From: Rogério Brito Date: Wed, 24 Feb 2016 20:23:49 +0000 (-0300) Subject: Imported Upstream version 2016.02.22 X-Git-Url: https://git.rapsys.eu/youtubedl/commitdiff_plain/9f2b33881274af98a9145c533a1d295fad71521a?ds=inline;hp=-c Imported Upstream version 2016.02.22 --- 9f2b33881274af98a9145c533a1d295fad71521a diff --git a/Makefile b/Makefile index fdb1abb..cb449b7 100644 --- a/Makefile +++ b/Makefile @@ -44,7 +44,7 @@ test: ot: offlinetest offlinetest: codetest - nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py + nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py tar: youtube-dl.tar.gz @@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py chmod a+x youtube-dl README.md: youtube_dl/*.py youtube_dl/*/*.py - COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py + COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py CONTRIBUTING.md: README.md - python devscripts/make_contributing.py README.md CONTRIBUTING.md + $(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md supportedsites: - python devscripts/make_supportedsites.py docs/supportedsites.md + $(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md README.txt: README.md pandoc -f markdown -t plain README.md -o README.txt youtube-dl.1: README.md - python devscripts/prepare_manpage.py >youtube-dl.1.temp.md + $(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1 rm -f youtube-dl.1.temp.md youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in - python devscripts/bash-completion.py + $(PYTHON) devscripts/bash-completion.py bash-completion: youtube-dl.bash-completion youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in - python devscripts/zsh-completion.py + $(PYTHON) devscripts/zsh-completion.py zsh-completion: youtube-dl.zsh youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in - python devscripts/fish-completion.py + $(PYTHON) devscripts/fish-completion.py fish-completion: youtube-dl.fish diff --git a/README.md b/README.md index df419ab..db49ab6 100644 --- a/README.md +++ b/README.md @@ -35,7 +35,7 @@ You can also use pip: sudo pip install youtube-dl -Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html . +Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). # DESCRIPTION **youtube-dl** is a small command-line program to download videos from @@ -173,6 +173,10 @@ which means you can modify it, redistribute it or use it however you like. expected filesize (experimental) --hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental) + --hls-use-mpegts Use the mpegts container for HLS videos, + allowing to play the video while + downloading (some players may not be able + to play it) --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,axel,curl,httpie,wget @@ -319,7 +323,7 @@ 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 of specified + -F, --list-formats List all available formats of requested videos --youtube-skip-dash-manifest Do not download the DASH manifests and related data on YouTube videos @@ -339,8 +343,8 @@ which means you can modify it, redistribute it or use it however you like. preference, for example: "srt" or "ass/srt/best" --sub-lang LANGS Languages of the subtitles to download - (optional) separated by commas, use IETF - language tags like 'en,pt' + (optional) separated by commas, use --list- + subs for available language tags ## Authentication Options: -u, --username USERNAME Login with this account ID @@ -400,7 +404,7 @@ which means you can modify it, redistribute it or use it however you like. downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm {}' - --convert-subtitles FORMAT Convert the subtitles to other format + --convert-subs FORMAT Convert the subtitles to other format (currently supported: srt|ass|vtt) # CONFIGURATION @@ -414,7 +418,7 @@ You can configure youtube-dl by placing any supported command line option to a c You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run. -### Authentication with `.netrc` file ### +### 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 the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only: ``` @@ -438,41 +442,172 @@ On Windows you may also need to setup the `%HOME%` environment variable manually 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 parentheses, followed by a lowercase S. Allowed names are: - - `id`: The sequence will be replaced by the video identifier. - - `url`: The sequence will be replaced by the video URL. - - `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video. - - `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format. - - `title`: The sequence will be replaced by the video title. - - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4). - - `epoch`: The sequence will be replaced by the Unix epoch when creating the file. - - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero. - - `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video. - - `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist. - - `format_id`: The sequence will be replaced by the format code specified by `--format`. - - `duration`: The sequence will be replaced by the length of the video in seconds. + - `id`: Video identifier + - `title`: Video title + - `url`: Video URL + - `ext`: Video filename extension + - `alt_title`: A secondary title of the video + - `display_id`: An alternative identifier for the video + - `uploader`: Full name of the video uploader + - `creator`: The main artist who created the video + - `release_date`: The date (YYYYMMDD) when the video was released + - `timestamp`: UNIX timestamp of the moment the video became available + - `upload_date`: Video upload date (YYYYMMDD) + - `uploader_id`: Nickname or id of the video uploader + - `location`: Physical location where the video was filmed + - `duration`: Length of the video in seconds + - `view_count`: How many users have watched the video on the platform + - `like_count`: Number of positive ratings of the video + - `dislike_count`: Number of negative ratings of the video + - `repost_count`: Number of reposts of the video + - `average_rating`: Average rating give by users, the scale used depends on the webpage + - `comment_count`: Number of comments on the video + - `age_limit`: Age restriction for the video (years) + - `format`: A human-readable description of the format + - `format_id`: Format code specified by `--format` + - `format_note`: Additional info about the format + - `width`: Width of the video + - `height`: Height of the video + - `resolution`: Textual description of width and height + - `tbr`: Average bitrate of audio and video in KBit/s + - `abr`: Average audio bitrate in KBit/s + - `acodec`: Name of the audio codec in use + - `asr`: Audio sampling rate in Hertz + - `vbr`: Average video bitrate in KBit/s + - `fps`: Frame rate + - `vcodec`: Name of the video codec in use + - `container`: Name of the container format + - `filesize`: The number of bytes, if known in advance + - `filesize_approx`: An estimate for the number of bytes + - `protocol`: The protocol that will be used for the actual download + - `extractor`: Name of the extractor + - `extractor_key`: Key name of the extractor + - `epoch`: Unix epoch when creating the file + - `autonumber`: Five-digit number that will be increased with each download, starting at zero + - `playlist`: Name or id of the playlist that contains the video + - `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist + +Available for the video that belongs to some logical chapter or section: + - `chapter`: Name or title of the chapter the video belongs to + - `chapter_number`: Number of the chapter the video belongs to + - `chapter_id`: Id of the chapter the video belongs to + +Available for the video that is an episode of some series or programme: + - `series`: Title of the series or programme the video episode belongs to + - `season`: Title of the season the video episode belongs to + - `season_number`: Number of the season the video episode belongs to + - `season_id`: Id of the season the video episode belongs to + - `episode`: Title of the video episode + - `episode_number`: Number of the video episode within a season + - `episode_id`: Id of the video episode + +Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`. + +For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory. + +Output template can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` that will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you. + +To specify percent literal in output template use `%%`. To output to stdout use `-o -`. The current default template is `%(title)s-%(id)s.%(ext)s`. In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title: +Examples (note on Windows you may need to use double quotes instead of single): + ```bash -$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc +$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters -$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames + +$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc --restrict-filenames youtube-dl_test_video_.mp4 # A simple file name + +# Download YouTube playlist videos in separate directory indexed by video order in a playlist +$ youtube-dl -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re + +# Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home +$ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/ + +# Download entire series season keeping each series and each season in separate directory under C:/MyVideos +$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617 + +# Stream the video being downloaded to stdout +$ youtube-dl -o - BaW_jenozKc ``` # FORMAT SELECTION -By default youtube-dl tries to download the best quality, but sometimes you may want to download in a different format. -The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`. +By default youtube-dl tries to download the best available quality, i.e. if you want the best quality you **don't need** to pass any special options, youtube-dl will guess it for you by **default**. + +But sometimes you may want to download in a different format, for example when you are on a slow or intermittent connection. The key mechanism for achieving this is so called *format selection* based on which you can explicitly specify desired format, select formats based on some criterion or criteria, setup precedence and much more. + +The general syntax for format selection is `--format FORMAT` or shorter `-f FORMAT` where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download. + +The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific. + +You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download best quality format of particular file extension served as a single file, e.g. `-f webm` will download best quality format with `webm` extension served as a single file. + +You can also use special names to select particular edge case format: + - `best`: Select best quality format represented by single file with video and audio + - `worst`: Select worst quality format represented by single file with video and audio + - `bestvideo`: Select best quality video only format (e.g. DASH video), may not be available + - `worstvideo`: Select worst quality video only format, may not be available + - `bestaudio`: Select best quality audio only format, may not be available + - `worstaudio`: Select worst quality audio only format, may not be available + +For example, to download worst quality video only format you can use `-f worstvideo`. + +If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that slash is left-associative, i.e. formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download. + +If you want to download several formats of the same video use comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or more sophisticated example combined with precedence feature `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. + +You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). -If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f +` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`. +The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals): + - `filesize`: The number of bytes, if known in advance + - `width`: Width of the video, if known + - `height`: Height of the video, if known + - `tbr`: Average bitrate of audio and video in KBit/s + - `abr`: Average audio bitrate in KBit/s + - `vbr`: Average video bitrate in KBit/s + - `asr`: Audio sampling rate in Hertz + - `fps`: Frame rate -Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. +Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields: + - `ext`: File extension + - `acodec`: Name of the audio codec in use + - `vcodec`: Name of the video codec in use + - `container`: Name of the container format + - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native` + +Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by video hoster. + +Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. + +You can merge the video and audio of two formats into a single file using `-f +` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download best video only format, best audio only format and mux them together with ffmpeg/avconv. + +Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`. + +Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl. +Examples (note on Windows you may need to use double quotes instead of single): +```bash +# Download best mp4 format available or any other best if no mp4 available +$ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best' + +# Download best format available but not better that 480p +$ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]' + +# Download best video only format but no bigger that 50 MB +$ youtube-dl -f 'best[filesize<50M]' + +# Download best format available via direct link over HTTP/HTTPS protocol +$ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]' +``` + + # VIDEO SELECTION Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats: @@ -559,11 +694,11 @@ If you want to play the video on a machine that is not running youtube-dl, you c YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl. -### ERROR: unable to download video ### +### ERROR: unable to download video YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl. -### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ### +### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell). @@ -587,7 +722,7 @@ In February 2015, the new YouTube player contained a character sequence in a str 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 The error @@ -616,7 +751,7 @@ From then on, after restarting your shell, you will be able to access both youtu Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration). -### How do I download a video starting with a `-` ? +### How do I download a video starting with a `-`? Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`: @@ -627,7 +762,7 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. -Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. +Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare). ### Can you add support for this anime video site, or site which shows current movies for free? @@ -757,7 +892,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) ``` -Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object. +Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object. Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: @@ -798,9 +933,23 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: # BUGS -Bugs and suggestions should be reported at: . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode. +Bugs and suggestions should be reported at: . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)). -**Please include the full output of youtube-dl when run with `-v`**. +**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: +``` +$ youtube-dl -v +[debug] System config: [] +[debug] User config: [] +[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] +[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 +[debug] youtube-dl version 2015.12.06 +[debug] Git HEAD: 135392e +[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2 +[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 +[debug] Proxy map: {} +... +``` +**Do not post screenshots of verbose log only plain text is acceptable.** The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. @@ -816,13 +965,13 @@ So please elaborate on what feature you are requesting, or what bug you want to - How it could be fixed - How your proposed solution would look like -If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. +If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information. If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). -**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. +**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL. ### Are you using the latest version? @@ -830,7 +979,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're ### Is the issue already documented? -Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. ### Why are existing options not enough? @@ -860,4 +1009,4 @@ It may sound strange, but some bug reports we receive are completely unrelated t youtube-dl is released into the public domain by the copyright holders. -This README file was originally written by Daniel Bolton () and is likewise released into the public domain. +This README file was originally written by [Daniel Bolton](https://github.com/dbbolton) and is likewise released into the public domain. diff --git a/README.txt b/README.txt index 54d4c33..1a674b5 100644 --- a/README.txt +++ b/README.txt @@ -41,7 +41,7 @@ You can also use pip: Alternatively, refer to the developer instructions for how to check out and work with the git repository. For further options, including PGP -signatures, see https://rg3.github.io/youtube-dl/download.html . +signatures, see the youtube-dl Download Page. @@ -194,6 +194,10 @@ Download Options: expected filesize (experimental) --hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental) + --hls-use-mpegts Use the mpegts container for HLS videos, + allowing to play the video while + downloading (some players may not be able + to play it) --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,axel,curl,httpie,wget @@ -350,7 +354,7 @@ 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 of specified + -F, --list-formats List all available formats of requested videos --youtube-skip-dash-manifest Do not download the DASH manifests and related data on YouTube videos @@ -372,8 +376,8 @@ Subtitle Options: preference, for example: "srt" or "ass/srt/best" --sub-lang LANGS Languages of the subtitles to download - (optional) separated by commas, use IETF - language tags like 'en,pt' + (optional) separated by commas, use --list- + subs for available language tags Authentication Options: @@ -437,7 +441,7 @@ Post-processing Options: downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm {}' - --convert-subtitles FORMAT Convert the subtitles to other format + --convert-subs FORMAT Convert the subtitles to other format (currently supported: srt|ass|vtt) @@ -505,28 +509,86 @@ video. The special sequences have the format %(NAME)s. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are: -- id: The sequence will be replaced by the video identifier. -- url: The sequence will be replaced by the video URL. -- uploader: The sequence will be replaced by the nickname of the - person who uploaded the video. -- upload_date: The sequence will be replaced by the upload date in - YYYYMMDD format. -- title: The sequence will be replaced by the video title. -- ext: The sequence will be replaced by the appropriate extension - (like flv or mp4). -- epoch: The sequence will be replaced by the Unix epoch when creating - the file. -- autonumber: The sequence will be replaced by a five-digit number - that will be increased with each download, starting at zero. -- playlist: The sequence will be replaced by the name or the id of the - playlist that contains the video. -- playlist_index: The sequence will be replaced by the index of the - video in the playlist padded with leading zeros according to the - total length of the playlist. -- format_id: The sequence will be replaced by the format code - specified by --format. -- duration: The sequence will be replaced by the length of the video - in seconds. +- id: Video identifier +- title: Video title +- url: Video URL +- ext: Video filename extension +- alt_title: A secondary title of the video +- display_id: An alternative identifier for the video +- uploader: Full name of the video uploader +- creator: The main artist who created the video +- release_date: The date (YYYYMMDD) when the video was released +- timestamp: UNIX timestamp of the moment the video became available +- upload_date: Video upload date (YYYYMMDD) +- uploader_id: Nickname or id of the video uploader +- location: Physical location where the video was filmed +- duration: Length of the video in seconds +- view_count: How many users have watched the video on the platform +- like_count: Number of positive ratings of the video +- dislike_count: Number of negative ratings of the video +- repost_count: Number of reposts of the video +- average_rating: Average rating give by users, the scale used depends + on the webpage +- comment_count: Number of comments on the video +- age_limit: Age restriction for the video (years) +- format: A human-readable description of the format +- format_id: Format code specified by --format +- format_note: Additional info about the format +- width: Width of the video +- height: Height of the video +- resolution: Textual description of width and height +- tbr: Average bitrate of audio and video in KBit/s +- abr: Average audio bitrate in KBit/s +- acodec: Name of the audio codec in use +- asr: Audio sampling rate in Hertz +- vbr: Average video bitrate in KBit/s +- fps: Frame rate +- vcodec: Name of the video codec in use +- container: Name of the container format +- filesize: The number of bytes, if known in advance +- filesize_approx: An estimate for the number of bytes +- protocol: The protocol that will be used for the actual download +- extractor: Name of the extractor +- extractor_key: Key name of the extractor +- epoch: Unix epoch when creating the file +- autonumber: Five-digit number that will be increased with each + download, starting at zero +- playlist: Name or id of the playlist that contains the video +- playlist_index: Index of the video in the playlist padded with + leading zeros according to the total length of the playlist + +Available for the video that belongs to some logical chapter or section: +- chapter: Name or title of the chapter the video belongs to - +chapter_number: Number of the chapter the video belongs to - chapter_id: +Id of the chapter the video belongs to + +Available for the video that is an episode of some series or programme: +- series: Title of the series or programme the video episode belongs to +- season: Title of the season the video episode belongs to - +season_number: Number of the season the video episode belongs to - +season_id: Id of the season the video episode belongs to - episode: +Title of the video episode - episode_number: Number of the video episode +within a season - episode_id: Id of the video episode + +Each aforementioned sequence when referenced in output template will be +replaced by the actual value corresponding to the sequence name. Note +that some of the sequences are not guaranteed to be present since they +depend on the metadata obtained by particular extractor, such sequences +will be replaced with NA. + +For example for -o %(title)s-%(id)s.%(ext)s and mp4 video with title +youtube-dl test video and id BaW_jenozKcj this will result in a +youtube-dl test video-BaW_jenozKcj.mp4 file created in the current +directory. + +Output template can also contain arbitrary hierarchical path, e.g. +-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' that will +result in downloading each video in a directory corresponding to this +path template. Any missing directory will be automatically created for +you. + +To specify percent literal in output template use %%. To output to +stdout use -o -. The current default template is %(title)s-%(id)s.%(ext)s. @@ -535,44 +597,120 @@ In some cases, you don't want special characters such as 中, spaces, or or the filename through an 8bit-unsafe channel. In these cases, add the --restrict-filenames flag to get a shorter title: -``` {.bash} -$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc -youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters -$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames -youtube-dl_test_video_.mp4 # A simple file name -``` +Examples (note on Windows you may need to use double quotes instead of +single): + + $ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc + youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters + + $ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc --restrict-filenames + youtube-dl_test_video_.mp4 # A simple file name + + # Download YouTube playlist videos in separate directory indexed by video order in a playlist + $ youtube-dl -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re + + # Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home + $ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/ + + # Download entire series season keeping each series and each season in separate directory under C:/MyVideos + $ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617 + + # Stream the video being downloaded to stdout + $ youtube-dl -o - BaW_jenozKc FORMAT SELECTION -By default youtube-dl tries to download the best quality, but sometimes -you may want to download in a different format. The simplest case is -requesting a specific format, for example -f 22. You can get the list of -available formats using --list-formats, you can also use a file -extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or -the special names best, bestvideo, bestaudio and worst. +By default youtube-dl tries to download the best available quality, i.e. +if you want the best quality you DON'T NEED to pass any special options, +youtube-dl will guess it for you by DEFAULT. + +But sometimes you may want to download in a different format, for +example when you are on a slow or intermittent connection. The key +mechanism for achieving this is so called _format selection_ based on +which you can explicitly specify desired format, select formats based on +some criterion or criteria, setup precedence and much more. + +The general syntax for format selection is --format FORMAT or shorter +-f FORMAT where FORMAT is a _selector expression_, i.e. an expression +that describes format or formats you would like to download. + +The simplest case is requesting a specific format, for example with +-f 22 you can download the format with format code equal to 22. You can +get the list of available format codes for particular video using +--list-formats or -F. Note that these format codes are extractor +specific. + +You can also use a file extension (currently 3gp, aac, flv, m4a, mp3, +mp4, ogg, wav, webm are supported) to download best quality format of +particular file extension served as a single file, e.g. -f webm will +download best quality format with webm extension served as a single +file. + +You can also use special names to select particular edge case format: - +best: Select best quality format represented by single file with video +and audio - worst: Select worst quality format represented by single +file with video and audio - bestvideo: Select best quality video only +format (e.g. DASH video), may not be available - worstvideo: Select +worst quality video only format, may not be available - bestaudio: +Select best quality audio only format, may not be available - +worstaudio: Select worst quality audio only format, may not be available + +For example, to download worst quality video only format you can use +-f worstvideo. If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using -slashes, as in -f 22/17/18. You can also filter the video results by -putting a condition in brackets, as in -f "best[height=720]" (or --f "[filesize>10M]"). This works for filesize, height, width, tbr, abr, -vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, -acodec, vcodec, container, and protocol and the comparisons =, != . +slashes. Note that slash is left-associative, i.e. formats on the left +hand side are preferred, for example -f 22/17/18 will download format 22 +if it's available, otherwise it will download format 17 if it's +available, otherwise it will download format 18 if it's available, +otherwise it will complain that no suitable formats are available for +download. + +If you want to download several formats of the same video use comma as a +separator, e.g. -f 22,17,18 will download all these three formats, of +course if they are available. Or more sophisticated example combined +with precedence feature -f 136/137/mp4/bestvideo,140/m4a/bestaudio. + +You can also filter the video formats by putting a condition in +brackets, as in -f "best[height=720]" (or -f "[filesize>10M]"). + +The following numeric meta fields can be used with comparisons <, <=, >, +>=, = (equals), != (not equals): - filesize: The number of bytes, if +known in advance - width: Width of the video, if known - height: Height +of the video, if known - tbr: Average bitrate of audio and video in +KBit/s - abr: Average audio bitrate in KBit/s - vbr: Average video +bitrate in KBit/s - asr: Audio sampling rate in Hertz - fps: Frame rate + +Also filtering work for comparisons = (equals), != (not equals), ^= +(begins with), $= (ends with), *= (contains) and following string meta +fields: - ext: File extension - acodec: Name of the audio codec in use - +vcodec: Name of the video codec in use - container: Name of the +container format - protocol: The protocol that will be used for the +actual download, lower-case. http, https, rtsp, rtmp, rtmpe, m3u8, or +m3u8_native + +Note that none of the aforementioned meta fields are guaranteed to be +present since this solely depends on the metadata obtained by particular +extractor, i.e. the metadata offered by video hoster. + Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so -f "[height <=? 720][tbr>500]" selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. -Use commas to download multiple formats, such as --f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and -audio of two formats into a single file using --f + (requires ffmpeg or avconv), for -example -f bestvideo+bestaudio. Format selectors can also be grouped -using parentheses, for example if you want to download the best mp4 and -webm formats with a height lower than 480 you can use --f '(mp4,webm)[height<480]'. + +You can merge the video and audio of two formats into a single file +using -f + (requires ffmpeg or avconv +installed), for example -f bestvideo+bestaudio will download best video +only format, best audio only format and mux them together with +ffmpeg/avconv. + +Format selectors can also be grouped using parentheses, for example if +you want to download the best mp4 and webm formats with a height lower +than 480 you can use -f '(mp4,webm)[height<480]'. Since the end of April 2015 and version 2015.04.26 youtube-dl uses -f bestvideo+bestaudio/best as default format selection (see #5447, @@ -582,7 +720,7 @@ single file giving the best overall quality available. Otherwise it falls back to best and results in downloading the best available quality served as a single file. best is also needed for videos that don't come from YouTube because they don't provide the audio and video in two -different files. If you want to only download some dash formats (for +different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add -f bestvideo[height<=?1080]+bestaudio/best to your configuration file. @@ -598,6 +736,21 @@ quality media served as a single file, you should explicitly specify your choice with -f best. You may want to add it to the configuration file in order not to type it every time you run youtube-dl. +Examples (note on Windows you may need to use double quotes instead of +single): + + # Download best mp4 format available or any other best if no mp4 available + $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best' + + # Download best format available but not better that 480p + $ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]' + + # Download best video only format but no bigger that 50 MB + $ youtube-dl -f 'best[filesize<50M]' + + # Download best format available via direct link over HTTP/HTTPS protocol + $ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]' + VIDEO SELECTION @@ -612,16 +765,14 @@ Videos can be filtered by their upload date using the options --date, Examples: -``` {.bash} -# Download only the videos uploaded in the last 6 months -$ youtube-dl --dateafter now-6months + # Download only the videos uploaded in the last 6 months + $ youtube-dl --dateafter now-6months -# Download only the videos uploaded on January 1, 1970 -$ youtube-dl --date 19700101 + # Download only the videos uploaded on January 1, 1970 + $ youtube-dl --date 19700101 -$ # Download only the videos uploaded in the 200x decade -$ youtube-dl --dateafter 20000101 --datebefore 20091231 -``` + $ # Download only the videos uploaded in the 200x decade + $ youtube-dl --dateafter 20000101 --datebefore 20091231 @@ -832,7 +983,7 @@ Use the -o to specify an output template, for example -o "/home/user/videos/%(title)s-%(id)s.%(ext)s". If you want this for all of your downloads, put the option into your configuration file. -How do I download a video starting with a - ? +How do I download a video starting with a -? Either prepend http://www.youtube.com/watch?v= or separate the ID from the options with --: @@ -852,7 +1003,9 @@ LF (\n) for Linux and CR (\r) for Mac OS. HTTP Error 400: Bad Request when using --cookies is a good sign of invalid newline format. Passing cookies to youtube-dl is a good way to workaround login when a -particular extractor does not implement it explicitly. +particular extractor does not implement it explicitly. Another use case +is working around CAPTCHA some websites require you to solve in +particular cases in order to get access (e.g. YouTube, CloudFlare). Can you add support for this anime video site, or site which shows current movies for free? @@ -966,46 +1119,44 @@ list (assuming your service is called yourextractor): 4. Start with this simple template and save it to youtube_dl/extractor/yourextractor.py: - ``` {.python} - # coding: utf-8 - from __future__ import unicode_literals - - from .common import InfoExtractor - - - class YourExtractorIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P[0-9]+)' - _TEST = { - 'url': 'http://yourextractor.com/watch/42', - 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', - 'info_dict': { - 'id': '42', - 'ext': 'mp4', - 'title': 'Video title goes here', - 'thumbnail': 're:^https?://.*\.jpg$', - # TODO more properties, either as: - # * A value - # * MD5 checksum; start the string with md5: - # * A regular expression; start the string with re: - # * Any Python type (for example int or float) + # coding: utf-8 + from __future__ import unicode_literals + + from .common import InfoExtractor + + + class YourExtractorIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P[0-9]+)' + _TEST = { + 'url': 'http://yourextractor.com/watch/42', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': '42', + 'ext': 'mp4', + 'title': 'Video title goes here', + 'thumbnail': 're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } } - } - 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) - # TODO more code goes here, for example ... - title = self._html_search_regex(r'

(.+?)

', webpage, 'title') + # TODO more code goes here, for example ... + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') - return { - 'id': video_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), - # TODO more properties (see youtube_dl/extractor/common.py) - } - ``` + return { + 'id': video_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + # TODO more properties (see youtube_dl/extractor/common.py) + } 5. Add an import in youtube_dl/extractor/__init__.py. 6. Run python test/test_download.py TestDownload.test_YourExtractor. @@ -1043,14 +1194,12 @@ any problems parsing its output, feel free to create a report. From a Python program, you can embed youtube-dl in a more powerful fashion, like this: -``` {.python} -from __future__ import unicode_literals -import youtube_dl + from __future__ import unicode_literals + import youtube_dl -ydl_opts = {} -with youtube_dl.YoutubeDL(ydl_opts) as ydl: - ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) -``` + ydl_opts = {} + with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) Most likely, you'll want to use various options. For a list of what can be done, have a look at youtube_dl/YoutubeDL.py. For a start, if you @@ -1060,40 +1209,38 @@ Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: -``` {.python} -from __future__ import unicode_literals -import youtube_dl + from __future__ import unicode_literals + import youtube_dl -class MyLogger(object): - def debug(self, msg): - pass + class MyLogger(object): + def debug(self, msg): + pass - def warning(self, msg): - pass + def warning(self, msg): + pass - def error(self, msg): - print(msg) + def error(self, msg): + print(msg) -def my_hook(d): - if d['status'] == 'finished': - print('Done downloading, now converting ...') + def my_hook(d): + if d['status'] == 'finished': + print('Done downloading, now converting ...') -ydl_opts = { - 'format': 'bestaudio/best', - 'postprocessors': [{ - 'key': 'FFmpegExtractAudio', - 'preferredcodec': 'mp3', - 'preferredquality': '192', - }], - 'logger': MyLogger(), - 'progress_hooks': [my_hook], -} -with youtube_dl.YoutubeDL(ydl_opts) as ydl: - ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) -``` + ydl_opts = { + 'format': 'bestaudio/best', + 'postprocessors': [{ + 'key': 'FFmpegExtractAudio', + 'preferredcodec': 'mp3', + 'preferredquality': '192', + }], + 'logger': MyLogger(), + 'progress_hooks': [my_hook], + } + with youtube_dl.YoutubeDL(ydl_opts) as ydl: + ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) @@ -1101,12 +1248,30 @@ BUGS Bugs and suggestions should be reported at: -https://github.com/rg3/youtube-dl/issues . Unless you were prompted so -or there is another pertinent reason (e.g. GitHub fails to accept the -bug report), please do not send bug reports via personal email. For -discussions, join us in the irc channel #youtube-dl on freenode. - -PLEASE INCLUDE THE FULL OUTPUT OF YOUTUBE-DL WHEN RUN WITH -v. +https://github.com/rg3/youtube-dl/issues. Unless you were prompted so or +there is another pertinent reason (e.g. GitHub fails to accept the bug +report), please do not send bug reports via personal email. For +discussions, join us in the IRC channel #youtube-dl on freenode +(webchat). + +PLEASE INCLUDE THE FULL OUTPUT OF YOUTUBE-DL WHEN RUN WITH -v, i.e. ADD +-v flag to YOUR COMMAND LINE, copy the WHOLE output and post it in the +issue body wrapped in ``` for better formatting. It should look similar +to this: + + $ youtube-dl -v + [debug] System config: [] + [debug] User config: [] + [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] + [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 + [debug] youtube-dl version 2015.12.06 + [debug] Git HEAD: 135392e + [debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2 + [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 + [debug] Proxy map: {} + ... + +DO NOT POST SCREENSHOTS OF VERBOSE LOG ONLY PLAIN TEXT IS ACCEPTABLE. The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible @@ -1133,7 +1298,7 @@ want to be fixed. Make sure that it's obvious If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes -misinterpretation likely. As a commiter myself, I often get frustrated +misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. @@ -1152,9 +1317,9 @@ command-line) or upload the .dump files you get when you add SITE SUPPORT REQUESTS MUST CONTAIN AN EXAMPLE URL. An example URL is a URL you might want to download, like -http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious +http://www.youtube.com/watch?v=BaW_jenozKc. There should be an obvious video present. Except under very special circumstances, the main page of -a video service (e.g. http://www.youtube.com/ ) is _not_ an example URL. +a video service (e.g. http://www.youtube.com/) is _not_ an example URL. Are you using the latest version? @@ -1166,12 +1331,11 @@ requests as well. Is the issue already documented? Make sure that someone has not already opened the issue you're trying to -open. Search at the top of the window or at -https://github.com/rg3/youtube-dl/search?type=Issues . If there is an -issue, feel free to write something along the lines of "This affects me -as well, with version 2015.01.01. Here is some more information on the -issue: ...". While some issues may be old, a new post into them often -spurs rapid activity. +open. Search at the top of the window or browse the GitHub Issues of +this repository. If there is an issue, feel free to write something +along the lines of "This affects me as well, with version 2015.01.01. +Here is some more information on the issue: ...". While some issues may +be old, a new post into them often spurs rapid activity. Why are existing options not enough? @@ -1242,6 +1406,5 @@ COPYRIGHT youtube-dl is released into the public domain by the copyright holders. -This README file was originally written by Daniel Bolton -(https://github.com/dbbolton) and is likewise released into the public -domain. +This README file was originally written by Daniel Bolton and is likewise +released into the public domain. diff --git a/devscripts/gh-pages/update-copyright.py b/devscripts/gh-pages/update-copyright.py index 3663c8a..e6c3abc 100755 --- a/devscripts/gh-pages/update-copyright.py +++ b/devscripts/gh-pages/update-copyright.py @@ -5,7 +5,7 @@ from __future__ import with_statement, unicode_literals import datetime import glob -import io # For Python 2 compatibilty +import io # For Python 2 compatibility import os import re diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 1df4086..7459615 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1,6 +1,7 @@ # Supported sites - **1tv**: Первый канал - **1up.com** + - **20min** - **220.ro** - **22tracks:genre** - **22tracks:track** @@ -15,37 +16,48 @@ - **abc.net.au** - **Abc7News** - **AcademicEarth:Course** + - **acast** + - **acast:channel** - **AddAnime** - **AdobeTV** + - **AdobeTVChannel** + - **AdobeTVShow** - **AdobeTVVideo** - **AdultSwim** - - **Aftenposten** + - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network - **Aftonbladet** - **AirMozilla** - **AlJazeera** - **Allocine** - **AlphaPorno** + - **AnimeOnDemand** - **anitube.se** - **AnySex** - **Aparat** - **AppleConnect** - **AppleDaily**: 臺灣蘋果日報 - - **AppleTrailers** + - **appletrailers** + - **appletrailers:section** - **archive.org**: archive.org videos - **ARD** + - **ARD:mediathek**: Saarländischer Rundfunk - **ARD:mediathek** - **arte.tv** - **arte.tv:+7** + - **arte.tv:cinema** - **arte.tv:concert** - **arte.tv:creative** - **arte.tv:ddc** - **arte.tv:embed** - **arte.tv:future** + - **arte.tv:magazine** - **AtresPlayer** - **ATTTechChannel** + - **AudiMedia** - **audiomack** - **audiomack:album** - **Azubu** + - **AzubuLive** - **BaiduVideo**: 百度视频 - **bambuser** - **bambuser:channel** @@ -58,11 +70,12 @@ - **Beeg** - **BehindKink** - **Bet** + - **Bigflix** - **Bild**: Bild.de - **BiliBili** + - **BleacherReport** + - **BleacherReportCMS** - **blinkx** - - **blip.tv:user** - - **BlipTV** - **Bloomberg** - **Bpb**: Bundeszentrale für politische Bildung - **BR**: Bayerischer Rundfunk Mediathek @@ -75,11 +88,14 @@ - **BYUtv** - **Camdemy** - **CamdemyFolder** - - **Canal13cl** - **canalc2.tv** - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv + - **Canvas** + - **CBC** + - **CBCPlayer** - **CBS** - **CBSNews**: CBS News + - **CBSNewsLiveVideo**: CBS News Live Videos - **CBSSports** - **CeskaTelevize** - **channel9**: Channel 9 @@ -92,6 +108,7 @@ - **Clipfish** - **cliphunter** - **Clipsyndicate** + - **cloudtime**: CloudTime - **Cloudy** - **Clubic** - **Clyp** @@ -107,6 +124,7 @@ - **ComedyCentralShows**: The Daily Show / The Colbert Report - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED - **Cracked** + - **Crackle** - **Criterion** - **CrooksAndLiars** - **Crunchyroll** @@ -114,18 +132,27 @@ - **CSpan**: C-SPAN - **CtsNews**: 華視新聞 - **culturebox.francetvinfo.fr** + - **CultureUnplugged** + - **CWTV** - **dailymotion** - **dailymotion:playlist** - **dailymotion:user** - **DailymotionCloud** - **daum.net** + - **daum.net:clip** + - **daum.net:playlist** + - **daum.net:user** - **DBTV** - **DCN** + - **dcn:live** + - **dcn:season** + - **dcn:video** - **DctpTv** - **DeezerPlaylist** - **defense.gouv.fr** - **democracynow** - **DHM**: Filmarchiv - Deutsches Historisches Museum + - **Digiteka** - **Discovery** - **Dotsub** - **DouyuTV**: 斗鱼 @@ -154,7 +181,7 @@ - **Eporner** - **EroProfile** - **Escapist** - - **ESPN** (Currently broken) + - **ESPN** - **EsriVideo** - **Europa** - **EveryonesMixtape** @@ -162,6 +189,7 @@ - **ExpoTV** - **ExtremeTube** - **facebook** + - **facebook:post** - **faz.net** - **fc2** - **Fczenit** @@ -171,18 +199,22 @@ - **Flickr** - **Folketinget**: Folketinget (ft.dk; Danish parliament) - **FootyRoom** + - **FOX** - **Foxgay** - **FoxNews**: Fox News and Fox Business Video - **FoxSports** - **france2.fr:generation-quoi** - **FranceCulture** + - **FranceCultureEmission** - **FranceInter** - **francetv**: France 2, 3, 4, 5 and Ô - **francetvinfo.fr** - **Freesound** - **freespeech.org** - **FreeVideo** + - **Funimation** - **FunnyOrDie** + - **GameInformer** - **Gamekings** - **GameOne** - **gameone:playlist** @@ -202,7 +234,9 @@ - **GodTube** - **GoldenMoustache** - **Golem** + - **GoogleDrive** - **Goshgay** + - **GPUTechConf** - **Groupon** - **Hark** - **HearThisAt** @@ -211,11 +245,11 @@ - **Helsinki**: helsinki.fi - **HentaiStigma** - **HistoricFilms** - - **History** - **hitbox** - **hitbox:live** - **HornBunny** - **HotNewHipHop** + - **HotStar** - **Howcast** - **HowStuffWorks** - **HuffPost**: Huffington Post @@ -238,12 +272,13 @@ - **Ir90Tv** - **ivi**: ivi.ru - **ivi:compilation**: ivi.ru compilations + - **ivideon**: Ivideon TV - **Izlesene** - **JadoreCettePub** - **JeuxVideo** - **Jove** - **jpopsuki.tv** - - **Jukebox** + - **JWPlatform** - **Kaltura** - **KanalPlay**: Kanal 5/9/11 Play - **Kankan** @@ -253,6 +288,7 @@ - **KeezMovies** - **KhanAcademy** - **KickStarter** + - **KonserthusetPlay** - **kontrtube**: KontrTube.ru - Труба зовёт - **KrasView**: Красвью - **Ku6** @@ -265,7 +301,9 @@ - **la7.tv** - **Laola1Tv** - **Lecture2Go** + - **Lemonde** - **Letv**: 乐视网 + - **LetvCloud**: 乐视云 - **LetvPlaylist** - **LetvTv** - **Libsyn** @@ -278,13 +316,16 @@ - **livestream** - **livestream:original** - **LnkGo** + - **LoveHomePorn** - **lrt.lt** - **lynda**: lynda.com videos - **lynda:course**: lynda.com online courses - **m6** - **macgamestore**: MacGameStore trailers - **mailru**: Видео@Mail.Ru + - **MakerTV** - **Malemotion** + - **MatchTV** - **MDR**: MDR.DE and KiKA - **media.ccc.de** - **metacafe** @@ -307,7 +348,6 @@ - **MovieClips** - **MovieFap** - **Moviezine** - - **movshare**: MovShare - **MPORA** - **MSNBC** - **MTV** @@ -322,7 +362,7 @@ - **MySpace:album** - **MySpass** - **Myvi** - - **myvideo** + - **myvideo** (Currently broken) - **MyVidster** - **n-tv.de** - **NationalGeographic** @@ -350,11 +390,13 @@ - **Newstube** - **NextMedia**: 蘋果日報 - **NextMediaActionNews**: 蘋果日報 - 動新聞 + - **nextmovie.com** - **nfb**: National Film Board of Canada - **nfl.com** - **nhl.com** - **nhl.com:news**: NHL news - **nhl.com:videocenter**: NHL videocenter category + - **nick.com** - **niconico**: ニコニコ動画 - **NiconicoPlaylist** - **njoy**: N-JOY @@ -367,13 +409,15 @@ - **nowness** - **nowness:playlist** - **nowness:series** - - **NowTV** + - **NowTV** (Currently broken) - **NowTVList** - **nowvideo**: NowVideo + - **Noz** - **npo**: npo.nl and ntr.nl - **npo.nl:live** - **npo.nl:radio** - **npo.nl:radio:fragment** + - **Npr** - **NRK** - **NRKPlaylist** - **NRKTV**: NRK TV and NRK Radio @@ -388,22 +432,26 @@ - **OnionStudios** - **Ooyala** - **OoyalaExternal** + - **OraTV** - **orf:fm4**: radio FM4 - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek + - **pandora.tv**: 판도라TV - **parliamentlive.tv**: UK parliament videos - **Patreon** - - **PBS** + - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC) + - **pcmag** - **Periscope**: Periscope - **PhilharmonieDeParis**: Philharmonie de Paris - - **Phoenix** + - **phoenix.de** - **Photobucket** - **Pinkbike** - **Pladform** - **PlanetaPlay** - **play.fm** - **played.to** + - **PlaysTV** - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz - **Playvid** - **Playwire** @@ -415,6 +463,7 @@ - **PornHd** - **PornHub** - **PornHubPlaylist** + - **PornHubUserVideos** - **Pornotube** - **PornoVoisines** - **PornoXO** @@ -435,16 +484,20 @@ - **radiofrance** - **RadioJavan** - **Rai** + - **RaiTV** - **RBMARadio** - **RDS**: RDS.ca - **RedTube** + - **RegioTV** - **Restudy** - **ReverbNation** + - **Revision3** - **RingTV** - **RottenTomatoes** - **Roxwel** - **RTBF** - - **Rte** + - **rte**: Raidió Teilifís Éireann TV + - **rte:radio**: Raidió Teilifís Éireann radio - **rtl.nl**: rtl.nl and rtlxl.nl - **RTL2** - **RTP** @@ -454,6 +507,7 @@ - **rtve.es:live**: RTVE.es live streams - **RTVNH** - **RUHD** + - **RulePorn** - **rutube**: Rutube videos - **rutube:channel**: Rutube channels - **rutube:embed**: Rutube embedded videos @@ -467,10 +521,12 @@ - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au + - **schooltv** - **SciVee** - **screen.yahoo:search**: Yahoo screen search - **Screencast** - **ScreencastOMatic** + - **ScreenJunkies** - **ScreenwaveMedia** - **SenateISVP** - **ServingSys** @@ -480,6 +536,8 @@ - **Shared**: shared.sx and vivo.sx - **ShareSix** - **Sina** + - **skynewsarabia:video** + - **skynewsarabia:video** - **Slideshare** - **Slutload** - **smotri**: Smotri.com @@ -490,8 +548,6 @@ - **SnagFilmsEmbed** - **Snotr** - **Sohu** - - **soompi** - - **soompi:show** - **soundcloud** - **soundcloud:playlist** - **soundcloud:search**: Soundcloud search @@ -516,8 +572,8 @@ - **SportBoxEmbed** - **SportDeutschland** - **Sportschau** - - **Srf** - - **SRMediathek**: Saarländischer Rundfunk + - **SRGSSR** + - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites - **SSA** - **stanfordoc**: Stanford Open ClassRoom - **Steam** @@ -542,14 +598,15 @@ - **TechTalks** - **techtv.mit.edu** - **ted** + - **Tele13** - **TeleBruxelles** - **Telecinco**: telecinco.es, cuatro.com and mediaset.es - **Telegraaf** - **TeleMB** - **TeleTask** - **TenPlay** - - **TestTube** - **TF1** + - **TheIntercept** - **TheOnion** - **ThePlatform** - **ThePlatformFeed** @@ -559,22 +616,28 @@ - **THVideo** - **THVideoPlaylist** - **tinypic**: tinypic.com videos - - **tlc.com** - **tlc.de** - **TMZ** - **TMZArticle** - **TNAFlix** + - **toggle** - **tou.tv** - **Toypics**: Toypics user profile - **ToypicsUser**: Toypics user profile - **TrailerAddict** (Currently broken) - **Trilulilu** + - **trollvids** - **TruTube** - **Tube8** - **TubiTv** - - **Tudou** + - **tudou** + - **tudou:album** + - **tudou:playlist** - **Tumblr** - - **TuneIn** + - **tunein:clip** + - **tunein:program** + - **tunein:station** + - **tunein:topic** - **Turbo** - **Tutv** - **tv.dfb.de** @@ -584,6 +647,7 @@ - **TVC** - **TVCArticle** - **tvigle**: Интернет-телевидение Tvigle.ru + - **tvland.com** - **tvp.pl** - **tvp.pl:Series** - **TVPlay**: TV3Play and related services @@ -596,12 +660,12 @@ - **twitch:video** - **twitch:vod** - **twitter** + - **twitter:amplify** - **twitter:card** - **Ubu** - **udemy** - **udemy:course** - **UDNEmbed**: 聯合影音 - - **Ultimedia** - **Unistra** - **Urort**: NRK P3 Urørt - **ustream** @@ -613,7 +677,7 @@ - **Vessel** - **Vesti**: Вести.Ru - **Vevo** - - **VGTV**: VGTV and BTTV + - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet - **vh1.com** - **Vice** - **Viddler** @@ -621,11 +685,16 @@ - **video.mit.edu** - **VideoDetective** - **videofy.me** - - **VideoMega** + - **VideoMega** (Currently broken) + - **videomore** + - **videomore:season** + - **videomore:video** - **VideoPremium** - - **VideoTt**: video.tt - Your True Tube + - **VideoTt**: video.tt - Your True Tube (Currently broken) - **videoweed**: VideoWeed - - **Vidme** + - **vidme** + - **vidme:user** + - **vidme:user:likes** - **Vidzi** - **vier** - **vier:videos** @@ -665,6 +734,8 @@ - **WebOfStories** - **WebOfStoriesPlaylist** - **Weibo** + - **WeiqiTV**: WQTV + - **wholecloud**: WholeCloud - **Wimp** - **Wistia** - **WNL** @@ -701,6 +772,7 @@ - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication) - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication) - **youtube:playlist**: YouTube.com playlists + - **youtube:playlists**: YouTube.com user/channel playlists - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication) - **youtube:search**: YouTube.com searches - **youtube:search:date**: YouTube.com searches, newest videos first @@ -708,10 +780,10 @@ - **youtube:show**: YouTube.com (multi-season) shows - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication) - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) - - **youtube:user:playlists**: YouTube.com user playlists - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication) - **Zapiks** - **ZDF** - **ZDFChannel** - **zingmp3:album**: mp3.zing.vn albums - **zingmp3:song**: mp3.zing.vn songs + - **ZippCast** diff --git a/test/swftests/ArrayAccess.swf b/test/swftests/ArrayAccess.swf index 93f88cf..6cb49ab 100644 Binary files a/test/swftests/ArrayAccess.swf and b/test/swftests/ArrayAccess.swf differ diff --git a/test/swftests/ClassCall.swf b/test/swftests/ClassCall.swf index bde78fb..849cca4 100644 Binary files a/test/swftests/ClassCall.swf and b/test/swftests/ClassCall.swf differ diff --git a/test/swftests/ClassConstruction.swf b/test/swftests/ClassConstruction.swf index b17e844..5e27a13 100644 Binary files a/test/swftests/ClassConstruction.swf and b/test/swftests/ClassConstruction.swf differ diff --git a/test/swftests/ConstArrayAccess.swf b/test/swftests/ConstArrayAccess.swf index 35cf790..00bde84 100644 Binary files a/test/swftests/ConstArrayAccess.swf and b/test/swftests/ConstArrayAccess.swf differ diff --git a/test/swftests/ConstantInt.swf b/test/swftests/ConstantInt.swf index b3a39b3..fe9c5c6 100644 Binary files a/test/swftests/ConstantInt.swf and b/test/swftests/ConstantInt.swf differ diff --git a/test/swftests/DictCall.swf b/test/swftests/DictCall.swf index e80614c..b0296d0 100644 Binary files a/test/swftests/DictCall.swf and b/test/swftests/DictCall.swf differ diff --git a/test/swftests/EqualsOperator.swf b/test/swftests/EqualsOperator.swf index 0cf4152..d5628df 100644 Binary files a/test/swftests/EqualsOperator.swf and b/test/swftests/EqualsOperator.swf differ diff --git a/test/swftests/LocalVars.swf b/test/swftests/LocalVars.swf index e044396..02a267f 100644 Binary files a/test/swftests/LocalVars.swf and b/test/swftests/LocalVars.swf differ diff --git a/test/swftests/MemberAssignment.swf b/test/swftests/MemberAssignment.swf index 3bc02a4..970cfcb 100644 Binary files a/test/swftests/MemberAssignment.swf and b/test/swftests/MemberAssignment.swf differ diff --git a/test/swftests/NeOperator.swf b/test/swftests/NeOperator.swf index 5622a91..f882b5f 100644 Binary files a/test/swftests/NeOperator.swf and b/test/swftests/NeOperator.swf differ diff --git a/test/swftests/PrivateCall.swf b/test/swftests/PrivateCall.swf index 6638f2b..abc66d6 100644 Binary files a/test/swftests/PrivateCall.swf and b/test/swftests/PrivateCall.swf differ diff --git a/test/swftests/PrivateVoidCall.swf b/test/swftests/PrivateVoidCall.swf index d47c438..3d60c75 100644 Binary files a/test/swftests/PrivateVoidCall.swf and b/test/swftests/PrivateVoidCall.swf differ diff --git a/test/swftests/StaticAssignment.swf b/test/swftests/StaticAssignment.swf index 1f9873b..2b8bf88 100644 Binary files a/test/swftests/StaticAssignment.swf and b/test/swftests/StaticAssignment.swf differ diff --git a/test/swftests/StaticRetrieval.swf b/test/swftests/StaticRetrieval.swf index 9a32705..0823df4 100644 Binary files a/test/swftests/StaticRetrieval.swf and b/test/swftests/StaticRetrieval.swf differ diff --git a/test/swftests/StringBasics.swf b/test/swftests/StringBasics.swf index 3fa6e9f..7ba6ba6 100644 Binary files a/test/swftests/StringBasics.swf and b/test/swftests/StringBasics.swf differ diff --git a/test/swftests/StringCharCodeAt.swf b/test/swftests/StringCharCodeAt.swf index a0de83a..d037757 100644 Binary files a/test/swftests/StringCharCodeAt.swf and b/test/swftests/StringCharCodeAt.swf differ diff --git a/test/swftests/StringConversion.swf b/test/swftests/StringConversion.swf index b5bbb72..8c88556 100644 Binary files a/test/swftests/StringConversion.swf and b/test/swftests/StringConversion.swf differ diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 0388c0b..59f7ab4 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -12,8 +12,9 @@ import copy from test.helper import FakeYDL, assertRegexpMatches from youtube_dl import YoutubeDL -from youtube_dl.compat import compat_str +from youtube_dl.compat import compat_str, compat_urllib_error from youtube_dl.extractor import YoutubeIE +from youtube_dl.extractor.common import InfoExtractor from youtube_dl.postprocessor.common import PostProcessor from youtube_dl.utils import ExtractorError, match_filter_func @@ -221,9 +222,19 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'dash-video-low') + formats = [ + {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') + def test_youtube_format_selection(self): order = [ - '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13', + '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', # Apple HTTP Live Streaming '96', '95', '94', '93', '92', '132', '151', # 3D @@ -237,6 +248,17 @@ class TestFormatSelection(unittest.TestCase): def format_info(f_id): info = YoutubeIE._formats[f_id].copy() + + # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec' + # and 'vcodec', while in tests such information is incomplete since + # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593 + # test_YoutubeDL.test_youtube_format_selection is broken without + # this fix + if 'acodec' in info and 'vcodec' not in info: + info['vcodec'] = 'none' + elif 'vcodec' in info and 'acodec' not in info: + info['acodec'] = 'none' + info['format_id'] = f_id info['url'] = 'url:' + f_id return info @@ -631,6 +653,47 @@ class TestYoutubeDL(unittest.TestCase): result = get_ids({'playlist_items': '10'}) self.assertEqual(result, []) + def test_urlopen_no_file_protocol(self): + # see https://github.com/rg3/youtube-dl/issues/8227 + ydl = YDL() + self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd') + + def test_do_not_override_ie_key_in_url_transparent(self): + ydl = YDL() + + class Foo1IE(InfoExtractor): + _VALID_URL = r'foo1:' + + def _real_extract(self, url): + return { + '_type': 'url_transparent', + 'url': 'foo2:', + 'ie_key': 'Foo2', + } + + class Foo2IE(InfoExtractor): + _VALID_URL = r'foo2:' + + def _real_extract(self, url): + return { + '_type': 'url', + 'url': 'foo3:', + 'ie_key': 'Foo3', + } + + class Foo3IE(InfoExtractor): + _VALID_URL = r'foo3:' + + def _real_extract(self, url): + return _make_result([{'url': TEST_URL}]) + + ydl.add_info_extractor(Foo1IE(ydl)) + ydl.add_info_extractor(Foo2IE(ydl)) + ydl.add_info_extractor(Foo3IE(ydl)) + ydl.extract_info('foo1:') + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['url'], TEST_URL) + if __name__ == '__main__': unittest.main() diff --git a/test/test_all_urls.py b/test/test_all_urls.py index a9db42b..f5af184 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -56,7 +56,7 @@ class TestAllURLsMatching(unittest.TestCase): assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos') def test_youtube_user_matching(self): - self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user']) + self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user']) def test_youtube_feeds(self): self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater']) @@ -121,8 +121,8 @@ class TestAllURLsMatching(unittest.TestCase): def test_pbs(self): # https://github.com/rg3/youtube-dl/issues/2350 - self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS']) - self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS']) + self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) + self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) def test_yahoo_https(self): # https://github.com/rg3/youtube-dl/issues/2701 diff --git a/test/test_iqiyi_sdk_interpreter.py b/test/test_iqiyi_sdk_interpreter.py new file mode 100644 index 0000000..9d95cb6 --- /dev/null +++ b/test/test_iqiyi_sdk_interpreter.py @@ -0,0 +1,47 @@ +#!/usr/bin/env python + +from __future__ import unicode_literals + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from test.helper import FakeYDL +from youtube_dl.extractor import IqiyiIE + + +class IqiyiIEWithCredentials(IqiyiIE): + def _get_login_info(self): + return 'foo', 'bar' + + +class WarningLogger(object): + def __init__(self): + self.messages = [] + + def warning(self, msg): + self.messages.append(msg) + + def debug(self, msg): + pass + + def error(self, msg): + pass + + +class TestIqiyiSDKInterpreter(unittest.TestCase): + def test_iqiyi_sdk_interpreter(self): + ''' + Test the functionality of IqiyiSDKInterpreter by trying to log in + + If `sign` is incorrect, /validate call throws an HTTP 556 error + ''' + logger = WarningLogger() + ie = IqiyiIEWithCredentials(FakeYDL({'logger': logger})) + ie._login() + self.assertTrue('unable to log in:' in logger.messages[0]) + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 75f0ea7..27e763e 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -11,7 +11,6 @@ from test.helper import FakeYDL, md5 from youtube_dl.extractor import ( - BlipTVIE, YoutubeIE, DailymotionIE, TEDIE, @@ -22,7 +21,7 @@ from youtube_dl.extractor import ( NPOIE, ComedyCentralIE, NRKTVIE, - RaiIE, + RaiTVIE, VikiIE, ThePlatformIE, ThePlatformFeedIE, @@ -66,16 +65,16 @@ class TestYoutubeSubtitles(BaseTestSubtitles): self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() self.assertEqual(len(subtitles.keys()), 13) - self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260') - self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d') - for lang in ['it', 'fr', 'de']: + self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') + self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5') + for lang in ['fr', 'de']: self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) - def test_youtube_subtitles_sbv_format(self): + def test_youtube_subtitles_ttml_format(self): self.DL.params['writesubtitles'] = True - self.DL.params['subtitlesformat'] = 'sbv' + self.DL.params['subtitlesformat'] = 'ttml' subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b') + self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54') def test_youtube_subtitles_vtt_format(self): self.DL.params['writesubtitles'] = True @@ -145,18 +144,6 @@ class TestTedSubtitles(BaseTestSubtitles): self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) -class TestBlipTVSubtitles(BaseTestSubtitles): - url = 'http://blip.tv/a/a-6603250' - IE = BlipTVIE - - def test_allsubtitles(self): - self.DL.params['writesubtitles'] = True - self.DL.params['allsubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(set(subtitles.keys()), set(['en'])) - self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4') - - class TestVimeoSubtitles(BaseTestSubtitles): url = 'http://vimeo.com/76979871' IE = VimeoIE @@ -273,7 +260,7 @@ class TestNRKSubtitles(BaseTestSubtitles): class TestRaiSubtitles(BaseTestSubtitles): url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html' - IE = RaiIE + IE = RaiTVIE def test_allsubtitles(self): self.DL.params['writesubtitles'] = True diff --git a/test/test_update.py b/test/test_update.py new file mode 100644 index 0000000..d9c7151 --- /dev/null +++ b/test/test_update.py @@ -0,0 +1,30 @@ +#!/usr/bin/env python + +from __future__ import unicode_literals + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + + +import json +from youtube_dl.update import rsa_verify + + +class TestUpdate(unittest.TestCase): + def test_rsa_verify(self): + UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537) + with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'versions.json'), 'rb') as f: + versions_info = f.read().decode() + versions_info = json.loads(versions_info) + signature = versions_info['signature'] + del versions_info['signature'] + self.assertTrue(rsa_verify( + json.dumps(versions_info, sort_keys=True).encode('utf-8'), + signature, UPDATES_RSA_KEY)) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index 501355c..e6887be 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -22,6 +22,8 @@ from youtube_dl.utils import ( DateRange, detect_exe_version, determine_ext, + dict_get, + encode_compat_str, encodeFilename, escape_rfc3986, escape_url, @@ -33,6 +35,7 @@ from youtube_dl.utils import ( is_html, js_to_json, limit_length, + ohdave_rsa_encrypt, OnDemandPagedList, orderedSet, parse_duration, @@ -43,6 +46,7 @@ from youtube_dl.utils import ( sanitize_path, prepend_extension, replace_extension, + remove_quotes, shell_quote, smuggle_url, str_to_int, @@ -200,6 +204,15 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_remove_quotes(self): + self.assertEqual(remove_quotes(None), None) + self.assertEqual(remove_quotes('"'), '"') + self.assertEqual(remove_quotes("'"), "'") + self.assertEqual(remove_quotes(';'), ';') + self.assertEqual(remove_quotes('";'), '";') + self.assertEqual(remove_quotes('""'), '') + self.assertEqual(remove_quotes('";"'), ';') + def test_ordered_set(self): self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) self.assertEqual(orderedSet([]), []) @@ -439,6 +452,32 @@ class TestUtil(unittest.TestCase): data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) self.assertTrue(isinstance(data, bytes)) + def test_dict_get(self): + FALSE_VALUES = { + 'none': None, + 'false': False, + 'zero': 0, + 'empty_string': '', + 'empty_list': [], + } + d = FALSE_VALUES.copy() + d['a'] = 42 + self.assertEqual(dict_get(d, 'a'), 42) + self.assertEqual(dict_get(d, 'b'), None) + self.assertEqual(dict_get(d, 'b', 42), 42) + self.assertEqual(dict_get(d, ('a', )), 42) + self.assertEqual(dict_get(d, ('b', 'a', )), 42) + self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42) + self.assertEqual(dict_get(d, ('b', 'c', )), None) + self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42) + for key, false_value in FALSE_VALUES.items(): + self.assertEqual(dict_get(d, ('b', 'c', key, )), None) + self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value) + + def test_encode_compat_str(self): + self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест') + self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест') + def test_parse_iso8601(self): self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) @@ -456,6 +495,10 @@ class TestUtil(unittest.TestCase): d = json.loads(stripped) self.assertEqual(d, {'STATUS': 'OK'}) + stripped = strip_jsonp('ps.embedHandler({"status": "success"});') + d = json.loads(stripped) + self.assertEqual(d, {'status': 'success'}) + def test_uppercase_escape(self): self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') @@ -651,12 +694,13 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') {'like_count': 190, 'dislike_count': 10})) def test_parse_dfxp_time_expr(self): - self.assertEqual(parse_dfxp_time_expr(None), 0.0) - self.assertEqual(parse_dfxp_time_expr(''), 0.0) + self.assertEqual(parse_dfxp_time_expr(None), None) + self.assertEqual(parse_dfxp_time_expr(''), None) self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1) self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1) self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0) self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1) + self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1) def test_dfxp2srt(self): dfxp_data = ''' @@ -666,6 +710,9 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')

The following line contains Chinese characters and special symbols

第二行
♪♪

Third
Line

+

Lines with invalid timestamps are ignored

+

Ignore, two

+

Ignored, three

''' @@ -746,6 +793,13 @@ The first line {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), ['--check-certificate=true']) + def test_ohdave_rsa_encrypt(self): + N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd + e = 65537 + + self.assertEqual( + ohdave_rsa_encrypt(b'aa111222', e, N), + '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881') if __name__ == '__main__': unittest.main() diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py index 84b8f39..8de08f2 100644 --- a/test/test_write_annotations.py +++ b/test/test_write_annotations.py @@ -66,7 +66,7 @@ class TestAnnotations(unittest.TestCase): textTag = a.find('TEXT') text = textTag.text self.assertTrue(text in expected) # assertIn only added in python 2.7 - # remove the first occurance, there could be more than one annotation with the same text + # remove the first occurrence, there could be more than one annotation with the same text expected.remove(text) # We should have seen (and removed) all the expected annotation texts. self.assertEqual(len(expected), 0, 'Not all expected annotations were found.') diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index 26aadb3..47df0f3 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -34,7 +34,7 @@ class TestYoutubeLists(unittest.TestCase): ie = YoutubePlaylistIE(dl) # TODO find a > 100 (paginating?) videos course result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') - entries = result['entries'] + entries = list(result['entries']) self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs') self.assertEqual(len(entries), 25) self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0') diff --git a/test/versions.json b/test/versions.json new file mode 100644 index 0000000..6cccc22 --- /dev/null +++ b/test/versions.json @@ -0,0 +1,34 @@ +{ + "latest": "2013.01.06", + "signature": "72158cdba391628569ffdbea259afbcf279bbe3d8aeb7492690735dc1cfa6afa754f55c61196f3871d429599ab22f2667f1fec98865527b32632e7f4b3675a7ef0f0fbe084d359256ae4bba68f0d33854e531a70754712f244be71d4b92e664302aa99653ee4df19800d955b6c4149cd2b3f24288d6e4b40b16126e01f4c8ce6", + "versions": { + "2013.01.02": { + "bin": [ + "http://youtube-dl.org/downloads/2013.01.02/youtube-dl", + "f5b502f8aaa77675c4884938b1e4871ebca2611813a0c0e74f60c0fbd6dcca6b" + ], + "exe": [ + "http://youtube-dl.org/downloads/2013.01.02/youtube-dl.exe", + "75fa89d2ce297d102ff27675aa9d92545bbc91013f52ec52868c069f4f9f0422" + ], + "tar": [ + "http://youtube-dl.org/downloads/2013.01.02/youtube-dl-2013.01.02.tar.gz", + "6a66d022ac8e1c13da284036288a133ec8dba003b7bd3a5179d0c0daca8c8196" + ] + }, + "2013.01.06": { + "bin": [ + "http://youtube-dl.org/downloads/2013.01.06/youtube-dl", + "64b6ed8865735c6302e836d4d832577321b4519aa02640dc508580c1ee824049" + ], + "exe": [ + "http://youtube-dl.org/downloads/2013.01.06/youtube-dl.exe", + "58609baf91e4389d36e3ba586e21dab882daaaee537e4448b1265392ae86ff84" + ], + "tar": [ + "http://youtube-dl.org/downloads/2013.01.06/youtube-dl-2013.01.06.tar.gz", + "fe77ab20a95d980ed17a659aa67e371fdd4d656d19c4c7950e7b720b0c2f1a86" + ] + } + } +} \ No newline at end of file diff --git a/youtube-dl b/youtube-dl index ee414e4..c70dbae 100755 Binary files a/youtube-dl and b/youtube-dl differ diff --git a/youtube-dl.1 b/youtube-dl.1 index d5967c8..7c038b8 100644 --- a/youtube-dl.1 +++ b/youtube-dl.1 @@ -1,4 +1,7 @@ +.\" Automatically generated by Pandoc 1.16.0.2 +.\" .TH "YOUTUBE\-DL" "1" "" "" "" +.hy .SH NAME .PP youtube\-dl \- download videos from youtube.com or other video platforms @@ -286,6 +289,12 @@ Use the native HLS downloader instead of ffmpeg (experimental) .RS .RE .TP +.B \-\-hls\-use\-mpegts +Use the mpegts container for HLS videos, allowing to play the video +while downloading (some players may not be able to play it) +.RS +.RE +.TP .B \-\-external\-downloader \f[I]COMMAND\f[] Use the specified external downloader. Currently supports aria2c,axel,curl,httpie,wget @@ -636,7 +645,7 @@ Prefer free video formats unless a specific one is requested .RE .TP .B \-F, \-\-list\-formats -List all available formats of specified videos +List all available formats of requested videos .RS .RE .TP @@ -682,7 +691,7 @@ Subtitle format, accepts formats preference, for example: "srt" or .TP .B \-\-sub\-lang \f[I]LANGS\f[] Languages of the subtitles to download (optional) separated by commas, -use IETF language tags like \[aq]en,pt\[aq] +use \-\-list\- subs for available language tags .RS .RE .SS Authentication Options: @@ -816,7 +825,7 @@ Example: \-\-exec \[aq]adb push {} /sdcard/Music/ && rm {}\[aq] .RS .RE .TP -.B \-\-convert\-subtitles \f[I]FORMAT\f[] +.B \-\-convert\-subs \f[I]FORMAT\f[] Convert the subtitles to other format (currently supported: srt|ass|vtt) .RS .RE @@ -901,39 +910,134 @@ To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are: .IP \[bu] 2 -\f[C]id\f[]: The sequence will be replaced by the video identifier. +\f[C]id\f[]: Video identifier +.IP \[bu] 2 +\f[C]title\f[]: Video title +.IP \[bu] 2 +\f[C]url\f[]: Video URL +.IP \[bu] 2 +\f[C]ext\f[]: Video filename extension +.IP \[bu] 2 +\f[C]alt_title\f[]: A secondary title of the video +.IP \[bu] 2 +\f[C]display_id\f[]: An alternative identifier for the video +.IP \[bu] 2 +\f[C]uploader\f[]: Full name of the video uploader +.IP \[bu] 2 +\f[C]creator\f[]: The main artist who created the video +.IP \[bu] 2 +\f[C]release_date\f[]: The date (YYYYMMDD) when the video was released +.IP \[bu] 2 +\f[C]timestamp\f[]: UNIX timestamp of the moment the video became +available +.IP \[bu] 2 +\f[C]upload_date\f[]: Video upload date (YYYYMMDD) +.IP \[bu] 2 +\f[C]uploader_id\f[]: Nickname or id of the video uploader +.IP \[bu] 2 +\f[C]location\f[]: Physical location where the video was filmed +.IP \[bu] 2 +\f[C]duration\f[]: Length of the video in seconds +.IP \[bu] 2 +\f[C]view_count\f[]: How many users have watched the video on the +platform +.IP \[bu] 2 +\f[C]like_count\f[]: Number of positive ratings of the video +.IP \[bu] 2 +\f[C]dislike_count\f[]: Number of negative ratings of the video +.IP \[bu] 2 +\f[C]repost_count\f[]: Number of reposts of the video +.IP \[bu] 2 +\f[C]average_rating\f[]: Average rating give by users, the scale used +depends on the webpage +.IP \[bu] 2 +\f[C]comment_count\f[]: Number of comments on the video +.IP \[bu] 2 +\f[C]age_limit\f[]: Age restriction for the video (years) +.IP \[bu] 2 +\f[C]format\f[]: A human\-readable description of the format +.IP \[bu] 2 +\f[C]format_id\f[]: Format code specified by \f[C]\-\-format\f[] +.IP \[bu] 2 +\f[C]format_note\f[]: Additional info about the format +.IP \[bu] 2 +\f[C]width\f[]: Width of the video +.IP \[bu] 2 +\f[C]height\f[]: Height of the video +.IP \[bu] 2 +\f[C]resolution\f[]: Textual description of width and height +.IP \[bu] 2 +\f[C]tbr\f[]: Average bitrate of audio and video in KBit/s +.IP \[bu] 2 +\f[C]abr\f[]: Average audio bitrate in KBit/s +.IP \[bu] 2 +\f[C]acodec\f[]: Name of the audio codec in use .IP \[bu] 2 -\f[C]url\f[]: The sequence will be replaced by the video URL. +\f[C]asr\f[]: Audio sampling rate in Hertz .IP \[bu] 2 -\f[C]uploader\f[]: The sequence will be replaced by the nickname of the -person who uploaded the video. +\f[C]vbr\f[]: Average video bitrate in KBit/s .IP \[bu] 2 -\f[C]upload_date\f[]: The sequence will be replaced by the upload date -in YYYYMMDD format. +\f[C]fps\f[]: Frame rate .IP \[bu] 2 -\f[C]title\f[]: The sequence will be replaced by the video title. +\f[C]vcodec\f[]: Name of the video codec in use .IP \[bu] 2 -\f[C]ext\f[]: The sequence will be replaced by the appropriate extension -(like flv or mp4). +\f[C]container\f[]: Name of the container format .IP \[bu] 2 -\f[C]epoch\f[]: The sequence will be replaced by the Unix epoch when -creating the file. +\f[C]filesize\f[]: The number of bytes, if known in advance .IP \[bu] 2 -\f[C]autonumber\f[]: The sequence will be replaced by a five\-digit -number that will be increased with each download, starting at zero. +\f[C]filesize_approx\f[]: An estimate for the number of bytes .IP \[bu] 2 -\f[C]playlist\f[]: The sequence will be replaced by the name or the id -of the playlist that contains the video. +\f[C]protocol\f[]: The protocol that will be used for the actual +download .IP \[bu] 2 -\f[C]playlist_index\f[]: The sequence will be replaced by the index of -the video in the playlist padded with leading zeros according to the -total length of the playlist. +\f[C]extractor\f[]: Name of the extractor .IP \[bu] 2 -\f[C]format_id\f[]: The sequence will be replaced by the format code -specified by \f[C]\-\-format\f[]. +\f[C]extractor_key\f[]: Key name of the extractor .IP \[bu] 2 -\f[C]duration\f[]: The sequence will be replaced by the length of the -video in seconds. +\f[C]epoch\f[]: Unix epoch when creating the file +.IP \[bu] 2 +\f[C]autonumber\f[]: Five\-digit number that will be increased with each +download, starting at zero +.IP \[bu] 2 +\f[C]playlist\f[]: Name or id of the playlist that contains the video +.IP \[bu] 2 +\f[C]playlist_index\f[]: Index of the video in the playlist padded with +leading zeros according to the total length of the playlist +.PP +Available for the video that belongs to some logical chapter or section: +\- \f[C]chapter\f[]: Name or title of the chapter the video belongs to +\- \f[C]chapter_number\f[]: Number of the chapter the video belongs to +\- \f[C]chapter_id\f[]: Id of the chapter the video belongs to +.PP +Available for the video that is an episode of some series or programme: +\- \f[C]series\f[]: Title of the series or programme the video episode +belongs to \- \f[C]season\f[]: Title of the season the video episode +belongs to \- \f[C]season_number\f[]: Number of the season the video +episode belongs to \- \f[C]season_id\f[]: Id of the season the video +episode belongs to \- \f[C]episode\f[]: Title of the video episode \- +\f[C]episode_number\f[]: Number of the video episode within a season \- +\f[C]episode_id\f[]: Id of the video episode +.PP +Each aforementioned sequence when referenced in output template will be +replaced by the actual value corresponding to the sequence name. +Note that some of the sequences are not guaranteed to be present since +they depend on the metadata obtained by particular extractor, such +sequences will be replaced with \f[C]NA\f[]. +.PP +For example for \f[C]\-o\ %(title)s\-%(id)s.%(ext)s\f[] and mp4 video +with title \f[C]youtube\-dl\ test\ video\f[] and id +\f[C]BaW_jenozKcj\f[] this will result in a +\f[C]youtube\-dl\ test\ video\-BaW_jenozKcj.mp4\f[] file created in the +current directory. +.PP +Output template can also contain arbitrary hierarchical path, e.g. +\f[C]\-o\ \[aq]%(playlist)s/%(playlist_index)s\ \-\ %(title)s.%(ext)s\[aq]\f[] +that will result in downloading each video in a directory corresponding +to this path template. +Any missing directory will be automatically created for you. +.PP +To specify percent literal in output template use \f[C]%%\f[]. +To output to stdout use \f[C]\-o\ \-\f[]. .PP The current default template is \f[C]%(title)s\-%(id)s.%(ext)s\f[]. .PP @@ -942,47 +1046,137 @@ or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit\-unsafe channel. In these cases, add the \f[C]\-\-restrict\-filenames\f[] flag to get a shorter title: +.PP +Examples (note on Windows you may need to use double quotes instead of +single): .IP .nf \f[C] -$\ youtube\-dl\ \-\-get\-filename\ \-o\ "%(title)s.%(ext)s"\ BaW_jenozKc +$\ youtube\-dl\ \-\-get\-filename\ \-o\ \[aq]%(title)s.%(ext)s\[aq]\ BaW_jenozKc youtube\-dl\ test\ video\ \[aq]\[aq]_ä↭𝕐.mp4\ \ \ \ #\ All\ kinds\ of\ weird\ characters -$\ youtube\-dl\ \-\-get\-filename\ \-o\ "%(title)s.%(ext)s"\ BaW_jenozKc\ \-\-restrict\-filenames + +$\ youtube\-dl\ \-\-get\-filename\ \-o\ \[aq]%(title)s.%(ext)s\[aq]\ BaW_jenozKc\ \-\-restrict\-filenames youtube\-dl_test_video_.mp4\ \ \ \ \ \ \ \ \ \ #\ A\ simple\ file\ name + +#\ Download\ YouTube\ playlist\ videos\ in\ separate\ directory\ indexed\ by\ video\ order\ in\ a\ playlist +$\ youtube\-dl\ \-o\ \[aq]%(playlist)s/%(playlist_index)s\ \-\ %(title)s.%(ext)s\[aq]\ https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re + +#\ Download\ Udemy\ course\ keeping\ each\ chapter\ in\ separate\ directory\ under\ MyVideos\ directory\ in\ your\ home +$\ youtube\-dl\ \-u\ user\ \-p\ password\ \-o\ \[aq]~/MyVideos/%(playlist)s/%(chapter_number)s\ \-\ %(chapter)s/%(title)s.%(ext)s\[aq]\ https://www.udemy.com/java\-tutorial/ + +#\ Download\ entire\ series\ season\ keeping\ each\ series\ and\ each\ season\ in\ separate\ directory\ under\ C:/MyVideos +$\ youtube\-dl\ \-o\ "C:/MyVideos/%(series)s/%(season_number)s\ \-\ %(season)s/%(episode_number)s\ \-\ %(episode)s.%(ext)s"\ http://videomore.ru/kino_v_detalayah/5_sezon/367617 + +#\ Stream\ the\ video\ being\ downloaded\ to\ stdout +$\ youtube\-dl\ \-o\ \-\ BaW_jenozKc \f[] .fi .SH FORMAT SELECTION .PP -By default youtube\-dl tries to download the best quality, but sometimes -you may want to download in a different format. -The simplest case is requesting a specific format, for example -\f[C]\-f\ 22\f[]. -You can get the list of available formats using -\f[C]\-\-list\-formats\f[], you can also use a file extension (currently -it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names -\f[C]best\f[], \f[C]bestvideo\f[], \f[C]bestaudio\f[] and -\f[C]worst\f[]. +By default youtube\-dl tries to download the best available quality, +i.e. +if you want the best quality you \f[B]don\[aq]t need\f[] to pass any +special options, youtube\-dl will guess it for you by \f[B]default\f[]. +.PP +But sometimes you may want to download in a different format, for +example when you are on a slow or intermittent connection. +The key mechanism for achieving this is so called \f[I]format +selection\f[] based on which you can explicitly specify desired format, +select formats based on some criterion or criteria, setup precedence and +much more. +.PP +The general syntax for format selection is \f[C]\-\-format\ FORMAT\f[] +or shorter \f[C]\-f\ FORMAT\f[] where \f[C]FORMAT\f[] is a \f[I]selector +expression\f[], i.e. +an expression that describes format or formats you would like to +download. +.PP +The simplest case is requesting a specific format, for example with +\f[C]\-f\ 22\f[] you can download the format with format code equal to +22. +You can get the list of available format codes for particular video +using \f[C]\-\-list\-formats\f[] or \f[C]\-F\f[]. +Note that these format codes are extractor specific. +.PP +You can also use a file extension (currently \f[C]3gp\f[], \f[C]aac\f[], +\f[C]flv\f[], \f[C]m4a\f[], \f[C]mp3\f[], \f[C]mp4\f[], \f[C]ogg\f[], +\f[C]wav\f[], \f[C]webm\f[] are supported) to download best quality +format of particular file extension served as a single file, e.g. +\f[C]\-f\ webm\f[] will download best quality format with \f[C]webm\f[] +extension served as a single file. +.PP +You can also use special names to select particular edge case format: \- +\f[C]best\f[]: Select best quality format represented by single file +with video and audio \- \f[C]worst\f[]: Select worst quality format +represented by single file with video and audio \- \f[C]bestvideo\f[]: +Select best quality video only format (e.g. +DASH video), may not be available \- \f[C]worstvideo\f[]: Select worst +quality video only format, may not be available \- \f[C]bestaudio\f[]: +Select best quality audio only format, may not be available \- +\f[C]worstaudio\f[]: Select worst quality audio only format, may not be +available +.PP +For example, to download worst quality video only format you can use +\f[C]\-f\ worstvideo\f[]. .PP If you want to download multiple videos and they don\[aq]t have the same formats available, you can specify the order of preference using -slashes, as in \f[C]\-f\ 22/17/18\f[]. -You can also filter the video results by putting a condition in +slashes. +Note that slash is left\-associative, i.e. +formats on the left hand side are preferred, for example +\f[C]\-f\ 22/17/18\f[] will download format 22 if it\[aq]s available, +otherwise it will download format 17 if it\[aq]s available, otherwise it +will download format 18 if it\[aq]s available, otherwise it will +complain that no suitable formats are available for download. +.PP +If you want to download several formats of the same video use comma as a +separator, e.g. +\f[C]\-f\ 22,17,18\f[] will download all these three formats, of course +if they are available. +Or more sophisticated example combined with precedence feature +\f[C]\-f\ 136/137/mp4/bestvideo,140/m4a/bestaudio\f[]. +.PP +You can also filter the video formats by putting a condition in brackets, as in \f[C]\-f\ "best[height=720]"\f[] (or \f[C]\-f\ "[filesize>10M]"\f[]). -This works for filesize, height, width, tbr, abr, vbr, asr, and fps and -the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, -container, and protocol and the comparisons =, != . +.PP +The following numeric meta fields can be used with comparisons +\f[C]<\f[], \f[C]<=\f[], \f[C]>\f[], \f[C]>=\f[], \f[C]=\f[] (equals), +\f[C]!=\f[] (not equals): \- \f[C]filesize\f[]: The number of bytes, if +known in advance \- \f[C]width\f[]: Width of the video, if known \- +\f[C]height\f[]: Height of the video, if known \- \f[C]tbr\f[]: Average +bitrate of audio and video in KBit/s \- \f[C]abr\f[]: Average audio +bitrate in KBit/s \- \f[C]vbr\f[]: Average video bitrate in KBit/s \- +\f[C]asr\f[]: Audio sampling rate in Hertz \- \f[C]fps\f[]: Frame rate +.PP +Also filtering work for comparisons \f[C]=\f[] (equals), \f[C]!=\f[] +(not equals), \f[C]^=\f[] (begins with), \f[C]$=\f[] (ends with), +\f[C]*=\f[] (contains) and following string meta fields: \- +\f[C]ext\f[]: File extension \- \f[C]acodec\f[]: Name of the audio codec +in use \- \f[C]vcodec\f[]: Name of the video codec in use \- +\f[C]container\f[]: Name of the container format \- \f[C]protocol\f[]: +The protocol that will be used for the actual download, lower\-case. +\f[C]http\f[], \f[C]https\f[], \f[C]rtsp\f[], \f[C]rtmp\f[], +\f[C]rtmpe\f[], \f[C]m3u8\f[], or \f[C]m3u8_native\f[] +.PP +Note that none of the aforementioned meta fields are guaranteed to be +present since this solely depends on the metadata obtained by particular +extractor, i.e. +the metadata offered by video hoster. +.PP Formats for which the value is not known are excluded unless you put a -question mark (?) after the operator. +question mark (\f[C]?\f[]) after the operator. You can combine format filters, so \f[C]\-f\ "[height\ <=?\ 720][tbr>500]"\f[] selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. -Use commas to download multiple formats, such as -\f[C]\-f\ 136/137/mp4/bestvideo,140/m4a/bestaudio\f[]. +.PP You can merge the video and audio of two formats into a single file using \f[C]\-f\ +\f[] (requires ffmpeg or -avconv), for example \f[C]\-f\ bestvideo+bestaudio\f[]. +avconv installed), for example \f[C]\-f\ bestvideo+bestaudio\f[] will +download best video only format, best audio only format and mux them +together with ffmpeg/avconv. +.PP Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use \f[C]\-f\ \[aq](mp4,webm)[height<480]\[aq]\f[]. @@ -998,7 +1192,7 @@ best available quality served as a single file. \f[C]best\f[] is also needed for videos that don\[aq]t come from YouTube because they don\[aq]t provide the audio and video in two different files. -If you want to only download some dash formats (for example if you are +If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add \f[C]\-f\ bestvideo[height<=?1080]+bestaudio/best\f[] to your configuration file. @@ -1015,6 +1209,25 @@ you want to download the best available quality media served as a single file, you should explicitly specify your choice with \f[C]\-f\ best\f[]. You may want to add it to the configuration file (#configuration) in order not to type it every time you run youtube\-dl. +.PP +Examples (note on Windows you may need to use double quotes instead of +single): +.IP +.nf +\f[C] +#\ Download\ best\ mp4\ format\ available\ or\ any\ other\ best\ if\ no\ mp4\ available +$\ youtube\-dl\ \-f\ \[aq]bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best\[aq] + +#\ Download\ best\ format\ available\ but\ not\ better\ that\ 480p +$\ youtube\-dl\ \-f\ \[aq]bestvideo[height<=480]+bestaudio/best[height<=480]\[aq] + +#\ Download\ best\ video\ only\ format\ but\ no\ bigger\ that\ 50\ MB +$\ youtube\-dl\ \-f\ \[aq]best[filesize<50M]\[aq] + +#\ Download\ best\ format\ available\ via\ direct\ link\ over\ HTTP/HTTPS\ protocol +$\ youtube\-dl\ \-f\ \[aq](bestvideo+bestaudio/best)[protocol^=http]\[aq] +\f[] +.fi .SH VIDEO SELECTION .PP Videos can be filtered by their upload date using the options @@ -1277,7 +1490,7 @@ Use the \f[C]\-o\f[] to specify an output template (#output-template), for example \f[C]\-o\ "/home/user/videos/%(title)s\-%(id)s.%(ext)s"\f[]. If you want this for all of your downloads, put the option into your configuration file (#configuration). -.SS How do I download a video starting with a \f[C]\-\f[] ? +.SS How do I download a video starting with a \f[C]\-\f[]? .PP Either prepend \f[C]http://www.youtube.com/watch?v=\f[] or separate the ID from the options with \f[C]\-\-\f[]: @@ -1306,6 +1519,10 @@ is a good sign of invalid newline format. .PP Passing cookies to youtube\-dl is a good way to workaround login when a particular extractor does not implement it explicitly. +Another use case is working around +CAPTCHA (https://en.wikipedia.org/wiki/CAPTCHA) some websites require +you to solve in particular cases in order to get access (e.g. +YouTube, CloudFlare). .SS Can you add support for this anime video site, or site which shows current movies for free? .PP @@ -1552,7 +1769,7 @@ with\ youtube_dl.YoutubeDL(ydl_opts)\ as\ ydl: .PP Most likely, you\[aq]ll want to use various options. For a list of what can be done, have a look at -youtube_dl/YoutubeDL.py (https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). +\f[C]youtube_dl/YoutubeDL.py\f[] (https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube\-dl\[aq]s output, set a \f[C]logger\f[] object. .PP @@ -1599,14 +1816,39 @@ with\ youtube_dl.YoutubeDL(ydl_opts)\ as\ ydl: .SH BUGS .PP Bugs and suggestions should be reported at: - . +. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. -For discussions, join us in the irc channel #youtube\-dl on freenode. +For discussions, join us in the IRC channel +#youtube\-dl (irc://chat.freenode.net/#youtube-dl) on freenode +(webchat (http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)). .PP \f[B]Please include the full output of youtube\-dl when run with -\f[C]\-v\f[]\f[]. +\f[C]\-v\f[]\f[], i.e. +\f[B]add\f[] \f[C]\-v\f[] flag to \f[B]your command line\f[], copy the +\f[B]whole\f[] output and post it in the issue body wrapped in ``` for +better formatting. +It should look similar to this: +.IP +.nf +\f[C] +$\ youtube\-dl\ \-v\ +[debug]\ System\ config:\ [] +[debug]\ User\ config:\ [] +[debug]\ Command\-line\ args:\ [u\[aq]\-v\[aq],\ u\[aq]http://www.youtube.com/watch?v=BaW_jenozKcj\[aq]] +[debug]\ Encodings:\ locale\ cp1251,\ fs\ mbcs,\ out\ cp866,\ pref\ cp1251 +[debug]\ youtube\-dl\ version\ 2015.12.06 +[debug]\ Git\ HEAD:\ 135392e +[debug]\ Python\ version\ 2.6.6\ \-\ Windows\-2003Server\-5.2.3790\-SP2 +[debug]\ exe\ versions:\ ffmpeg\ N\-75573\-g1d0487f,\ ffprobe\ N\-75573\-g1d0487f,\ rtmpdump\ 2.4 +[debug]\ Proxy\ map:\ {} +\&... +\f[] +.fi +.PP +\f[B]Do not post screenshots of verbose log only plain text is +acceptable.\f[] .PP The output (including the first lines) contains important debugging information. @@ -1638,7 +1880,7 @@ If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We\[aq]re often too polite to close the issue outright, but the missing info makes misinterpretation likely. -As a commiter myself, I often get frustrated by these issues, since the +As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. .PP @@ -1659,11 +1901,11 @@ command\-line) or upload the \f[C]\&.dump\f[] files you get when you add .PP \f[B]Site support requests must contain an example URL\f[]. An example URL is a URL you might want to download, like -http://www.youtube.com/watch?v=BaW_jenozKc . +\f[C]http://www.youtube.com/watch?v=BaW_jenozKc\f[]. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. -http://www.youtube.com/ ) is \f[I]not\f[] an example URL. +\f[C]http://www.youtube.com/\f[]) is \f[I]not\f[] an example URL. .SS Are you using the latest version? .PP Before reporting any issue, type \f[C]youtube\-dl\ \-U\f[]. @@ -1675,8 +1917,9 @@ This goes for feature requests as well. .PP Make sure that someone has not already opened the issue you\[aq]re trying to open. -Search at the top of the window or at -https://github.com/rg3/youtube\-dl/search?type=Issues . +Search at the top of the window or browse the GitHub +Issues (https://github.com/rg3/youtube-dl/search?type=Issues) of this +repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". @@ -1753,6 +1996,6 @@ bug. .PP youtube\-dl is released into the public domain by the copyright holders. .PP -This README file was originally written by Daniel Bolton -() and is likewise released into the public -domain. +This README file was originally written by Daniel +Bolton (https://github.com/dbbolton) and is likewise released into the +public domain. diff --git a/youtube-dl.bash-completion b/youtube-dl.bash-completion index 893d7e7..d8c2ef1 100644 --- a/youtube-dl.bash-completion +++ b/youtube-dl.bash-completion @@ -4,7 +4,7 @@ __youtube_dl() 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 --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" + 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 --hls-use-mpegts --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-subs" keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory" fileopts="-a|--batch-file|--download-archive|--cookies|--load-info" diropts="--cache-dir" diff --git a/youtube-dl.fish b/youtube-dl.fish index c70743c..5f30e09 100644 --- a/youtube-dl.fish +++ b/youtube-dl.fish @@ -45,6 +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 hls-use-mpegts --description 'Use the mpegts container for HLS videos, allowing to play the video while downloading (some players may not be able to play it)' complete --command youtube-dl --long-option external-downloader --description 'Use the specified external downloader. Currently supports aria2c,axel,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 @@ -107,7 +108,7 @@ complete --command youtube-dl --long-option sleep-interval --description 'Number complete --command youtube-dl --long-option format --short-option f --description 'Video format code, see the "FORMAT SELECTION" for all the info' complete --command youtube-dl --long-option all-formats --description 'Download all available video formats' 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 of specified videos' +complete --command youtube-dl --long-option list-formats --short-option F --description 'List all available formats of requested videos' 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 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' @@ -116,7 +117,7 @@ complete --command youtube-dl --long-option write-auto-sub --description 'Write complete --command youtube-dl --long-option all-subs --description 'Download all the available subtitles of the video' complete --command youtube-dl --long-option list-subs --description 'List all available subtitles for the video' complete --command youtube-dl --long-option sub-format --description 'Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"' -complete --command youtube-dl --long-option sub-lang --description 'Languages of the subtitles to download (optional) separated by commas, use IETF language tags like '"'"'en,pt'"'"'' +complete --command youtube-dl --long-option sub-lang --description 'Languages of the subtitles to download (optional) separated by commas, use --list-subs for available language tags' complete --command youtube-dl --long-option username --short-option u --description 'Login with this account ID' complete --command youtube-dl --long-option password --short-option p --description 'Account password. If this option is left out, youtube-dl will ask interactively.' complete --command youtube-dl --long-option twofactor --short-option 2 --description 'Two-factor auth code' @@ -139,7 +140,7 @@ complete --command youtube-dl --long-option prefer-avconv --description 'Prefer 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 exec --description 'Execute a command on the file after downloading, similar to find'"'"'s -exec syntax. Example: --exec '"'"'adb push {} /sdcard/Music/ && rm {}'"'"'' -complete --command youtube-dl --long-option convert-subtitles --description 'Convert the subtitles to other format (currently supported: srt|ass|vtt)' +complete --command youtube-dl --long-option convert-subs --description 'Convert the subtitles to other format (currently supported: srt|ass|vtt)' complete --command youtube-dl --arguments ":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory" diff --git a/youtube-dl.zsh b/youtube-dl.zsh index 73c95b0..66ac24a 100644 --- a/youtube-dl.zsh +++ b/youtube-dl.zsh @@ -19,7 +19,7 @@ __youtube_dl() { 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 --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)' + _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 --hls-use-mpegts --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-subs)' fi ;; esac diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 9a8c7da..f432403 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -46,8 +46,11 @@ from .utils import ( DateRange, DEFAULT_OUTTMPL, determine_ext, + determine_protocol, DownloadError, + encode_compat_str, encodeFilename, + error_to_compat_str, ExtractorError, format_bytes, formatSeconds, @@ -260,7 +263,7 @@ class YoutubeDL(object): the downloader (see youtube_dl/downloader/common.py): nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, noresizebuffer, retries, continuedl, noprogress, consoletitle, - xattr_set_filesize, external_downloader_args. + xattr_set_filesize, external_downloader_args, hls_use_mpegts. The following options are used by the post processors: prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, @@ -495,7 +498,7 @@ class YoutubeDL(object): tb = '' if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) - tb += compat_str(traceback.format_exc()) + tb += encode_compat_str(traceback.format_exc()) else: tb_data = traceback.format_list(traceback.extract_stack()) tb = ''.join(tb_data) @@ -602,12 +605,12 @@ class YoutubeDL(object): if rejecttitle: if re.search(rejecttitle, title, re.IGNORECASE): return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' - date = info_dict.get('upload_date', None) + date = info_dict.get('upload_date') if date is not None: dateRange = self.params.get('daterange', DateRange()) if date not in dateRange: return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) - view_count = info_dict.get('view_count', None) + view_count = info_dict.get('view_count') if view_count is not None: min_views = self.params.get('min_views') if min_views is not None and view_count < min_views: @@ -674,14 +677,14 @@ class YoutubeDL(object): return self.process_ie_result(ie_result, download, extra_info) else: return ie_result - except ExtractorError as de: # An error we somewhat expected - self.report_error(compat_str(de), de.format_traceback()) + except ExtractorError as e: # An error we somewhat expected + self.report_error(compat_str(e), e.format_traceback()) break except MaxDownloadsReached: raise except Exception as e: if self.params.get('ignoreerrors', False): - self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) + self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc())) break else: raise @@ -704,7 +707,6 @@ class YoutubeDL(object): It will also download the videos if 'download'. Returns the resolved ie_result. """ - result_type = ie_result.get('_type', 'video') if result_type in ('url', 'url_transparent'): @@ -733,7 +735,7 @@ class YoutubeDL(object): force_properties = dict( (k, v) for k, v in ie_result.items() if v is not None) - for f in ('_type', 'url'): + for f in ('_type', 'url', 'ie_key'): if f in force_properties: del force_properties[f] new_result = info.copy() @@ -745,18 +747,18 @@ class YoutubeDL(object): new_result, download=download, extra_info=extra_info) elif result_type == 'playlist' or result_type == 'multi_video': # We process each entry in the playlist - playlist = ie_result.get('title', None) or ie_result.get('id', None) + playlist = ie_result.get('title') or ie_result.get('id') self.to_screen('[download] Downloading playlist: %s' % playlist) playlist_results = [] playliststart = self.params.get('playliststart', 1) - 1 - playlistend = self.params.get('playlistend', None) + playlistend = self.params.get('playlistend') # For backwards compatibility, interpret -1 as whole list if playlistend == -1: playlistend = None - playlistitems_str = self.params.get('playlist_items', None) + playlistitems_str = self.params.get('playlist_items') playlistitems = None if playlistitems_str is not None: def iter_playlistitems(format): @@ -780,7 +782,7 @@ class YoutubeDL(object): entries = ie_entries[playliststart:playlistend] n_entries = len(entries) self.to_screen( - "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % + '[%s] playlist %s: Collected %d video ids (downloading %d of them)' % (ie_result['extractor'], playlist, n_all_entries, n_entries)) elif isinstance(ie_entries, PagedList): if playlistitems: @@ -794,7 +796,7 @@ class YoutubeDL(object): playliststart, playlistend) n_entries = len(entries) self.to_screen( - "[%s] playlist %s: Downloading %d videos" % + '[%s] playlist %s: Downloading %d videos' % (ie_result['extractor'], playlist, n_entries)) else: # iterable if playlistitems: @@ -805,7 +807,7 @@ class YoutubeDL(object): ie_entries, playliststart, playlistend)) n_entries = len(entries) self.to_screen( - "[%s] playlist %s: Downloading %d videos" % + '[%s] playlist %s: Downloading %d videos' % (ie_result['extractor'], playlist, n_entries)) if self.params.get('playlistreverse', False): @@ -896,11 +898,14 @@ class YoutubeDL(object): STR_OPERATORS = { '=': operator.eq, '!=': operator.ne, + '^=': lambda attr, value: attr.startswith(value), + '$=': lambda attr, value: attr.endswith(value), + '*=': lambda attr, value: value in attr, } str_operator_rex = re.compile(r'''(?x) \s*(?Pext|acodec|vcodec|container|protocol) \s*(?P%s)(?P\s*\?)? - \s*(?P[a-zA-Z0-9_-]+) + \s*(?P[a-zA-Z0-9._-]+) \s*$ ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) m = str_operator_rex.search(filter_spec) @@ -1110,6 +1115,12 @@ class YoutubeDL(object): 'contain the video, try using ' '"-f %s+%s"' % (format_2, format_1)) return + # Formats must be opposite (video+audio) + if formats_info[0].get('acodec') == 'none' and formats_info[1].get('acodec') == 'none': + self.report_error( + 'Both formats %s and %s are video-only, you must specify "-f video+audio"' + % (format_1, format_2)) + return output_ext = ( formats_info[0]['ext'] if self.params.get('merge_output_format') is None @@ -1236,6 +1247,12 @@ class YoutubeDL(object): except (ValueError, OverflowError, OSError): pass + # Auto generate title fields corresponding to the *_number fields when missing + # in order to always have clean titles. This is very common for TV series. + for field in ('chapter', 'season', 'episode'): + if info_dict.get('%s_number' % field) is not None and not info_dict.get(field): + info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field]) + subtitles = info_dict.get('subtitles') if subtitles: for _, subtitle in subtitles.items(): @@ -1271,6 +1288,9 @@ class YoutubeDL(object): if format.get('format_id') is None: format['format_id'] = compat_str(i) + else: + # Sanitize format_id from characters used in format selector expression + format['format_id'] = re.sub('[\s,/+\[\]()]', '_', format['format_id']) format_id = format['format_id'] if format_id not in formats_dict: formats_dict[format_id] = [] @@ -1292,6 +1312,10 @@ class YoutubeDL(object): # Automatically determine file extension if missing if 'ext' not in format: format['ext'] = determine_ext(format['url']).lower() + # Automatically determine protocol if missing (useful for format + # selection purposes) + if 'protocol' not in format: + format['protocol'] = determine_protocol(format) # Add HTTP headers, so that external programs can use them from the # json output full_format_info = info_dict.copy() @@ -1304,7 +1328,7 @@ class YoutubeDL(object): # only set the 'formats' fields if the original info_dict list them # otherwise we end up with a circular reference, the first (and unique) # element in the 'formats' field in info_dict is info_dict itself, - # wich can't be exported to json + # which can't be exported to json info_dict['formats'] = formats if self.params.get('listformats'): self.list_formats(info_dict) @@ -1317,7 +1341,6 @@ class YoutubeDL(object): if req_format is None: req_format_list = [] if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and - info_dict['extractor'] in ['youtube', 'ted'] and not info_dict.get('is_live')): merger = FFmpegMergerPP(self) if merger.available and merger.can_merge(): @@ -1453,7 +1476,7 @@ class YoutubeDL(object): if dn and not os.path.exists(dn): os.makedirs(dn) except (OSError, IOError) as err: - self.report_error('unable to create directory ' + compat_str(err)) + self.report_error('unable to create directory ' + error_to_compat_str(err)) return if self.params.get('writedescription', False): @@ -1504,7 +1527,7 @@ class YoutubeDL(object): sub_info['url'], info_dict['id'], note=False) except ExtractorError as err: self.report_warning('Unable to download subtitle for "%s": %s' % - (sub_lang, compat_str(err.cause))) + (sub_lang, error_to_compat_str(err.cause))) continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) @@ -1774,7 +1797,7 @@ class YoutubeDL(object): else: res = '%sp' % format['height'] elif format.get('width') is not None: - res = '?x%d' % format['width'] + res = '%dx?' % format['width'] else: res = default return res @@ -1783,6 +1806,10 @@ class YoutubeDL(object): res = '' if fdict.get('ext') in ['f4f', 'f4m']: res += '(unsupported) ' + if fdict.get('language'): + if res: + res += ' ' + res += '[%s]' % fdict['language'] if fdict.get('format_note') is not None: res += fdict['format_note'] + ' ' if fdict.get('tbr') is not None: @@ -1974,8 +2001,19 @@ class YoutubeDL(object): https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) data_handler = compat_urllib_request_DataHandler() + + # When passing our own FileHandler instance, build_opener won't add the + # default FileHandler and allows us to disable the file protocol, which + # can be used for malicious purposes (see + # https://github.com/rg3/youtube-dl/issues/8227) + file_handler = compat_urllib_request.FileHandler() + + def file_open(*args, **kwargs): + raise compat_urllib_error.URLError('file:// scheme is explicitly disabled in youtube-dl for security reasons') + file_handler.file_open = file_open + opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh, data_handler) + proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play @@ -2033,4 +2071,4 @@ class YoutubeDL(object): (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename)) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self.report_warning('Unable to download thumbnail "%s": %s' % - (t['url'], compat_str(err))) + (t['url'], error_to_compat_str(err))) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 9f131f5..f5f0642 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -369,6 +369,7 @@ def _real_main(argv=None): 'no_color': opts.no_color, 'ffmpeg_location': opts.ffmpeg_location, 'hls_prefer_native': opts.hls_prefer_native, + 'hls_use_mpegts': opts.hls_use_mpegts, 'external_downloader_args': external_downloader_args, 'postprocessor_args': postprocessor_args, 'cn_verification_proxy': opts.cn_verification_proxy, diff --git a/youtube_dl/__main__.py b/youtube_dl/__main__.py index 42a0f8c..138f5fb 100755 --- a/youtube_dl/__main__.py +++ b/youtube_dl/__main__.py @@ -7,7 +7,7 @@ from __future__ import unicode_literals import sys -if __package__ is None and not hasattr(sys, "frozen"): +if __package__ is None and not hasattr(sys, 'frozen'): # direct call of __main__.py import os.path path = os.path.realpath(os.path.abspath(__file__)) diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index 7817adc..a01c367 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -161,7 +161,7 @@ def aes_decrypt_text(data, password, key_size_bytes): nonce = data[:NONCE_LENGTH_BYTES] cipher = data[NONCE_LENGTH_BYTES:] - class Counter: + class Counter(object): __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) def next_value(self): diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index a3e8526..b497da6 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -181,20 +181,20 @@ except ImportError: # Python < 3.4 # parameter := attribute "=" value url = req.get_full_url() - scheme, data = url.split(":", 1) - mediatype, data = data.split(",", 1) + scheme, data = url.split(':', 1) + mediatype, data = data.split(',', 1) # even base64 encoded data URLs might be quoted so unquote in any case: data = compat_urllib_parse_unquote_to_bytes(data) - if mediatype.endswith(";base64"): + if mediatype.endswith(';base64'): data = binascii.a2b_base64(data) mediatype = mediatype[:-7] if not mediatype: - mediatype = "text/plain;charset=US-ASCII" + mediatype = 'text/plain;charset=US-ASCII' headers = email.message_from_string( - "Content-type: %s\nContent-length: %d\n" % (mediatype, len(data))) + 'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data))) return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url) @@ -268,7 +268,7 @@ except ImportError: # Python 2 nv = name_value.split('=', 1) if len(nv) != 2: if strict_parsing: - raise ValueError("bad query field: %r" % (name_value,)) + raise ValueError('bad query field: %r' % (name_value,)) # Handle case of a control-name with no equal sign if keep_blank_values: nv.append('') @@ -433,7 +433,7 @@ if sys.version_info < (3, 0) and sys.platform == 'win32': else: compat_getpass = getpass.getpass -# Old 2.6 and 2.7 releases require kwargs to be bytes +# Python < 2.6.5 require kwargs to be bytes try: def _testfunc(x): pass @@ -466,7 +466,7 @@ if sys.version_info < (2, 7): if err is not None: raise err else: - raise socket.error("getaddrinfo returns an empty list") + raise socket.error('getaddrinfo returns an empty list') else: compat_socket_create_connection = socket.create_connection diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index b8bf8da..2d51540 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -5,9 +5,9 @@ import re import sys import time -from ..compat import compat_str from ..utils import ( encodeFilename, + error_to_compat_str, decodeArgument, format_bytes, timeconvert, @@ -45,6 +45,7 @@ class FileDownloader(object): (experimental) external_downloader_args: A list of additional command-line arguments for the external downloader. + hls_use_mpegts: Use the mpegts container for HLS videos. Subclasses of this one must re-define the real_download method. """ @@ -156,7 +157,7 @@ class FileDownloader(object): def slow_down(self, start_time, now, byte_counter): """Sleep if the download speed is over the rate limit.""" - rate_limit = self.params.get('ratelimit', None) + rate_limit = self.params.get('ratelimit') if rate_limit is None or byte_counter == 0: return if now is None: @@ -186,7 +187,7 @@ class FileDownloader(object): return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) except (IOError, OSError) as err: - self.report_error('unable to rename file: %s' % compat_str(err)) + self.report_error('unable to rename file: %s' % error_to_compat_str(err)) def try_utime(self, filename, last_modified_hdr): """Try to set the last-modified time of the given file.""" @@ -295,7 +296,7 @@ class FileDownloader(object): def report_retry(self, count, retries): """Report retry in case of HTTP error 5xx""" - self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %.0f)...' % (count, retries)) def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py index 535f2a7..8b1b17c 100644 --- a/youtube_dl/downloader/dash.py +++ b/youtube_dl/downloader/dash.py @@ -1,66 +1,59 @@ from __future__ import unicode_literals +import os import re -from .common import FileDownloader -from ..utils import sanitized_Request +from .fragment import FragmentFD +from ..utils import ( + sanitize_open, + encodeFilename, +) -class DashSegmentsFD(FileDownloader): +class DashSegmentsFD(FragmentFD): """ 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 = sanitized_Request(target_url) - if remaining_bytes is not None: - req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1)) + FD_NAME = 'dashsegments' - data = self.ydl.urlopen(req).read() + def real_download(self, filename, info_dict): + base_url = info_dict['url'] + segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls'] + initialization_url = info_dict.get('initialization_url') - if remaining_bytes is not None: - data = data[:remaining_bytes] + ctx = { + 'filename': filename, + 'total_frags': len(segment_urls) + (1 if initialization_url else 0), + } - outf.write(data) - return len(data) + self._prepare_and_start_frag_download(ctx) def combine_url(base_url, target_url): if re.match(r'^https?://', target_url): return target_url return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', 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 + segments_filenames = [] - self.try_rename(tmpfilename, filename) + def append_url_to_file(target_url, target_filename): + success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)}) + if not success: + return False + down, target_sanitized = sanitize_open(target_filename, 'rb') + ctx['dest_stream'].write(down.read()) + down.close() + segments_filenames.append(target_sanitized) - self._hook_progress({ - 'downloaded_bytes': byte_counter, - 'total_bytes': byte_counter, - 'filename': filename, - 'status': 'finished', - }) + if initialization_url: + append_url_to_file(initialization_url, ctx['tmpfilename'] + '-Init') + for i, segment_url in enumerate(segment_urls): + segment_filename = '%s-Seg%d' % (ctx['tmpfilename'], i) + append_url_to_file(segment_url, segment_filename) + + self._finish_frag_download(ctx) + + for segment_file in segments_filenames: + os.remove(encodeFilename(segment_file)) return True diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 6170cc1..fc96429 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -15,6 +15,7 @@ from ..compat import ( ) from ..utils import ( encodeFilename, + fix_xml_ampersands, sanitize_open, struct_pack, struct_unpack, @@ -272,15 +273,21 @@ class F4mFD(FragmentFD): return fragments_list def _parse_bootstrap_node(self, node, base_url): - if node.text is None: + # Sometimes non empty inline bootstrap info can be specified along + # with bootstrap url attribute (e.g. dummy inline bootstrap info + # contains whitespace characters in [1]). We will prefer bootstrap + # url over inline bootstrap info when present. + # 1. http://live-1-1.rutube.ru/stream/1024/HDS/SD/C2NKsS85HQNckgn5HdEmOQ/1454167650/S-s604419906/move/four/dirs/upper/1024-576p.f4m + bootstrap_url = node.get('url') + if bootstrap_url: bootstrap_url = compat_urlparse.urljoin( - base_url, node.attrib['url']) + base_url, bootstrap_url) boot_info = self._get_bootstrap_from_url(bootstrap_url) else: bootstrap_url = None bootstrap = base64.b64decode(node.text.encode('ascii')) boot_info = read_bootstrap_info(bootstrap) - return (boot_info, bootstrap_url) + return boot_info, bootstrap_url def real_download(self, filename, info_dict): man_url = info_dict['url'] @@ -288,7 +295,10 @@ class F4mFD(FragmentFD): self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) urlh = self.ydl.urlopen(man_url) man_url = urlh.geturl() - manifest = urlh.read() + # Some manifests may be malformed, e.g. prosiebensat1 generated manifests + # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244 + # and https://github.com/rg3/youtube-dl/issues/7823) + manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip() doc = compat_etree_fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) @@ -312,7 +322,8 @@ class F4mFD(FragmentFD): metadata = None fragments_list = build_fragments_list(boot_info) - if self.params.get('test', False): + test = self.params.get('test', False) + if test: # We only download the first fragment fragments_list = fragments_list[:1] total_frags = len(fragments_list) @@ -322,6 +333,7 @@ class F4mFD(FragmentFD): ctx = { 'filename': filename, 'total_frags': total_frags, + 'live': live, } self._prepare_frag_download(ctx) @@ -376,7 +388,7 @@ class F4mFD(FragmentFD): else: raise - if not fragments_list and live and bootstrap_url: + if not fragments_list and not test and live and bootstrap_url: fragments_list = self._update_live_fragments(bootstrap_url, frag_i) total_frags += len(fragments_list) if fragments_list and (fragments_list[0][1] > frag_i + 1): diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index 5a64b29..5bc9949 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -26,7 +26,11 @@ class FragmentFD(FileDownloader): self._start_frag_download(ctx) def _prepare_frag_download(self, ctx): - self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags'])) + if 'live' not in ctx: + ctx['live'] = False + self.to_screen( + '[%s] Total fragments: %s' + % (self.FD_NAME, ctx['total_frags'] if not ctx['live'] else 'unknown (live)')) self.report_destination(ctx['filename']) dl = HttpQuietDownloader( self.ydl, @@ -34,7 +38,7 @@ class FragmentFD(FileDownloader): 'continuedl': True, 'quiet': True, 'noprogress': True, - 'ratelimit': self.params.get('ratelimit', None), + 'ratelimit': self.params.get('ratelimit'), 'retries': self.params.get('retries', 0), 'test': self.params.get('test', False), } @@ -59,37 +63,44 @@ class FragmentFD(FileDownloader): 'filename': ctx['filename'], 'tmpfilename': ctx['tmpfilename'], } + start = time.time() - ctx['started'] = start + ctx.update({ + 'started': start, + # Total complete fragments downloaded so far in bytes + 'complete_frags_downloaded_bytes': 0, + # Amount of fragment's bytes downloaded by the time of the previous + # frag progress hook invocation + 'prev_frag_downloaded_bytes': 0, + }) def frag_progress_hook(s): if s['status'] not in ('downloading', 'finished'): return - frag_total_bytes = s.get('total_bytes', 0) - if s['status'] == 'finished': - state['downloaded_bytes'] += frag_total_bytes - state['frag_index'] += 1 - - estimated_size = ( - (state['downloaded_bytes'] + frag_total_bytes) / - (state['frag_index'] + 1) * total_frags) time_now = time.time() - state['total_bytes_estimate'] = estimated_size state['elapsed'] = time_now - start + frag_total_bytes = s.get('total_bytes') or 0 + if not ctx['live']: + estimated_size = ( + (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) / + (state['frag_index'] + 1) * total_frags) + state['total_bytes_estimate'] = estimated_size if s['status'] == 'finished': - progress = self.calc_percent(state['frag_index'], total_frags) + state['frag_index'] += 1 + state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes'] + ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes'] + ctx['prev_frag_downloaded_bytes'] = 0 else: frag_downloaded_bytes = s['downloaded_bytes'] - frag_progress = self.calc_percent(frag_downloaded_bytes, - frag_total_bytes) - progress = self.calc_percent(state['frag_index'], total_frags) - progress += frag_progress / float(total_frags) - - state['eta'] = self.calc_eta( - start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes) + state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes'] + if not ctx['live']: + state['eta'] = self.calc_eta( + start, time_now, estimated_size, + state['downloaded_bytes']) state['speed'] = s.get('speed') + ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes self._hook_progress(state) ctx['dl'].add_progress_hook(frag_progress_hook) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 92765a3..2a775bf 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import os import re import subprocess +import sys from .common import FileDownloader from .fragment import FragmentFD @@ -13,6 +14,7 @@ from ..utils import ( encodeArgument, encodeFilename, sanitize_open, + handle_youtubedl_headers, ) @@ -33,18 +35,34 @@ class HlsFD(FileDownloader): if info_dict['http_headers'] and re.match(r'^https?://', url): # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv: # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header. + headers = handle_youtubedl_headers(info_dict['http_headers']) args += [ '-headers', - ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items() if key.lower() != 'accept-encoding')] + ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())] - args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc'] + args += ['-i', url, '-c', 'copy'] + if self.params.get('hls_use_mpegts', False): + args += ['-f', 'mpegts'] + else: + args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc'] args = [encodeArgument(opt) for opt in args] args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True)) self._debug_cmd(args) - retval = subprocess.call(args) + proc = subprocess.Popen(args, stdin=subprocess.PIPE) + try: + retval = proc.wait() + except KeyboardInterrupt: + # subprocces.run would send the SIGKILL signal to ffmpeg and the + # mp4 file couldn't be played, but if we ask ffmpeg to quit it + # produces a file that is playable (this is mostly useful for live + # streams). Note that Windows is not affected and produces playable + # files (see https://github.com/rg3/youtube-dl/issues/8300). + if sys.platform != 'win32': + proc.communicate(b'q') + raise if retval == 0: fsize = os.path.getsize(encodeFilename(tmpfilename)) self.to_screen('\r[%s] %s bytes' % (args[0], fsize)) diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 56840e0..f8b69d1 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -140,8 +140,8 @@ class HttpFD(FileDownloader): if data_len is not None: data_len = int(data_len) + resume_len - min_data_len = self.params.get("min_filesize", None) - max_data_len = self.params.get("max_filesize", None) + min_data_len = self.params.get('min_filesize') + max_data_len = self.params.get('max_filesize') if min_data_len is not None and data_len < min_data_len: self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len)) return False diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 14d56db..9de6e70 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -94,15 +94,15 @@ class RtmpFD(FileDownloader): return proc.returncode url = info_dict['url'] - player_url = info_dict.get('player_url', None) - page_url = info_dict.get('page_url', None) - app = info_dict.get('app', None) - play_path = info_dict.get('play_path', None) - tc_url = info_dict.get('tc_url', None) - flash_version = info_dict.get('flash_version', None) + player_url = info_dict.get('player_url') + page_url = info_dict.get('page_url') + app = info_dict.get('app') + play_path = info_dict.get('play_path') + tc_url = info_dict.get('tc_url') + flash_version = info_dict.get('flash_version') live = info_dict.get('rtmp_live', False) - conn = info_dict.get('rtmp_conn', None) - protocol = info_dict.get('rtmp_protocol', None) + conn = info_dict.get('rtmp_conn') + protocol = info_dict.get('rtmp_protocol') real_time = info_dict.get('rtmp_real_time', False) no_resume = info_dict.get('no_resume', False) continue_dl = self.params.get('continuedl', True) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 947b836..1ae606f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -3,24 +3,34 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE from .academicearth import AcademicEarthCourseIE +from .acast import ( + ACastIE, + ACastChannelIE, +) from .addanime import AddAnimeIE from .adobetv import ( AdobeTVIE, + AdobeTVShowIE, + AdobeTVChannelIE, AdobeTVVideoIE, ) from .adultswim import AdultSwimIE -from .aftenposten import AftenpostenIE +from .aenetworks import AENetworksIE from .aftonbladet import AftonbladetIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE +from .animeondemand import AnimeOnDemandIE from .anitube import AnitubeIE from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE from .appleconnect import AppleConnectIE -from .appletrailers import AppleTrailersIE +from .appletrailers import ( + AppleTrailersIE, + AppleTrailersSectionIE, +) from .archiveorg import ArchiveOrgIE from .ard import ( ARDIE, @@ -33,13 +43,16 @@ from .arte import ( ArteTVCreativeIE, ArteTVConcertIE, ArteTVFutureIE, + ArteTVCinemaIE, ArteTVDDCIE, + ArteTVMagazineIE, ArteTVEmbedIE, ) from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE +from .audimedia import AudiMediaIE from .audiomack import AudiomackIE, AudiomackAlbumIE -from .azubu import AzubuIE +from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE @@ -52,10 +65,14 @@ from .beeg import BeegIE from .behindkink import BehindKinkIE from .beatportpro import BeatportProIE from .bet import BetIE +from .bigflix import BigflixIE from .bild import BildIE from .bilibili import BiliBiliIE +from .bleacherreport import ( + BleacherReportIE, + BleacherReportCMSIE, +) from .blinkx import BlinkxIE -from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE from .bpb import BpbIE from .br import BRIE @@ -71,11 +88,18 @@ from .camdemy import ( CamdemyIE, CamdemyFolderIE ) -from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE +from .canvas import CanvasIE +from .cbc import ( + CBCIE, + CBCPlayerIE, +) from .cbs import CBSIE -from .cbsnews import CBSNewsIE +from .cbsnews import ( + CBSNewsIE, + CBSNewsLiveVideoIE, +) from .cbssports import CBSSportsIE from .ccc import CCCIE from .ceskatelevize import CeskaTelevizeIE @@ -108,6 +132,7 @@ from .comcarcoff import ComCarCoffIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .condenast import CondeNastIE from .cracked import CrackedIE +from .crackle import CrackleIE from .criterion import CriterionIE from .crooksandliars import CrooksAndLiarsIE from .crunchyroll import ( @@ -116,15 +141,27 @@ from .crunchyroll import ( ) from .cspan import CSpanIE from .ctsnews import CtsNewsIE +from .cultureunplugged import CultureUnpluggedIE +from .cwtv import CWTVIE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, DailymotionUserIE, DailymotionCloudIE, ) -from .daum import DaumIE +from .daum import ( + DaumIE, + DaumClipIE, + DaumPlaylistIE, + DaumUserIE, +) from .dbtv import DBTVIE -from .dcn import DCNIE +from .dcn import ( + DCNIE, + DCNVideoIE, + DCNLiveIE, + DCNSeasonIE, +) from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE from .democracynow import DemocracynowIE @@ -171,7 +208,10 @@ from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE -from .facebook import FacebookIE +from .facebook import ( + FacebookIE, + FacebookPostIE, +) from .faz import FazIE from .fc2 import FC2IE from .fczenit import FczenitIE @@ -184,10 +224,14 @@ from .flickr import FlickrIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE from .fourtube import FourTubeIE +from .fox import FOXIE from .foxgay import FoxgayIE from .foxnews import FoxNewsIE from .foxsports import FoxSportsIE -from .franceculture import FranceCultureIE +from .franceculture import ( + FranceCultureIE, + FranceCultureEmissionIE, +) from .franceinter import FranceInterIE from .francetv import ( PluzzIE, @@ -199,7 +243,9 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freevideo import FreeVideoIE +from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE +from .gameinformer import GameInformerIE from .gamekings import GamekingsIE from .gameone import ( GameOneIE, @@ -223,9 +269,11 @@ from .globo import ( from .godtube import GodTubeIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE +from .googledrive import GoogleDriveIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE +from .gputechconf import GPUTechConfIE from .groupon import GrouponIE from .hark import HarkIE from .hearthisat import HearThisAtIE @@ -234,16 +282,20 @@ from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .historicfilms import HistoricFilmsIE -from .history import HistoryIE from .hitbox import HitboxIE, HitboxLiveIE from .hornbunny import HornBunnyIE from .hotnewhiphop import HotNewHipHopIE +from .hotstar import HotStarIE from .howcast import HowcastIE from .howstuffworks import HowStuffWorksIE from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE -from .ign import IGNIE, OneUPIE +from .ign import ( + IGNIE, + OneUPIE, + PCMagIE, +) from .imdb import ( ImdbIE, ImdbListIE @@ -267,11 +319,12 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .ivideon import IvideonIE from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE from .jove import JoveIE -from .jukebox import JukeboxIE +from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE @@ -282,6 +335,7 @@ from .keezmovies import KeezMoviesIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE +from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE @@ -296,10 +350,12 @@ from .kuwo import ( from .la7 import LA7IE from .laola1tv import Laola1TvIE from .lecture2go import Lecture2GoIE +from .lemonde import LemondeIE from .letv import ( LetvIE, LetvTvIE, - LetvPlaylistIE + LetvPlaylistIE, + LetvCloudIE, ) from .libsyn import LibsynIE from .lifenews import ( @@ -318,6 +374,7 @@ from .livestream import ( LivestreamShortenerIE, ) from .lnkgo import LnkGoIE +from .lovehomeporn import LoveHomePornIE from .lrt import LRTIE from .lynda import ( LyndaIE, @@ -326,7 +383,9 @@ from .lynda import ( from .m6 import M6IE from .macgamestore import MacGameStoreIE from .mailru import MailRuIE +from .makertv import MakerTVIE from .malemotion import MalemotionIE +from .matchtv import MatchTVIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE @@ -349,7 +408,6 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE -from .movshare import MovShareIE from .mtv import ( MTVIE, MTVServicesEmbeddedIE, @@ -402,6 +460,7 @@ from .nextmedia import ( NextMediaActionNewsIE, AppleDailyIE, ) +from .nextmovie import NextMovieIE from .nfb import NFBIE from .nfl import NFLIE from .nhl import ( @@ -409,13 +468,20 @@ from .nhl import ( NHLNewsIE, NHLVideocenterIE, ) +from .nick import NickIE from .niconico import NiconicoIE, NiconicoPlaylistIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE from .nova import NovaIE -from .novamov import NovaMovIE +from .novamov import ( + NovaMovIE, + WholeCloudIE, + NowVideoIE, + VideoWeedIE, + CloudTimeIE, +) from .nowness import ( NownessIE, NownessPlaylistIE, @@ -425,15 +491,17 @@ from .nowtv import ( NowTVIE, NowTVListIE, ) -from .nowvideo import NowVideoIE +from .noz import NozIE from .npo import ( NPOIE, NPOLiveIE, NPORadioIE, NPORadioFragmentIE, + SchoolTVIE, VPROIE, WNLIE ) +from .npr import NprIE from .nrk import ( NRKIE, NRKPlaylistIE, @@ -453,12 +521,14 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) +from .ora import OraTVIE from .orf import ( ORFTVthekIE, ORFOE1IE, ORFFM4IE, ORFIPTVIE, ) +from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE @@ -471,6 +541,7 @@ from .planetaplay import PlanetaPlayIE from .pladform import PladformIE from .played import PlayedIE from .playfm import PlayFMIE +from .plays import PlaysTVIE from .playtvak import PlaytvakIE from .playvid import PlayvidIE from .playwire import PlaywireIE @@ -484,6 +555,7 @@ from .pornhd import PornHdIE from .pornhub import ( PornHubIE, PornHubPlaylistIE, + PornHubUserVideosIE, ) from .pornotube import PornotubeIE from .pornovoisines import PornoVoisinesIE @@ -506,18 +578,23 @@ from .radiode import RadioDeIE from .radiojavan import RadioJavanIE from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE -from .rai import RaiIE +from .rai import ( + RaiTVIE, + RaiIE, +) from .rbmaradio import RBMARadioIE from .rds import RDSIE from .redtube import RedTubeIE +from .regiotv import RegioTVIE from .restudy import RestudyIE from .reverbnation import ReverbNationIE +from .revision3 import Revision3IE from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE -from .rte import RteIE +from .rte import RteIE, RteRadioIE from .rtlnl import RtlNlIE from .rtl2 import RTL2IE from .rtp import RTPIE @@ -525,6 +602,7 @@ from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE from .rtvnh import RTVNHIE from .ruhd import RUHDIE +from .ruleporn import RulePornIE from .rutube import ( RutubeIE, RutubeChannelIE, @@ -545,6 +623,7 @@ from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE +from .screenjunkies import ScreenJunkiesIE from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE from .senateisvp import SenateISVPIE from .servingsys import ServingSysIE @@ -554,6 +633,10 @@ from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE +from .skynewsarabia import ( + SkyNewsArabiaIE, + SkyNewsArabiaArticleIE, +) from .slideshare import SlideshareIE from .slutload import SlutloadIE from .smotri import ( @@ -568,10 +651,6 @@ from .snagfilms import ( ) from .snotr import SnotrIE from .sohu import SohuIE -from .soompi import ( - SoompiIE, - SoompiShowIE, -) from .soundcloud import ( SoundcloudIE, SoundcloudSetIE, @@ -603,7 +682,10 @@ from .sportbox import ( SportBoxEmbedIE, ) from .sportdeutschland import SportDeutschlandIE -from .srf import SrfIE +from .srgssr import ( + SRGSSRIE, + SRGSSRPlayIE, +) from .srmediathek import SRMediathekIE from .ssa import SSAIE from .stanfordoc import StanfordOpenClassroomIE @@ -630,6 +712,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tele13 import Tele13IE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telegraaf import TelegraafIE @@ -637,8 +720,8 @@ from .telemb import TeleMBIE from .teletask import TeleTaskIE from .tenplay import TenPlayIE from .testurl import TestURLIE -from .testtube import TestTubeIE from .tf1 import TF1IE +from .theintercept import TheInterceptIE from .theonion import TheOnionIE from .theplatform import ( ThePlatformIE, @@ -648,7 +731,7 @@ from .thesixtyone import TheSixtyOneIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .tinypic import TinyPicIE -from .tlc import TlcIE, TlcDeIE +from .tlc import TlcDeIE from .tmz import ( TMZIE, TMZArticleIE, @@ -658,6 +741,7 @@ from .tnaflix import ( EMPFlixIE, MovieFapIE, ) +from .toggle import ToggleIE from .thvideo import ( THVideoIE, THVideoPlaylistIE @@ -666,12 +750,23 @@ from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE +from .trollvids import TrollvidsIE from .trutube import TruTubeIE from .tube8 import Tube8IE from .tubitv import TubiTvIE -from .tudou import TudouIE +from .tudou import ( + TudouIE, + TudouPlaylistIE, + TudouAlbumIE, +) from .tumblr import TumblrIE -from .tunein import TuneInIE +from .tunein import ( + TuneInClipIE, + TuneInStationIE, + TuneInProgramIE, + TuneInTopicIE, + TuneInShortenerIE, +) from .turbo import TurboIE from .tutv import TutvIE from .tv2 import ( @@ -684,10 +779,12 @@ from .tvc import ( TVCArticleIE, ) from .tvigle import TvigleIE +from .tvland import TVLandIE from .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE +from .twentymin import TwentyMinutenIE from .twentytwotracks import ( TwentyTwoTracksIE, TwentyTwoTracksGenreIE @@ -701,14 +798,18 @@ from .twitch import ( TwitchBookmarksIE, TwitchStreamIE, ) -from .twitter import TwitterCardIE, TwitterIE +from .twitter import ( + TwitterCardIE, + TwitterIE, + TwitterAmplifyIE, +) from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE ) from .udn import UDNEmbedIE -from .ultimedia import UltimediaIE +from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE @@ -730,10 +831,18 @@ from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE from .videomega import VideoMegaIE +from .videomore import ( + VideomoreIE, + VideomoreVideoIE, + VideomoreSeasonIE, +) from .videopremium import VideoPremiumIE from .videott import VideoTtIE -from .videoweed import VideoWeedIE -from .vidme import VidmeIE +from .vidme import ( + VidmeIE, + VidmeUserIE, + VidmeUserLikesIE, +) from .vidzi import VidziIE from .vier import VierIE, VierVideosIE from .viewster import ViewsterIE @@ -783,6 +892,7 @@ from .webofstories import ( WebOfStoriesPlaylistIE, ) from .weibo import WeiboIE +from .weiqitv import WeiqiTVIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE @@ -834,7 +944,7 @@ from .youtube import ( YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, YoutubeUserIE, - YoutubeUserPlaylistsIE, + YoutubePlaylistsIE, YoutubeWatchLaterIE, ) from .zapiks import ZapiksIE @@ -843,6 +953,7 @@ from .zingmp3 import ( ZingMp3SongIE, ZingMp3AlbumIE, ) +from .zippcast import ZippCastIE _ALL_CLASSES = [ klass diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index c0e5d1a..6a29e58 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -23,6 +23,7 @@ class ABCIE(InfoExtractor): 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, + 'skip': 'this video has expired', }, { 'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326', 'md5': 'db2a5369238b51f9811ad815b69dc086', @@ -36,6 +37,7 @@ class ABCIE(InfoExtractor): 'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill', }, 'add_ie': ['Youtube'], + 'skip': 'Not accessible from Travis CI server', }, { 'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080', 'md5': 'b96eee7c9edf4fc5a358a0252881cc1f', @@ -58,6 +60,9 @@ class ABCIE(InfoExtractor): r'inline(?PVideo|Audio|YouTube)Data\.push\((?P[^)]+)\);', webpage) if mobj is None: + expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?(.+?)', webpage, 'expired', None) + if expired: + raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True) raise ExtractorError('Unable to extract video urls') urls_info = self._parse_json( diff --git a/youtube_dl/extractor/abc7news.py b/youtube_dl/extractor/abc7news.py index c04949c..122dc90 100644 --- a/youtube_dl/extractor/abc7news.py +++ b/youtube_dl/extractor/abc7news.py @@ -44,7 +44,6 @@ class Abc7NewsIE(InfoExtractor): 'contentURL', webpage, 'm3u8 url', fatal=True) formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4') - self._sort_formats(formats) title = self._og_search_title(webpage).strip() description = self._og_search_description(webpage).strip() diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py new file mode 100644 index 0000000..92eee81 --- /dev/null +++ b/youtube_dl/extractor/acast.py @@ -0,0 +1,72 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class ACastIE(InfoExtractor): + IE_NAME = 'acast' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', + 'md5': 'ada3de5a1e3a2a381327d749854788bb', + 'info_dict': { + 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', + 'ext': 'mp3', + 'title': '"Where Are You?": Taipei 101, Taiwan', + 'timestamp': 1196172000000, + 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e', + 'duration': 211, + } + } + + def _real_extract(self, url): + channel, display_id = re.match(self._VALID_URL, url).groups() + + embed_page = self._download_webpage( + re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id) + cast_data = self._parse_json(self._search_regex( + r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'), + display_id)['GetAcast/%s/%s' % (channel, display_id)] + + return { + 'id': compat_str(cast_data['id']), + 'display_id': display_id, + 'url': cast_data['blings'][0]['audio'], + 'title': cast_data['name'], + 'description': cast_data.get('description'), + 'thumbnail': cast_data.get('image'), + 'timestamp': int_or_none(cast_data.get('publishingDate')), + 'duration': int_or_none(cast_data.get('duration')), + } + + +class ACastChannelIE(InfoExtractor): + IE_NAME = 'acast:channel' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler', + 'info_dict': { + 'id': '50544219-29bb-499e-a083-6087f4cb7797', + 'title': 'Condé Nast Traveler Podcast', + 'description': 'md5:98646dee22a5b386626ae31866638fbd', + }, + 'playlist_mincount': 20, + } + _API_BASE_URL = 'https://www.acast.com/api/' + + @classmethod + def suitable(cls, url): + return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) + casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) + entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] + + return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description')) diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 5e43adc..8753ee2 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -1,23 +1,32 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, unified_strdate, str_to_int, + int_or_none, float_or_none, ISO639Utils, + determine_ext, ) -class AdobeTVIE(InfoExtractor): - _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P[^/]+)' +class AdobeTVBaseIE(InfoExtractor): + _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + + +class AdobeTVIE(AdobeTVBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?watch/(?P[^/]+)/(?P[^/]+)' _TEST = { 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/', 'md5': '9bc5727bcdd55251f35ad311ca74fa1e', 'info_dict': { - 'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop', + 'id': '10981', 'ext': 'mp4', 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', @@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - player = self._parse_json( - self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'), - video_id) + language, show_urlname, urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' - title = player.get('title') or self._search_regex( - r'data-title="([^"]+)"', webpage, 'title') - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - - upload_date = unified_strdate( - self._html_search_meta('datepublished', webpage, 'upload date')) - - duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration') or - self._search_regex( - r'Runtime:\s*(\d{2}:\d{2}:\d{2})', - webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'
\s*Views?:\s*([\d,.]+)\s*
