cor',
-        'ky': 'kir',
-        'la': 'lat',
-        'lb': 'ltz',
-        'lg': 'lug',
-        'li': 'lim',
-        'ln': 'lin',
-        'lo': 'lao',
-        'lt': 'lit',
-        'lu': 'lub',
-        'lv': 'lav',
-        'mg': 'mlg',
-        'mh': 'mah',
-        'mi': 'mri',
-        'mk': 'mkd',
-        'ml': 'mal',
-        'mn': 'mon',
-        'mr': 'mar',
-        'ms': 'msa',
-        'mt': 'mlt',
-        'my': 'mya',
-        'na': 'nau',
-        'nb': 'nob',
-        'nd': 'nde',
-        'ne': 'nep',
-        'ng': 'ndo',
-        'nl': 'nld',
-        'nn': 'nno',
-        'no': 'nor',
-        'nr': 'nbl',
-        'nv': 'nav',
-        'ny': 'nya',
-        'oc': 'oci',
-        'oj': 'oji',
-        'om': 'orm',
-        'or': 'ori',
-        'os': 'oss',
-        'pa': 'pan',
-        'pi': 'pli',
-        'pl': 'pol',
-        'ps': 'pus',
-        'pt': 'por',
-        'qu': 'que',
-        'rm': 'roh',
-        'rn': 'run',
-        'ro': 'ron',
-        'ru': 'rus',
-        'rw': 'kin',
-        'sa': 'san',
-        'sc': 'srd',
-        'sd': 'snd',
-        'se': 'sme',
-        'sg': 'sag',
-        'si': 'sin',
-        'sk': 'slk',
-        'sl': 'slv',
-        'sm': 'smo',
-        'sn': 'sna',
-        'so': 'som',
-        'sq': 'sqi',
-        'sr': 'srp',
-        'ss': 'ssw',
-        'st': 'sot',
-        'su': 'sun',
-        'sv': 'swe',
-        'sw': 'swa',
-        'ta': 'tam',
-        'te': 'tel',
-        'tg': 'tgk',
-        'th': 'tha',
-        'ti': 'tir',
-        'tk': 'tuk',
-        'tl': 'tgl',
-        'tn': 'tsn',
-        'to': 'ton',
-        'tr': 'tur',
-        'ts': 'tso',
-        'tt': 'tat',
-        'tw': 'twi',
-        'ty': 'tah',
-        'ug': 'uig',
-        'uk': 'ukr',
-        'ur': 'urd',
-        'uz': 'uzb',
-        've': 'ven',
-        'vi': 'vie',
-        'vo': 'vol',
-        'wa': 'wln',
-        'wo': 'wol',
-        'xh': 'xho',
-        'yi': 'yid',
-        'yo': 'yor',
-        'za': 'zha',
-        'zh': 'zho',
-        'zu': 'zul',
-    }
-
-    @classmethod
-    def _conver_lang_code(cls, code):
-        """Convert language code from ISO 639-1 to ISO 639-2/T"""
-        return cls._lang_map.get(code[:2])
-
     def run(self, information):
         if information['ext'] not in ['mp4', 'mkv']:
             self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 or mkv files')
     def run(self, information):
         if information['ext'] not in ['mp4', 'mkv']:
             self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 or mkv files')
@@ -525,7 +338,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
             opts += ['-c:s', 'mov_text']
         for (i, lang) in enumerate(sub_langs):
             opts.extend(['-map', '%d:0' % (i + 1)])
             opts += ['-c:s', 'mov_text']
         for (i, lang) in enumerate(sub_langs):
             opts.extend(['-map', '%d:0' % (i + 1)])
-            lang_code = self._conver_lang_code(lang)
+            lang_code = ISO639Utils.short2long(lang)
             if lang_code is not None:
                 opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
 
             if lang_code is not None:
                 opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
 
index de3169eef1d6ec29d82a60b2f4b6a68f49d7dd4e..fc7ac8305d71c8cce077ef3040cd0903ac9f09c5 100644 (file)
@@ -50,7 +50,7 @@ def rsa_verify(message, signature, key):
 def update_self(to_screen, verbose):
     """Update the program file with the latest version from the repository"""
 
 def update_self(to_screen, verbose):
     """Update the program file with the latest version from the repository"""
 
-    UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
+    UPDATE_URL = "https://rg3.github.io/youtube-dl/update/"
     VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
     JSON_URL = UPDATE_URL + 'versions.json'
     UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
     VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
     JSON_URL = UPDATE_URL + 'versions.json'
     UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
index 52d198fa3c2eb36a1a3d41620cd645b90d52f854..942f76d2452c06a261d75e03cebc999fff02874c 100644 (file)
@@ -62,6 +62,8 @@ std_headers = {
 }
 