', - webpage, 'view count')) + video_data = self._download_json( + self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), + urlname)['data'][0] formats = [{ - 'url': source['src'], - 'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None, - 'tbr': source.get('bitrate'), - } for source in player['sources']] + 'url': source['url'], + 'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None, + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('video_data_rate')), + } for source in video_data['videos']] self._sort_formats(formats) return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'view_count': view_count, + 'id': compat_str(video_data['id']), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'upload_date': unified_strdate(video_data.get('start_date')), + 'duration': parse_duration(video_data.get('duration')), + 'view_count': str_to_int(video_data.get('playcount')), 'formats': formats, } +class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): + def _parse_page_data(self, page_data): + return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + + def _extract_playlist_entries(self, url, display_id): + page = self._download_json(url, display_id) + entries = self._parse_page_data(page['data']) + for page_num in range(2, page['paging']['pages'] + 1): + entries.extend(self._parse_page_data( + self._download_json(url + '&page=%d' % page_num, display_id)['data'])) + return entries + + +class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?show/(?P[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost', + 'info_dict': { + 'id': '36', + 'title': 'The Complete Picture with Julieanne Kost', + 'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27', + }, + 'playlist_mincount': 136, + } + + def _get_element_url(self, element_data): + return element_data['urls'][0] + + def _real_extract(self, url): + language, show_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&show_urlname=%s' % (language, show_urlname) + + show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), + compat_str(show_data['id']), + show_data['show_name'], + show_data['show_description']) + + +class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?channel/(?P[^/]+)(?:/(?P[^/]+))?' + + _TEST = { + 'url': 'http://tv.adobe.com/channel/development', + 'info_dict': { + 'id': 'development', + }, + 'playlist_mincount': 96, + } + + def _get_element_url(self, element_data): + return element_data['url'] + + def _real_extract(self, url): + language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + if category_urlname: + query += '&category_urlname=%s' % category_urlname + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + channel_urlname) + + class AdobeTVVideoIE(InfoExtractor): _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P\d+)' @@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor): 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) + video_data = self._download_json(url + '?format=json', video_id) formats = [{ + 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), 'url': source['src'], - 'width': source.get('width'), - 'height': source.get('height'), - 'tbr': source.get('bitrate'), - } for source in player_params['sources']] + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('bitrate')), + } for source in video_data['sources']] + self._sort_formats(formats) # 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']])) + for source in video_data['sources']])) subtitles = {} - for translation in player_params.get('translations', []): + for translation in video_data.get('translations', []): lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) if lang_id not in subtitles: subtitles[lang_id] = [] @@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'title': player_params['title'], - 'description': self._og_search_description(webpage), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data['video'].get('poster'), 'duration': duration, 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 3ae618e..8157da2 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -68,7 +68,7 @@ class AdultSwimIE(InfoExtractor): 'md5': '3e346a2ab0087d687a05e1e7f3b3e529', 'info_dict': { 'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine', 'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n', }, @@ -79,6 +79,10 @@ class AdultSwimIE(InfoExtractor): 'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine', 'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n', }, + 'params': { + # m3u8 download + 'skip_download': True, + } }] @staticmethod @@ -183,7 +187,8 @@ class AdultSwimIE(InfoExtractor): media_url = file_el.text if determine_ext(media_url) == 'm3u8': formats.extend(self._extract_m3u8_formats( - media_url, segment_title, 'mp4', preference=0, m3u8_id='hls')) + media_url, segment_title, 'mp4', preference=0, + m3u8_id='hls', fatal=False)) else: formats.append({ 'format_id': '%s_%s' % (bitrate, ftype), diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py new file mode 100644 index 0000000..6018ae7 --- /dev/null +++ b/youtube_dl/extractor/aenetworks.py @@ -0,0 +1,66 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import smuggle_url + + +class AENetworksIE(InfoExtractor): + IE_NAME = 'aenetworks' + IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' + _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P[^/]+?)(?:$|[?#])' + + _TESTS = [{ + 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', + 'info_dict': { + 'id': 'g12m5Gyt3fdR', + 'ext': 'mp4', + 'title': "Bet You Didn't Know: Valentine's Day", + 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['ThePlatform'], + 'expected_warnings': ['JSON-LD'], + }, { + 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', + 'info_dict': { + 'id': 'eg47EERs_JsZ', + 'ext': 'mp4', + 'title': 'Winter Is Coming', + 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['ThePlatform'], + }, { + 'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry', + 'only_matching': True + }, { + 'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage', + 'only_matching': True + }, { + 'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients', + 'only_matching': True + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url_re = [ + r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id, + r"media_url\s*=\s*'([^']+)'" + ] + video_url = self._search_regex(video_url_re, webpage, 'video url') + + info = self._search_json_ld(webpage, video_id, fatal=False) + info.update({ + '_type': 'url_transparent', + 'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}), + }) + return info diff --git a/youtube_dl/extractor/aftenposten.py b/youtube_dl/extractor/aftenposten.py deleted file mode 100644 index 0c00acf..0000000 --- a/youtube_dl/extractor/aftenposten.py +++ /dev/null @@ -1,23 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class AftenpostenIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P\d+)' - _TEST = { - 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more', - 'md5': 'fd828cd29774a729bf4d4425fe192972', - 'info_dict': { - 'id': '21039', - 'ext': 'mov', - 'title': 'TRAILER: "Sweatshop" - I can´t take any more', - 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238', - 'timestamp': 1416927969, - 'upload_date': '20141125', - } - } - - def _real_extract(self, url): - return self.url_result('xstream:ap:%s' % self._match_id(url), 'Xstream') diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 7d65b81..190bc2c 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -8,6 +8,8 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( qualities, + unescapeHTML, + xpath_element, ) @@ -31,7 +33,7 @@ class AllocineIE(InfoExtractor): 'id': '19540403', 'ext': 'mp4', 'title': 'Planes 2 Bande-annonce VF', - 'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e', + 'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway', 'thumbnail': 're:http://.*\.jpg', }, }, { @@ -41,7 +43,7 @@ class AllocineIE(InfoExtractor): 'id': '19544709', 'ext': 'mp4', 'title': 'Dragons 2 - Bande annonce finale VF', - 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', + 'description': 'md5:601d15393ac40f249648ef000720e7e3', 'thumbnail': 're:http://.*\.jpg', }, }, { @@ -59,14 +61,18 @@ class AllocineIE(InfoExtractor): if typ == 'film': video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id') else: - player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player') - - player_data = json.loads(player) - video_id = compat_str(player_data['refMedia']) + player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None) + if player: + player_data = json.loads(player) + video_id = compat_str(player_data['refMedia']) + else: + model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model') + model_data = self._parse_json(unescapeHTML(model), display_id) + video_id = compat_str(model_data['id']) xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id) - video = xml.find('.//AcVisionVideo').attrib + video = xpath_element(xml, './/AcVisionVideo').attrib quality = qualities(['ld', 'md', 'hd']) formats = [] diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py new file mode 100644 index 0000000..69e6baf --- /dev/null +++ b/youtube_dl/extractor/amp.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class AMPIE(InfoExtractor): + # parse Akamai Adaptive Media Player feed + def _extract_feed_info(self, url): + item = self._download_json( + url, None, 'Downloading Akamai AMP feed', + 'Unable to download Akamai AMP feed')['channel']['item'] + + video_id = item['guid'] + + def get_media_node(name, default=None): + media_name = 'media-%s' % name + media_group = item.get('media-group') or item + return media_group.get(media_name) or item.get(media_name) or item.get(name, default) + + thumbnails = [] + media_thumbnail = get_media_node('thumbnail') + if media_thumbnail: + if isinstance(media_thumbnail, dict): + media_thumbnail = [media_thumbnail] + for thumbnail_data in media_thumbnail: + thumbnail = thumbnail_data['@attributes'] + thumbnails.append({ + 'url': self._proto_relative_url(thumbnail['url'], 'http:'), + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) + + subtitles = {} + media_subtitle = get_media_node('subTitle') + if media_subtitle: + if isinstance(media_subtitle, dict): + media_subtitle = [media_subtitle] + for subtitle_data in media_subtitle: + subtitle = subtitle_data['@attributes'] + lang = subtitle.get('lang') or 'en' + subtitles[lang] = [{'url': subtitle['href']}] + + formats = [] + media_content = get_media_node('content') + if isinstance(media_content, dict): + media_content = [media_content] + for media_data in media_content: + media = media_data['@attributes'] + media_type = media['type'] + if media_type == 'video/f4m': + formats.extend(self._extract_f4m_formats( + media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', + video_id, f4m_id='hds', fatal=False)) + elif media_type == 'application/x-mpegURL': + formats.extend(self._extract_m3u8_formats( + media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'format_id': media_data['media-category']['@attributes']['label'], + 'url': media['url'], + 'tbr': int_or_none(media.get('bitrate')), + 'filesize': int_or_none(media.get('fileSize')), + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': get_media_node('title'), + 'description': get_media_node('description'), + 'thumbnails': thumbnails, + 'timestamp': parse_iso8601(item.get('pubDate'), ' '), + 'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')), + 'subtitles': subtitles, + 'formats': formats, + } diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py new file mode 100644 index 0000000..a7d8daf --- /dev/null +++ b/youtube_dl/extractor/animeondemand.py @@ -0,0 +1,160 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + determine_ext, + encode_dict, + ExtractorError, + sanitized_Request, + urlencode_postdata, +) + + +class AnimeOnDemandIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P\d+)' + _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in' + _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply' + _NETRC_MACHINE = 'animeondemand' + _TEST = { + 'url': 'https://www.anime-on-demand.de/anime/161', + 'info_dict': { + 'id': '161', + 'title': 'Grimgar, Ashes and Illusions (OmU)', + 'description': 'md5:6681ce3c07c7189d255ac6ab23812d31', + }, + 'playlist_mincount': 4, + } + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._form_hidden_inputs('new_user', login_page) + + login_form.update({ + 'user[login]': username, + 'user[password]': password, + }) + + post_url = self._search_regex( + r']+action=(["\'])(?P.+?)\1', login_page, + 'post url', default=self._LOGIN_URL, group='url') + + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + + request = sanitized_Request( + post_url, urlencode_postdata(encode_dict(login_form))) + request.add_header('Referer', self._LOGIN_URL) + + response = self._download_webpage( + request, None, 'Logging in as %s' % username) + + if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')): + error = self._search_regex( + r'

(.+?)

', + response, 'error', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + anime_id = self._match_id(url) + + webpage = self._download_webpage(url, anime_id) + + if 'data-playlist=' not in webpage: + self._download_webpage( + self._APPLY_HTML5_URL, anime_id, + 'Activating HTML5 beta', 'Unable to apply HTML5 beta') + webpage = self._download_webpage(url, anime_id) + + csrf_token = self._html_search_meta( + 'csrf-token', webpage, 'csrf token', fatal=True) + + anime_title = self._html_search_regex( + r'(?s)]+itemprop="name"[^>]*>(.+?)', + webpage, 'anime name') + anime_description = self._html_search_regex( + r'(?s)]+itemprop="description"[^>]*>(.+?)', + webpage, 'anime description', default=None) + + entries = [] + + for episode_html in re.findall(r'(?s)]+class="episodebox-title".+?>Episodeninhalt<', webpage): + m = re.search( + r'class="episodebox-title"[^>]+title="Episode (?P\d+) - (?P.+?)"', episode_html) + if not m: + continue + + episode_number = int(m.group('number')) + episode_title = m.group('title') + video_id = 'episode-%d' % episode_number + + common_info = { + 'id': video_id, + 'series': anime_title, + 'episode': episode_title, + 'episode_number': episode_number, + } + + formats = [] + + playlist_url = self._search_regex( + r'data-playlist=(["\'])(?P<url>.+?)\1', + episode_html, 'data playlist', default=None, group='url') + if playlist_url: + request = sanitized_Request( + compat_urlparse.urljoin(url, playlist_url), + headers={ + 'X-Requested-With': 'XMLHttpRequest', + 'X-CSRF-Token': csrf_token, + 'Referer': url, + 'Accept': 'application/json, text/javascript, */*; q=0.01', + }) + + playlist = self._download_json( + request, video_id, 'Downloading playlist JSON', fatal=False) + if playlist: + playlist = playlist['playlist'][0] + title = playlist['title'] + description = playlist.get('description') + for source in playlist.get('sources', []): + file_ = source.get('file') + if file_ and determine_ext(file_) == 'm3u8': + formats = self._extract_m3u8_formats( + file_, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + + if formats: + f = common_info.copy() + f.update({ + 'title': title, + 'description': description, + 'formats': formats, + }) + entries.append(f) + + m = re.search( + r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<', + episode_html) + if m: + f = common_info.copy() + f.update({ + 'id': '%s-teaser' % f['id'], + 'title': m.group('title'), + 'url': compat_urlparse.urljoin(url, m.group('href')), + }) + entries.append(f) + + return self.playlist_result(entries, anime_id, anime_title, anime_description) diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py index 23f942a..2fd912d 100644 --- a/youtube_dl/extractor/anitube.py +++ b/youtube_dl/extractor/anitube.py @@ -1,11 +1,9 @@ from __future__ import unicode_literals -import re +from .nuevo import NuevoBaseIE -from .common import InfoExtractor - -class AnitubeIE(InfoExtractor): +class AnitubeIE(NuevoBaseIE): IE_NAME = 'anitube.se' _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)' @@ -22,38 +20,11 @@ class AnitubeIE(InfoExtractor): } 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) key = self._search_regex( r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key') - config_xml = self._download_xml( - 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key) - - video_title = config_xml.find('title').text - thumbnail = config_xml.find('image').text - duration = float(config_xml.find('duration').text) - - formats = [] - video_url = config_xml.find('file') - if video_url is not None: - formats.append({ - 'format_id': 'sd', - 'url': video_url.text, - }) - video_url = config_xml.find('filehd') - if video_url is not None: - formats.append({ - 'format_id': 'hd', - 'url': video_url.text, - }) - - return { - 'id': video_id, - 'title': video_title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats - } + return self._extract_nuevo( + 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id) diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index f68dc32..be40f85 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -11,7 +11,8 @@ from ..utils import ( class AppleTrailersIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)' + IE_NAME = 'appletrailers' + _VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)' _TESTS = [{ 'url': 'http://trailers.apple.com/trailers/wb/manofsteel/', 'info_dict': { @@ -63,9 +64,18 @@ class AppleTrailersIE(InfoExtractor): }, }, ] + }, { + 'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/', + 'info_dict': { + 'id': 'blackthorn', + }, + 'playlist_mincount': 2, }, { 'url': 'http://trailers.apple.com/ca/metropole/autrui/', 'only_matching': True, + }, { + 'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/', + 'only_matching': True, }] _JSON_RE = r'iTunes.playURL\((.*?)\);' @@ -79,7 +89,7 @@ class AppleTrailersIE(InfoExtractor): def fix_html(s): s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) - s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) + s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s) # The ' in the onClick attributes are not escaped, it couldn't be parsed # like: http://trailers.apple.com/trailers/wb/gravity/ @@ -96,6 +106,9 @@ class AppleTrailersIE(InfoExtractor): trailer_info_json = self._search_regex(self._JSON_RE, on_click, 'trailer info') trailer_info = json.loads(trailer_info_json) + first_url = trailer_info.get('url') + if not first_url: + continue title = trailer_info['title'] video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() thumbnail = li.find('.//img').attrib['src'] @@ -107,7 +120,6 @@ class AppleTrailersIE(InfoExtractor): if m: duration = 60 * int(m.group('minutes')) + int(m.group('seconds')) - first_url = trailer_info['url'] trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower() settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id) settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json') @@ -144,3 +156,76 @@ class AppleTrailersIE(InfoExtractor): 'id': movie, 'entries': playlist, } + + +class AppleTrailersSectionIE(InfoExtractor): + IE_NAME = 'appletrailers:section' + _SECTIONS = { + 'justadded': { + 'feed_path': 'just_added', + 'title': 'Just Added', + }, + 'exclusive': { + 'feed_path': 'exclusive', + 'title': 'Exclusive', + }, + 'justhd': { + 'feed_path': 'just_hd', + 'title': 'Just HD', + }, + 'mostpopular': { + 'feed_path': 'most_pop', + 'title': 'Most Popular', + }, + 'moviestudios': { + 'feed_path': 'studios', + 'title': 'Movie Studios', + }, + } + _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS) + _TESTS = [{ + 'url': 'http://trailers.apple.com/#section=justadded', + 'info_dict': { + 'title': 'Just Added', + 'id': 'justadded', + }, + 'playlist_mincount': 80, + }, { + 'url': 'http://trailers.apple.com/#section=exclusive', + 'info_dict': { + 'title': 'Exclusive', + 'id': 'exclusive', + }, + 'playlist_mincount': 80, + }, { + 'url': 'http://trailers.apple.com/#section=justhd', + 'info_dict': { + 'title': 'Just HD', + 'id': 'justhd', + }, + 'playlist_mincount': 80, + }, { + 'url': 'http://trailers.apple.com/#section=mostpopular', + 'info_dict': { + 'title': 'Most Popular', + 'id': 'mostpopular', + }, + 'playlist_mincount': 80, + }, { + 'url': 'http://trailers.apple.com/#section=moviestudios', + 'info_dict': { + 'title': 'Movie Studios', + 'id': 'moviestudios', + }, + 'playlist_mincount': 80, + }] + + def _real_extract(self, url): + section = self._match_id(url) + section_data = self._download_json( + 'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'], + section) + entries = [ + self.url_result('http://trailers.apple.com' + e['location']) + for e in section_data] + return self.playlist_result(entries, section, self._SECTIONS[section]['title']) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 73be6d2..9fb8491 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -110,13 +110,15 @@ class ARDMediathekIE(InfoExtractor): server = stream.get('_server') for stream_url in stream_urls: ext = determine_ext(stream_url) + if quality != 'auto' and ext in ('f4m', 'm3u8'): + continue 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')) + video_id, preference=-1, f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - stream_url, video_id, 'mp4', preference=1, m3u8_id='hls')) + stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False)) else: if server and server.startswith('rtmp'): f = { diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 2a00da3..efde7e2 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -13,6 +13,7 @@ from ..utils import ( unified_strdate, get_element_by_attribute, int_or_none, + NO_DEFAULT, qualities, ) @@ -22,7 +23,7 @@ from ..utils import ( class ArteTvIE(InfoExtractor): - _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html' + _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html' IE_NAME = 'arte.tv' def _real_extract(self, url): @@ -62,15 +63,19 @@ class ArteTvIE(InfoExtractor): class ArteTVPlus7IE(InfoExtractor): IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])' @classmethod def _extract_url_info(cls, url): mobj = re.match(cls._VALID_URL, url) lang = mobj.group('lang') - # This is not a real id, it can be for example AJT for the news - # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal - video_id = mobj.group('id') + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + if 'vid' in query: + video_id = query['vid'][0] + else: + # This is not a real id, it can be for example AJT for the news + # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal + video_id = mobj.group('id') return video_id, lang def _real_extract(self, url): @@ -79,16 +84,50 @@ class ArteTVPlus7IE(InfoExtractor): return self._extract_from_webpage(webpage, video_id, lang) def _extract_from_webpage(self, webpage, video_id, lang): + patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']') + ids = (video_id, '') + # some pages contain multiple videos (like + # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D), + # so we first try to look for json URLs that contain the video id from + # the 'vid' parameter. + patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates] json_url = self._html_search_regex( - [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], - webpage, 'json vp url', default=None) + patterns, webpage, 'json vp url', default=None) if not json_url: - iframe_url = self._html_search_regex( - r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', - webpage, 'iframe url', group='url') - json_url = compat_parse_qs( - compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] - return self._extract_from_json_url(json_url, video_id, lang) + def find_iframe_url(webpage, default=NO_DEFAULT): + return self._html_search_regex( + r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', + webpage, 'iframe url', group='url', default=default) + + iframe_url = find_iframe_url(webpage, None) + if not iframe_url: + embed_url = self._html_search_regex( + r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None) + if embed_url: + player = self._download_json( + embed_url, video_id, 'Downloading player page') + iframe_url = find_iframe_url(player['html']) + # en and es URLs produce react-based pages with different layout (e.g. + # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) + if not iframe_url: + program = self._search_regex( + r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', + webpage, 'program', default=None) + if program: + embed_html = self._parse_json(program, video_id) + if embed_html: + iframe_url = find_iframe_url(embed_html['embed_html']) + if iframe_url: + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] + if json_url: + return self._extract_from_json_url(json_url, video_id, lang) + # Differend kind of embed URL (e.g. + # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) + embed_url = self._search_regex( + r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', + webpage, 'embed url', group='url') + return self.url_result(embed_url) def _extract_from_json_url(self, json_url, video_id, lang): info = self._download_json(json_url, video_id) @@ -96,7 +135,7 @@ class ArteTVPlus7IE(InfoExtractor): upload_date_str = player_info.get('shootingDate') if not upload_date_str: - upload_date_str = player_info.get('VDA', '').split(' ')[0] + upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] title = player_info['VTI'].strip() subtitle = player_info.get('VSU', '').strip() @@ -112,27 +151,30 @@ class ArteTVPlus7IE(InfoExtractor): } qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ']) + LANGS = { + 'fr': 'F', + 'de': 'A', + 'en': 'E[ANG]', + 'es': 'E[ESP]', + } + formats = [] for format_id, format_dict in player_info['VSR'].items(): f = dict(format_dict) versionCode = f.get('versionCode') - - langcode = { - 'fr': 'F', - 'de': 'A', - }.get(lang, lang) - lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode] - lang_pref = ( - None if versionCode is None else ( - 10 if any(re.match(r, versionCode) for r in lang_rexs) - else -10)) + langcode = LANGS.get(lang, lang) + lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)] + lang_pref = None + if versionCode: + matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)] + lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs) source_pref = 0 if versionCode is not None: # The original version with subtitles has lower relevance - if re.match(r'VO-ST(F|A)', versionCode): + if re.match(r'VO-ST(F|A|E)', versionCode): source_pref -= 10 # The version with sourds/mal subtitles has also lower relevance - elif re.match(r'VO?(F|A)-STM\1', versionCode): + elif re.match(r'VO?(F|A|E)-STM\1', versionCode): source_pref -= 9 format = { 'format_id': format_id, @@ -165,7 +207,7 @@ class ArteTVPlus7IE(InfoExtractor): # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' - _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)' + _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:magazine?/)?(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', @@ -189,30 +231,25 @@ class ArteTVCreativeIE(ArteTVPlus7IE): class ArteTVFutureIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:future' - _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)' + _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' - _TEST = { - 'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081', + _TESTS = [{ + 'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses', 'info_dict': { - 'id': '5201', + 'id': '050940-028-A', 'ext': 'mp4', - 'title': 'Les champignons au secours de la planète', - 'upload_date': '20131101', + 'title': 'Les écrevisses aussi peuvent être anxieuses', + 'upload_date': '20140902', }, - } - - def _real_extract(self, url): - anchor_id, lang = self._extract_url_info(url) - webpage = self._download_webpage(url, anchor_id) - row = self._search_regex( - r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id, - webpage, 'row') - return self._extract_from_webpage(row, anchor_id, lang) + }, { + 'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable', + 'only_matching': True, + }] class ArteTVDDCIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:ddc' - _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)' + _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)' def _real_extract(self, url): video_id, lang = self._extract_url_info(url) @@ -230,7 +267,7 @@ class ArteTVDDCIE(ArteTVPlus7IE): class ArteTVConcertIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:concert' - _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)' + _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' _TEST = { 'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde', @@ -245,6 +282,54 @@ class ArteTVConcertIE(ArteTVPlus7IE): } +class ArteTVCinemaIE(ArteTVPlus7IE): + IE_NAME = 'arte.tv:cinema' + _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)' + + _TEST = { + 'url': 'http://cinema.arte.tv/de/node/38291', + 'md5': '6b275511a5107c60bacbeeda368c3aa1', + 'info_dict': { + 'id': '055876-000_PWA12025-D', + 'ext': 'mp4', + 'title': 'Tod auf dem Nil', + 'upload_date': '20160122', + 'description': 'md5:7f749bbb77d800ef2be11d54529b96bc', + }, + } + + +class ArteTVMagazineIE(ArteTVPlus7IE): + IE_NAME = 'arte.tv:magazine' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' + + _TESTS = [{ + # Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..." + 'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium', + 'md5': '2a9369bcccf847d1c741e51416299f25', + 'info_dict': { + 'id': '065965-000-A', + 'ext': 'mp4', + 'title': 'Trepalium - Extrait Ep.01', + 'upload_date': '20160121', + }, + }, { + # Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium" + 'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium', + 'md5': 'fedc64fc7a946110fe311634e79782ca', + 'info_dict': { + 'id': '054813-004_PLUS7-F', + 'ext': 'mp4', + 'title': 'Trepalium (4/6)', + 'description': 'md5:10057003c34d54e95350be4f9b05cb40', + 'upload_date': '20160218', + }, + }, { + 'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis', + 'only_matching': True, + }] + + class ArteTVEmbedIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:embed' _VALID_URL = r'''(?x) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index 50e47ba..b8f9ae0 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -2,6 +2,8 @@ from __future__ import unicode_literals import time import hmac +import hashlib +import re from .common import InfoExtractor from ..compat import ( @@ -32,6 +34,19 @@ class AtresPlayerIE(InfoExtractor): 'duration': 5527.6, 'thumbnail': 're:^https?://.*\.jpg$', }, + 'skip': 'This video is only available for registered users' + }, + { + 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', + 'md5': '0d0e918533bbd4b263f2de4d197d4aac', + 'info_dict': { + 'id': 'capitulo-112-david-bustamante', + 'ext': 'flv', + 'title': 'David Bustamante', + 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6', + 'duration': 1439.0, + 'thumbnail': 're:^https?://.*\.jpg$', + }, }, { 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', @@ -50,6 +65,13 @@ class AtresPlayerIE(InfoExtractor): _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' + _ERRORS = { + 'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.', + 'DELETED': 'This video has expired and is no longer available for online streaming.', + 'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.', + # 'PREMIUM': 'PREMIUM', + } + def _real_initialize(self): self._login() @@ -83,58 +105,72 @@ class AtresPlayerIE(InfoExtractor): episode_id = self._search_regex( r'episode="([^"]+)"', webpage, 'episode id') + request = sanitized_Request( + self._PLAYER_URL_TEMPLATE % episode_id, + headers={'User-Agent': self._USER_AGENT}) + player = self._download_json(request, episode_id, 'Downloading player JSON') + + episode_type = player.get('typeOfEpisode') + error_message = self._ERRORS.get(episode_type) + if error_message: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + + formats = [] + video_url = player.get('urlVideo') + if video_url: + format_info = { + 'url': video_url, + 'format_id': 'http', + } + mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url) + if mobj: + format_info.update({ + 'width': int_or_none(mobj.group('width')), + 'height': int_or_none(mobj.group('height')), + 'tbr': int_or_none(mobj.group('bitrate')), + }) + formats.append(format_info) + timestamp = int_or_none(self._download_webpage( self._TIME_API_URL, video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) token = hmac.new( self._MAGIC.encode('ascii'), - (episode_id + timestamp_shifted).encode('utf-8') + (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5 ).hexdigest() - formats = [] - for fmt in ['windows', 'android_tablet']: - request = sanitized_Request( - self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token)) - request.add_header('User-Agent', self._USER_AGENT) - - fmt_json = self._download_json( - request, video_id, 'Downloading %s video JSON' % fmt) - - result = fmt_json.get('resultDes') - if result.lower() != 'ok': - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, result), expected=True) - - for format_id, video_url in fmt_json['resultObject'].items(): - if format_id == 'token' or not video_url.startswith('http'): - continue - if video_url.endswith('/Manifest'): - if 'geodeswowsmpra3player' in video_url: - f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] - f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) - # this videos are protected by DRM, the f4m downloader doesn't support them - continue - else: - f4m_url = video_url[:-9] + '/manifest.f4m' - formats.extend(self._extract_f4m_formats(f4m_url, video_id)) - else: - formats.append({ - 'url': video_url, - 'format_id': 'android-%s' % format_id, - 'preference': 1, - }) - self._sort_formats(formats) + request = sanitized_Request( + self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token), + headers={'User-Agent': self._USER_AGENT}) - player = self._download_json( - self._PLAYER_URL_TEMPLATE % episode_id, - episode_id) + fmt_json = self._download_json( + request, video_id, 'Downloading windows video JSON') + + result = fmt_json.get('resultDes') + if result.lower() != 'ok': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, result), expected=True) + + for format_id, video_url in fmt_json['resultObject'].items(): + if format_id == 'token' or not video_url.startswith('http'): + continue + if 'geodeswowsmpra3player' in video_url: + f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] + f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) + # this videos are protected by DRM, the f4m downloader doesn't support them + continue + else: + f4m_url = video_url[:-9] + '/manifest.f4m' + formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)) + self._sort_formats(formats) path_data = player.get('pathData') episode = self._download_xml( - self._EPISODE_URL_TEMPLATE % path_data, - video_id, 'Downloading episode XML') + self._EPISODE_URL_TEMPLATE % path_data, video_id, + 'Downloading episode XML') duration = float_or_none(xpath_text( episode, './media/asset/info/technical/contentDuration', 'duration')) diff --git a/youtube_dl/extractor/audimedia.py b/youtube_dl/extractor/audimedia.py new file mode 100644 index 0000000..3b2effa --- /dev/null +++ b/youtube_dl/extractor/audimedia.py @@ -0,0 +1,80 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, + sanitized_Request, +) + + +class AudiMediaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test', + 'md5': '79a8b71c46d49042609795ab59779b66', + 'info_dict': { + 'id': '1565', + 'ext': 'mp4', + 'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test', + 'description': 'md5:60e5d30a78ced725f7b8d34370762941', + 'upload_date': '20151124', + 'timestamp': 1448354940, + 'duration': 74022, + 'view_count': int, + } + } + # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken) + _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload') + _, stage_mode, video_id, lang = raw_payload.split('-') + + # TODO: handle s and e stage_mode (live streams and ended live streams) + if stage_mode not in ('s', 'e'): + request = sanitized_Request( + 'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang), + headers={'X-Auth-Token': self._AUTH_TOKEN}) + json_data = self._download_json(request, video_id)['results'] + formats = [] + + stream_url_hls = json_data.get('stream_url_hls') + if stream_url_hls: + formats.extend(self._extract_m3u8_formats( + stream_url_hls, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + + stream_url_hds = json_data.get('stream_url_hds') + if stream_url_hds: + formats.extend(self._extract_f4m_formats( + stream_url_hds + '?hdcore=3.4.0', + video_id, f4m_id='hds', fatal=False)) + + for video_version in json_data.get('video_versions'): + video_version_url = video_version.get('download_url') or video_version.get('stream_url') + if not video_version_url: + continue + formats.append({ + 'url': video_version_url, + 'width': int_or_none(video_version.get('width')), + 'height': int_or_none(video_version.get('height')), + 'abr': int_or_none(video_version.get('audio_bitrate')), + 'vbr': int_or_none(video_version.get('video_bitrate')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': json_data['title'], + 'description': json_data.get('subtitle'), + 'thumbnail': json_data.get('thumbnail_image', {}).get('file'), + 'timestamp': parse_iso8601(json_data.get('publication_date')), + 'duration': int_or_none(json_data.get('duration')), + 'view_count': int_or_none(json_data.get('view_count')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index 693ba22..3eed912 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -56,7 +56,7 @@ class AudiomackIE(InfoExtractor): # API is inconsistent with errors if 'url' not in api_response or not api_response['url'] or 'error' in api_response: - raise ExtractorError('Invalid url %s', url) + raise ExtractorError('Invalid url %s' % url) # Audiomack wraps a lot of soundcloud tracks in their branded wrapper # if so, pass the work off to the soundcloud extractor diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py index 0961d33..011edf1 100644 --- a/youtube_dl/extractor/azubu.py +++ b/youtube_dl/extractor/azubu.py @@ -3,7 +3,11 @@ from __future__ import unicode_literals import json from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + ExtractorError, + float_or_none, + sanitized_Request, +) class AzubuIE(InfoExtractor): @@ -91,3 +95,37 @@ class AzubuIE(InfoExtractor): 'view_count': view_count, 'formats': formats, } + + +class AzubuLiveIE(InfoExtractor): + _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$' + + _TEST = { + 'url': 'http://www.azubu.tv/MarsTVMDLen', + 'only_matching': True, + } + + def _real_extract(self, url): + user = self._match_id(url) + + info = self._download_json( + 'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user), + user)['data'] + if info['type'] != 'STREAM': + raise ExtractorError('{0} is not streaming live'.format(user), expected=True) + + req = sanitized_Request( + 'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id']) + req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV') + bc_info = self._download_json(req, user) + m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS') + formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4') + + return { + 'id': info['id'], + 'title': self._live_title(info['title']), + 'uploader_id': user, + 'formats': formats, + 'is_live': True, + 'thumbnail': bc_info['poster'], + } diff --git a/youtube_dl/extractor/baidu.py b/youtube_dl/extractor/baidu.py index e37ee44..76b21e5 100644 --- a/youtube_dl/extractor/baidu.py +++ b/youtube_dl/extractor/baidu.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..utils import unescapeHTML class BaiduVideoIE(InfoExtractor): @@ -14,8 +14,8 @@ class BaiduVideoIE(InfoExtractor): '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', 'info_dict': { 'id': '1069', - 'title': '中华小当家 TV版 (全52集)', - 'description': 'md5:395a419e41215e531c857bb037bbaf80', + 'title': '中华小当家 TV版国语', + 'description': 'md5:51be07afe461cf99fa61231421b5397c', }, 'playlist_count': 52, }, { @@ -25,45 +25,32 @@ class BaiduVideoIE(InfoExtractor): 'title': 're:^奔跑吧兄弟', 'description': 'md5:1bf88bad6d850930f542d51547c089b8', }, - 'playlist_mincount': 3, + 'playlist_mincount': 12, }] + def _call_api(self, path, category, playlist_id, note): + return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % ( + path, category, playlist_id), playlist_id, note) + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') - category = category2 = mobj.group('type') + category, playlist_id = re.match(self._VALID_URL, url).groups() if category == 'show': - category2 = 'tvshow' - - webpage = self._download_webpage(url, playlist_id) - - playlist_title = self._html_search_regex( - r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage, - 'playlist title', group='title') - playlist_description = self._html_search_regex( - r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage, - playlist_id, 'playlist description') + category = 'tvshow' + if category == 'tv': + category = 'tvplay' - site = self._html_search_regex( - r'filterSite\s*:\s*["\']([^"]*)["\']', webpage, - 'primary provider site') - api_result = self._download_json( - 'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % ( - category, category2, playlist_id, site), - playlist_id, 'Get playlist links') + playlist_detail = self._call_api( + 'xqinfo', category, playlist_id, 'Download playlist JSON metadata') - entries = [] - for episode in api_result[0]['episodes']: - episode_id = '%s_%s' % (playlist_id, episode['episode']) + playlist_title = playlist_detail['title'] + playlist_description = unescapeHTML(playlist_detail.get('intro')) - redirect_page = self._download_webpage( - compat_urlparse.urljoin(url, episode['url']), episode_id, - note='Download Baidu redirect page') - real_url = self._html_search_regex( - r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL') + episodes_detail = self._call_api( + 'xqsingle', category, playlist_id, 'Download episodes JSON metadata') - entries.append(self.url_result( - real_url, video_title=episode['single_title'])) + entries = [self.url_result( + episode['url'], video_title=episode['title'] + ) for episode in episodes_detail['videos']] return self.playlist_result( entries, playlist_id, playlist_title, playlist_description) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 33b296e..9d0dfb9 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -22,7 +22,18 @@ from ..compat import ( class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})' + _ID_REGEX = r'[pb][\da-z]{7}' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?bbc\.co\.uk/ + (?: + programmes/(?!articles/)| + iplayer(?:/[^/]+)?/(?:episode/|playlist/)| + music/clips[/#]| + radio/player/ + ) + (?P<id>%s) + ''' % _ID_REGEX _MEDIASELECTOR_URLS = [ # Provides HQ HLS streams with even better quality that pc mediaset but fails @@ -46,9 +57,8 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', + 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, }, 'params': { # rtmp download @@ -76,7 +86,7 @@ class BBCCoUkIE(InfoExtractor): 'id': 'b00yng1d', 'ext': 'flv', 'title': 'The Voice UK: Series 3: Blind Auditions 5', - 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.", + 'description': 'Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.', 'duration': 5100, }, 'params': { @@ -111,16 +121,17 @@ class BBCCoUkIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', }, { - 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', + 'url': 'http://www.bbc.co.uk/music/clips/p022h44b', 'note': 'Audio', 'info_dict': { - 'id': 'p02frcch', + 'id': 'p022h44j', 'ext': 'flv', - 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', - 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', - 'duration': 3507, + 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances', + 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.", + 'duration': 227, }, 'params': { # rtmp download @@ -171,13 +182,25 @@ class BBCCoUkIE(InfoExtractor): }, { # iptv-all mediaset fails with geolocation however there is no geo restriction # for this programme at all - 'url': 'http://www.bbc.co.uk/programmes/b06bp7lf', + 'url': 'http://www.bbc.co.uk/programmes/b06rkn85', 'info_dict': { - 'id': 'b06bp7kf', + 'id': 'b06rkms3', 'ext': 'flv', - 'title': "Annie Mac's Friday Night, B.Traits sits in for Annie", - 'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.', - 'duration': 10800, + 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1", + 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!", + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # compact player (https://github.com/rg3/youtube-dl/issues/8147) + 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', + 'info_dict': { + 'id': 'p028bfkj', + 'ext': 'flv', + 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', + 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', }, 'params': { # rtmp download @@ -192,6 +215,9 @@ class BBCCoUkIE(InfoExtractor): }, { 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf', + 'only_matching': True, } ] @@ -222,11 +248,9 @@ class BBCCoUkIE(InfoExtractor): elif transfer_format == 'dash': pass elif transfer_format == 'hls': - m3u8_formats = self._extract_m3u8_formats( + formats.extend(self._extract_m3u8_formats( href, programme_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id=supplier, fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + m3u8_id=supplier, fatal=False)) # Direct link else: formats.append({ @@ -453,6 +477,7 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = None + duration = None tviplayer = self._search_regex( r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', @@ -465,14 +490,19 @@ class BBCCoUkIE(InfoExtractor): if not programme_id: programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None) if programme_id: formats, subtitles = self._download_media_selector(programme_id) - title = self._og_search_title(webpage) + title = self._og_search_title(webpage, default=None) or self._html_search_regex( + (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>', + r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title') description = self._search_regex( - r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', - webpage, 'description', fatal=False) + (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', + r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'), + webpage, 'description', default=None) + if not description: + description = self._html_search_meta('description', webpage) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -586,6 +616,7 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', 'duration': 56, + 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', }, 'params': { 'skip_download': True, @@ -702,19 +733,10 @@ class BBCIE(BBCCoUkIE): webpage = self._download_webpage(url, playlist_id) - timestamp = None - playlist_title = None - playlist_description = None - - ld = self._parse_json( - self._search_regex( - r'(?s)<script type="application/ld\+json">(.+?)</script>', - webpage, 'ld json', default='{}'), - playlist_id, fatal=False) - if ld: - timestamp = parse_iso8601(ld.get('datePublished')) - playlist_title = ld.get('headline') - playlist_description = ld.get('articleBody') + json_ld_info = self._search_json_ld(webpage, playlist_id, default=None) + timestamp = json_ld_info.get('timestamp') + playlist_title = json_ld_info.get('title') + playlist_description = json_ld_info.get('description') if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -728,6 +750,7 @@ class BBCIE(BBCCoUkIE): # article with multiple videos embedded with playlist.sxml (e.g. # http://www.bbc.com/sport/0/football/34475836) playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage) + playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) if playlists: entries = [ self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) @@ -780,8 +803,9 @@ class BBCIE(BBCCoUkIE): # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( - [r'data-video-player-vpid="([\da-z]{8})"', - r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], + [r'data-video-player-vpid="(%s)"' % self._ID_REGEX, + r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX, + r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX], webpage, 'vpid', default=None) if programme_id: @@ -816,7 +840,7 @@ class BBCIE(BBCCoUkIE): # Multiple video article (e.g. # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) - EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' + EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX entries = [] for match in extract_all(r'new\s+SMP\(({.+?})\)'): embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 61bc2f7..34c2a75 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,6 +1,11 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_chr, + compat_ord, + compat_urllib_parse_unquote, +) from ..utils import ( int_or_none, parse_iso8601, @@ -29,7 +34,38 @@ class BeegIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://beeg.com/api/v1/video/%s' % video_id, video_id) + 'https://api.beeg.com/api/v5/video/%s' % video_id, video_id) + + def split(o, e): + def cut(s, x): + n.append(s[:x]) + return s[x:] + n = [] + r = len(o) % e + if r > 0: + o = cut(o, r) + while len(o) > e: + o = cut(o, e) + n.append(o) + return n + + def decrypt_key(key): + # Reverse engineered from http://static.beeg.com/cpl/1105.js + a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB' + e = compat_urllib_parse_unquote(key) + o = ''.join([ + compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) + for n in range(len(e))]) + return ''.join(split(o, 3)[::-1]) + + def decrypt_url(encrypted_url): + encrypted_url = self._proto_relative_url( + encrypted_url.replace('{DATA_MARKERS}', ''), 'https:') + key = self._search_regex( + r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) + if not key: + return encrypted_url + return encrypted_url.replace(key, decrypt_key(key)) formats = [] for format_id, video_url in video.items(): @@ -40,7 +76,7 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'), + 'url': decrypt_url(video_url), 'format_id': format_id, 'height': int(height), }) diff --git a/youtube_dl/extractor/bigflix.py b/youtube_dl/extractor/bigflix.py new file mode 100644 index 0000000..33762ad --- /dev/null +++ b/youtube_dl/extractor/bigflix.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import base64 +import re + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote + + +class BigflixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537', + 'md5': 'ec76aa9b1129e2e5b301a474e54fab74', + 'info_dict': { + 'id': '16537', + 'ext': 'mp4', + 'title': 'Singham Returns', + 'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d', + } + }, { + # 2 formats + 'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070', + 'info_dict': { + 'id': '16070', + 'ext': 'mp4', + 'title': 'Madarasapatinam', + 'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca', + 'formats': 'mincount:2', + }, + 'params': { + 'skip_download': True, + } + }, { + # multiple formats + 'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>', + webpage, 'title') + + def decode_url(quoted_b64_url): + return base64.b64decode(compat_urllib_parse_unquote( + quoted_b64_url).encode('ascii')).decode('utf-8') + + formats = [] + for height, encoded_url in re.findall( + r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage): + video_url = decode_url(encoded_url) + f = { + 'url': video_url, + 'format_id': '%sp' % height, + 'height': int(height), + } + if video_url.startswith('rtmp'): + f['ext'] = 'flv' + formats.append(f) + + file_url = self._search_regex( + r'file=([^&]+)', webpage, 'video url', default=None) + if file_url: + video_url = decode_url(file_url) + if all(f['url'] != video_url for f in formats): + formats.append({ + 'url': decode_url(file_url), + }) + + self._sort_formats(formats) + + description = self._html_search_meta('description', webpage) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'formats': formats + } diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 6c66a12..59beb11 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -2,143 +2,109 @@ from __future__ import unicode_literals import re -import itertools -import json from .common import InfoExtractor -from ..compat import ( - compat_etree_fromstring, -) +from ..compat import compat_str from ..utils import ( int_or_none, - unified_strdate, + unescapeHTML, ExtractorError, + xpath_text, ) class BiliBiliIE(InfoExtractor): - _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/' + _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', 'md5': '2c301e4dab317596e837c3e7633e7d86', 'info_dict': { - 'id': '1074402_part1', + 'id': '1554319', 'ext': 'flv', 'title': '【金坷垃】金泡沫', - 'duration': 308, + 'duration': 308313, 'upload_date': '20140420', 'thumbnail': 're:^https?://.+\.jpg', + 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', + 'timestamp': 1397983878, + 'uploader': '菊子桑', }, }, { 'url': 'http://www.bilibili.com/video/av1041170/', 'info_dict': { 'id': '1041170', 'title': '【BD1080P】刀语【诸神&异域】', + 'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~', + 'uploader': '枫叶逝去', + 'timestamp': 1396501299, }, 'playlist_count': 9, }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - 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') - - title = self._html_search_meta( - 'media:title', video_code, 'title', fatal=True) - duration_str = self._html_search_meta( - 'duration', video_code, 'duration') - if duration_str is None: - duration = None - else: - duration_mobj = re.match( - r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$', - duration_str) - duration = ( - int_or_none(duration_mobj.group('hours'), default=0) * 3600 + - int(duration_mobj.group('minutes')) * 60 + - int(duration_mobj.group('seconds'))) - upload_date = unified_strdate(self._html_search_meta( - 'uploadDate', video_code, fatal=False)) - thumbnail = self._html_search_meta( - 'thumbnailUrl', video_code, 'thumbnail', fatal=False) - - cid = self._search_regex(r'cid=(\d+)', webpage, 'cid') - - entries = [] - - lq_page = self._download_webpage( - 'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid, - video_id, - note='Downloading LQ video info' + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + page_num = mobj.group('page_num') or '1' + + view_data = self._download_json( + 'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num), + video_id) + if 'error' in view_data: + raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True) + + cid = view_data['cid'] + title = unescapeHTML(view_data['title']) + + doc = self._download_xml( + 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, + cid, + 'Downloading page %s/%s' % (page_num, view_data['pages']) ) - try: - err_info = json.loads(lq_page) - raise ExtractorError( - 'BiliBili said: ' + err_info['error_text'], expected=True) - except ValueError: - pass - lq_doc = compat_etree_fromstring(lq_page) - lq_durls = lq_doc.findall('./durl') + if xpath_text(doc, './result') == 'error': + raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True) - hq_doc = self._download_xml( - 'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid, - video_id, - note='Downloading HQ video info', - fatal=False, - ) - if hq_doc is not False: - hq_durls = hq_doc.findall('./durl') - assert len(lq_durls) == len(hq_durls) - else: - hq_durls = itertools.repeat(None) + entries = [] - i = 1 - for lq_durl, hq_durl in zip(lq_durls, hq_durls): + for durl in doc.findall('./durl'): + size = xpath_text(durl, ['./filesize', './size']) formats = [{ - 'format_id': 'lq', - 'quality': 1, - 'url': lq_durl.find('./url').text, - 'filesize': int_or_none( - lq_durl.find('./size'), get_attr='text'), + 'url': durl.find('./url').text, + 'filesize': int_or_none(size), + 'ext': 'flv', }] - if hq_durl is not None: - formats.append({ - 'format_id': 'hq', - 'quality': 2, - 'ext': 'flv', - 'url': hq_durl.find('./url').text, - 'filesize': int_or_none( - hq_durl.find('./size'), get_attr='text'), - }) - self._sort_formats(formats) + backup_urls = durl.find('./backup_url') + if backup_urls is not None: + for backup_url in backup_urls.findall('./url'): + formats.append({'url': backup_url.text}) + formats.reverse() entries.append({ - 'id': '%s_part%d' % (video_id, i), + 'id': '%s_part%s' % (cid, xpath_text(durl, './order')), 'title': title, + 'duration': int_or_none(xpath_text(durl, './length'), 1000), 'formats': formats, - 'duration': duration, - 'upload_date': upload_date, - 'thumbnail': thumbnail, }) - i += 1 - - return { - '_type': 'multi_video', - 'entries': entries, - 'id': video_id, - 'title': title + info = { + 'id': compat_str(cid), + 'title': title, + 'description': view_data.get('description'), + 'thumbnail': view_data.get('pic'), + 'uploader': view_data.get('author'), + 'timestamp': int_or_none(view_data.get('created')), + 'view_count': int_or_none(view_data.get('play')), + 'duration': int_or_none(xpath_text(doc, './timelength')), } + + if len(entries) == 1: + entries[0].update(info) + return entries[0] + else: + info.update({ + '_type': 'multi_video', + 'id': video_id, + 'entries': entries, + }) + return info diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py new file mode 100644 index 0000000..38bda3a --- /dev/null +++ b/youtube_dl/extractor/bleacherreport.py @@ -0,0 +1,106 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .amp import AMPIE +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, +) + + +class BleacherReportIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football', + 'md5': 'a3ffc3dc73afdbc2010f02d98f990f20', + 'info_dict': { + 'id': '2496438', + 'ext': 'mp4', + 'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?', + 'uploader_id': 3992341, + 'description': 'CFB, ACC, Florida State', + 'timestamp': 1434380212, + 'upload_date': '20150615', + 'uploader': 'Team Stream Now ', + }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo', + 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50', + 'info_dict': { + 'id': '2586817', + 'ext': 'mp4', + 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', + 'timestamp': 1446839961, + 'uploader': 'Sean Fay', + 'description': 'md5:825e94e0f3521df52fa83b2ed198fa20', + 'uploader_id': 6466954, + 'upload_date': '20151011', + }, + 'add_ie': ['Youtube'], + }] + + def _real_extract(self, url): + article_id = self._match_id(url) + + article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article'] + + thumbnails = [] + primary_photo = article_data.get('primaryPhoto') + if primary_photo: + thumbnails = [{ + 'url': primary_photo['url'], + 'width': primary_photo.get('width'), + 'height': primary_photo.get('height'), + }] + + info = { + '_type': 'url_transparent', + 'id': article_id, + 'title': article_data['title'], + 'uploader': article_data.get('author', {}).get('name'), + 'uploader_id': article_data.get('authorId'), + 'timestamp': parse_iso8601(article_data.get('createdAt')), + 'thumbnails': thumbnails, + 'comment_count': int_or_none(article_data.get('commentsCount')), + 'view_count': int_or_none(article_data.get('hitCount')), + } + + video = article_data.get('video') + if video: + video_type = video['type'] + if video_type == 'cms.bleacherreport.com': + info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id'] + elif video_type == 'ooyala.com': + info['url'] = 'ooyala:%s' % video['id'] + elif video_type == 'youtube.com': + info['url'] = video['id'] + elif video_type == 'vine.co': + info['url'] = 'https://vine.co/v/%s' % video['id'] + else: + info['url'] = video_type + video['id'] + return info + else: + raise ExtractorError('no video in the article', expected=True) + + +class BleacherReportCMSIE(AMPIE): + _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})' + _TESTS = [{ + 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1', + 'md5': '8c2c12e3af7805152675446c905d159b', + 'info_dict': { + 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', + 'ext': 'flv', + 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', + 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id) + info['id'] = video_id + return info diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py deleted file mode 100644 index 35375f7..0000000 --- a/youtube_dl/extractor/bliptv.py +++ /dev/null @@ -1,290 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - -from ..compat import compat_urlparse -from ..utils import ( - clean_html, - int_or_none, - parse_iso8601, - sanitized_Request, - unescapeHTML, - xpath_text, - xpath_with_ns, -) - - -class BlipTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))' - - _TESTS = [ - { - 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', - 'md5': '80baf1ec5c3d2019037c1c707d676b9f', - 'info_dict': { - 'id': '5779306', - 'ext': 'm4v', - 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3', - 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596', - 'timestamp': 1323138843, - 'upload_date': '20111206', - 'uploader': 'cbr', - 'uploader_id': '679425', - 'duration': 81, - } - }, - { - # https://github.com/rg3/youtube-dl/pull/2274 - 'note': 'Video with subtitles', - 'url': 'http://blip.tv/play/h6Uag5OEVgI.html', - 'md5': '309f9d25b820b086ca163ffac8031806', - 'info_dict': { - 'id': '6586561', - 'ext': 'mp4', - 'title': 'Red vs. Blue Season 11 Episode 1', - 'description': 'One-Zero-One', - 'timestamp': 1371261608, - 'upload_date': '20130615', - 'uploader': 'redvsblue', - 'uploader_id': '792887', - 'duration': 279, - } - }, - { - # https://bugzilla.redhat.com/show_bug.cgi?id=967465 - 'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI', - 'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6', - 'info_dict': { - 'id': '6573122', - 'ext': 'mov', - 'upload_date': '20130520', - 'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.', - 'title': 'Red vs. Blue Season 11 Trailer', - 'timestamp': 1369029609, - 'uploader': 'redvsblue', - 'uploader_id': '792887', - } - }, - { - 'url': 'http://blip.tv/play/gbk766dkj4Yn', - 'md5': 'fe0a33f022d49399a241e84a8ea8b8e3', - 'info_dict': { - 'id': '1749452', - 'ext': 'mp4', - 'upload_date': '20090208', - 'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.', - 'title': 'Nostalgia Critic: Transformers', - 'timestamp': 1234068723, - 'uploader': 'NostalgiaCritic', - 'uploader_id': '246467', - } - }, - { - # https://github.com/rg3/youtube-dl/pull/4404 - 'note': 'Audio only', - 'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982', - 'md5': '76c0a56f24e769ceaab21fbb6416a351', - 'info_dict': { - 'id': '7103299', - 'ext': 'flv', - 'title': 'Weekly Manga Recap: Kingdom', - 'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?', - 'timestamp': 1417660321, - 'upload_date': '20141204', - 'uploader': 'The Rollo T', - 'uploader_id': '407429', - 'duration': 7251, - '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 - def _extract_url(webpage): - mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) - if mobj: - return 'http://blip.tv/a/a-' + mobj.group(1) - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) - if mobj: - return mobj.group(1) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - lookup_id = mobj.group('lookup_id') - - # See https://github.com/rg3/youtube-dl/issues/857 and - # https://github.com/rg3/youtube-dl/issues/4197 - if lookup_id: - urlh = self._request_webpage( - 'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id') - url = compat_urlparse.urlparse(urlh.geturl()) - qs = compat_urlparse.parse_qs(url.query) - mobj = re.match(self._VALID_URL, qs['file'][0]) - - video_id = mobj.group('id') - - rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS') - - 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') - - 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 = {} - - media_group = item.find(_x('media:group')) - for media_content in media_group.findall(_x('media:content')): - url = media_content.get('url') - 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) - real_url = compat_urlparse.parse_qs(msg.strip())['message'][0] - - media_type = media_content.get('type') - if media_type == 'text/srt' or url.endswith('.srt'): - LANGS = { - 'english': 'en', - } - lang = role.rpartition('-')[-1].strip().lower() - langcode = LANGS.get(lang, lang) - subtitles_urls[langcode] = url - elif media_type.startswith('video/'): - formats.append({ - 'url': real_url, - 'format_id': role, - 'format_note': media_type, - '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')), - }) - self._check_formats(formats, video_id) - self._sort_formats(formats) - - subtitles = self.extract_subtitles(video_id, subtitles_urls) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'duration': duration, - 'thumbnail': thumbnail, - 'categories': categories, - 'formats': formats, - 'subtitles': subtitles, - } - - def _get_subtitles(self, video_id, subtitles_urls): - subtitles = {} - for lang, url in subtitles_urls.items(): - # For some weird reason, blip.tv serves a video instead of subtitles - # when we request with a common UA - req = sanitized_Request(url) - req.add_header('User-Agent', 'youtube-dl') - subtitles[lang] = [{ - # The extension is 'srt' but it's actually an 'ass' file - 'ext': 'ass', - 'data': self._download_webpage(req, None, note=False), - }] - return subtitles - - -class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' - _PAGE_SIZE = 12 - IE_NAME = 'blip.tv:user' - _TEST = { - 'url': 'http://blip.tv/actone', - 'info_dict': { - 'id': 'actone', - 'title': 'Act One: The Series', - }, - 'playlist_count': 5, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - username = mobj.group(1) - - page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' - - page = self._download_webpage(url, username, 'Downloading user page') - mobj = re.search(r'data-users-id="([^"]+)"', page) - page_base = page_base % mobj.group(1) - title = self._og_search_title(page) - - # Download video ids using BlipTV Ajax calls. Result size per - # query is limited (currently to 12 videos) so we need to query - # page by page until there are no video ids - it means we got - # all of them. - - video_ids = [] - pagenum = 1 - - while True: - url = page_base + "&page=" + str(pagenum) - page = self._download_webpage( - url, username, 'Downloading video ids from page %d' % pagenum) - - # Extract video identifiers - ids_in_page = [] - - for mobj in re.finditer(r'href="/([^"]+)"', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(unescapeHTML(mobj.group(1))) - - video_ids.extend(ids_in_page) - - # A little optimization - if current page is not - # "full", ie. does not contain PAGE_SIZE video ids then - # we can assume that this page is the last one - there - # are no more ids on further pages - no need to query - # again. - - if len(ids_in_page) < self._PAGE_SIZE: - break - - pagenum += 1 - - urls = ['http://blip.tv/%s' % video_id for video_id in video_ids] - url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] - return self.playlist_result( - url_entries, playlist_title=title, playlist_id=username) diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 11ace91..13343bc 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)' _TESTS = [{ 'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2', @@ -20,22 +20,32 @@ class BloombergIE(InfoExtractor): }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, + }, { + 'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump', + 'only_matching': True, }] def _real_extract(self, url): name = self._match_id(url) webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id') + video_id = self._search_regex( + r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1', + webpage, 'id', group='url') title = re.sub(': Video$', '', self._og_search_title(webpage)) embed_info = self._download_json( 'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id) formats = [] for stream in embed_info['streams']: - if stream["muxing_format"] == "TS": - formats.extend(self._extract_m3u8_formats(stream['url'], video_id)) + stream_url = stream.get('url') + if not stream_url: + continue + if stream['muxing_format'] == 'TS': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) else: - formats.extend(self._extract_f4m_formats(stream['url'], video_id)) + formats.extend(self._extract_f4m_formats( + stream_url, video_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/bpb.py b/youtube_dl/extractor/bpb.py index 510813f..c28e729 100644 --- a/youtube_dl/extractor/bpb.py +++ b/youtube_dl/extractor/bpb.py @@ -1,7 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..utils import ( + js_to_json, + determine_ext, +) class BpbIE(InfoExtractor): @@ -10,7 +16,8 @@ class BpbIE(InfoExtractor): _TEST = { 'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr', - 'md5': '0792086e8e2bfbac9cdf27835d5f2093', + # md5 fails in Python 2.6 due to buggy server response and wrong handling of urllib2 + 'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f', 'info_dict': { 'id': '297', 'ext': 'mp4', @@ -25,13 +32,26 @@ class BpbIE(InfoExtractor): title = self._html_search_regex( r'<h2 class="white">(.*?)</h2>', webpage, 'title') - video_url = self._html_search_regex( - r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)', - webpage, 'video URL') + video_info_dicts = re.findall( + r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage) + + formats = [] + for video_info in video_info_dicts: + video_info = self._parse_json(video_info, video_id, transform_source=js_to_json) + quality = video_info['quality'] + video_url = video_info['src'] + formats.append({ + 'url': video_url, + 'preference': 10 if quality == 'high' else 0, + 'format_note': quality, + 'format_id': '%s-%s' % (quality, determine_ext(video_url)), + }) + + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, + 'formats': formats, 'title': title, 'description': self._og_search_description(webpage), } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 66e394e..11cf498 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -1,18 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, parse_duration, + xpath_element, + xpath_text, ) class BRIE(InfoExtractor): IE_DESC = 'Bayerischer Rundfunk Mediathek' - _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' - _BASE_URL = 'http://www.br.de' + _VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html' _TESTS = [ { @@ -22,7 +25,7 @@ class BRIE(InfoExtractor): 'id': '48f656ef-287e-486f-be86-459122db22cc', 'ext': 'mp4', 'title': 'Die böse Überraschung', - 'description': 'Betriebliche Altersvorsorge: Die böse Überraschung', + 'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9', 'duration': 180, 'uploader': 'Reinhard Weber', 'upload_date': '20150422', @@ -30,23 +33,23 @@ class BRIE(InfoExtractor): }, { 'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html', - 'md5': 'a44396d73ab6a68a69a568fae10705bb', + 'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef', 'info_dict': { 'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Manfred Schreiber ist tot', - 'description': 'Abendschau kompakt: Manfred Schreiber ist tot', + 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97', 'duration': 26, } }, { - 'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html', + 'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html', 'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d', 'info_dict': { 'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b', 'ext': 'aac', 'title': 'Kurzweilig und sehr bewegend', - 'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend', + 'description': 'md5:0351996e3283d64adeb38ede91fac54e', 'duration': 296, } }, @@ -57,7 +60,7 @@ class BRIE(InfoExtractor): 'id': '6ba73750-d405-45d3-861d-1ce8c524e059', 'ext': 'mp4', 'title': 'Umweltbewusster Häuslebauer', - 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer', + 'description': 'md5:d52dae9792d00226348c1dbb13c9bae2', 'duration': 116, } }, @@ -68,7 +71,7 @@ class BRIE(InfoExtractor): 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d', 'ext': 'mp4', 'title': 'Folge 1 - Metaphysik', - 'description': 'Kant für Anfänger: Folge 1 - Metaphysik', + 'description': 'md5:bb659990e9e59905c3d41e369db1fbe3', 'duration': 893, 'uploader': 'Eva Maria Steimle', 'upload_date': '20140117', @@ -77,28 +80,31 @@ class BRIE(InfoExtractor): ] def _real_extract(self, url): - display_id = self._match_id(url) + base_url, display_id = re.search(self._VALID_URL, url).groups() page = self._download_webpage(url, display_id) xml_url = self._search_regex( r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL') - xml = self._download_xml(self._BASE_URL + xml_url, None) + xml = self._download_xml(base_url + xml_url, display_id) medias = [] for xml_media in xml.findall('video') + xml.findall('audio'): + media_id = xml_media.get('externalId') media = { - 'id': xml_media.get('externalId'), - 'title': xml_media.find('title').text, - 'duration': parse_duration(xml_media.find('duration').text), - 'formats': self._extract_formats(xml_media.find('assets')), - 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')), - 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()), - 'webpage_url': xml_media.find('permalink').text + 'id': media_id, + 'title': xpath_text(xml_media, 'title', 'title', True), + 'duration': parse_duration(xpath_text(xml_media, 'duration')), + 'formats': self._extract_formats(xpath_element( + xml_media, 'assets'), media_id), + 'thumbnails': self._extract_thumbnails(xpath_element( + xml_media, 'teaserImage/variants'), base_url), + 'description': xpath_text(xml_media, 'desc'), + 'webpage_url': xpath_text(xml_media, 'permalink'), + 'uploader': xpath_text(xml_media, 'author'), } - if xml_media.find('author').text: - media['uploader'] = xml_media.find('author').text - if xml_media.find('broadcastDate').text: - media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.'))) + broadcast_date = xpath_text(xml_media, 'broadcastDate') + if broadcast_date: + media['upload_date'] = ''.join(reversed(broadcast_date.split('.'))) medias.append(media) if len(medias) > 1: @@ -109,35 +115,54 @@ class BRIE(InfoExtractor): raise ExtractorError('No media entries found') return medias[0] - def _extract_formats(self, assets): - - def text_or_none(asset, tag): - elem = asset.find(tag) - return None if elem is None else elem.text - - formats = [{ - 'url': text_or_none(asset, 'downloadUrl'), - 'ext': text_or_none(asset, 'mediaType'), - 'format_id': asset.get('type'), - 'width': int_or_none(text_or_none(asset, 'frameWidth')), - 'height': int_or_none(text_or_none(asset, 'frameHeight')), - 'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')), - 'abr': int_or_none(text_or_none(asset, 'bitrateAudio')), - 'vcodec': text_or_none(asset, 'codecVideo'), - 'acodec': text_or_none(asset, 'codecAudio'), - 'container': text_or_none(asset, 'mediaType'), - 'filesize': int_or_none(text_or_none(asset, 'size')), - } for asset in assets.findall('asset') - if asset.find('downloadUrl') is not None] - + def _extract_formats(self, assets, media_id): + formats = [] + for asset in assets.findall('asset'): + format_url = xpath_text(asset, ['downloadUrl', 'url']) + asset_type = asset.get('type') + if asset_type == 'HDS': + formats.extend(self._extract_f4m_formats( + format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False)) + elif asset_type == 'HLS': + formats.extend(self._extract_m3u8_formats( + format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False)) + else: + format_info = { + 'ext': xpath_text(asset, 'mediaType'), + 'width': int_or_none(xpath_text(asset, 'frameWidth')), + 'height': int_or_none(xpath_text(asset, 'frameHeight')), + 'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')), + 'abr': int_or_none(xpath_text(asset, 'bitrateAudio')), + 'vcodec': xpath_text(asset, 'codecVideo'), + 'acodec': xpath_text(asset, 'codecAudio'), + 'container': xpath_text(asset, 'mediaType'), + 'filesize': int_or_none(xpath_text(asset, 'size')), + } + format_url = self._proto_relative_url(format_url) + if format_url: + http_format_info = format_info.copy() + http_format_info.update({ + 'url': format_url, + 'format_id': 'http-%s' % asset_type, + }) + formats.append(http_format_info) + server_prefix = xpath_text(asset, 'serverPrefix') + if server_prefix: + rtmp_format_info = format_info.copy() + rtmp_format_info.update({ + 'url': server_prefix, + 'play_path': xpath_text(asset, 'fileName'), + 'format_id': 'rtmp-%s' % asset_type, + }) + formats.append(rtmp_format_info) self._sort_formats(formats) return formats - def _extract_thumbnails(self, variants): + def _extract_thumbnails(self, variants, base_url): thumbnails = [{ - 'url': self._BASE_URL + variant.find('url').text, - 'width': int_or_none(variant.find('width').text), - 'height': int_or_none(variant.find('height').text), - } for variant in variants.findall('variant')] + 'url': base_url + xpath_text(variant, 'url'), + 'width': int_or_none(xpath_text(variant, 'width')), + 'height': int_or_none(xpath_text(variant, 'height')), + } for variant in variants.findall('variant') if xpath_text(variant, 'url')] thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True) return thumbnails diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index f5ebae1..c947337 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -355,7 +355,7 @@ class BrightcoveLegacyIE(InfoExtractor): class BrightcoveNewIE(InfoExtractor): IE_NAME = 'brightcove:new' - _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+)' + _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)' _TESTS = [{ 'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001', 'md5': 'c8100925723840d4b0d243f7025703be', @@ -387,14 +387,24 @@ class BrightcoveNewIE(InfoExtractor): 'params': { 'skip_download': True, } + }, { + # ref: prefixed video id + 'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442', + 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + urls = BrightcoveNewIE._extract_urls(webpage) + return urls[0] if urls else None + @staticmethod def _extract_urls(webpage): # Reference: # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe - # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript) + # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html + # 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player entries = [] @@ -407,9 +417,10 @@ class BrightcoveNewIE(InfoExtractor): for video_id, account_id, player_id, embed in re.findall( # According to examples from [3] it's unclear whether video id # may be optional and what to do when it is + # According to [4] data-video-id may be prefixed with ref: r'''(?sx) <video[^>]+ - data-video-id=["\'](\d+)["\'][^>]*>.*? + data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*? </video>.*? <script[^>]+ src=["\'](?:https?:)?//players\.brightcove\.net/ @@ -458,11 +469,9 @@ class BrightcoveNewIE(InfoExtractor): if source_type == 'application/x-mpegURL': if not src: continue - m3u8_formats = self._extract_m3u8_formats( + formats.extend(self._extract_m3u8_formats( src, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + m3u8_id='hls', fatal=False)) else: streaming_src = source.get('streaming_src') stream_name, app_name = source.get('stream_name'), source.get('app_name') diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 3b2de51..dda9805 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor): 'info_dict': { 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', - 'description': 'md5:5438d33774b6bdc662f9485a340401cc', + 'description': 'md5:e07269172baff037f8e8bf9956bc9747', 'title': 'Season 5 Episode 5', - 'thumbnail': 're:^https?://.*\.jpg$' + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 1486.486, }, 'params': { 'skip_download': True, diff --git a/youtube_dl/extractor/canal13cl.py b/youtube_dl/extractor/canal13cl.py deleted file mode 100644 index 93241fe..0000000 --- a/youtube_dl/extractor/canal13cl.py +++ /dev/null @@ -1,48 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - - -class Canal13clIE(InfoExtractor): - _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'md5': '4cb1fa38adcad8fea88487a078831755', - 'info_dict': { - 'id': '1403022125', - 'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'ext': 'mp4', - 'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda', - 'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - - webpage = self._download_webpage(url, display_id) - - title = self._html_search_meta( - 'twitter:title', webpage, 'title', fatal=True) - description = self._html_search_meta( - 'twitter:description', webpage, 'description') - url = self._html_search_regex( - r'articuloVideo = \"(.*?)\"', webpage, 'url') - real_id = self._search_regex( - r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id) - thumbnail = self._html_search_regex( - r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail') - - return { - 'id': real_id, - 'display_id': display_id, - 'url': url, - 'title': title, - 'description': description, - 'ext': 'mp4', - 'thumbnail': thumbnail, - } diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py index f6a1ff3..f1f128c 100644 --- a/youtube_dl/extractor/canalc2.py +++ b/youtube_dl/extractor/canalc2.py @@ -9,9 +9,9 @@ from ..utils import parse_duration class Canalc2IE(InfoExtractor): IE_NAME = 'canalc2.tv' - _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.canalc2.tv/video/12163', 'md5': '060158428b650f896c542dfbb3d6487f', 'info_dict': { @@ -23,24 +23,36 @@ class Canalc2IE(InfoExtractor): 'params': { 'skip_download': True, # Requires rtmpdump } - } + }, { + 'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_url = self._search_regex( - r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2', - webpage, 'video_url', group='file') - formats = [{'url': video_url}] - if video_url.startswith('rtmp://'): - rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url) - formats[0].update({ - 'url': rtmp.group('url'), - 'ext': 'flv', - 'app': rtmp.group('app'), - 'play_path': rtmp.group('play_path'), - 'page_url': url, - }) + + webpage = self._download_webpage( + 'http://www.canalc2.tv/video/%s' % video_id, video_id) + + formats = [] + for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage): + if video_url.startswith('rtmp://'): + rtmp = re.search( + r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url) + formats.append({ + 'url': rtmp.group('url'), + 'format_id': 'rtmp', + 'ext': 'flv', + 'app': rtmp.group('app'), + 'play_path': rtmp.group('play_path'), + 'page_url': url, + }) + else: + formats.append({ + 'url': video_url, + 'format_id': 'http', + }) + self._sort_formats(formats) title = self._html_search_regex( r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title') diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 004372f..25b2d4e 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -10,13 +10,14 @@ from ..utils import ( unified_strdate, url_basename, qualities, + int_or_none, ) class CanalplusIE(InfoExtractor): IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' - _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s' + _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' _SITE_ID_MAP = { 'canalplus.fr': 'cplus', 'piwiplus.fr': 'teletoon', @@ -26,10 +27,10 @@ class CanalplusIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092', - 'md5': 'b3481d7ca972f61e37420798d0a9d934', + 'md5': '12164a6f14ff6df8bd628e8ba9b10b78', 'info_dict': { 'id': '1263092', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Le Zapping - 13/05/15', 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f', 'upload_date': '20150513', @@ -56,10 +57,10 @@ class CanalplusIE(InfoExtractor): 'skip': 'videos get deleted after a while', }, { 'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559', - 'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4', + 'md5': '38b8f7934def74f0d6f3ba6c036a5f82', 'info_dict': { 'id': '1213714', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45', 'description': 'md5:8216206ec53426ea6321321f3b3c16db', 'upload_date': '20150211', @@ -82,15 +83,16 @@ class CanalplusIE(InfoExtractor): webpage, 'video id', group='id') info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id) - doc = self._download_xml(info_url, video_id, 'Downloading video XML') + video_data = self._download_json(info_url, video_id, 'Downloading video JSON') - video_info = [video for video in doc if video.find('ID').text == video_id][0] - media = video_info.find('MEDIA') - infos = video_info.find('INFOS') + if isinstance(video_data, list): + video_data = [video for video in video_data if video.get('ID') == video_id][0] + media = video_data['MEDIA'] + infos = video_data['INFOS'] - preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']) + preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD']) - fmt_url = next(iter(media.find('VIDEOS'))).text + fmt_url = next(iter(media.get('VIDEOS'))) if '/geo' in fmt_url.lower(): response = self._request_webpage( HEADRequest(fmt_url), video_id, @@ -101,35 +103,42 @@ class CanalplusIE(InfoExtractor): expected=True) formats = [] - for fmt in media.find('VIDEOS'): - format_url = fmt.text + for format_id, format_url in media['VIDEOS'].items(): if not format_url: continue - format_id = fmt.tag if format_id == 'HLS': formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', preference=preference(format_id))) + format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False)) elif format_id == 'HDS': formats.extend(self._extract_f4m_formats( - format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id))) + format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False)) else: formats.append({ - 'url': format_url, + # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js + 'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes', 'format_id': format_id, 'preference': preference(format_id), }) self._sort_formats(formats) + thumbnails = [{ + 'id': image_id, + 'url': image_url, + } for image_id, image_url in media.get('images', {}).items()] + + titrage = infos['TITRAGE'] + return { 'id': video_id, 'display_id': display_id, - 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text, - infos.find('TITRAGE/SOUS_TITRE').text), - 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text), - 'thumbnail': media.find('IMAGES/GRAND').text, - 'description': infos.find('DESCRIPTION').text, - 'view_count': int(infos.find('NB_VUES').text), - 'like_count': int(infos.find('NB_LIKES').text), - 'comment_count': int(infos.find('NB_COMMENTS').text), + 'title': '%s - %s' % (titrage['TITRE'], + titrage['SOUS_TITRE']), + 'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')), + 'thumbnails': thumbnails, + 'description': infos.get('DESCRIPTION'), + 'duration': int_or_none(infos.get('DURATION')), + 'view_count': int_or_none(infos.get('NB_VUES')), + 'like_count': int_or_none(infos.get('NB_LIKES')), + 'comment_count': int_or_none(infos.get('NB_COMMENTS')), 'formats': formats, } diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py new file mode 100644 index 0000000..ec6d24d --- /dev/null +++ b/youtube_dl/extractor/canvas.py @@ -0,0 +1,94 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import float_or_none + + +class CanvasIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week', + 'md5': 'ea838375a547ac787d4064d8c7860a6c', + 'info_dict': { + 'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e', + 'display_id': 'de-afspraak-veilt-voor-de-warmste-week', + 'ext': 'mp4', + 'title': 'De afspraak veilt voor de Warmste Week', + 'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 49.02, + } + }, { + # with subtitles + 'url': 'http://www.canvas.be/video/panorama/2016/pieter-0167', + 'info_dict': { + 'id': 'mz-ast-5240ff21-2d30-4101-bba6-92b5ec67c625', + 'display_id': 'pieter-0167', + 'ext': 'mp4', + 'title': 'Pieter 0167', + 'description': 'md5:943cd30f48a5d29ba02c3a104dc4ec4e', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2553.08, + 'subtitles': { + 'nl': [{ + 'ext': 'vtt', + }], + }, + }, + 'params': { + 'skip_download': True, + } + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + title = self._search_regex( + r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>', + webpage, 'title', default=None) or self._og_search_title(webpage) + + video_id = self._html_search_regex( + r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id') + + data = self._download_json( + 'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id) + + formats = [] + for target in data['targetUrls']: + format_url, format_type = target.get('url'), target.get('type') + if not format_url or not format_type: + continue + if format_type == 'HLS': + formats.extend(self._extract_m3u8_formats( + format_url, display_id, entry_protocol='m3u8_native', + ext='mp4', preference=0, fatal=False, m3u8_id=format_type)) + elif format_type == 'HDS': + formats.extend(self._extract_f4m_formats( + format_url, display_id, f4m_id=format_type, fatal=False)) + else: + formats.append({ + 'format_id': format_type, + 'url': format_url, + }) + self._sort_formats(formats) + + subtitles = {} + subtitle_urls = data.get('subtitleUrls') + if isinstance(subtitle_urls, list): + for subtitle in subtitle_urls: + subtitle_url = subtitle.get('url') + if subtitle_url and subtitle.get('type') == 'CLOSED': + subtitles.setdefault('nl', []).append({'url': subtitle_url}) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'formats': formats, + 'duration': float_or_none(data.get('duration'), 1000), + 'thumbnail': data.get('posterImageUrl'), + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py new file mode 100644 index 0000000..d8aa310 --- /dev/null +++ b/youtube_dl/extractor/cbc.py @@ -0,0 +1,113 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import js_to_json + + +class CBCIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)' + _TESTS = [{ + # with mediaId + 'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs', + 'info_dict': { + 'id': '2682904050', + 'ext': 'flv', + 'title': 'Don Cherry – All-Stars', + 'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.', + 'timestamp': 1454475540, + 'upload_date': '20160203', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # with clipId + 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live', + 'info_dict': { + 'id': '2487345465', + 'ext': 'flv', + 'title': 'Robin Williams freestyles on 90 Minutes Live', + 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.', + 'upload_date': '19700101', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # multiple iframes + 'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot', + 'playlist': [{ + 'info_dict': { + 'id': '2680832926', + 'ext': 'flv', + 'title': 'An Eagle\'s-Eye View Off Burrard Bridge', + 'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.', + 'upload_date': '19700101', + }, + }, { + 'info_dict': { + 'id': '2658915080', + 'ext': 'flv', + 'title': 'Fly like an eagle!', + 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower', + 'upload_date': '19700101', + }, + }], + 'params': { + # rtmp download + 'skip_download': True, + }, + }] + + @classmethod + def suitable(cls, url): + return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + player_init = self._search_regex( + r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init', + default=None) + if player_init: + player_info = self._parse_json(player_init, display_id, js_to_json) + media_id = player_info.get('mediaId') + if not media_id: + clip_id = player_info['clipId'] + media_id = self._download_json( + 'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id, + clip_id)['entries'][0]['id'].split('/')[-1] + return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) + else: + entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)] + return self.playlist_result(entries) + + +class CBCPlayerIE(InfoExtractor): + _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)' + _TEST = { + 'url': 'http://www.cbc.ca/player/play/2683190193', + 'info_dict': { + 'id': '2683190193', + 'ext': 'flv', + 'title': 'Gerry Runs a Sweat Shop', + 'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0', + 'timestamp': 1455067800, + 'upload_date': '20160210', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id, + 'ThePlatformFeed', video_id) diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index f9a64a0..7319ee1 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -1,15 +1,17 @@ # encoding: utf-8 from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from .theplatform import ThePlatformIE +from ..utils import ( + parse_duration, + find_xpath_attr, +) -class CBSNewsIE(InfoExtractor): +class CBSNewsIE(ThePlatformIE): IE_DESC = 'CBS News' - _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)' + _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)' _TESTS = [ { @@ -30,56 +32,57 @@ class CBSNewsIE(InfoExtractor): 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', 'info_dict': { 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, + 'subtitles': { + 'en': [{ + 'ext': 'ttml', + }], + }, }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, }, }, ] + def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): + closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL') + return { + 'en': [{ + 'ext': 'ttml', + 'url': closed_caption_e.attrib['value'], + }] + } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else [] + 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) - video_info = json.loads(self._html_search_regex( + video_info = self._parse_json(self._html_search_regex( r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'', - webpage, 'video JSON info')) + webpage, 'video JSON info'), video_id) item = video_info['item'] if 'item' in video_info else video_info title = item.get('articleTitle') or item.get('hed') duration = item.get('duration') thumbnail = item.get('mediaImage') or item.get('thumbnail') + subtitles = {} formats = [] for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: - uri = item.get('media' + format_id + 'URI') - if not uri: + pid = item.get('media' + format_id) + if not pid: continue - fmt = { - 'url': uri, - 'format_id': format_id, - } - if uri.startswith('rtmp'): - play_path = re.sub( - r'{slistFilePath}', '', - uri.split('<break>')[-1].split('{break}')[-1]) - fmt.update({ - 'app': 'ondemand?auth=cbs', - 'play_path': 'mp4:' + play_path, - 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', - 'page_url': 'http://www.cbsnews.com', - 'ext': 'flv', - }) - elif uri.endswith('.m3u8'): - fmt['ext'] = 'mp4' - formats.append(fmt) + release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid + tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid) + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + self._sort_formats(formats) return { 'id': video_id, @@ -87,4 +90,43 @@ class CBSNewsIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, + 'subtitles': subtitles, + } + + +class CBSNewsLiveVideoIE(InfoExtractor): + IE_DESC = 'CBS News Live Videos' + _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)' + + _TEST = { + 'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/', + 'info_dict': { + 'id': 'clinton-sanders-prepare-to-face-off-in-nh', + 'ext': 'flv', + 'title': 'Clinton, Sanders Prepare To Face Off In NH', + 'duration': 334, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_info = self._parse_json(self._html_search_regex( + r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story'] + + hdcore_sign = 'hdcore=3.3.1' + f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id) + if f4m_formats: + for entry in f4m_formats: + # URLs without the extra param induce an 404 error + entry.update({'extra_param_to_segment_url': hdcore_sign}) + + return { + 'id': video_id, + 'title': video_info['headline'], + 'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'), + 'duration': parse_duration(video_info.get('segmentDur')), + 'formats': f4m_formats, } diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index 6924eac..dda2c09 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, + parse_duration, qualities, unified_strdate, ) @@ -12,21 +13,25 @@ from ..utils import ( class CCCIE(InfoExtractor): IE_NAME = 'media.ccc.de' - _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P<id>[0-9]{8,})._[^?#/]*\.html' + _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)' - _TEST = { - 'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video', + _TESTS = [{ + 'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video', 'md5': '3a1eda8f3a29515d27f5adb967d7e740', 'info_dict': { - 'id': '20131228183', + 'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor', 'ext': 'mp4', 'title': 'Introduction to Processor Design', - 'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b', + 'description': 'md5:80be298773966f66d56cb11260b879af', 'thumbnail': 're:^https?://.*\.jpg$', 'view_count': int, - 'upload_date': '20131229', + 'upload_date': '20131228', + 'duration': 3660, } - } + }, { + 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -40,21 +45,25 @@ class CCCIE(InfoExtractor): title = self._html_search_regex( r'(?s)<h1>(.*?)</h1>', webpage, 'title') description = self._html_search_regex( - r"(?s)<p class='description'>(.*?)</p>", + r'(?s)<h3>About</h3>(.+?)<h3>', webpage, 'description', fatal=False) upload_date = unified_strdate(self._html_search_regex( - r"(?s)<span class='[^']*fa-calendar-o'></span>(.*?)</li>", + r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>", webpage, 'upload date', fatal=False)) view_count = int_or_none(self._html_search_regex( r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>", webpage, 'view count', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li', + webpage, 'duration', fatal=False, group='duration')) matches = re.finditer(r'''(?xs) - <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s* + <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s* + <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s* <a\s+download\s+href='(?P<http_url>[^']+)'>\s* (?: .*? - <a\s+href='(?P<torrent_url>[^']+\.torrent)' + <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)' )?''', webpage) formats = [] for m in matches: @@ -62,12 +71,15 @@ class CCCIE(InfoExtractor): format_id = self._search_regex( r'.