 
 }
 
 
+NO_DEFAULT = object()
+
 ENGLISH_MONTH_NAMES = [
     'January', 'February', 'March', 'April', 'May', 'June',
     'July', 'August', 'September', 'October', 'November', 'December']
 ENGLISH_MONTH_NAMES = [
     'January', 'February', 'March', 'April', 'May', 'June',
     'July', 'August', 'September', 'October', 'November', 'December']
@@ -171,13 +173,15 @@ def xpath_with_ns(path, ns_map):
     return '/'.join(replaced)
 
 
     return '/'.join(replaced)
 
 
-def xpath_text(node, xpath, name=None, fatal=False):
+def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
     if sys.version_info < (2, 7):  # Crazy 2.6
         xpath = xpath.encode('ascii')
 
     n = node.find(xpath)
     if n is None or n.text is None:
     if sys.version_info < (2, 7):  # Crazy 2.6
         xpath = xpath.encode('ascii')
 
     n = node.find(xpath)
     if n is None or n.text is None:
-        if fatal:
+        if default is not NO_DEFAULT:
+            return default
+        elif fatal:
             name = xpath if name is None else name
             raise ExtractorError('Could not find XML element %s' % name)
         else:
             name = xpath if name is None else name
             raise ExtractorError('Could not find XML element %s' % name)
         else:
@@ -1841,7 +1845,10 @@ def srt_subtitles_timecode(seconds):
 
 
 def dfxp2srt(dfxp_data):
 
 
 def dfxp2srt(dfxp_data):
-    _x = functools.partial(xpath_with_ns, ns_map={'ttml': 'http://www.w3.org/ns/ttml'})
+    _x = functools.partial(xpath_with_ns, ns_map={
+        'ttml': 'http://www.w3.org/ns/ttml',
+        'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+    })
 
     def parse_node(node):
         str_or_empty = functools.partial(str_or_none, default='')
 
     def parse_node(node):
         str_or_empty = functools.partial(str_or_none, default='')
@@ -1849,9 +1856,9 @@ def dfxp2srt(dfxp_data):
         out = str_or_empty(node.text)
 
         for child in node:
         out = str_or_empty(node.text)
 
         for child in node:
-            if child.tag in (_x('ttml:br'), 'br'):
+            if child.tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'):
                 out += '\n' + str_or_empty(child.tail)
                 out += '\n' + str_or_empty(child.tail)
-            elif child.tag in (_x('ttml:span'), 'span'):
+            elif child.tag in (_x('ttml:span'), _x('ttaf1:span'), 'span'):
                 out += str_or_empty(parse_node(child))
             else:
                 out += str_or_empty(xml.etree.ElementTree.tostring(child))
                 out += str_or_empty(parse_node(child))
             else:
                 out += str_or_empty(xml.etree.ElementTree.tostring(child))
@@ -1860,7 +1867,7 @@ def dfxp2srt(dfxp_data):
 
     dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
     out = []
 
     dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
     out = []
-    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
+    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')
 
     if not paras:
         raise ValueError('Invalid dfxp/TTML subtitle')
 
     if not paras:
         raise ValueError('Invalid dfxp/TTML subtitle')
@@ -1879,6 +1886,468 @@ def dfxp2srt(dfxp_data):
     return ''.join(out)
 
 
     return ''.join(out)
 
 
+class ISO639Utils(object):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    @classmethod
+    def short2long(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    @classmethod
+    def long2short(cls, code):
+        """Convert language code from ISO 639-2/T to ISO 639-1"""
+        for short_name, long_name in cls._lang_map.items():
+            if long_name == code:
+                return short_name
+
+
+class ISO3166Utils(object):
+    # From http://data.okfn.org/data/core/country-list
+    _country_map = {
+        'AF': 'Afghanistan',
+        'AX': 'Åland Islands',
+        'AL': 'Albania',
+        'DZ': 'Algeria',
+        'AS': 'American Samoa',
+        'AD': 'Andorra',
+        'AO': 'Angola',
+        'AI': 'Anguilla',
+        'AQ': 'Antarctica',
+        'AG': 'Antigua and Barbuda',
+        'AR': 'Argentina',
+        'AM': 'Armenia',
+        'AW': 'Aruba',
+        'AU': 'Australia',
+        'AT': 'Austria',
+        'AZ': 'Azerbaijan',
+        'BS': 'Bahamas',
+        'BH': 'Bahrain',
+        'BD': 'Bangladesh',
+        'BB': 'Barbados',
+        'BY': 'Belarus',
+        'BE': 'Belgium',
+        'BZ': 'Belize',
+        'BJ': 'Benin',
+        'BM': 'Bermuda',
+        'BT': 'Bhutan',
+        'BO': 'Bolivia, Plurinational State of',
+        'BQ': 'Bonaire, Sint Eustatius and Saba',
+        'BA': 'Bosnia and Herzegovina',
+        'BW': 'Botswana',
+        'BV': 'Bouvet Island',
+        'BR': 'Brazil',
+        'IO': 'British Indian Ocean Territory',
+        'BN': 'Brunei Darussalam',
+        'BG': 'Bulgaria',
+        'BF': 'Burkina Faso',
+        'BI': 'Burundi',
+        'KH': 'Cambodia',
+        'CM': 'Cameroon',
+        'CA': 'Canada',
+        'CV': 'Cape Verde',
+        'KY': 'Cayman Islands',
+        'CF': 'Central African Republic',
+        'TD': 'Chad',
+        'CL': 'Chile',
+        'CN': 'China',
+        'CX': 'Christmas Island',
+        'CC': 'Cocos (Keeling) Islands',
+        'CO': 'Colombia',
+        'KM': 'Comoros',
+        'CG': 'Congo',
+        'CD': 'Congo, the Democratic Republic of the',
+        'CK': 'Cook Islands',
+        'CR': 'Costa Rica',
+        'CI': 'Côte d\'Ivoire',
+        'HR': 'Croatia',
+        'CU': 'Cuba',
+        'CW': 'Curaçao',
+        'CY': 'Cyprus',
+        'CZ': 'Czech Republic',
+        'DK': 'Denmark',
+        'DJ': 'Djibouti',
+        'DM': 'Dominica',
+        'DO': 'Dominican Republic',
+        'EC': 'Ecuador',
+        'EG': 'Egypt',
+        'SV': 'El Salvador',
+        'GQ': 'Equatorial Guinea',
+        'ER': 'Eritrea',
+        'EE': 'Estonia',
+        'ET': 'Ethiopia',
+        'FK': 'Falkland Islands (Malvinas)',
+        'FO': 'Faroe Islands',
+        'FJ': 'Fiji',
+        'FI': 'Finland',
+        'FR': 'France',
+        'GF': 'French Guiana',
+        'PF': 'French Polynesia',
+        'TF': 'French Southern Territories',
+        'GA': 'Gabon',
+        'GM': 'Gambia',
+        'GE': 'Georgia',
+        'DE': 'Germany',
+        'GH': 'Ghana',
+        'GI': 'Gibraltar',
+        'GR': 'Greece',
+        'GL': 'Greenland',
+        'GD': 'Grenada',
+        'GP': 'Guadeloupe',
+        'GU': 'Guam',
+        'GT': 'Guatemala',
+        'GG': 'Guernsey',
+        'GN': 'Guinea',
+        'GW': 'Guinea-Bissau',
+        'GY': 'Guyana',
+        'HT': 'Haiti',
+        'HM': 'Heard Island and McDonald Islands',
+        'VA': 'Holy See (Vatican City State)',
+        'HN': 'Honduras',
+        'HK': 'Hong Kong',
+        'HU': 'Hungary',
+        'IS': 'Iceland',
+        'IN': 'India',
+        'ID': 'Indonesia',
+        'IR': 'Iran, Islamic Republic of',
+        'IQ': 'Iraq',
+        'IE': 'Ireland',
+        'IM': 'Isle of Man',
+        'IL': 'Israel',
+        'IT': 'Italy',
+        'JM': 'Jamaica',
+        'JP': 'Japan',
+        'JE': 'Jersey',
+        'JO': 'Jordan',
+        'KZ': 'Kazakhstan',
+        'KE': 'Kenya',
+        'KI': 'Kiribati',
+        'KP': 'Korea, Democratic People\'s Republic of',
+        'KR': 'Korea, Republic of',
+        'KW': 'Kuwait',
+        'KG': 'Kyrgyzstan',
+        'LA': 'Lao People\'s Democratic Republic',
+        'LV': 'Latvia',
+        'LB': 'Lebanon',
+        'LS': 'Lesotho',
+        'LR': 'Liberia',
+        'LY': 'Libya',
+        'LI': 'Liechtenstein',
+        'LT': 'Lithuania',
+        'LU': 'Luxembourg',