*/([a-z0-9_-]+)/[^/]*$', m.group('http_url'), 'format id', default=None) + if format_id: + format_id = m.group('lang') + '-' + format_id vcodec = 'h264' if 'h264' in format_id else ( 'none' if format_id in ('mp3', 'opus') else None ) formats.append({ 'format_id': format_id, 'format': format, + 'language': m.group('lang'), 'url': m.group('http_url'), 'vcodec': vcodec, 'preference': preference(format_id), @@ -95,5 +107,6 @@ class CCCIE(InfoExtractor): 'thumbnail': thumbnail, 'view_count': view_count, 'upload_date': upload_date, + 'duration': duration, 'formats': formats, } diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 6f7b2a7..b27b4e6 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -177,16 +177,16 @@ class CeskaTelevizeIE(InfoExtractor): for divider in [1000, 60, 60, 100]: components.append(msec % divider) msec //= divider - return "{3:02}:{2:02}:{1:02},{0:03}".format(*components) + return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components) def _fix_subtitle(subtitle): for line in subtitle.splitlines(): - m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line) + m = re.match(r'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line) if m: yield m.group(1) start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:]) - yield "{0} --> {1}".format(start, stop) + yield '{0} --> {1}'.format(start, stop) else: yield line - return "\r\n".join(_fix_subtitle(subtitles)) + return '\r\n'.join(_fix_subtitle(subtitles)) diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 0b67ba6..242fba3 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -23,6 +23,8 @@ class ChaturbateIE(InfoExtractor): 'only_matching': True, }] + _ROOM_OFFLINE = 'Room is currently offline' + def _real_extract(self, url): video_id = self._match_id(url) @@ -34,9 +36,16 @@ class ChaturbateIE(InfoExtractor): if not m3u8_url: error = self._search_regex( - r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>', - webpage, 'error', group='error') - raise ExtractorError(error, expected=True) + [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>', + r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'], + webpage, 'error', group='error', default=None) + if not error: + if any(p not in webpage for p in ( + self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')): + error = self._ROOM_OFFLINE + if error: + raise ExtractorError(error, expected=True) + raise ExtractorError('Unable to find stream URL') formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index fd1770d..6d9cd8a 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..utils import ExtractorError -from .bliptv import BlipTVIE from .screenwavemedia import ScreenwaveMediaIE @@ -34,18 +33,17 @@ class CinemassacreIE(InfoExtractor): }, }, { - # blip.tv embedded video + # Youtube embedded video 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de', + 'md5': 'df4cf8a1dcedaec79a73d96d83b99023', 'info_dict': { - 'id': '4065369', - 'ext': 'flv', + 'id': 'OEVzPCY2T-g', + 'ext': 'mp4', 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', 'upload_date': '20061207', - 'uploader': 'cinemassacre', - 'uploader_id': '250778', - 'timestamp': 1283233867, - 'description': 'md5:0a108c78d130676b207d0f6d029ecffd', + 'uploader': 'Cinemassacre', + 'uploader_id': 'JamesNintendoNerd', + 'description': 'md5:784734696c2b8b7f4b8625cc799e07f6', } }, { @@ -88,8 +86,6 @@ class CinemassacreIE(InfoExtractor): r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', ], webpage, 'player data URL', default=None, group='url') - if not playerdata_url: - playerdata_url = BlipTVIE._extract_url(webpage) if not playerdata_url: raise ExtractorError('Unable to find player data') diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 7af9035..3a47f6f 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,14 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - determine_ext, int_or_none, - js_to_json, - parse_iso8601, - remove_end, + unified_strdate, ) @@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor): 'id': '3966754', 'ext': 'mp4', 'title': 'FIFA 14 - E3 2013 Trailer', - 'timestamp': 1370938118, + 'description': 'Video zu FIFA 14: E3 2013 Trailer', 'upload_date': '20130611', 'duration': 82, + 'view_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_info = self._parse_json( - js_to_json(self._html_search_regex( - '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')), - video_id) + video_info = self._download_json( + 'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id, + video_id)['items'][0] formats = [] - for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage): - ext = determine_ext(video_url) - if ext == 'm3u8': - formats.append({ - 'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), - 'ext': 'mp4', - 'format_id': 'hls', - }) - else: - formats.append({ - 'url': video_url, - 'format_id': ext, - }) - self._sort_formats(formats) - title = remove_end(self._og_search_title(webpage), ' - Video') - thumbnail = self._og_search_thumbnail(webpage) - duration = int_or_none(video_info.get('length')) - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date')) + m3u8_url = video_info.get('media_videourl_hls') + if m3u8_url: + formats.append({ + 'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), + 'ext': 'mp4', + 'format_id': 'hls', + }) + + mp4_url = video_info.get('media_videourl') + if mp4_url: + formats.append({ + 'url': mp4_url, + 'format_id': 'mp4', + 'width': int_or_none(video_info.get('width')), + 'height': int_or_none(video_info.get('height')), + 'tbr': int_or_none(video_info.get('bitrate')), + }) return { 'id': video_id, - 'title': title, + 'title': video_info['title'], + 'description': video_info.get('descr'), 'formats': formats, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, + 'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'), + 'duration': int_or_none(video_info.get('media_length')), + 'upload_date': unified_strdate(video_info.get('pubDate')), + 'view_count': int_or_none(video_info.get('media_views')) } diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index d46592c..2996b6b 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,7 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext +from ..utils import int_or_none _translation_table = { @@ -42,31 +42,26 @@ class CliphunterIE(InfoExtractor): video_title = self._search_regex( r'mediaTitle = "([^"]+)"', webpage, 'title') - fmts = {} - for fmt in ('mp4', 'flv'): - fmt_list = self._parse_json(self._search_regex( - r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id) - for f in fmt_list: - fmts[f['fname']] = _decode(f['sUrl']) - - qualities = self._parse_json(self._search_regex( - r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id) + gexo_files = self._parse_json( + self._search_regex( + r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), + video_id) formats = [] - for fname, url in fmts.items(): - f = { - 'url': url, - } - if fname in qualities: - qual = qualities[fname] - f.update({ - 'format_id': '%s_%sp' % (determine_ext(url), qual['h']), - 'width': qual['w'], - 'height': qual['h'], - 'tbr': qual['br'], - }) - formats.append(f) - + for format_id, f in gexo_files.items(): + video_url = f.get('url') + if not video_url: + continue + fmt = f.get('fmt') + height = f.get('h') + format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id + formats.append({ + 'url': _decode(video_url), + 'format_id': format_id, + 'width': int_or_none(f.get('w')), + 'height': int_or_none(height), + 'tbr': int_or_none(f.get('br')), + }) self._sort_formats(formats) thumbnail = self._search_regex( diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 5dd69bf..5c3908f 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -1,15 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import json +from .theplatform import ThePlatformIE +from ..utils import int_or_none -from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) - -class CNETIE(InfoExtractor): +class CNETIE(ThePlatformIE): _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _TESTS = [{ 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', @@ -18,25 +14,20 @@ class CNETIE(InfoExtractor): 'ext': 'flv', 'title': 'Hands-on with Microsoft Windows 8.1 Update', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', - 'thumbnail': 're:^http://.*/flmswindows8.jpg$', 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', 'uploader': 'Sarah Mitroff', + 'duration': 70, }, - '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', + 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', '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 + 'duration': 1482, }, }] @@ -45,26 +36,13 @@ class CNETIE(InfoExtractor): webpage = self._download_webpage(url, display_id) data_json = self._html_search_regex( - r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", + r"data-cnet-video(?:-uvp)?-options='([^']+)'", webpage, 'data json') - data = json.loads(data_json) - vdata = data['video'] - if not vdata: - vdata = data['videos'][0] - if not vdata: - raise ExtractorError('Cannot find video data') - - mpx_account = data['config']['players']['default']['mpx_account'] - vid = vdata['files'].get('rtmp', vdata['files']['hds']) - tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid) + data = self._parse_json(data_json, display_id) + vdata = data.get('video') or data['videos'][0] video_id = vdata['id'] - title = vdata.get('headline') - if title is None: - title = vdata.get('title') - if title is None: - raise ExtractorError('Cannot find title!') - thumbnail = vdata.get('image', {}).get('path') + title = vdata['title'] author = vdata.get('author') if author: uploader = '%s %s' % (author['firstName'], author['lastName']) @@ -73,13 +51,34 @@ class CNETIE(InfoExtractor): uploader = None uploader_id = None + mpx_account = data['config']['uvpConfig']['default']['mpx_account'] + + metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id) + description = vdata.get('description') or metadata.get('description') + duration = int_or_none(vdata.get('duration')) or metadata.get('duration') + + formats = [] + subtitles = {} + for (fkey, vid) in vdata['files'].items(): + if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: + continue + release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid) + if fkey == 'hds': + release_url += '&manifest=f4m' + tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey) + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + self._sort_formats(formats) + return { - '_type': 'url_transparent', - 'url': tp_link, 'id': video_id, 'display_id': display_id, 'title': title, + 'description': description, + 'thumbnail': metadata.get('thumbnail'), + 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'thumbnail': thumbnail, + 'subtitles': subtitles, + 'formats': formats, } diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 3b1bd40..53489a1 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -26,14 +26,14 @@ class CNNIE(InfoExtractor): 'upload_date': '20130609', }, }, { - "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", - "md5": "b5cc60c60a3477d185af8f19a2a26f4e", - "info_dict": { + 'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29', + 'md5': 'b5cc60c60a3477d185af8f19a2a26f4e', + 'info_dict': { 'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology', 'ext': 'mp4', - "title": "Student's epic speech stuns new freshmen", - "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", - "upload_date": "20130821", + 'title': "Student's epic speech stuns new freshmen", + 'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", + 'upload_date': '20130821', } }, { 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html', diff --git a/youtube_dl/extractor/collegerama.py b/youtube_dl/extractor/collegerama.py index 40667a0..f9e8419 100644 --- a/youtube_dl/extractor/collegerama.py +++ b/youtube_dl/extractor/collegerama.py @@ -46,9 +46,9 @@ class CollegeRamaIE(InfoExtractor): video_id = self._match_id(url) player_options_request = { - "getPlayerOptionsRequest": { - "ResourceId": video_id, - "QueryString": "", + 'getPlayerOptionsRequest': { + 'ResourceId': video_id, + 'QueryString': '', } } diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py index 81f3d76..7dff684 100644 --- a/youtube_dl/extractor/comcarcoff.py +++ b/youtube_dl/extractor/comcarcoff.py @@ -1,10 +1,13 @@ # encoding: utf-8 from __future__ import unicode_literals -import json - from .common import InfoExtractor -from ..utils import parse_iso8601 +from ..compat import compat_str +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, +) class ComCarCoffIE(InfoExtractor): @@ -12,13 +15,13 @@ class ComCarCoffIE(InfoExtractor): _TESTS = [{ 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', 'info_dict': { - 'id': 'miranda-sings-happy-thanksgiving-miranda', + 'id': '2494164', 'ext': 'mp4', 'upload_date': '20141127', 'timestamp': 1417107600, + 'duration': 1232, 'title': 'Happy Thanksgiving Miranda', 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', - 'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg', }, 'params': { 'skip_download': 'requires ffmpeg', @@ -31,27 +34,36 @@ class ComCarCoffIE(InfoExtractor): display_id = 'comediansincarsgettingcoffee.com' webpage = self._download_webpage(url, display_id) - full_data = json.loads(self._search_regex( - r'<script type="application/json" id="videoData">(?P<json>.+?)</script>', - webpage, 'full data json')) + full_data = self._parse_json( + self._search_regex( + r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'), + display_id)['videoData'] - video_id = full_data['activeVideo']['video'] - video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id] + display_id = full_data['activeVideo']['video'] + video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id] + video_id = compat_str(video_data['mediaId']) thumbnails = [{ 'url': video_data['images']['thumb'], }, { 'url': video_data['images']['poster'], }] - formats = self._extract_m3u8_formats( - video_data['mediaUrl'], video_id, ext='mp4') + + timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601( + video_data.get('pubDate')) + duration = int_or_none(video_data.get('durationSeconds')) or parse_duration( + video_data.get('duration')) return { + '_type': 'url_transparent', + 'url': 'crackle:%s' % video_id, 'id': video_id, 'display_id': display_id, 'title': video_data['title'], 'description': video_data.get('description'), - 'timestamp': parse_iso8601(video_data.get('pubDate')), + 'timestamp': timestamp, + 'duration': duration, 'thumbnails': thumbnails, - 'formats': formats, + 'season_number': int_or_none(video_data.get('season')), + 'episode_number': int_or_none(video_data.get('episode')), 'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))), } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 3e4bd10..5b1b996 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -16,11 +16,11 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ - (video-clips|episodes|cc-studios|video-collections|full-episodes) + (video-clips|episodes|cc-studios|video-collections|full-episodes|shows) /(?P<title>.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' - _TEST = { + _TESTS = [{ 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { @@ -29,7 +29,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor): 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother', 'description': 'After a certain point, breastfeeding becomes c**kblocking.', }, - } + }, { + 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', + 'only_matching': True, + }] class ComedyCentralShowsIE(MTVServicesInfoExtractor): @@ -192,7 +195,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): if len(altMovieParams) == 0: raise ExtractorError('unable to find Flash URL in webpage ' + url) else: - mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] + mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])] uri = mMovieParams[0][1] # Correct cc.com in uri diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index eb9bfa3..14f5756 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -10,6 +10,7 @@ import re import socket import sys import time +import math from ..compat import ( compat_cookiejar, @@ -18,7 +19,6 @@ from ..compat import ( compat_http_client, compat_urllib_error, compat_urllib_parse, - compat_urllib_parse_urlparse, compat_urlparse, compat_str, compat_etree_fromstring, @@ -30,10 +30,12 @@ from ..utils import ( clean_html, compiled_regex_type, determine_ext, + error_to_compat_str, ExtractorError, fix_xml_ampersands, float_or_none, int_or_none, + parse_iso8601, RegexNotFoundError, sanitize_filename, sanitized_Request, @@ -42,6 +44,9 @@ from ..utils import ( url_basename, xpath_text, xpath_with_ns, + determine_protocol, + parse_duration, + mimetype2ext, ) @@ -107,8 +112,9 @@ class InfoExtractor(object): -2 or smaller for less than default. < -1000 to hide the format (if there is another one which is strictly better) - * language_preference Is this in the correct requested - language? + * language Language code, e.g. "de" or "en-US". + * language_preference Is this in the language mentioned in + the URL? 10 if it's what the URL is about, -1 for default (don't know), -10 otherwise, other values reserved for now. @@ -167,7 +173,7 @@ class InfoExtractor(object): "ext" will be calculated from URL if missing automatic_captions: Like 'subtitles', used by the YoutubeIE for automatically generated captions - duration: Length of the video in seconds, as an integer. + duration: Length of the video in seconds, as an integer or float. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video @@ -199,6 +205,26 @@ class InfoExtractor(object): end_time: Time in seconds where the reproduction should end, as specified in the URL. + The following fields should only be used when the video belongs to some logical + chapter or section: + + chapter: Name or title of the chapter the video belongs to. + chapter_number: Number of the chapter the video belongs to, as an integer. + chapter_id: Id of the chapter the video belongs to, as a unicode string. + + The following fields should only be used when the video is an episode of some + series or programme: + + series: Title of the series or programme the video episode belongs to. + season: Title of the season the video episode belongs to. + season_number: Number of the season the video episode belongs to, as an integer. + season_id: Id of the season the video episode belongs to, as a unicode string. + episode: Title of the video episode. Unlike mandatory video title field, + this field should denote the exact title of the video episode + without any kind of decoration. + episode_number: Number of the video episode within a season, as an integer. + episode_id: Id of the video episode, as a unicode string. + Unless mentioned otherwise, the fields should be Unicode strings. Unless mentioned otherwise, None is equivalent to absence of information. @@ -291,9 +317,9 @@ class InfoExtractor(object): except ExtractorError: raise except compat_http_client.IncompleteRead as e: - raise ExtractorError('A network error has occured.', cause=e, expected=True) + raise ExtractorError('A network error has occurred.', cause=e, expected=True) except (KeyError, StopIteration) as e: - raise ExtractorError('An extractor error has occured.', cause=e) + raise ExtractorError('An extractor error has occurred.', cause=e) def set_downloader(self, downloader): """Sets the downloader for this IE.""" @@ -332,7 +358,8 @@ class InfoExtractor(object): return False if errnote is None: errnote = 'Unable to download webpage' - errmsg = '%s: %s' % (errnote, compat_str(err)) + + errmsg = '%s: %s' % (errnote, error_to_compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -610,7 +637,7 @@ class InfoExtractor(object): downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: + if downloader_params.get('username') is not None: username = downloader_params['username'] password = downloader_params['password'] elif downloader_params.get('usenetrc', False): @@ -622,7 +649,7 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) + self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err)) return (username, password) @@ -637,7 +664,7 @@ class InfoExtractor(object): return None downloader_params = self._downloader.params - if downloader_params.get('twofactor', None) is not None: + if downloader_params.get('twofactor') is not None: return downloader_params['twofactor'] return compat_getpass('Type %s and press [Return]: ' % note) @@ -718,7 +745,7 @@ class InfoExtractor(object): 'mature': 17, 'restricted': 19, } - return RATING_TABLE.get(rating.lower(), None) + return RATING_TABLE.get(rating.lower()) def _family_friendly_search(self, html): # See http://schema.org/VideoObject @@ -733,12 +760,48 @@ class InfoExtractor(object): '0': 18, 'false': 18, } - return RATING_TABLE.get(family_friendly.lower(), None) + return RATING_TABLE.get(family_friendly.lower()) def _twitter_search_player(self, html): return self._html_search_meta('twitter:player', html, 'twitter card player') + def _search_json_ld(self, html, video_id, **kwargs): + json_ld = self._search_regex( + r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>', + html, 'JSON-LD', group='json_ld', **kwargs) + if not json_ld: + return {} + return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True)) + + def _json_ld(self, json_ld, video_id, fatal=True): + if isinstance(json_ld, compat_str): + json_ld = self._parse_json(json_ld, video_id, fatal=fatal) + if not json_ld: + return {} + info = {} + if json_ld.get('@context') == 'http://schema.org': + item_type = json_ld.get('@type') + if item_type == 'TVEpisode': + info.update({ + 'episode': unescapeHTML(json_ld.get('name')), + 'episode_number': int_or_none(json_ld.get('episodeNumber')), + 'description': unescapeHTML(json_ld.get('description')), + }) + part_of_season = json_ld.get('partOfSeason') + if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason': + info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) + part_of_series = json_ld.get('partOfSeries') + if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries': + info['series'] = unescapeHTML(part_of_series.get('name')) + elif item_type == 'Article': + info.update({ + 'timestamp': parse_iso8601(json_ld.get('datePublished')), + 'title': unescapeHTML(json_ld.get('headline')), + 'description': unescapeHTML(json_ld.get('articleBody')), + }) + return dict((k, v) for k, v in info.items() if v is not None) + @staticmethod def _hidden_inputs(html): html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html) @@ -765,6 +828,12 @@ class InfoExtractor(object): if not formats: raise ExtractorError('No video formats found') + for f in formats: + # Automatically determine tbr when missing based on abr and vbr (improves + # formats sorting in some cases) + if 'tbr' not in f and f.get('abr') is not None and f.get('vbr') is not None: + f['tbr'] = f['abr'] + f['vbr'] + def _formats_key(f): # TODO remove the following workaround from ..utils import determine_ext @@ -776,14 +845,12 @@ class InfoExtractor(object): preference = f.get('preference') if preference is None: - proto = f.get('protocol') - if proto is None: - proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme - - preference = 0 if proto in ['http', 'https'] else -0.1 + preference = 0 if f.get('ext') in ['f4f', 'f4m']: # Not yet supported preference -= 0.5 + proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1 + if f.get('vcodec') == 'none': # audio only if self._downloader.params.get('prefer_free_formats'): ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] @@ -814,6 +881,7 @@ class InfoExtractor(object): f.get('vbr') if f.get('vbr') is not None else -1, f.get('height') if f.get('height') is not None else -1, f.get('width') if f.get('width') is not None else -1, + proto_preference, ext_preference, f.get('abr') if f.get('abr') is not None else -1, audio_ext_preference, @@ -832,6 +900,16 @@ class InfoExtractor(object): item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'), formats) + @staticmethod + def _remove_duplicate_formats(formats): + format_urls = set() + unique_formats = [] + for f in formats: + if f['url'] not in format_urls: + format_urls.add(f['url']) + unique_formats.append(f) + formats[:] = unique_formats + def _is_valid_url(self, url, video_id, item='video'): url = self._proto_relative_url(url, scheme='http:') # For now assume non HTTP(S) URLs always valid @@ -883,7 +961,7 @@ class InfoExtractor(object): fatal=fatal) if manifest is False: - return manifest + return [] formats = [] manifest_version = '1.0' @@ -909,10 +987,8 @@ class InfoExtractor(object): # may differ leading to inability to resolve the format by requested # bitrate in f4m downloader if determine_ext(manifest_url) == 'f4m': - f4m_formats = self._extract_f4m_formats( - manifest_url, video_id, preference, f4m_id, fatal=fatal) - if f4m_formats: - formats.extend(f4m_formats) + formats.extend(self._extract_f4m_formats( + manifest_url, video_id, preference, f4m_id, fatal=fatal)) continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ @@ -954,9 +1030,21 @@ class InfoExtractor(object): errnote=errnote or 'Failed to download m3u8 information', fatal=fatal) if res is False: - return res + return [] m3u8_doc, urlh = res m3u8_url = urlh.geturl() + # A Media Playlist Tag MUST NOT appear in a Master Playlist + # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3 + # The EXT-X-TARGETDURATION tag is REQUIRED for every M3U8 Media Playlists + # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1 + if '#EXT-X-TARGETDURATION' in m3u8_doc: + return [{ + 'url': m3u8_url, + 'format_id': m3u8_id, + 'ext': ext, + 'protocol': entry_protocol, + 'preference': preference, + }] last_info = None last_media = None kv_rex = re.compile( @@ -1001,9 +1089,9 @@ class InfoExtractor(object): # TODO: looks like video codec is not always necessarily goes first va_codecs = codecs.split(',') if va_codecs[0]: - f['vcodec'] = va_codecs[0].partition('.')[0] + f['vcodec'] = va_codecs[0] if len(va_codecs) > 1 and va_codecs[1]: - f['acodec'] = va_codecs[1].partition('.')[0] + f['acodec'] = va_codecs[1] resolution = last_info.get('RESOLUTION') if resolution: width_str, height_str = resolution.split('x') @@ -1107,12 +1195,15 @@ class InfoExtractor(object): formats = [] rtmp_count = 0 http_count = 0 + m3u8_count = 0 + srcs = [] videos = smil.findall(self._xpath_ns('.//video', namespace)) for video in videos: src = video.get('src') - if not src: + if not src or src in srcs: continue + srcs.append(src) bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) filesize = int_or_none(video.get('size') or video.get('fileSize')) @@ -1144,12 +1235,20 @@ class InfoExtractor(object): continue src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src) + src_url = src_url.strip() if proto == 'm3u8' or src_ext == 'm3u8': m3u8_formats = self._extract_m3u8_formats( src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + if len(m3u8_formats) == 1: + m3u8_count += 1 + m3u8_formats[0].update({ + 'format_id': 'hls-%d' % (m3u8_count if bitrate is None else bitrate), + 'tbr': bitrate, + 'width': width, + 'height': height, + }) + formats.extend(m3u8_formats) continue if src_ext == 'f4m': @@ -1161,9 +1260,7 @@ class InfoExtractor(object): } f4m_url += '&' if '?' in f4m_url else '?' f4m_url += compat_urllib_parse.urlencode(f4m_params) - f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False) - if f4m_formats: - formats.extend(f4m_formats) + formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)) continue if src_url.startswith('http') and self._is_valid_url(src, video_id): @@ -1184,21 +1281,14 @@ class InfoExtractor(object): return formats def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): + urls = [] subtitles = {} for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))): src = textstream.get('src') - if not src: + if not src or src in urls: continue - ext = textstream.get('ext') or determine_ext(src) - if not ext: - type_ = textstream.get('type') - SUBTITLES_TYPES = { - 'text/vtt': 'vtt', - 'text/srt': 'srt', - 'application/smptett+xml': 'tt', - } - if type_ in SUBTITLES_TYPES: - ext = SUBTITLES_TYPES[type_] + urls.append(src) + ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type')) lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang subtitles.setdefault(lang, []).append({ 'url': src, @@ -1249,10 +1339,167 @@ class InfoExtractor(object): }) return entries + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}): + res = self._download_webpage_handle( + mpd_url, video_id, + note=note or 'Downloading MPD manifest', + errnote=errnote or 'Failed to download MPD manifest', + fatal=fatal) + if res is False: + return [] + mpd, urlh = res + mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group() + + return self._parse_mpd_formats( + compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict) + + def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}): + if mpd_doc.get('type') == 'dynamic': + return [] + + namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace', default=None) + + def _add_ns(path): + return self._xpath_ns(path, namespace) + + def is_drm_protected(element): + return element.find(_add_ns('ContentProtection')) is not None + + def extract_multisegment_info(element, ms_parent_info): + ms_info = ms_parent_info.copy() + segment_list = element.find(_add_ns('SegmentList')) + if segment_list is not None: + segment_urls_e = segment_list.findall(_add_ns('SegmentURL')) + if segment_urls_e: + ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e] + initialization = segment_list.find(_add_ns('Initialization')) + if initialization is not None: + ms_info['initialization_url'] = initialization.attrib['sourceURL'] + else: + segment_template = element.find(_add_ns('SegmentTemplate')) + if segment_template is not None: + start_number = segment_template.get('startNumber') + if start_number: + ms_info['start_number'] = int(start_number) + segment_timeline = segment_template.find(_add_ns('SegmentTimeline')) + if segment_timeline is not None: + s_e = segment_timeline.findall(_add_ns('S')) + if s_e: + ms_info['total_number'] = 0 + for s in s_e: + ms_info['total_number'] += 1 + int(s.get('r', '0')) + else: + timescale = segment_template.get('timescale') + if timescale: + ms_info['timescale'] = int(timescale) + segment_duration = segment_template.get('duration') + if segment_duration: + ms_info['segment_duration'] = int(segment_duration) + media_template = segment_template.get('media') + if media_template: + ms_info['media_template'] = media_template + initialization = segment_template.get('initialization') + if initialization: + ms_info['initialization_url'] = initialization + else: + initialization = segment_template.find(_add_ns('Initialization')) + if initialization is not None: + ms_info['initialization_url'] = initialization.attrib['sourceURL'] + return ms_info + + mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration')) + formats = [] + for period in mpd_doc.findall(_add_ns('Period')): + period_duration = parse_duration(period.get('duration')) or mpd_duration + period_ms_info = extract_multisegment_info(period, { + 'start_number': 1, + 'timescale': 1, + }) + for adaptation_set in period.findall(_add_ns('AdaptationSet')): + if is_drm_protected(adaptation_set): + continue + adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info) + for representation in adaptation_set.findall(_add_ns('Representation')): + if is_drm_protected(representation): + continue + representation_attrib = adaptation_set.attrib.copy() + representation_attrib.update(representation.attrib) + mime_type = representation_attrib.get('mimeType') + content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType') + if content_type == 'text': + # TODO implement WebVTT downloading + pass + elif content_type == 'video' or content_type == 'audio': + base_url = '' + for element in (representation, adaptation_set, period, mpd_doc): + base_url_e = element.find(_add_ns('BaseURL')) + if base_url_e is not None: + base_url = base_url_e.text + base_url + if re.match(r'^https?://', base_url): + break + if mpd_base_url and not re.match(r'^https?://', base_url): + if not mpd_base_url.endswith('/') and not base_url.startswith('/'): + mpd_base_url += '/' + base_url = mpd_base_url + base_url + representation_id = representation_attrib.get('id') + lang = representation_attrib.get('lang') + url_el = representation.find(_add_ns('BaseURL')) + filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None) + f = { + 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, + 'url': base_url, + 'width': int_or_none(representation_attrib.get('width')), + 'height': int_or_none(representation_attrib.get('height')), + 'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000), + 'asr': int_or_none(representation_attrib.get('audioSamplingRate')), + 'fps': int_or_none(representation_attrib.get('frameRate')), + 'vcodec': 'none' if content_type == 'audio' else representation_attrib.get('codecs'), + 'acodec': 'none' if content_type == 'video' else representation_attrib.get('codecs'), + 'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None, + 'format_note': 'DASH %s' % content_type, + 'filesize': filesize, + } + representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info) + if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info: + if 'total_number' not in representation_ms_info and 'segment_duration': + segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale']) + representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration)) + media_template = representation_ms_info['media_template'] + media_template = media_template.replace('$RepresentationID$', representation_id) + media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template) + media_template.replace('$$', '$') + representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])] + if 'segment_urls' in representation_ms_info: + f.update({ + 'segment_urls': representation_ms_info['segment_urls'], + 'protocol': 'http_dash_segments', + }) + if 'initialization_url' in representation_ms_info: + initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id) + f.update({ + 'initialization_url': initialization_url, + }) + if not f.get('url'): + f['url'] = initialization_url + try: + existing_format = next( + fo for fo in formats + if fo['format_id'] == representation_id) + except StopIteration: + full_info = formats_dict.get(representation_id, {}).copy() + full_info.update(f) + formats.append(full_info) + else: + existing_format.update(f) + else: + self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) + self._sort_formats(formats) + return formats + def _live_title(self, name): """ Generate the title for a live video """ now = datetime.datetime.now() - now_str = now.strftime("%Y-%m-%d %H:%M") + now_str = now.strftime('%Y-%m-%d %H:%M') return name + ' ' + now_str def _int(self, v, name, fatal=False, **kwargs): @@ -1325,7 +1572,7 @@ class InfoExtractor(object): return {} def _get_subtitles(self, *args, **kwargs): - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') @staticmethod def _merge_subtitle_items(subtitle_list1, subtitle_list2): @@ -1351,7 +1598,7 @@ class InfoExtractor(object): return {} def _get_automatic_captions(self, *args, **kwargs): - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') class SearchInfoExtractor(InfoExtractor): @@ -1391,7 +1638,7 @@ class SearchInfoExtractor(InfoExtractor): def _get_n_results(self, query, n): """Get a specified number of results for a query""" - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') @property def SEARCH_KEY(self): diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py new file mode 100644 index 0000000..79238cc --- /dev/null +++ b/youtube_dl/extractor/crackle.py @@ -0,0 +1,95 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class CrackleIE(InfoExtractor): + _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)' + _TEST = { + 'url': 'http://www.crackle.com/the-art-of-more/2496419', + 'info_dict': { + 'id': '2496419', + 'ext': 'mp4', + 'title': 'Heavy Lies the Head', + 'description': 'md5:bb56aa0708fe7b9a4861535f15c3abca', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + } + + # extracted from http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx + _SUBTITLE_SERVER = 'http://web-us-az.crackle.com' + _UPLYNK_OWNER_ID = 'e8773f7770a44dbd886eee4fca16a66b' + _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614' + + # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx + _MEDIA_FILE_SLOTS = { + 'c544.flv': { + 'width': 544, + 'height': 306, + }, + '360p.mp4': { + 'width': 640, + 'height': 360, + }, + '480p.mp4': { + 'width': 852, + 'height': 478, + }, + '480p_1mbps.mp4': { + 'width': 852, + 'height': 478, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + item = self._download_xml( + 'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id, + video_id).find('i') + title = item.attrib['t'] + + thumbnail = None + subtitles = {} + formats = self._extract_m3u8_formats( + 'http://content.uplynk.com/ext/%s/%s.m3u8' % (self._UPLYNK_OWNER_ID, video_id), + video_id, 'mp4', m3u8_id='hls', fatal=None) + path = item.attrib.get('p') + if path: + thumbnail = self._THUMBNAIL_TEMPLATE % path + http_base_url = 'http://ahttp.crackle.com/' + path + for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items(): + formats.append({ + 'url': http_base_url + mfs_path, + 'format_id': 'http-' + mfs_path.split('.')[0], + 'width': mfs_info['width'], + 'height': mfs_info['height'], + }) + for cc in item.findall('cc'): + locale = cc.attrib.get('l') + v = cc.attrib.get('v') + if locale and v: + if locale not in subtitles: + subtitles[locale] = [] + subtitles[locale] = [{ + 'url': '%s/%s%s_%s.xml' % (self._SUBTITLE_SERVER, path, locale, v), + 'ext': 'ttml', + }] + self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id')) + + return { + 'id': video_id, + 'title': title, + 'description': item.attrib.get('d'), + 'duration': int(item.attrib.get('r'), 16) if item.attrib.get('r') else None, + 'series': item.attrib.get('sn'), + 'season_number': int_or_none(item.attrib.get('se')), + 'episode_number': int_or_none(item.attrib.get('ep')), + 'thumbnail': thumbnail, + 'subtitles': subtitles, + 'formats': formats, + } diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 00d943f..c7032ff 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -180,40 +180,40 @@ class CrunchyrollIE(CrunchyrollBaseIE): return assvalue output = '[Script Info]\n' - output += 'Title: %s\n' % sub_root.attrib["title"] + output += 'Title: %s\n' % sub_root.attrib['title'] output += 'ScriptType: v4.00+\n' - output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"] - output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"] - output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"] + output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style'] + output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x'] + output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y'] output += """ScaledBorderAndShadow: yes [V4+ Styles] Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding """ for style in sub_root.findall('./styles/style'): - output += 'Style: ' + style.attrib["name"] - output += ',' + style.attrib["font_name"] - output += ',' + style.attrib["font_size"] - output += ',' + style.attrib["primary_colour"] - output += ',' + style.attrib["secondary_colour"] - output += ',' + style.attrib["outline_colour"] - output += ',' + style.attrib["back_colour"] - output += ',' + ass_bool(style.attrib["bold"]) - output += ',' + ass_bool(style.attrib["italic"]) - output += ',' + ass_bool(style.attrib["underline"]) - output += ',' + ass_bool(style.attrib["strikeout"]) - output += ',' + style.attrib["scale_x"] - output += ',' + style.attrib["scale_y"] - output += ',' + style.attrib["spacing"] - output += ',' + style.attrib["angle"] - output += ',' + style.attrib["border_style"] - output += ',' + style.attrib["outline"] - output += ',' + style.attrib["shadow"] - output += ',' + style.attrib["alignment"] - output += ',' + style.attrib["margin_l"] - output += ',' + style.attrib["margin_r"] - output += ',' + style.attrib["margin_v"] - output += ',' + style.attrib["encoding"] + output += 'Style: ' + style.attrib['name'] + output += ',' + style.attrib['font_name'] + output += ',' + style.attrib['font_size'] + output += ',' + style.attrib['primary_colour'] + output += ',' + style.attrib['secondary_colour'] + output += ',' + style.attrib['outline_colour'] + output += ',' + style.attrib['back_colour'] + output += ',' + ass_bool(style.attrib['bold']) + output += ',' + ass_bool(style.attrib['italic']) + output += ',' + ass_bool(style.attrib['underline']) + output += ',' + ass_bool(style.attrib['strikeout']) + output += ',' + style.attrib['scale_x'] + output += ',' + style.attrib['scale_y'] + output += ',' + style.attrib['spacing'] + output += ',' + style.attrib['angle'] + output += ',' + style.attrib['border_style'] + output += ',' + style.attrib['outline'] + output += ',' + style.attrib['shadow'] + output += ',' + style.attrib['alignment'] + output += ',' + style.attrib['margin_l'] + output += ',' + style.attrib['margin_r'] + output += ',' + style.attrib['margin_v'] + output += ',' + style.attrib['encoding'] output += '\n' output += """ @@ -222,15 +222,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text """ for event in sub_root.findall('./events/event'): output += 'Dialogue: 0' - output += ',' + event.attrib["start"] - output += ',' + event.attrib["end"] - output += ',' + event.attrib["style"] - output += ',' + event.attrib["name"] - output += ',' + event.attrib["margin_l"] - output += ',' + event.attrib["margin_r"] - output += ',' + event.attrib["margin_v"] - output += ',' + event.attrib["effect"] - output += ',' + event.attrib["text"] + output += ',' + event.attrib['start'] + output += ',' + event.attrib['end'] + output += ',' + event.attrib['style'] + output += ',' + event.attrib['name'] + output += ',' + event.attrib['margin_l'] + output += ',' + event.attrib['margin_r'] + output += ',' + event.attrib['margin_v'] + output += ',' + event.attrib['effect'] + output += ',' + event.attrib['text'] output += '\n' return output @@ -329,8 +329,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text streamdata_req, video_id, note='Downloading media info for %s' % video_format) stream_info = streamdata.find('./{default}preload/stream_info') - video_url = stream_info.find('./host').text - video_play_path = stream_info.find('./file').text + video_url = xpath_text(stream_info, './host') + video_play_path = xpath_text(stream_info, './file') + if not video_url or not video_play_path: + continue metadata = stream_info.find('./metadata') format_info = { 'format': video_format, @@ -374,7 +376,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): - IE_NAME = "crunchyroll:playlist" + IE_NAME = 'crunchyroll:playlist' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)' _TESTS = [{ diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index fbefd37..b8b9d05 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -9,6 +9,7 @@ from ..utils import ( find_xpath_attr, smuggle_url, determine_ext, + ExtractorError, ) from .senateisvp import SenateISVPIE @@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor): IE_DESC = 'C-SPAN' _TESTS = [{ 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', - 'md5': '8e44ce11f0f725527daccc453f553eb0', + 'md5': '94b29a4f131ff03d23471dd6f60b6a1d', 'info_dict': { 'id': '315139', 'ext': 'mp4', 'title': 'Attorney General Eric Holder on Voting Rights Act Decision', - 'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.', + 'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.', }, 'skip': 'Regularly fails on travis, for unknown reasons', }, { 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models', - # For whatever reason, the served video alternates between - # two different ones + 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b', 'info_dict': { - 'id': '340723', + 'id': 'c4486943', 'ext': 'mp4', - 'title': 'International Health Care Models', + 'title': 'CSPAN - International Health Care Models', 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', } }, { 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', - 'md5': '446562a736c6bf97118e389433ed88d4', + 'md5': '2ae5051559169baadba13fc35345ae74', 'info_dict': { 'id': '342759', 'ext': 'mp4', 'title': 'General Motors Ignition Switch Recall', 'duration': 14848, - 'description': 'md5:70c7c3b8fa63fa60d42772440596034c' + 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3' }, }, { # Video from senate.gov @@ -57,67 +57,94 @@ class CSpanIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - webpage = self._download_webpage(url, page_id) - video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id') + video_id = self._match_id(url) + video_type = None + webpage = self._download_webpage(url, video_id) + # We first look for clipid, because clipprog always appears before + patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')] + results = list(filter(None, (re.search(p, webpage) for p in patterns))) + if results: + matches = results[0] + video_type, video_id = matches.groups() + video_type = 'clip' if video_type == 'id' else 'program' + else: + m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage) + if m: + video_id = m.group('id') + video_type = 'program' if m.group('type') == 'prog' else 'clip' + else: + senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) + if senate_isvp_url: + title = self._og_search_title(webpage) + surl = smuggle_url(senate_isvp_url, {'force_title': title}) + return self.url_result(surl, 'SenateISVP', video_id, title) + if video_type is None or video_id is None: + raise ExtractorError('unable to find video id and type') - description = self._html_search_regex( - [ - # The full description - r'<div class=\'expandable\'>(.*?)<a href=\'#\'', - # If the description is small enough the other div is not - # present, otherwise this is a stripped version - r'<p class=\'initial\'>(.*?)</p>' - ], - webpage, 'description', flags=re.DOTALL, default=None) + def get_text_attr(d, attr): + return d.get(attr, {}).get('#text') - info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id - data = self._download_json(info_url, video_id) + data = self._download_json( + 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id), + video_id)['video'] + if data['@status'] != 'Success': + raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True) doc = self._download_xml( - 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, + 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id), video_id) + description = self._html_search_meta('description', webpage) + title = find_xpath_attr(doc, './/string', 'name', 'title').text thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text - senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) - if senate_isvp_url: - surl = smuggle_url(senate_isvp_url, {'force_title': title}) - return self.url_result(surl, 'SenateISVP', video_id, title) - - files = data['video']['files'] - try: - capfile = data['video']['capfile']['#text'] - except KeyError: - capfile = None + files = data['files'] + capfile = get_text_attr(data, 'capfile') - entries = [{ - 'id': '%s_%d' % (video_id, partnum + 1), - 'title': ( - title if len(files) == 1 else - '%s part %d' % (title, partnum + 1)), - 'url': unescapeHTML(f['path']['#text']), - 'description': description, - 'thumbnail': thumbnail, - 'duration': int_or_none(f.get('length', {}).get('#text')), - 'subtitles': { - 'en': [{ - 'url': capfile, - 'ext': determine_ext(capfile, 'dfxp') - }], - } if capfile else None, - } for partnum, f in enumerate(files)] + entries = [] + for partnum, f in enumerate(files): + formats = [] + for quality in f['qualities']: + formats.append({ + 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')), + 'url': unescapeHTML(get_text_attr(quality, 'file')), + 'height': int_or_none(get_text_attr(quality, 'height')), + 'tbr': int_or_none(get_text_attr(quality, 'bitrate')), + }) + if not formats: + path = unescapeHTML(get_text_attr(f, 'path')) + if not path: + continue + formats = self._extract_m3u8_formats( + path, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }] + self._sort_formats(formats) + entries.append({ + 'id': '%s_%d' % (video_id, partnum + 1), + 'title': ( + title if len(files) == 1 else + '%s part %d' % (title, partnum + 1)), + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': int_or_none(get_text_attr(f, 'length')), + 'subtitles': { + 'en': [{ + 'url': capfile, + 'ext': determine_ext(capfile, 'dfxp') + }], + } if capfile else None, + }) if len(entries) == 1: entry = dict(entries[0]) - entry['id'] = video_id + entry['id'] = 'c' + video_id if video_type == 'clip' else video_id return entry else: return { '_type': 'playlist', 'entries': entries, 'title': title, - 'id': video_id, + 'id': 'c' + video_id if video_type == 'clip' else video_id, } diff --git a/youtube_dl/extractor/cultureunplugged.py b/youtube_dl/extractor/cultureunplugged.py new file mode 100644 index 0000000..9c764fe --- /dev/null +++ b/youtube_dl/extractor/cultureunplugged.py @@ -0,0 +1,63 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class CultureUnpluggedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?' + _TESTS = [{ + 'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West', + 'md5': 'ac6c093b089f7d05e79934dcb3d228fc', + 'info_dict': { + 'id': '53662', + 'display_id': 'The-Next--Best-West', + 'ext': 'mp4', + 'title': 'The Next, Best West', + 'description': 'md5:0423cd00833dea1519cf014e9d0903b1', + 'thumbnail': 're:^https?://.*\.jpg$', + 'creator': 'Coldstream Creative', + 'duration': 2203, + 'view_count': int, + } + }, { + 'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662', + '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') or video_id + + movie_data = self._download_json( + 'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id) + + video_url = movie_data['url'] + title = movie_data['title'] + + description = movie_data.get('synopsis') + creator = movie_data.get('producer') + duration = int_or_none(movie_data.get('duration')) + view_count = int_or_none(movie_data.get('views')) + + thumbnails = [{ + 'url': movie_data['%s_thumb' % size], + 'id': size, + 'preference': preference, + } for preference, size in enumerate(( + 'small', 'large')) if movie_data.get('%s_thumb' % size)] + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'creator': creator, + 'duration': duration, + 'view_count': view_count, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py new file mode 100644 index 0000000..36af670 --- /dev/null +++ b/youtube_dl/extractor/cwtv.py @@ -0,0 +1,88 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class CWTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' + _TESTS = [{ + 'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63', + 'info_dict': { + 'id': '6b15e985-9345-4f60-baf8-56e96be57c63', + 'ext': 'mp4', + 'title': 'Legends of Yesterday', + 'description': 'Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote location to keep them hidden from Vandal Savage while they figure out how to defeat him.', + 'duration': 2665, + 'series': 'Arrow', + 'season_number': 4, + 'season': '4', + 'episode_number': 8, + 'upload_date': '20151203', + 'timestamp': 1449122100, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + }, { + 'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088', + 'info_dict': { + 'id': '24282b12-ead2-42f2-95ad-26770c2c6088', + 'ext': 'mp4', + 'title': 'Jeff Davis 4', + 'description': 'Jeff Davis is back to make you laugh.', + 'duration': 1263, + 'series': 'Whose Line Is It Anyway?', + 'season_number': 11, + 'season': '11', + 'episode_number': 20, + 'upload_date': '20151006', + 'timestamp': 1444107300, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_json( + 'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id) + + formats = self._extract_m3u8_formats( + video_data['videos']['variantplaylist']['uri'], video_id, 'mp4') + + thumbnails = [{ + 'url': image['uri'], + 'width': image.get('width'), + 'height': image.get('height'), + } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None + + video_metadata = video_data['assetFields'] + + subtitles = { + 'en': [{ + 'url': video_metadata['UnicornCcUrl'], + }], + } if video_metadata.get('UnicornCcUrl') else None + + return { + 'id': video_id, + 'title': video_metadata['title'], + 'description': video_metadata.get('description'), + 'duration': int_or_none(video_metadata.get('duration')), + 'series': video_metadata.get('seriesName'), + 'season_number': int_or_none(video_metadata.get('seasonNumber')), + 'season': video_metadata.get('seasonName'), + 'episode_number': int_or_none(video_metadata.get('episodeNumber')), + 'timestamp': parse_iso8601(video_data.get('startTime')), + 'thumbnails': thumbnails, + 'formats': formats, + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index ab7f3ae..2e6226e 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -7,10 +7,10 @@ import itertools from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( - ExtractorError, determine_ext, + error_to_compat_str, + ExtractorError, int_or_none, parse_iso8601, sanitized_Request, @@ -37,7 +37,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): class DailymotionIE(DailymotionBaseInfoExtractor): - _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)' + _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)' IE_NAME = 'dailymotion' _FORMATS = [ @@ -99,6 +99,15 @@ class DailymotionIE(DailymotionBaseInfoExtractor): { 'url': 'http://www.dailymotion.com/video/xhza0o', 'only_matching': True, + }, + # with subtitles + { + 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news', + 'only_matching': True, + }, + { + 'url': 'http://www.dailymotion.com/swf/video/x3n92nf', + 'only_matching': True, } ] @@ -113,16 +122,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor): description = self._og_search_description(webpage) or self._html_search_meta( 'description', webpage, 'description') - view_count = str_to_int(self._search_regex( - [r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"', - r'video_views_count[^>]+>\s+([\d\.,]+)'], - webpage, 'view count', fatal=False)) + view_count_str = self._search_regex( + (r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"', + r'video_views_count[^>]+>\s+([\s\d\,.]