+        'MO': 'Macao',
+        'MK': 'Macedonia, the Former Yugoslav Republic of',
+        'MG': 'Madagascar',
+        'MW': 'Malawi',
+        'MY': 'Malaysia',
+        'MV': 'Maldives',
+        'ML': 'Mali',
+        'MT': 'Malta',
+        'MH': 'Marshall Islands',
+        'MQ': 'Martinique',
+        'MR': 'Mauritania',
+        'MU': 'Mauritius',
+        'YT': 'Mayotte',
+        'MX': 'Mexico',
+        'FM': 'Micronesia, Federated States of',
+        'MD': 'Moldova, Republic of',
+        'MC': 'Monaco',
+        'MN': 'Mongolia',
+        'ME': 'Montenegro',
+        'MS': 'Montserrat',
+        'MA': 'Morocco',
+        'MZ': 'Mozambique',
+        'MM': 'Myanmar',
+        'NA': 'Namibia',
+        'NR': 'Nauru',
+        'NP': 'Nepal',
+        'NL': 'Netherlands',
+        'NC': 'New Caledonia',
+        'NZ': 'New Zealand',
+        'NI': 'Nicaragua',
+        'NE': 'Niger',
+        'NG': 'Nigeria',
+        'NU': 'Niue',
+        'NF': 'Norfolk Island',
+        'MP': 'Northern Mariana Islands',
+        'NO': 'Norway',
+        'OM': 'Oman',
+        'PK': 'Pakistan',
+        'PW': 'Palau',
+        'PS': 'Palestine, State of',
+        'PA': 'Panama',
+        'PG': 'Papua New Guinea',
+        'PY': 'Paraguay',
+        'PE': 'Peru',
+        'PH': 'Philippines',
+        'PN': 'Pitcairn',
+        'PL': 'Poland',
+        'PT': 'Portugal',
+        'PR': 'Puerto Rico',
+        'QA': 'Qatar',
+        'RE': 'Réunion',
+        'RO': 'Romania',
+        'RU': 'Russian Federation',
+        'RW': 'Rwanda',
+        'BL': 'Saint Barthélemy',
+        'SH': 'Saint Helena, Ascension and Tristan da Cunha',
+        'KN': 'Saint Kitts and Nevis',
+        'LC': 'Saint Lucia',
+        'MF': 'Saint Martin (French part)',
+        'PM': 'Saint Pierre and Miquelon',
+        'VC': 'Saint Vincent and the Grenadines',
+        'WS': 'Samoa',
+        'SM': 'San Marino',
+        'ST': 'Sao Tome and Principe',
+        'SA': 'Saudi Arabia',
+        'SN': 'Senegal',
+        'RS': 'Serbia',
+        'SC': 'Seychelles',
+        'SL': 'Sierra Leone',
+        'SG': 'Singapore',
+        'SX': 'Sint Maarten (Dutch part)',
+        'SK': 'Slovakia',
+        'SI': 'Slovenia',
+        'SB': 'Solomon Islands',
+        'SO': 'Somalia',
+        'ZA': 'South Africa',
+        'GS': 'South Georgia and the South Sandwich Islands',
+        'SS': 'South Sudan',
+        'ES': 'Spain',
+        'LK': 'Sri Lanka',
+        'SD': 'Sudan',
+        'SR': 'Suriname',
+        'SJ': 'Svalbard and Jan Mayen',
+        'SZ': 'Swaziland',
+        'SE': 'Sweden',
+        'CH': 'Switzerland',
+        'SY': 'Syrian Arab Republic',
+        'TW': 'Taiwan, Province of China',
+        'TJ': 'Tajikistan',
+        'TZ': 'Tanzania, United Republic of',
+        'TH': 'Thailand',
+        'TL': 'Timor-Leste',
+        'TG': 'Togo',
+        'TK': 'Tokelau',
+        'TO': 'Tonga',
+        'TT': 'Trinidad and Tobago',
+        'TN': 'Tunisia',
+        'TR': 'Turkey',
+        'TM': 'Turkmenistan',
+        'TC': 'Turks and Caicos Islands',
+        'TV': 'Tuvalu',
+        'UG': 'Uganda',
+        'UA': 'Ukraine',
+        'AE': 'United Arab Emirates',
+        'GB': 'United Kingdom',
+        'US': 'United States',
+        'UM': 'United States Minor Outlying Islands',
+        'UY': 'Uruguay',
+        'UZ': 'Uzbekistan',
+        'VU': 'Vanuatu',
+        'VE': 'Venezuela, Bolivarian Republic of',
+        'VN': 'Viet Nam',
+        'VG': 'Virgin Islands, British',
+        'VI': 'Virgin Islands, U.S.',
+        'WF': 'Wallis and Futuna',
+        'EH': 'Western Sahara',
+        'YE': 'Yemen',
+        'ZM': 'Zambia',
+        'ZW': 'Zimbabwe',
+    }
+
+    @classmethod
+    def short2full(cls, code):
+        """Convert an ISO 3166-2 country code to the corresponding full name"""
+        return cls._country_map.get(code.upper())
+
+
 class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
     def __init__(self, proxies=None):
         # Set default handlers
 class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
     def __init__(self, proxies=None):
         # Set default handlers
index 9cf84ff712da103b9c3ce0b3e2f0c9386082e574..280afdd7f8f21cc058768eba232a11672ca32761 100644 (file)
@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-__version__ = '2015.06.04.1'
+__version__ = '2015.07.21'