+)'), + webpage, 'view count', fatal=False) + if view_count_str: + view_count_str = re.sub(r'\s', '', view_count_str) + view_count = str_to_int(view_count_str) comment_count = int_or_none(self._search_regex( r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"', webpage, 'comment count', fatal=False)) player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'], + [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826 + r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + r'buildPlayer\(({.+?})\);'], webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) @@ -141,19 +155,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor): continue ext = determine_ext(media_url) if type_ == 'application/x-mpegURL' or ext == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - media_url, video_id, 'mp4', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + formats.extend(self._extract_m3u8_formats( + media_url, video_id, 'mp4', preference=-1, + m3u8_id='hls', fatal=False)) elif type_ == 'application/f4m' or ext == 'f4m': - f4m_formats = self._extract_f4m_formats( - media_url, video_id, preference=-1, f4m_id='hds', fatal=False) - if f4m_formats: - formats.extend(f4m_formats) + formats.extend(self._extract_f4m_formats( + media_url, video_id, preference=-1, f4m_id='hds', fatal=False)) else: f = { 'url': media_url, - 'format_id': quality, + 'format_id': 'http-%s' % quality, } m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url) if m: @@ -172,11 +183,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): uploader_id = metadata.get('owner', {}).get('id') subtitles = {} - for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] + subtitles_data = metadata.get('subtitles', {}).get('data', {}) + if subtitles_data and isinstance(subtitles_data, dict): + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'ext': determine_ext(subtitle_url), + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] return { 'id': video_id, @@ -269,7 +282,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): @@ -330,7 +343,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' _TESTS = [{ 'url': 'https://www.dailymotion.com/user/nqtv', @@ -386,13 +399,13 @@ class DailymotionCloudIE(DailymotionBaseInfoExtractor): }] @classmethod - def _extract_dmcloud_url(self, webpage): - mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage) + def _extract_dmcloud_url(cls, webpage): + mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage) if mobj: return mobj.group(1) mobj = re.search( - r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, + r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage) if mobj: return mobj.group(1) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 934da76..c84c510 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -3,56 +3,91 @@ from __future__ import unicode_literals import re +import itertools from .common import InfoExtractor from ..compat import ( + compat_parse_qs, compat_urllib_parse, + compat_urllib_parse_unquote, + compat_urlparse, +) +from ..utils import ( + int_or_none, + str_to_int, + xpath_text, + unescapeHTML, ) class DaumIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)' + _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)' IE_NAME = 'daum.net' _TESTS = [{ - 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', + 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz', 'info_dict': { - 'id': '52554690', + 'id': 'vab4dyeDBysyBssyukBUjBz', 'ext': 'mp4', - 'title': 'DOTA 2GETHER 시즌2 6회 - 2부', - 'description': 'DOTA 2GETHER 시즌2 6회 - 2부', - 'upload_date': '20130831', - 'duration': 3868, + 'title': '마크 헌트 vs 안토니오 실바', + 'description': 'Mark Hunt vs Antonio Silva', + 'upload_date': '20131217', + 'thumbnail': 're:^https?://.*\.(?:jpg|png)', + 'duration': 2117, + 'view_count': int, + 'comment_count': int, }, }, { - 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz', - 'only_matching': True, + 'url': 'http://m.tvpot.daum.net/v/65139429', + 'info_dict': { + 'id': '65139429', + 'ext': 'mp4', + 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118', + 'description': 'md5:79794514261164ff27e36a21ad229fc5', + 'upload_date': '20150604', + 'thumbnail': 're:^https?://.*\.(?:jpg|png)', + 'duration': 154, + 'view_count': int, + 'comment_count': int, + }, }, { 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', 'only_matching': True, + }, { + 'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=', + 'info_dict': { + 'id': 'vwIpVpCQsT8$', + 'ext': 'flv', + 'title': '01-Korean War ( Trouble on the horizon )', + 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름', + 'upload_date': '20080223', + 'thumbnail': 're:^https?://.*\.(?:jpg|png)', + 'duration': 249, + 'view_count': int, + 'comment_count': int, + }, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - canonical_url = 'http://tvpot.daum.net/v/%s' % video_id - webpage = self._download_webpage(canonical_url, video_id) - full_id = self._search_regex( - r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']', - webpage, 'full id') - query = compat_urllib_parse.urlencode({'vid': full_id}) + video_id = compat_urllib_parse_unquote(self._match_id(url)) + query = compat_urllib_parse.urlencode({'vid': video_id}) + movie_data = self._download_json( + 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query, + video_id, 'Downloading video formats info') + + # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid + if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): + return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) + info = self._download_xml( 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id, 'Downloading video info') - urls = self._download_xml( - 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, - video_id, 'Downloading video formats info') formats = [] - for format_el in urls.findall('result/output_list/output_list'): - profile = format_el.attrib['profile'] + for format_el in movie_data['output_list']['output_list']: + profile = format_el['profile'] format_query = compat_urllib_parse.urlencode({ - 'vid': full_id, + 'vid': video_id, 'profile': profile, }) url_doc = self._download_xml( @@ -62,14 +97,202 @@ class DaumIE(InfoExtractor): formats.append({ 'url': format_url, 'format_id': profile, + 'width': int_or_none(format_el.get('width')), + 'height': int_or_none(format_el.get('height')), + 'filesize': int_or_none(format_el.get('filesize')), }) + self._sort_formats(formats) return { 'id': video_id, 'title': info.find('TITLE').text, 'formats': formats, - 'thumbnail': self._og_search_thumbnail(webpage), - 'description': info.find('CONTENTS').text, - 'duration': int(info.find('DURATION').text), + 'thumbnail': xpath_text(info, 'THUMB_URL'), + 'description': xpath_text(info, 'CONTENTS'), + 'duration': int_or_none(xpath_text(info, 'DURATION')), 'upload_date': info.find('REGDTTM').text[:8], + 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')), + 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')), } + + +class DaumClipIE(InfoExtractor): + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)' + IE_NAME = 'daum.net:clip' + _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s' + + _TESTS = [{ + 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', + 'info_dict': { + 'id': '52554690', + 'ext': 'mp4', + 'title': 'DOTA 2GETHER 시즌2 6회 - 2부', + 'description': 'DOTA 2GETHER 시즌2 6회 - 2부', + 'upload_date': '20130831', + 'thumbnail': 're:^https?://.*\.(?:jpg|png)', + 'duration': 3868, + 'view_count': int, + }, + }, { + 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url) + + def _real_extract(self, url): + video_id = self._match_id(url) + clip_info = self._download_json( + 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id, + video_id, 'Downloading clip info')['clip_bean'] + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'], + 'title': unescapeHTML(clip_info['title']), + 'thumbnail': clip_info.get('thumb_url'), + 'description': clip_info.get('contents'), + 'duration': int_or_none(clip_info.get('duration')), + 'upload_date': clip_info.get('up_date')[:8], + 'view_count': int_or_none(clip_info.get('play_count')), + 'ie_key': 'Daum', + } + + +class DaumListIE(InfoExtractor): + def _get_entries(self, list_id, list_id_type): + name = None + entries = [] + for pagenum in itertools.count(1): + list_info = self._download_json( + 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % ( + pagenum, list_id_type, list_id), list_id, 'Downloading list info - %s' % pagenum) + + entries.extend([ + self.url_result( + 'http://tvpot.daum.net/v/%s' % clip['vid']) + for clip in list_info['clip_list'] + ]) + + if not name: + name = list_info.get('playlist_bean', {}).get('name') or \ + list_info.get('potInfo', {}).get('name') + + if not list_info.get('has_more'): + break + + return name, entries + + def _check_clip(self, url, list_id): + query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query) + if 'clipid' in query_dict: + clip_id = query_dict['clipid'][0] + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just video %s because of --no-playlist' % clip_id) + return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip') + else: + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id) + + +class DaumPlaylistIE(DaumListIE): + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)' + IE_NAME = 'daum.net:playlist' + _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s' + + _TESTS = [{ + 'note': 'Playlist url with clipid', + 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844', + 'info_dict': { + 'id': '6213966', + 'title': 'Woorissica Official', + }, + 'playlist_mincount': 181 + }, { + 'note': 'Playlist url with clipid - noplaylist', + 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844', + 'info_dict': { + 'id': '73806844', + 'ext': 'mp4', + 'title': '151017 Airport', + 'upload_date': '20160117', + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, + } + }] + + @classmethod + def suitable(cls, url): + return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + list_id = self._match_id(url) + + clip_result = self._check_clip(url, list_id) + if clip_result: + return clip_result + + name, entries = self._get_entries(list_id, 'playlistid') + + return self.playlist_result(entries, list_id, name) + + +class DaumUserIE(DaumListIE): + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.(?:do|tv)\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)' + IE_NAME = 'daum.net:user' + + _TESTS = [{ + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0', + 'info_dict': { + 'id': 'o2scDLIVbHc0', + 'title': '마이 리틀 텔레비전', + }, + 'playlist_mincount': 213 + }, { + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156', + 'info_dict': { + 'id': '73801156', + 'ext': 'mp4', + 'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116', + 'upload_date': '20160117', + 'description': 'md5:5e91d2d6747f53575badd24bd62b9f36' + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, + } + }, { + 'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence', + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631', + 'info_dict': { + 'id': '6196631', + 'title': '마이 리틀 텔레비전 - 20160109', + }, + 'playlist_count': 11 + }, { + 'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0', + 'only_matching': True, + }, { + 'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733', + 'only_matching': True, + }] + + def _real_extract(self, url): + list_id = self._match_id(url) + + clip_result = self._check_clip(url, list_id) + if clip_result: + return clip_result + + query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query) + if 'playlistid' in query_dict: + playlist_id = query_dict['playlistid'][0] + return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist') + + name, entries = self._get_entries(list_id, 'ownerid') + + return self.playlist_result(entries, list_id, name) diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index 2122176..133cdc5 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -13,8 +13,8 @@ from ..utils import ( class DBTVIE(InfoExtractor): - _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?' + _TESTS = [{ 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', 'info_dict': { @@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor): 'view_count': int, 'categories': list, } - } + }, { + 'url': 'http://dbtv.no/3649835190001', + 'only_matching': True, + }, { + 'url': 'http://www.dbtv.no/lazyplayer/4631135248001', + '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') + display_id = mobj.group('display_id') or video_id data = self._download_json( 'http://api.dbtv.no/discovery/%s' % video_id, display_id) diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 9737cff..15a1c40 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -1,26 +1,90 @@ # coding: utf-8 from __future__ import unicode_literals +import re +import base64 + from .common import InfoExtractor -from ..compat import compat_urllib_parse +from ..compat import ( + compat_urllib_parse, + compat_str, +) from ..utils import ( int_or_none, parse_iso8601, sanitized_Request, + smuggle_url, + unsmuggle_url, ) class DCNIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?' + + def _real_extract(self, url): + show_id, video_id, season_id = re.match(self._VALID_URL, url).groups() + if video_id and int(video_id) > 0: + return self.url_result( + 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo') + elif season_id and int(season_id) > 0: + return self.url_result(smuggle_url( + 'http://www.dcndigital.ae/program/season/%s' % season_id, + {'show_id': show_id}), 'DCNSeason') + else: + return self.url_result( + 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason') + + +class DCNBaseIE(InfoExtractor): + def _extract_video_info(self, video_data, video_id, is_live): + title = video_data.get('title_en') or video_data['title_ar'] + img = video_data.get('img') + thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None + duration = int_or_none(video_data.get('duration')) + description = video_data.get('description_en') or video_data.get('description_ar') + timestamp = parse_iso8601(video_data.get('create_time'), ' ') + + return { + 'id': video_id, + 'title': self._live_title(title) if is_live else title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'is_live': is_live, + } + + def _extract_video_formats(self, webpage, video_id, entry_protocol): + formats = [] + m3u8_url = self._html_search_regex( + r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False) + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)) + + rtsp_url = self._search_regex( + r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) + if rtsp_url: + formats.append({ + 'url': rtsp_url, + 'format_id': 'rtsp', + }) + + self._sort_formats(formats) + return formats + + +class DCNVideoIE(DCNBaseIE): + IE_NAME = 'dcn:video' + _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)' _TEST = { - 'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887', + 'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375', 'info_dict': { 'id': '17375', 'ext': 'mp4', 'title': 'رحلة العمر : الحلقة 1', 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', - 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 2041, 'timestamp': 1227504126, 'upload_date': '20081124', @@ -37,46 +101,96 @@ class DCNIE(InfoExtractor): request = sanitized_Request( 'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id, headers={'Origin': 'http://www.dcndigital.ae'}) - - video = self._download_json(request, video_id) - title = video.get('title_en') or video['title_ar'] + video_data = self._download_json(request, video_id) + info = self._extract_video_info(video_data, video_id, False) webpage = self._download_webpage( 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse.urlencode({ - 'id': video['id'], - 'user_id': video['user_id'], - 'signature': video['signature'], + 'id': video_data['id'], + 'user_id': video_data['user_id'], + 'signature': video_data['signature'], 'countries': 'Q0M=', 'filter': 'DENY', }), video_id) + info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native') + return info - m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url') - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') - rtsp_url = self._search_regex( - r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) - if rtsp_url: - formats.append({ - 'url': rtsp_url, - 'format_id': 'rtsp', +class DCNLiveIE(DCNBaseIE): + IE_NAME = 'dcn:live' + _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)' + + def _real_extract(self, url): + channel_id = self._match_id(url) + + request = sanitized_Request( + 'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id, + headers={'Origin': 'http://www.dcndigital.ae'}) + + channel_data = self._download_json(request, channel_id) + info = self._extract_video_info(channel_data, channel_id, True) + + webpage = self._download_webpage( + 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + + compat_urllib_parse.urlencode({ + 'id': base64.b64encode(channel_data['user_id'].encode()).decode(), + 'channelid': base64.b64encode(channel_data['id'].encode()).decode(), + 'signature': channel_data['signature'], + 'countries': 'Q0M=', + 'filter': 'DENY', + }), channel_id) + info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8') + return info + + +class DCNSeasonIE(InfoExtractor): + IE_NAME = 'dcn:season' + _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))' + _TEST = { + 'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A', + 'info_dict': + { + 'id': '7910', + 'title': 'محاضرات الشيخ الشعراوي', + }, + 'playlist_mincount': 27, + } + + def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + show_id, season_id = re.match(self._VALID_URL, url).groups() + + data = {} + if season_id: + data['season'] = season_id + show_id = smuggled_data.get('show_id') + if show_id is None: + request = sanitized_Request( + 'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id, + headers={'Origin': 'http://www.dcndigital.ae'}) + season = self._download_json(request, season_id) + show_id = season['id'] + data['show_id'] = show_id + request = sanitized_Request( + 'http://admin.mangomolo.com/analytics/index.php/plus/show', + compat_urllib_parse.urlencode(data), + { + 'Origin': 'http://www.dcndigital.ae', + 'Content-Type': 'application/x-www-form-urlencoded' }) - self._sort_formats(formats) + show = self._download_json(request, show_id) + if not season_id: + season_id = show['default_season'] + for season in show['seasons']: + if season['id'] == season_id: + title = season.get('title_en') or season['title_ar'] - img = video.get('img') - thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None - duration = int_or_none(video.get('duration')) - description = video.get('description_en') or video.get('description_ar') - timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ') + entries = [] + for video in show['videos']: + video_id = compat_str(video['id']) + entries.append(self.url_result( + 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id)) - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - } + return self.playlist_result(entries, season_id, title) diff --git a/youtube_dl/extractor/digiteka.py b/youtube_dl/extractor/digiteka.py new file mode 100644 index 0000000..7bb79ff --- /dev/null +++ b/youtube_dl/extractor/digiteka.py @@ -0,0 +1,112 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class DigitekaIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:www\.)?(?:digiteka\.net|ultimedia\.com)/ + (?: + deliver/ + (?P<embed_type> + generic| + musique + ) + (?:/[^/]+)*/ + (?: + src| + article + )| + default/index/video + (?P<site_type> + generic| + music + ) + /id + )/(?P<id>[\d+a-z]+)''' + _TESTS = [{ + # news + 'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r', + 'md5': '276a0e49de58c7e85d32b057837952a2', + 'info_dict': { + 'id': 's8uk0r', + 'ext': 'mp4', + 'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 74, + 'upload_date': '20150317', + 'timestamp': 1426604939, + 'uploader_id': '3fszv', + }, + }, { + # music + 'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8', + 'md5': '2ea3513813cf230605c7e2ffe7eca61c', + 'info_dict': { + 'id': 'xvpfp8', + 'ext': 'mp4', + 'title': 'Two - C\'est La Vie (clip)', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 233, + 'upload_date': '20150224', + 'timestamp': 1424760500, + 'uploader_id': '3rfzk', + }, + }, { + 'url': 'https://www.digiteka.net/deliver/generic/iframe/mdtk/01637594/src/lqm3kl/zone/1/showtitle/1/autoplay/yes', + 'only_matching': True, + }] + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)', + webpage) + if mobj: + return mobj.group('url') + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + video_type = mobj.group('embed_type') or mobj.group('site_type') + if video_type == 'music': + video_type = 'musique' + + deliver_info = self._download_json( + 'http://www.ultimedia.com/deliver/video?video=%s&topic=%s' % (video_id, video_type), + video_id) + + yt_id = deliver_info.get('yt_id') + if yt_id: + return self.url_result(yt_id, 'Youtube') + + jwconf = deliver_info['jwconf'] + + formats = [] + for source in jwconf['playlist'][0]['sources']: + formats.append({ + 'url': source['file'], + 'format_id': source.get('label'), + }) + + self._sort_formats(formats) + + title = deliver_info['title'] + thumbnail = jwconf.get('image') + duration = int_or_none(deliver_info.get('duration')) + timestamp = int_or_none(deliver_info.get('release_time')) + uploader_id = deliver_info.get('owner_id') + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader_id': uploader_id, + 'formats': formats, + } diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index d6723ec..ce680a9 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -9,7 +9,17 @@ 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)?' + _VALID_URL = r'''(?x)http://(?:www\.)?(?: + discovery| + investigationdiscovery| + discoverylife| + animalplanet| + ahctv| + destinationamerica| + sciencechannel| + tlc| + velocity + )\.com/(?:[^/]+/)*(?P<id>[^./?#]+)''' _TESTS = [{ 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', 'info_dict': { @@ -21,8 +31,8 @@ class DiscoveryIE(InfoExtractor): 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' ' back.'), 'duration': 156, - 'timestamp': 1303099200, - 'upload_date': '20110418', + 'timestamp': 1302032462, + 'upload_date': '20110405', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -33,27 +43,38 @@ class DiscoveryIE(InfoExtractor): 'id': 'mythbusters-the-simpsons', 'title': 'MythBusters: The Simpsons', }, - 'playlist_count': 9, + 'playlist_mincount': 10, + }, { + 'url': 'http://www.animalplanet.com/longfin-eels-maneaters/', + 'info_dict': { + 'id': '78326', + 'ext': 'mp4', + 'title': 'Longfin Eels: Maneaters?', + 'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.', + 'upload_date': '20140725', + 'timestamp': 1406246400, + 'duration': 116, + }, }] def _real_extract(self, url): - video_id = self._match_id(url) - info = self._download_json(url + '?flat=1', video_id) + display_id = self._match_id(url) + info = self._download_json(url + '?flat=1', display_id) video_title = info.get('playlist_title') or info.get('video_title') entries = [{ 'id': compat_str(video_info['id']), 'formats': self._extract_m3u8_formats( - video_info['src'], video_id, ext='mp4', + video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls', 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'), + 'webpage_url': video_info.get('href') or video_info.get('url'), '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) + return self.playlist_result(entries, display_id, video_title) diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index d836c1a..d35e888 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import itertools -from .common import InfoExtractor +from .amp import AMPIE from ..compat import ( compat_HTTPError, compat_urllib_parse, @@ -12,14 +12,12 @@ from ..compat import ( from ..utils import ( ExtractorError, clean_html, - determine_ext, int_or_none, - parse_iso8601, sanitized_Request, ) -class DramaFeverBaseIE(InfoExtractor): +class DramaFeverBaseIE(AMPIE): _LOGIN_URL = 'https://www.dramafever.com/accounts/login/' _NETRC_MACHINE = 'dramafever' @@ -69,71 +67,56 @@ class DramaFeverBaseIE(InfoExtractor): class DramaFeverIE(DramaFeverBaseIE): IE_NAME = 'dramafever' _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)' - _TEST = { + _TESTS = [{ 'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/', 'info_dict': { 'id': '4512.1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Cooking with Shin 4512.1', 'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0', + 'episode': 'Episode 1', + 'episode_number': 1, 'thumbnail': 're:^https?://.*\.jpg', 'timestamp': 1404336058, 'upload_date': '20140702', 'duration': 343, - } - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1', + 'info_dict': { + 'id': '4826.4', + 'ext': 'mp4', + 'title': 'Mnet Asian Music Awards 2015 4826.4', + 'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91', + 'episode': 'Mnet Asian Music Awards 2015 - Part 3', + 'episode_number': 4, + 'thumbnail': 're:^https?://.*\.jpg', + 'timestamp': 1450213200, + 'upload_date': '20151215', + 'duration': 5602, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] 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'] + info = self._extract_feed_info( + 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) 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 @@ -143,24 +126,24 @@ class DramaFeverIE(DramaFeverBaseIE): 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, - } + if isinstance(value, list): + for v in value: + if v.get('type') == 'Episode': + subfile = v.get('subfile') or v.get('new_subfile') + if subfile and subfile != 'http://www.dramafever.com/st/': + info.setdefault('subtitles', {}).setdefault('English', []).append({ + 'ext': 'srt', + 'url': subfile, + }) + episode_number = int_or_none(v.get('number')) + episode_fallback = 'Episode' + if episode_number: + episode_fallback += ' %d' % episode_number + info['episode'] = v.get('title') or episode_fallback + info['episode_number'] = episode_number + break + + return info class DramaFeverSeriesIE(DramaFeverBaseIE): diff --git a/youtube_dl/extractor/drbonanza.py b/youtube_dl/extractor/drbonanza.py index 8b98b01..01271f8 100644 --- a/youtube_dl/extractor/drbonanza.py +++ b/youtube_dl/extractor/drbonanza.py @@ -87,7 +87,7 @@ class DRBonanzaIE(InfoExtractor): formats = [] for file in info['Files']: - if info['Type'] == "Video": + if info['Type'] == 'Video': if file['Type'] in video_types: format = parse_filename_info(file['Location']) format.update({ @@ -101,10 +101,10 @@ class DRBonanzaIE(InfoExtractor): if '/bonanza/' in rtmp_url: format['play_path'] = rtmp_url.split('/bonanza/')[1] formats.append(format) - elif file['Type'] == "Thumb": + elif file['Type'] == 'Thumb': thumbnail = file['Location'] - elif info['Type'] == "Audio": - if file['Type'] == "Audio": + elif info['Type'] == 'Audio': + if file['Type'] == 'Audio': format = parse_filename_info(file['Location']) format.update({ 'url': file['Location'], @@ -112,7 +112,7 @@ class DRBonanzaIE(InfoExtractor): 'vcodec': 'none', }) formats.append(format) - elif file['Type'] == "Thumb": + elif file['Type'] == 'Thumb': thumbnail = file['Location'] description = '%s\n%s\n%s\n' % ( diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index 8ac8587..028144f 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -2,14 +2,10 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - unified_strdate, -) +from .zdf import ZDFIE -class DreiSatIE(InfoExtractor): +class DreiSatIE(ZDFIE): IE_NAME = '3sat' _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' _TESTS = [ @@ -35,53 +31,4 @@ class DreiSatIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - details_doc = self._download_xml(details_url, video_id, 'Downloading video details') - - status_code = details_doc.find('./status/statuscode') - if status_code is not None and status_code.text != 'ok': - code = status_code.text - if code == 'notVisibleAnymore': - message = 'Video %s is not available' % video_id - else: - message = '%s returned error: %s' % (self.IE_NAME, code) - raise ExtractorError(message, expected=True) - - thumbnail_els = details_doc.findall('.//teaserimage') - thumbnails = [{ - 'width': int(te.attrib['key'].partition('x')[0]), - 'height': int(te.attrib['key'].partition('x')[2]), - 'url': te.text, - } for te in thumbnail_els] - - information_el = details_doc.find('.//information') - video_title = information_el.find('./title').text - video_description = information_el.find('./detail').text - - details_el = details_doc.find('.//details') - video_uploader = details_el.find('./channel').text - upload_date = unified_strdate(details_el.find('./airtime').text) - - format_els = details_doc.findall('.//formitaet') - formats = [{ - 'format_id': fe.attrib['basetype'], - 'width': int(fe.find('./width').text), - 'height': int(fe.find('./height').text), - 'url': fe.find('./url').text, - 'filesize': int(fe.find('./filesize').text), - 'video_bitrate': int(fe.find('./videoBitrate').text), - } for fe in format_els - if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')] - - self._sort_formats(formats) - - return { - '_type': 'video', - 'id': video_id, - 'title': video_title, - 'formats': formats, - 'description': video_description, - 'thumbnails': thumbnails, - 'thumbnail': thumbnails[-1]['url'], - 'uploader': video_uploader, - 'upload_date': upload_date, - } + return self.extract_from_xml_url(video_id, details_url) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index baa24c6..2d74ff8 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -91,7 +91,7 @@ class DRTVIE(InfoExtractor): subtitles_list = asset.get('SubtitlesList') if isinstance(subtitles_list, list): LANGS = { - 'Danish': 'dk', + 'Danish': 'da', } for subs in subtitles_list: lang = subs['Language'] diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index 0b61ea0..9a44f89 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -17,85 +17,85 @@ class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { - "name": "EightTracks", - "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a", - "info_dict": { + 'name': 'EightTracks', + 'url': 'http://8tracks.com/ytdl/youtube-dl-test-tracks-a', + 'info_dict': { 'id': '1336550', 'display_id': 'youtube-dl-test-tracks-a', - "description": "test chars: \"'/\\ä↭", - "title": "youtube-dl test tracks \"'/\\ä↭<>", + 'description': "test chars: \"'/\\ä↭", + 'title': "youtube-dl test tracks \"'/\\ä↭<>", }, - "playlist": [ + 'playlist': [ { - "md5": "96ce57f24389fc8734ce47f4c1abcc55", - "info_dict": { - "id": "11885610", - "ext": "m4a", - "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': '96ce57f24389fc8734ce47f4c1abcc55', + 'info_dict': { + 'id': '11885610', + 'ext': 'm4a', + 'title': "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "4ab26f05c1f7291ea460a3920be8021f", - "info_dict": { - "id": "11885608", - "ext": "m4a", - "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': '4ab26f05c1f7291ea460a3920be8021f', + 'info_dict': { + 'id': '11885608', + 'ext': 'm4a', + 'title': "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "d30b5b5f74217410f4689605c35d1fd7", - "info_dict": { - "id": "11885679", - "ext": "m4a", - "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': 'd30b5b5f74217410f4689605c35d1fd7', + 'info_dict': { + 'id': '11885679', + 'ext': 'm4a', + 'title': "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "4eb0a669317cd725f6bbd336a29f923a", - "info_dict": { - "id": "11885680", - "ext": "m4a", - "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': '4eb0a669317cd725f6bbd336a29f923a', + 'info_dict': { + 'id': '11885680', + 'ext': 'm4a', + 'title': "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "1893e872e263a2705558d1d319ad19e8", - "info_dict": { - "id": "11885682", - "ext": "m4a", - "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': '1893e872e263a2705558d1d319ad19e8', + 'info_dict': { + 'id': '11885682', + 'ext': 'm4a', + 'title': "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "b673c46f47a216ab1741ae8836af5899", - "info_dict": { - "id": "11885683", - "ext": "m4a", - "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': 'b673c46f47a216ab1741ae8836af5899', + 'info_dict': { + 'id': '11885683', + 'ext': 'm4a', + 'title': "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "1d74534e95df54986da7f5abf7d842b7", - "info_dict": { - "id": "11885684", - "ext": "m4a", - "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': '1d74534e95df54986da7f5abf7d842b7', + 'info_dict': { + 'id': '11885684', + 'ext': 'm4a', + 'title': "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } }, { - "md5": "f081f47af8f6ae782ed131d38b9cd1c0", - "info_dict": { - "id": "11885685", - "ext": "m4a", - "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", - "uploader_id": "ytdl" + 'md5': 'f081f47af8f6ae782ed131d38b9cd1c0', + 'info_dict': { + 'id': '11885685', + 'ext': 'm4a', + 'title': "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad", + 'uploader_id': 'ytdl' } } ] diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 5dfea0d..f733970 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -1,9 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + remove_start, + sanitized_Request, +) class EinthusanIE(InfoExtractor): @@ -34,27 +37,33 @@ class EinthusanIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) + video_id = self._match_id(url) + + request = sanitized_Request(url) + request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0') + webpage = self._download_webpage(request, video_id) + + title = self._html_search_regex( + r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>', + webpage, 'title') - video_title = self._html_search_regex( - r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title') + video_id = self._search_regex( + r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id) - video_url = self._html_search_regex( - r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''', - webpage, 'video url') + video_url = self._download_webpage( + 'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/' + % video_id, video_id) description = self._html_search_meta('description', webpage) thumbnail = self._html_search_regex( r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', webpage, "thumbnail url", fatal=False) if thumbnail is not None: - thumbnail = thumbnail.replace('..', 'http://www.einthusan.com') + thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..')) return { 'id': video_id, - 'title': video_title, + 'title': title, 'url': video_url, 'thumbnail': thumbnail, 'description': description, diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py index c83845f..713cb7b 100644 --- a/youtube_dl/extractor/eitb.py +++ b/youtube_dl/extractor/eitb.py @@ -65,18 +65,14 @@ class EitbIE(InfoExtractor): if token_data: token = token_data.get('token') if token: - m3u8_formats = self._extract_m3u8_formats( - '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + formats.extend(self._extract_m3u8_formats( + '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)) hds_url = media.get('HDS_SURL') if hds_url: - f4m_formats = self._extract_f4m_formats( + formats.extend(self._extract_f4m_formats( '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'), - video_id, f4m_id='hds', fatal=False) - if f4m_formats: - formats.extend(f4m_formats) + video_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 02c6a46..4c8190d 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -13,12 +13,12 @@ class EllenTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)' _TEST = { 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', - 'md5': '8e3c576bf2e9bfff4d76565f56f94c9c', + 'md5': '4294cf98bc165f218aaa0b89e0fd8042', 'info_dict': { 'id': '0_ipq1gsai', - 'ext': 'mp4', + 'ext': 'mov', 'title': 'Fast Fingers of Fate', - 'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6', + 'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a', 'timestamp': 1428035648, 'upload_date': '20150403', 'uploader_id': 'batchUser', @@ -72,7 +72,7 @@ class EllenTVClipsIE(InfoExtractor): def _extract_playlist(self, webpage): json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') try: - return json.loads("[{" + json_string + "}]") + return json.loads('[{' + json_string + '}]') except ValueError as ve: raise ExtractorError('Failed to download JSON', cause=ve) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index e6f8f03..db4b263 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -1,18 +1,30 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import remove_end class ESPNIE(InfoExtractor): _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)' - _WORKING = False _TESTS = [{ 'url': 'http://espn.go.com/video/clip?id=10365079', 'info_dict': { 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', 'ext': 'mp4', - 'title': 'dm_140128_30for30Shorts___JudgingJewellv2', - 'description': '', + 'title': '30 for 30 Shorts: Judging Jewell', + 'description': None, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season + 'url': 'http://espn.go.com/video/clip?id=2743663', + 'info_dict': { + 'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg', + 'ext': 'mp4', + 'title': 'Must-See Moments: Best of the MLS season', }, 'params': { # m3u8 download @@ -41,15 +53,26 @@ class ESPNIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_id = self._search_regex( - r'class="video-play-button"[^>]+data-id="(\d+)', - webpage, 'video id') + r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)', + webpage, 'video id', group='id') + cms = 'espn' + if 'data-source="intl"' in webpage: + cms = 'intl' + player_url = 'https://espn.go.com/video/iframe/twitter/?id=%s&cms=%s' % (video_id, cms) player = self._download_webpage( - 'https://espn.go.com/video/iframe/twitter/?id=%s' % video_id, video_id) + player_url, video_id) pcode = self._search_regex( r'["\']pcode=([^"\']+)["\']', player, 'pcode') - return self.url_result( - 'ooyalaexternal:espn:%s:%s' % (video_id, pcode), - 'OoyalaExternal') + title = remove_end( + self._og_search_title(webpage), + '- ESPN Video').strip() + + return { + '_type': 'url_transparent', + 'url': 'ooyalaexternal:%s:%s:%s' % (cms, video_id, pcode), + 'ie_key': 'OoyalaExternal', + 'title': title, + } diff --git a/youtube_dl/extractor/esri.py b/youtube_dl/extractor/esri.py index bf5d201..d4205d7 100644 --- a/youtube_dl/extractor/esri.py +++ b/youtube_dl/extractor/esri.py @@ -61,7 +61,7 @@ class EsriVideoIE(InfoExtractor): webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_meta( - 'last-modified', webpage, 'upload date', fatal=None)) + 'last-modified', webpage, 'upload date', fatal=False)) return { 'id': video_id, diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py index 493d38a..84a9b75 100644 --- a/youtube_dl/extractor/everyonesmixtape.py +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -14,14 +14,14 @@ class EveryonesMixtapeIE(InfoExtractor): _TESTS = [{ 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', - "info_dict": { + 'info_dict': { 'id': '5bfseWNmlds', 'ext': 'mp4', - "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", - "uploader": "FKR.TV", - "uploader_id": "frenchkissrecords", - "description": "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com", - "upload_date": "20081015" + 'title': "Passion Pit - \"Sleepyhead\" (Official Music Video)", + 'uploader': 'FKR.TV', + 'uploader_id': 'frenchkissrecords', + 'description': "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com", + 'upload_date': '20081015' }, 'params': { 'skip_download': True, # This is simply YouTube diff --git a/youtube_dl/extractor/exfm.py b/youtube_dl/extractor/exfm.py index 4de02ae..0c0fe6d 100644 --- a/youtube_dl/extractor/exfm.py +++ b/youtube_dl/extractor/exfm.py @@ -41,7 +41,7 @@ class ExfmIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) song_id = mobj.group('id') - info_url = "http://ex.fm/api/v3/song/%s" % song_id + info_url = 'http://ex.fm/api/v3/song/%s' % song_id info = self._download_json(info_url, song_id)['song'] song_url = info['url'] if re.match(self._SOUNDCLOUD_URL, song_url) is not None: diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index fd85441..0a9a5ca 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -6,12 +6,14 @@ import socket from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_http_client, - compat_str, compat_urllib_error, compat_urllib_parse_unquote, + compat_urllib_parse_unquote_plus, ) from ..utils import ( + error_to_compat_str, ExtractorError, limit_length, sanitized_Request, @@ -23,19 +25,30 @@ from ..utils import ( class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) - https?://(?:\w+\.)?facebook\.com/ - (?:[^#]*?\#!/)? - (?: - (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) - (?:v|video_id)=| - [^/]+/videos/(?:[^/]+/)? - ) - (?P<id>[0-9]+) - (?:.*)''' + (?: + https?:// + (?:\w+\.)?facebook\.com/ + (?:[^#]*?\#!/)? + (?: + (?: + video/video\.php| + photo\.php| + video\.php| + video/embed + )\?(?:.*?)(?:v|video_id)=| + [^/]+/videos/(?:[^/]+/)? + )| + facebook: + ) + (?P<id>[0-9]+) + ''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' + + _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' + _TESTS = [{ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', 'md5': '6a40d33c0eccbb1af76cf0485a052659', @@ -57,6 +70,16 @@ class FacebookIE(InfoExtractor): 'expected_warnings': [ 'title' ] + }, { + 'note': 'Video with DASH manifest', + 'url': 'https://www.facebook.com/video.php?v=957955867617029', + 'md5': '54706e4db4f5ad58fbad82dde1f1213f', + 'info_dict': { + 'id': '957955867617029', + 'ext': 'mp4', + 'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...', + 'uploader': 'Demy de Zeeuw', + }, }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, @@ -66,6 +89,9 @@ class FacebookIE(InfoExtractor): }, { 'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater', 'only_matching': True, + }, { + 'url': 'facebook:544765982287235', + 'only_matching': True, }] def _login(self): @@ -74,7 +100,7 @@ class FacebookIE(InfoExtractor): return login_page_req = sanitized_Request(self._LOGIN_URL) - login_page_req.add_header('Cookie', 'locale=en_US') + self._set_cookie('facebook.com', 'locale', 'en_US') login_page = self._download_webpage(login_page_req, None, note='Downloading login page', errnote='Unable to download login page') @@ -100,13 +126,25 @@ class FacebookIE(InfoExtractor): login_results = self._download_webpage(request, None, note='Logging in', errnote='unable to fetch login page') if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: - self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') + error = self._html_search_regex( + r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>', + login_results, 'login error', default=None, group='error') + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.') + return + + fb_dtsg = self._search_regex( + r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None) + h = self._search_regex( + r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None) + + if not fb_dtsg or not h: return check_form = { - 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'), - 'h': self._search_regex( - r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'), + 'fb_dtsg': fb_dtsg, + 'h': h, 'name_action_selected': 'dont_save', } check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) @@ -114,9 +152,9 @@ class FacebookIE(InfoExtractor): check_response = self._download_webpage(check_req, None, note='Confirming login') if re.search(r'id="checkpointSubmitButton"', check_response) is not None: - self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') + self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning('unable to log in: %s' % compat_str(err)) + self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err)) return def _real_initialize(self): @@ -124,13 +162,36 @@ class FacebookIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - url = 'https://www.facebook.com/video/video.php?v=%s' % video_id - webpage = self._download_webpage(url, video_id) + req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id) + req.add_header('User-Agent', self._CHROME_USER_AGENT) + webpage = self._download_webpage(req, video_id) + + video_data = None BEFORE = '{swf.addParam(param[0], param[1]);});\n' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) - if not m: + if m: + data = dict(json.loads(m.group(1))) + params_raw = compat_urllib_parse_unquote(data['params']) + video_data = json.loads(params_raw)['video_data'] + + def video_data_list2dict(video_data): + ret = {} + for item in video_data: + format_id = item['stream_type'] + ret.setdefault(format_id, []).append(item) + return ret + + if not video_data: + server_js_data = self._parse_json(self._search_regex( + r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id) + for item in server_js_data.get('instances', []): + if item[1][0] == 'VideoConfig': + video_data = video_data_list2dict(item[2][0]['videoData']) + break + + if not video_data: m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) if m_msg is not None: raise ExtractorError( @@ -138,12 +199,9 @@ class FacebookIE(InfoExtractor): expected=True) else: raise ExtractorError('Cannot parse data') - data = dict(json.loads(m.group(1))) - params_raw = compat_urllib_parse_unquote(data['params']) - params = json.loads(params_raw) formats = [] - for format_id, f in params['video_data'].items(): + for format_id, f in video_data.items(): if not f or not isinstance(f, list): continue for quality in ('sd', 'hd'): @@ -155,16 +213,22 @@ class FacebookIE(InfoExtractor): 'url': src, 'preference': -10 if format_id == 'progressive' else 0, }) + dash_manifest = f[0].get('dash_manifest') + if dash_manifest: + formats.extend(self._parse_mpd_formats( + compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest)))) if not formats: raise ExtractorError('Cannot find video formats') + self._sort_formats(formats) + video_title = self._html_search_regex( r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title', default=None) if not video_title: video_title = self._html_search_regex( r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', - webpage, 'alternative title', fatal=False) + webpage, 'alternative title', default=None) video_title = limit_length(video_title, 80) if not video_title: video_title = 'Facebook video #%s' % video_id @@ -176,3 +240,33 @@ class FacebookIE(InfoExtractor): 'formats': formats, 'uploader': uploader, } + + +class FacebookPostIE(InfoExtractor): + IE_NAME = 'facebook:post' + _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)' + _TEST = { + 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', + 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', + 'info_dict': { + 'id': '544765982287235', + 'ext': 'mp4', + 'title': '"What are you doing running in the snow?"', + 'uploader': 'FailArmy', + } + } + + def _real_extract(self, url): + post_id = self._match_id(url) + + webpage = self._download_webpage(url, post_id) + + entries = [ + self.url_result('facebook:%s' % video_id, FacebookIE.ie_key()) + for video_id in self._parse_json( + self._search_regex( + r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', + webpage, 'video ids', group='ids'), + post_id)] + + return self.playlist_result(entries, post_id) diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index cebdd01..fd53545 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -2,6 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, +) class FazIE(InfoExtractor): @@ -37,31 +42,32 @@ class FazIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + description = self._og_search_description(webpage) config_xml_url = self._search_regex( - r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') + r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url') config = self._download_xml( config_xml_url, video_id, 'Downloading config xml') - encodings = config.find('ENCODINGS') + encodings = xpath_element(config, 'ENCODINGS', 'encodings', True) formats = [] for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): - encoding = encodings.find(code) - if encoding is None: - continue - encoding_url = encoding.find('FILENAME').text - formats.append({ - 'url': encoding_url, - 'format_id': code.lower(), - 'quality': pref, - }) + encoding = xpath_element(encodings, code) + if encoding is not None: + encoding_url = xpath_text(encoding, 'FILENAME') + if encoding_url: + formats.append({ + 'url': encoding_url, + 'format_id': code.lower(), + 'quality': pref, + 'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')), + }) self._sort_formats(formats) - descr = self._html_search_regex( - r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False) return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': descr, - 'thumbnail': config.find('STILL/STILL_BIG').text, + 'description': description.strip() if description else None, + 'thumbnail': xpath_text(config, 'STILL/STILL_BIG'), + 'duration': int_or_none(xpath_text(config, 'DURATION')), } diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index 92e8c57..9580f5c 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -37,8 +37,8 @@ class FC2IE(InfoExtractor): 'params': { 'username': 'ytdl@yt-dl.org', 'password': '(snip)', - 'skip': 'requires actual password' - } + }, + 'skip': 'requires actual password', }, { 'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF', 'only_matching': True, @@ -87,7 +87,7 @@ class FC2IE(InfoExtractor): mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest() info_url = ( - "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&". + 'http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&'. format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E'))) info_webpage = self._download_webpage( diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 40ea278..5f6e65d 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( clean_html, determine_ext, - ExtractorError, + js_to_json, ) @@ -32,24 +30,22 @@ class FKTVIE(InfoExtractor): 'http://fernsehkritik.tv/folge-%s/play' % episode, episode) title = clean_html(self._html_search_regex( '<h3>([^<]+)</h3>', webpage, 'title')) - matches = re.search( - r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>', - webpage) - if matches is None: - raise ExtractorError('Unable to extract the video') - - poster, sources = matches.groups() - if poster is None: - self.report_warning('unable to extract thumbnail') - - urls = re.findall(r'<source[^>]+src="([^"]+)"', sources) - formats = [{ - 'url': furl, - 'format_id': determine_ext(furl), - } for furl in urls] + thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False) + sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json) + + formats = [] + for source in sources: + furl = source.get('src') + if furl: + formats.append({ + 'url': furl, + 'format_id': determine_ext(furl), + }) + self._sort_formats(formats) + return { 'id': episode, 'title': title, 'formats': formats, - 'thumbnail': poster, + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 91cd46e..18f439d 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -1,67 +1,93 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, - find_xpath_attr, - sanitized_Request, + int_or_none, + qualities, ) class FlickrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' + _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/[\w\-_@]+/(?P<id>\d+)' _TEST = { 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', + 'md5': '164fe3fa6c22e18d448d4d5af2330f31', 'info_dict': { 'id': '5645318632', - 'ext': 'mp4', - "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - "uploader_id": "forestwander-nature-pictures", - "title": "Dark Hollow Waterfalls" + 'ext': 'mpg', + 'description': 'Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.', + 'title': 'Dark Hollow Waterfalls', + 'duration': 19, + 'timestamp': 1303528740, + 'upload_date': '20110423', + 'uploader_id': '10922353@N03', + 'uploader': 'Forest Wander', + 'comment_count': int, + 'view_count': int, + 'tags': list, } } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + _API_BASE_URL = 'https://api.flickr.com/services/rest?' - video_id = mobj.group('id') - video_uploader_id = mobj.group('uploader_id') - webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id - req = sanitized_Request(webpage_url) - req.add_header( - 'User-Agent', - # it needs a more recent version - 'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)') - webpage = self._download_webpage(req, video_id) + def _call_api(self, method, video_id, api_key, note, secret=None): + query = { + 'photo_id': video_id, + 'method': 'flickr.%s' % method, + 'api_key': api_key, + 'format': 'json', + 'nojsoncallback': 1, + } + if secret: + query['secret'] = secret + data = self._download_json(self._API_BASE_URL + compat_urllib_parse.urlencode(query), video_id, note) + if data['stat'] != 'ok': + raise ExtractorError(data['message']) + return data - secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret') + def _real_extract(self, url): + video_id = self._match_id(url) - first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' - first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage') + api_key = self._download_json( + 'https://www.flickr.com/hermes_error_beacon.gne', video_id, + 'Downloading api key')['site_key'] - node_id = find_xpath_attr( - first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id', - 'id').text + video_info = self._call_api( + 'photos.getInfo', video_id, api_key, 'Downloading video info')['photo'] + if video_info['media'] == 'video': + streams = self._call_api( + 'video.getStreamInfo', video_id, api_key, + 'Downloading streams info', video_info['secret'])['streams'] - second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' - second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage') + preference = qualities( + ['288p', 'iphone_wifi', '100', '300', '700', '360p', 'appletv', '720p', '1080p', 'orig']) - self.report_extraction(video_id) + formats = [] + for stream in streams['stream']: + stream_type = str(stream.get('type')) + formats.append({ + 'format_id': stream_type, + 'url': stream['_content'], + 'preference': preference(stream_type), + }) + self._sort_formats(formats) - stream = second_xml.find('.//STREAM') - if stream is None: - raise ExtractorError('Unable to extract video url') - video_url = stream.attrib['APP'] + stream.attrib['FULLPATH'] + owner = video_info.get('owner', {}) - return { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader_id': video_uploader_id, - } + return { + 'id': video_id, + 'title': video_info['title']['_content'], + 'description': video_info.get('description', {}).get('_content'), + 'formats': formats, + 'timestamp': int_or_none(video_info.get('dateuploaded')), + 'duration': int_or_none(video_info.get('video', {}).get('duration')), + 'uploader_id': owner.get('nsid'), + 'uploader': owner.get('realname'), + 'comment_count': int_or_none(video_info.get('comments', {}).get('_content')), + 'view_count': int_or_none(video_info.get('views')), + 'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])] + } + else: + raise ExtractorError('not a video', expected=True) diff --git a/youtube_dl/extractor/footyroom.py b/youtube_dl/extractor/footyroom.py index 4c7dbca..370fd00 100644 --- a/youtube_dl/extractor/footyroom.py +++ b/youtube_dl/extractor/footyroom.py @@ -13,6 +13,7 @@ class FootyRoomIE(InfoExtractor): 'title': 'Schalke 04 0 – 2 Real Madrid', }, 'playlist_count': 3, + 'skip': 'Video for this match is not available', }, { 'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/', 'info_dict': { diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py new file mode 100644 index 0000000..fa05af5 --- /dev/null +++ b/youtube_dl/extractor/fox.py @@ -0,0 +1,36 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import smuggle_url + + +class FOXIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.fox.com/watch/255180355939/7684182528', + 'md5': 'ebd296fcc41dd4b19f8115d8461a3165', + 'info_dict': { + 'id': '255180355939', + 'ext': 'mp4', + 'title': 'Official Trailer: Gotham', + 'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.', + 'duration': 129, + }, + 'add_ie': ['ThePlatform'], + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + release_url = self._parse_json(self._search_regex( + r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'), + video_id)['release_url'] + '&switch=http' + + return { + '_type': 'url_transparent', + 'ie_key': 'ThePlatform', + 'url': smuggle_url(release_url, {'force_smil_url': True}), + 'id': video_id, + } diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 3a4a591..318ac01 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -2,14 +2,10 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import ( - parse_iso8601, - int_or_none, -) +from .amp import AMPIE -class FoxNewsIE(InfoExtractor): +class FoxNewsIE(AMPIE): IE_DESC = 'Fox News and Fox Business Video' _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' _TESTS = [ @@ -20,10 +16,10 @@ class FoxNewsIE(InfoExtractor): 'id': '3937480', 'ext': 'flv', 'title': 'Frozen in Time', - 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler', + 'description': '16-year-old girl is size of toddler', 'duration': 265, - 'timestamp': 1304411491, - 'upload_date': '20110503', + # 'timestamp': 1304411491, + # 'upload_date': '20110503', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -34,10 +30,10 @@ class FoxNewsIE(InfoExtractor): 'id': '3922535568001', 'ext': 'mp4', 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal", - 'description': "Congressman discusses the president's executive action", + 'description': "Congressman discusses president's plan", 'duration': 292, - 'timestamp': 1417662047, - 'upload_date': '20141204', + # 'timestamp': 1417662047, + # 'upload_date': '20141204', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -52,52 +48,9 @@ class FoxNewsIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - host = mobj.group('host') + host, video_id = re.match(self._VALID_URL, url).groups() - video = self._download_json( - 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id) - - item = video['channel']['item'] - title = item['title'] - description = item['description'] - timestamp = parse_iso8601(item['dc-date']) - - media_group = item['media-group'] - duration = None - formats = [] - for media in media_group['media-content']: - attributes = media['@attributes'] - video_url = attributes['url'] - if video_url.endswith('.f4m'): - formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id)) - elif video_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv')) - elif not video_url.endswith('.smil'): - duration = int_or_none(attributes.get('duration')) - formats.append({ - 'url': video_url, - 'format_id': media['media-category']['@attributes']['label'], - 'preference': 1, - 'vbr': int_or_none(attributes.get('bitrate')), - 'filesize': int_or_none(attributes.get('fileSize')) - }) - self._sort_formats(formats) - - media_thumbnail = media_group['media-thumbnail']['@attributes'] - thumbnails = [{ - 'url': media_thumbnail['url'], - 'width': int_or_none(media_thumbnail.get('width')), - 'height': int_or_none(media_thumbnail.get('height')), - }] if media_thumbnail else [] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - 'thumbnails': thumbnails, - } + info = self._extract_feed_info( + 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id)) + info['id'] = video_id + return info diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 1e83a4e..e2ca962 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -8,6 +8,7 @@ from ..compat import ( from ..utils import ( determine_ext, int_or_none, + ExtractorError, ) @@ -22,14 +23,13 @@ class FranceCultureIE(InfoExtractor): 'alt_title': 'Carnet nomade | 13-14', 'vcodec': 'none', 'upload_date': '20140301', - 'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', - 'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats', + 'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', + 'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche', 'timestamp': 1393700400, } } - def _real_extract(self, url): - video_id = self._match_id(url) + def _extract_from_player(self, url, video_id): webpage = self._download_webpage(url, video_id) video_path = self._search_regex( @@ -42,6 +42,9 @@ class FranceCultureIE(InfoExtractor): r'<a id="player".*?>\s+<img src="([^"]+)"', webpage, 'thumbnail', fatal=False) + display_id = self._search_regex( + r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id') + title = self._html_search_regex( r'<span class="title-diffusion">(.*?)</span>', webpage, 'title') alt_title = self._html_search_regex( @@ -66,4 +69,37 @@ class FranceCultureIE(InfoExtractor): 'alt_title': alt_title, 'thumbnail': thumbnail, 'description': description, + 'display_id': display_id, } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self._extract_from_player(url, video_id) + + +class FranceCultureEmissionIE(FranceCultureIE): + _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)' + _TEST = { + 'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'info_dict': { + 'title': 'Jean-Gabriel Périot, cinéaste', + 'alt_title': 'Les Carnets de la création', + 'id': '5093239', + 'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'ext': 'mp3', + 'timestamp': 1444762500, + 'upload_date': '20151013', + 'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_path = self._html_search_regex( + r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player') + if video_path == 'no_path_player': + raise ExtractorError('no player : no sound in this page.', expected=True) + new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id') + video_url = compat_urlparse.urljoin(url, video_path) + return self._extract_from_player(video_url, new_id) diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 6613ee1..0388ba0 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import int_or_none @@ -12,7 +10,7 @@ class FranceInterIE(InfoExtractor): _TEST = { 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', 'md5': '4764932e466e6f6c79c317d2e74f6884', - "info_dict": { + 'info_dict': { 'id': '793962', 'ext': 'mp3', 'title': 'L’Histoire dans les jeux vidéo', @@ -23,8 +21,7 @@ class FranceInterIE(InfoExtractor): } 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) @@ -33,7 +30,7 @@ class FranceInterIE(InfoExtractor): video_url = 'http://www.franceinter.fr/' + path title = self._html_search_regex( - r'<span class="title">(.+?)</span>', webpage, 'title') + r'<span class="title-diffusion">(.+?)</span>', webpage, 'title') description = self._html_search_regex( r'<span class="description">(.*?)</span>', webpage, 'description', fatal=False) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 8e60cf6..3f4ac30 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -289,7 +289,7 @@ class FranceTVIE(FranceTVBaseInfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_id, catalogue = self._html_search_regex( - r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"', + r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video ID').split('@') return self._extract_video(video_id, catalogue) diff --git a/youtube_dl/extractor/freevideo.py b/youtube_dl/extractor/freevideo.py index f755e3c..c7bec02 100644 --- a/youtube_dl/extractor/freevideo.py +++ b/youtube_dl/extractor/freevideo.py @@ -12,8 +12,8 @@ class FreeVideoIE(InfoExtractor): 'info_dict': { 'id': 'vysukany-zadecek-22033', 'ext': 'mp4', - "title": "vysukany-zadecek-22033", - "age_limit": 18, + 'title': 'vysukany-zadecek-22033', + 'age_limit': 18, }, 'skip': 'Blocked outside .cz', } diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py new file mode 100644 index 0000000..0f37ed7 --- /dev/null +++ b/youtube_dl/extractor/funimation.py @@ -0,0 +1,191 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + determine_ext, + encode_dict, + int_or_none, + sanitized_Request, + ExtractorError, + urlencode_postdata +) + + +class FunimationIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)' + + _NETRC_MACHINE = 'funimation' + + _TESTS = [{ + 'url': 'http://www.funimation.com/shows/air/videos/official/breeze', + 'info_dict': { + 'id': '658', + 'display_id': 'breeze', + 'ext': 'mp4', + 'title': 'Air - 1 - Breeze', + 'description': 'md5:1769f43cd5fc130ace8fd87232207892', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play', + 'info_dict': { + 'id': '31128', + 'display_id': 'role-play', + 'ext': 'mp4', + 'title': '.hack//SIGN - 1 - Role Play', + 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview', + 'info_dict': { + 'id': '9635', + 'display_id': 'broadcast-dub-preview', + 'ext': 'mp4', + 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview', + 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', + 'thumbnail': 're:https?://.*\.(?:jpg|png)', + }, + }] + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + data = urlencode_postdata(encode_dict({ + 'email_field': username, + 'password_field': password, + })) + login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ + 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', + 'Content-Type': 'application/x-www-form-urlencoded' + }) + login_page = self._download_webpage( + login_request, None, 'Logging in as %s' % username) + if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')): + return + error = self._html_search_regex( + r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>', + login_page, 'error messages', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + display_id = self._match_id(url) + + errors = [] + formats = [] + + ERRORS_MAP = { + 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn', + 'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut', + 'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut', + 'ERROR_VIDEO_EXPIRED': 'videoExpired', + 'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable', + 'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription', + 'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription', + 'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding', + 'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN', + 'ERROR_STREAM_NOT_FOUND': 'streamNotFound', + } + + USER_AGENTS = ( + # PC UA is served with m3u8 that provides some bonus lower quality formats + ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'), + # Mobile UA allows to extract direct links and also does not fail when + # PC UA fails with hulu error (e.g. + # http://www.funimation.com/shows/hacksign/videos/official/role-play) + ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'), + ) + + for kind, user_agent in USER_AGENTS: + request = sanitized_Request(url) + request.add_header('User-Agent', user_agent) + webpage = self._download_webpage( + request, display_id, 'Downloading %s webpage' % kind) + + playlist = self._parse_json( + self._search_regex( + r'var\s+playersData\s*=\s*(\[.+?\]);\n', + webpage, 'players data'), + display_id)[0]['playlist'] + + items = next(item['items'] for item in playlist if item.get('items')) + item = next(item for item in items if item.get('itemAK') == display_id) + + error_messages = {} + video_error_messages = self._search_regex( + r'var\s+videoErrorMessages\s*=\s*({.+?});\n', + webpage, 'error messages', default=None) + if video_error_messages: + error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False) + if error_messages_json: + for _, error in error_messages_json.items(): + type_ = error.get('type') + description = error.get('description') + content = error.get('content') + if type_ == 'text' and description and content: + error_message = ERRORS_MAP.get(description) + if error_message: + error_messages[error_message] = content + + for video in item.get('videoSet', []): + auth_token = video.get('authToken') + if not auth_token: + continue + funimation_id = video.get('FUNImationID') or video.get('videoId') + preference = 1 if video.get('languageMode') == 'dub' else 0 + if not auth_token.startswith('?'): + auth_token = '?%s' % auth_token + for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)): + format_url = video.get('%sUrl' % quality) + if not format_url: + continue + if not format_url.startswith(('http', '//')): + errors.append(format_url) + continue + if determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native', + preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False)) + else: + tbr = int_or_none(self._search_regex( + r'-(\d+)[Kk]', format_url, 'tbr', default=None)) + formats.append({ + 'url': format_url + auth_token, + 'format_id': '%s-http-%dp' % (funimation_id, height), + 'height': height, + 'tbr': tbr, + 'preference': preference, + }) + + if not formats and errors: + raise ExtractorError( + '%s returned error: %s' + % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))), + expected=True) + + self._sort_formats(formats) + + title = item['title'] + artist = item.get('artist') + if artist: + title = '%s - %s' % (artist, title) + description = self._og_search_description(webpage) or item.get('description') + thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl') + video_id = item.get('itemId') or display_id + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 7f21d74..4c4a87e 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -51,10 +51,8 @@ class FunnyOrDieIE(InfoExtractor): formats = [] - m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)] bitrates.sort() diff --git a/youtube_dl/extractor/gameinformer.py b/youtube_dl/extractor/gameinformer.py new file mode 100644 index 0000000..25870c1 --- /dev/null +++ b/youtube_dl/extractor/gameinformer.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class GameInformerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx' + _TEST = { + 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', + 'info_dict': { + 'id': '4515472681001', + 'ext': 'm3u8', + 'title': 'Replay - Animal Crossing', + 'description': 'md5:2e211891b215c85d061adc7a4dd2d930', + 'timestamp': 1443457610706, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url') + json_data = self._download_json( + bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions', + display_id) + + return { + 'id': compat_str(json_data['id']), + 'display_id': display_id, + 'url': json_data['IOSRenditions'][0]['url'], + 'title': json_data['name'], + 'description': json_data.get('shortDescription'), + 'timestamp': int_or_none(json_data.get('publishedDate')), + 'duration': int_or_none(json_data.get('length')), + } diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index 027f55e..f6b9046 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -6,24 +6,29 @@ from ..utils import ( xpath_text, xpath_with_ns, ) +from .youtube import YoutubeIE class GamekingsIE(InfoExtractor): - _VALID_URL = r'http://www\.gamekings\.tv/(?:videos|nieuws)/(?P<id>[^/]+)' + _VALID_URL = r'http://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)' _TESTS = [{ - 'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/', - # MD5 is flaky, seems to change regularly - # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3', + # YouTube embed video + 'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/', + 'md5': '5208d3a17adeaef829a7861887cb9029', 'info_dict': { - 'id': 'phoenix-wright-ace-attorney-dual-destinies-review', + 'id': 'HkSQKetlGOU', 'ext': 'mp4', - 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', - 'description': 'md5:36fd701e57e8c15ac8682a2374c99731', + 'title': 'Phoenix Wright: Ace Attorney - Dual Destinies Review', + 'description': 'md5:db88c0e7f47e9ea50df3271b9dc72e1d', 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader_id': 'UCJugRGo4STYMeFr5RoOShtQ', + 'uploader': 'Gamekings Vault', + 'upload_date': '20151123', }, + 'add_ie': ['Youtube'], }, { # vimeo video - 'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/', + 'url': 'http://www.gamekings.nl/videos/the-legend-of-zelda-majoras-mask/', 'md5': '12bf04dfd238e70058046937657ea68d', 'info_dict': { 'id': 'the-legend-of-zelda-majoras-mask', @@ -33,7 +38,7 @@ class GamekingsIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, { - 'url': 'http://www.gamekings.tv/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/', + 'url': 'http://www.gamekings.nl/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/', 'only_matching': True, }] @@ -43,7 +48,11 @@ class GamekingsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) playlist_id = self._search_regex( - r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id') + r'gogoVideo\([^,]+,\s*"([^"]+)', webpage, 'playlist id') + + # Check if a YouTube embed is used + if YoutubeIE.suitable(playlist_id): + return self.url_result(playlist_id, ie='Youtube') playlist = self._download_xml( 'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id, diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py index a6ab795..c3f031d 100644 --- a/youtube_dl/extractor/gametrailers.py +++ b/youtube_dl/extractor/gametrailers.py @@ -1,19 +1,62 @@ from __future__ import unicode_literals -from .mtv import MTVServicesInfoExtractor +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_age_limit, + url_basename, +) -class GametrailersIE(MTVServicesInfoExtractor): - _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' +class GametrailersIE(InfoExtractor): + _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)' + _TEST = { - 'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer', - 'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7', + 'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review', + 'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a', 'info_dict': { - 'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d', + 'id': '2983958', 'ext': 'mp4', - 'title': 'E3 2013: Debut Trailer', - 'description': 'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!', + 'display_id': '116437-Just-Cause-3-Review', + 'title': 'Just Cause 3 - Review', + 'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?', }, } - _FEED_URL = 'http://www.gametrailers.com/feeds/mrss' + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'<title>(.+?)\|', webpage, 'title').strip() + embed_url = self._proto_relative_url( + self._search_regex( + r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage, + 'embed url'), + scheme='http:') + video_id = url_basename(embed_url) + embed_page = self._download_webpage(embed_url, video_id) + embed_vars_json = self._search_regex( + r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page, + 'embed vars') + info = self._parse_json(embed_vars_json, video_id) + + formats = [] + for media in info['media']: + if media['mediaPurpose'] == 'play': + formats.append({ + 'url': media['uri'], + 'height': media['height'], + 'width:': media['width'], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'thumbnail': info.get('thumbUri'), + 'description': self._og_search_description(webpage), + 'duration': int_or_none(info.get('videoLengthInSeconds')), + 'age_limit': parse_age_limit(info.get('audienceRating')), + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5075d13..c6bf8d2 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -44,7 +44,6 @@ 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 .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE @@ -54,6 +53,11 @@ from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE from .screenwavemedia import ScreenwaveMediaIE from .mtv import MTVServicesEmbeddedIE +from .pladform import PladformIE +from .videomore import VideomoreIE +from .googledrive import GoogleDriveIE +from .jwplatform import JWPlatformIE +from .digiteka import DigitekaIE class GenericIE(InfoExtractor): @@ -220,6 +224,20 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + # MPD from http://dash-mse-test.appspot.com/media.html + { + 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd', + 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53', + 'info_dict': { + 'id': 'car-20120827-manifest', + 'ext': 'mp4', + 'title': 'car-20120827-manifest', + 'formats': 'mincount:9', + }, + 'params': { + 'format': 'bestvideo', + }, + }, # google redirect { 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', @@ -339,6 +357,7 @@ class GenericIE(InfoExtractor): 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get + 'duration': 238.231, }, 'add_ie': ['Ooyala'], }, @@ -350,6 +369,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': '"Steve Jobs: Man in the Machine" trailer', 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."', + 'duration': 135.427, }, 'params': { 'skip_download': True, @@ -481,7 +501,7 @@ class GenericIE(InfoExtractor): 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, - # Embeded Ustream video + # Embedded Ustream video { 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', 'md5': '27b99cdb639c9b12a79bca876a073417', @@ -960,8 +980,9 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', 'ext': 'mp4', - 'description': 'VIDEO: Index/Match versus VLOOKUP.', + 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', 'title': 'This is what separates the Excel masters from the wannabes', + 'duration': 191.933, }, 'params': { # m3u8 downloads @@ -1222,19 +1243,24 @@ class GenericIE(InfoExtractor): # Check for direct link to a video content_type = head_response.headers.get('Content-Type', '') - m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) + m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type) if m: upload_date = unified_strdate( head_response.headers.get('Last-Modified')) + formats = [] + if m.group('format_id').endswith('mpegurl'): + formats = self._extract_m3u8_formats(url, video_id, 'mp4') + else: + formats = [{ + 'format_id': m.group('format_id'), + 'url': url, + 'vcodec': 'none' if m.group('type') == 'audio' else None + }] return { 'id': video_id, 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), 'direct': True, - 'formats': [{ - 'format_id': m.group('format_id'), - 'url': url, - 'vcodec': 'none' if m.group('type') == 'audio' else None - }], + 'formats': formats, 'upload_date': upload_date, } @@ -1277,7 +1303,7 @@ class GenericIE(InfoExtractor): self.report_extraction(video_id) - # Is it an RSS feed, a SMIL file or a XSPF playlist? + # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest? try: doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': @@ -1286,6 +1312,13 @@ class GenericIE(InfoExtractor): return self._parse_smil(doc, url, video_id) elif doc.tag == '{http://xspf.org/ns/0/}playlist': return self.playlist_result(self._parse_xspf(doc, video_id), video_id) + elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): + return { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + 'formats': self._parse_mpd_formats( + doc, video_id, mpd_base_url=url.rpartition('/')[0]), + } except compat_xml_parse_error: pass @@ -1395,7 +1428,7 @@ class GenericIE(InfoExtractor): # Look for embedded Dailymotion player matches = re.findall( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) + r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) if matches: return _playlist_from_matches( matches, lambda m: unescapeHTML(m[1])) @@ -1436,11 +1469,6 @@ class GenericIE(InfoExtractor): 'id': match.group('id') } - # Look for embedded blip.tv player - bliptv_url = BlipTVIE._extract_url(webpage) - if bliptv_url: - return self.url_result(bliptv_url, 'BlipTV') - # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: @@ -1501,7 +1529,7 @@ class GenericIE(InfoExtractor): re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: - return OoyalaIE._build_url_result(mobj.group('ec')) + return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) # Look for multiple Ooyala embeds on SBN network websites mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) @@ -1509,7 +1537,7 @@ class GenericIE(InfoExtractor): embeds = self._parse_json(mobj.group(1), video_id, fatal=False) if embeds: return _playlist_from_matches( - embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala') + embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') # Look for Aparat videos mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) @@ -1545,6 +1573,11 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'VK') + # Look for embedded Odnoklassniki player + mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Odnoklassniki') + # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) if mobj is not None: @@ -1642,7 +1675,7 @@ class GenericIE(InfoExtractor): if myvi_url: return self.url_result(myvi_url) - # Look for embeded soundcloud player + # Look for embedded soundcloud player mobj = re.search( r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', webpage) @@ -1738,10 +1771,14 @@ class GenericIE(InfoExtractor): return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform') # Look for Pladform embeds - mobj = re.search( - r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Pladform') + pladform_url = PladformIE._extract_url(webpage) + if pladform_url: + return self.url_result(pladform_url) + + # Look for Videomore embeds + videomore_url = VideomoreIE._extract_url(webpage) + if videomore_url: + return self.url_result(videomore_url) # Look for Playwire embeds mobj = re.search( @@ -1766,6 +1803,11 @@ class GenericIE(InfoExtractor): if nbc_sports_url: return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') + # Look for Google Drive embeds + google_drive_url = GoogleDriveIE._extract_url(webpage) + if google_drive_url: + return self.url_result(google_drive_url, 'GoogleDrive') + # Look for UDN embeds mobj = re.search( r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) @@ -1793,11 +1835,32 @@ class GenericIE(InfoExtractor): if snagfilms_url: return self.url_result(snagfilms_url) + # Look for JWPlatform embeds + jwplatform_url = JWPlatformIE._extract_url(webpage) + if jwplatform_url: + return self.url_result(jwplatform_url, 'JWPlatform') + # Look for ScreenwaveMedia embeds mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) if mobj is not None: return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') + # Look for Digiteka embeds + digiteka_url = DigitekaIE._extract_url(webpage) + if digiteka_url: + return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key()) + + # Look for Limelight embeds + mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage) + if mobj: + lm = { + 'Media': 'media', + 'Channel': 'channel', + 'ChannelList': 'channel_list', + } + return self.url_result('limelight:%s:%s' % ( + lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + # Look for AdobeTVVideo embeds mobj = re.search( r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', @@ -1914,6 +1977,8 @@ class GenericIE(InfoExtractor): return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id) elif ext == 'm3u8': entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') + elif ext == 'mpd': + entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) else: entry_info_dict['url'] = video_url diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index c65ef6b..3de8356 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -65,7 +65,7 @@ class GloboIE(InfoExtractor): 'only_matching': True, }] - class MD5: + class MD5(object): HEX_FORMAT_LOWERCASE = 0 HEX_FORMAT_UPPERCASE = 1 BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = '' @@ -369,11 +369,9 @@ class GloboIE(InfoExtractor): resource_url = resource['url'] signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash') if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): - m3u8_formats = self._extract_m3u8_formats( + formats.extend(self._extract_m3u8_formats( signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + m3u8_id='hls', fatal=False)) else: formats.append({ 'url': signed_url, diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py new file mode 100644 index 0000000..37be340 --- /dev/null +++ b/youtube_dl/extractor/googledrive.py @@ -0,0 +1,88 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class GoogleDriveIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})' + _TEST = { + 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', + 'md5': '881f7700aec4f538571fa1e0eed4a7b6', + 'info_dict': { + 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ', + 'ext': 'mp4', + 'title': 'Big Buck Bunny.mp4', + 'duration': 46, + } + } + _FORMATS_EXT = { + '5': 'flv', + '6': 'flv', + '13': '3gp', + '17': '3gp', + '18': 'mp4', + '22': 'mp4', + '34': 'flv', + '35': 'flv', + '36': '3gp', + '37': 'mp4', + '38': 'mp4', + '43': 'webm', + '44': 'webm', + '45': 'webm', + '46': 'webm', + '59': 'mp4', + } + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})', + webpage) + if mobj: + return 'https://drive.google.com/file/d/%s' % mobj.group('id') + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape') + + reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) + if reason: + raise ExtractorError(reason) + + title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title') + duration = int_or_none(self._search_regex( + r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None)) + fmt_stream_map = self._search_regex( + r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',') + fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',') + + formats = [] + for fmt, fmt_stream in zip(fmt_list, fmt_stream_map): + fmt_id, fmt_url = fmt_stream.split('|') + resolution = fmt.split('/')[1] + width, height = resolution.split('x') + formats.append({ + 'url': fmt_url, + 'format_id': fmt_id, + 'resolution': resolution, + 'width': int_or_none(width), + 'height': int_or_none(height), + 'ext': self._FORMATS_EXT[fmt_id], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/gputechconf.py b/youtube_dl/extractor/gputechconf.py new file mode 100644 index 0000000..145b55b --- /dev/null +++ b/youtube_dl/extractor/gputechconf.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, + parse_duration, +) + + +class GPUTechConfIE(InfoExtractor): + _VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html', + 'md5': 'a8862a00a0fd65b8b43acc5b8e33f798', + 'info_dict': { + 'id': '5156', + 'ext': 'mp4', + 'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis', + 'duration': 1219, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + root_path = self._search_regex(r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path', 'http://evt.dispeak.com/nvidia/events/gtc15/') + xml_file_id = self._search_regex(r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id') + + doc = self._download_xml('%sxml/%s.xml' % (root_path, xml_file_id), video_id) + + metadata = xpath_element(doc, 'metadata') + http_host = xpath_text(metadata, 'httpHost', 'http host', True) + mbr_videos = xpath_element(metadata, 'MBRVideos') + + formats = [] + for mbr_video in mbr_videos.findall('MBRVideo'): + stream_name = xpath_text(mbr_video, 'streamName') + if stream_name: + formats.append({ + 'url': 'http://%s/%s' % (http_host, stream_name.replace('mp4:', '')), + 'tbr': int_or_none(xpath_text(mbr_video, 'bitrate')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': xpath_text(metadata, 'title'), + 'duration': parse_duration(xpath_text(metadata, 'endTime')), + 'creator': xpath_text(metadata, 'speaker'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py index 8b9e0e2..63c05b6 100644 --- a/youtube_dl/extractor/groupon.py +++ b/youtube_dl/extractor/groupon.py @@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor): 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', 'ext': 'mp4', 'title': 'Bikram Yoga Huntington Beach | Orange County', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 44.961, }, }], 'params': { diff --git a/youtube_dl/extractor/hentaistigma.py b/youtube_dl/extractor/hentaistigma.py index f5aa73d..86a93de 100644 --- a/youtube_dl/extractor/hentaistigma.py +++ b/youtube_dl/extractor/hentaistigma.py @@ -11,8 +11,8 @@ class HentaiStigmaIE(InfoExtractor): 'info_dict': { 'id': 'inyouchuu-etsu-bonus', 'ext': 'mp4', - "title": "Inyouchuu Etsu Bonus", - "age_limit": 18, + 'title': 'Inyouchuu Etsu Bonus', + 'age_limit': 18, } } diff --git a/youtube_dl/extractor/history.py b/youtube_dl/extractor/history.py deleted file mode 100644 index f86164a..0000000 --- a/youtube_dl/extractor/history.py +++ /dev/null @@ -1,31 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import smuggle_url - - -class HistoryIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?history\.com/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])' - - _TESTS = [{ - 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', - 'md5': '6fe632d033c92aa10b8d4a9be047a7c5', - 'info_dict': { - 'id': 'bLx5Dv5Aka1G', - 'ext': 'mp4', - 'title': "Bet You Didn't Know: Valentine's Day", - 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', - }, - 'add_ie': ['ThePlatform'], - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_url = self._search_regex( - r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id, - webpage, 'video url') - - return self.url_result(smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}})) diff --git a/youtube_dl/extractor/hitbox.py b/youtube_dl/extractor/hitbox.py index 421f55b..ff79743 100644 --- a/youtube_dl/extractor/hitbox.py +++ b/youtube_dl/extractor/hitbox.py @@ -159,6 +159,9 @@ class HitboxLiveIE(HitboxIE): cdns = player_config.get('cdns') servers = [] for cdn in cdns: + # Subscribe URLs are not playable + if cdn.get('rtmpSubscribe') is True: + continue base_url = cdn.get('netConnectionUrl') host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1) if base_url not in servers: diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py new file mode 100644 index 0000000..f05d765 --- /dev/null +++ b/youtube_dl/extractor/hotstar.py @@ -0,0 +1,83 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + int_or_none, +) + + +class HotStarIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})' + _TESTS = [{ + 'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273', + 'info_dict': { + 'id': '1000076273', + 'ext': 'mp4', + 'title': 'On Air With AIB - English', + 'description': 'md5:c957d8868e9bc793ccb813691cc4c434', + 'timestamp': 1447227000, + 'upload_date': '20151111', + 'duration': 381, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + }, { + 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583', + 'only_matching': True, + }, { + 'url': 'http://www.hotstar.com/1000000515', + 'only_matching': True, + }] + + _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s' + _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s' + + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True): + json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal) + if json_data['resultCode'] != 'OK': + if fatal: + raise ExtractorError(json_data['errorDescription']) + return None + return json_data['resultObj'] + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_json( + self._GET_CONTENT_TEMPLATE % video_id, + video_id)['contentInfo'][0] + + formats = [] + # PCTV for extracting f4m manifest + for f in ('TABLET',): + format_data = self._download_json( + self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'), + video_id, 'Downloading %s JSON metadata' % f, fatal=False) + if format_data: + format_url = format_data['src'] + ext = determine_ext(format_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + elif ext == 'f4m': + # produce broken files + continue + else: + formats.append({ + 'url': format_url, + 'width': int_or_none(format_data.get('width')), + 'height': int_or_none(format_data.get('height')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_data['episodeTitle'], + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'timestamp': int_or_none(video_data.get('broadcastDate')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py index 16677f1..e8f51e5 100644 --- a/youtube_dl/extractor/howcast.py +++ b/youtube_dl/extractor/howcast.py @@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor): 'description': 'md5:dbe792e5f6f1489027027bf2eba188a3', 'timestamp': 1276081287, 'upload_date': '20100609', + 'duration': 56.823, }, 'params': { # m3u8 download diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index cca3dd4..b3706fe 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -28,15 +28,12 @@ class HypemIE(InfoExtractor): track_id = self._match_id(url) data = {'ax': 1, 'ts': time.time()} - data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?" + data_encoded - request = sanitized_Request(complete_url) + request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data)) response, urlh = self._download_webpage_handle( request, track_id, 'Downloading webpage with the url') - cookie = urlh.headers.get('Set-Cookie', '') html_tracks = self._html_search_regex( - r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>', + r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>', response, 'tracks') try: track_list = json.loads(html_tracks) @@ -46,15 +43,14 @@ class HypemIE(InfoExtractor): key = track['key'] track_id = track['id'] - artist = track['artist'] title = track['song'] - serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key) request = sanitized_Request( - serve_url, '', {'Content-Type': 'application/json'}) - request.add_header('cookie', cookie) + 'http://hypem.com/serve/source/%s/%s' % (track_id, key), + '', {'Content-Type': 'application/json'}) song_data = self._download_json(request, track_id, 'Downloading metadata') - final_url = song_data["url"] + final_url = song_data['url'] + artist = track.get('artist') return { 'id': track_id, diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index bf2d204..c45c68c 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -3,6 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) class IGNIE(InfoExtractor): @@ -11,25 +15,24 @@ class IGNIE(InfoExtractor): Some videos of it.ign.com are also supported """ - _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)' + _VALID_URL = r'https?://.+?\.ign\.com/(?:[^/]+/)?(?P<type>videos|show_videos|articles|feature|(?:[^/]+/\d+/video))(/.+)?/(?P<name_or_id>.+)' IE_NAME = 'ign.com' - _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config' - _DESCRIPTION_RE = [ - r'<span class="page-object-description">(.+?)</span>', - r'id="my_show_video">.*?<p>(.*?)</p>', - r'<meta name="description" content="(.*?)"', - ] + _API_URL_TEMPLATE = 'http://apis.ign.com/video/v3/videos/%s' + _EMBED_RE = r'<iframe[^>]+?["\']((?:https?:)?//.+?\.ign\.com.+?/embed.+?)["\']' _TESTS = [ { 'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', - 'md5': 'eac8bdc1890980122c3b66f14bdd02e9', + 'md5': 'febda82c4bafecd2d44b6e1a18a595f8', 'info_dict': { 'id': '8f862beef863986b2785559b9e1aa599', 'ext': 'mp4', 'title': 'The Last of Us Review', 'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c', + 'timestamp': 1370440800, + 'upload_date': '20130605', + 'uploader_id': 'cberidon@ign.com', } }, { @@ -44,6 +47,9 @@ class IGNIE(InfoExtractor): 'ext': 'mp4', 'title': 'GTA 5 Video Review', 'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.', + 'timestamp': 1379339880, + 'upload_date': '20130916', + 'uploader_id': 'danieljkrupa@gmail.com', }, }, { @@ -52,6 +58,9 @@ class IGNIE(InfoExtractor): 'ext': 'mp4', 'title': '26 Twisted Moments from GTA 5 in Slow Motion', 'description': 'The twisted beauty of GTA 5 in stunning slow motion.', + 'timestamp': 1386878820, + 'upload_date': '20131212', + 'uploader_id': 'togilvie@ign.com', }, }, ], @@ -66,12 +75,20 @@ class IGNIE(InfoExtractor): 'id': '078fdd005f6d3c02f63d795faa1b984f', 'ext': 'mp4', 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', - 'description': ( - 'Giant skeletons, bloody hunts, and captivating' - ' natural beauty take our breath away.' - ), + 'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.', + 'timestamp': 1408047180, + 'upload_date': '20140814', + 'uploader_id': 'jamesduggan1990@gmail.com', }, }, + { + 'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s', + 'only_matching': True, + }, + { + 'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds', + 'only_matching': True, + }, ] def _find_video_id(self, webpage): @@ -82,7 +99,7 @@ class IGNIE(InfoExtractor): r'<object id="vid_(.+?)"', r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', ] - return self._search_regex(res_id, webpage, 'video id') + return self._search_regex(res_id, webpage, 'video id', default=None) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -91,7 +108,7 @@ class IGNIE(InfoExtractor): webpage = self._download_webpage(url, name_or_id) if page_type != 'video': multiple_urls = re.findall( - '<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', + r'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', webpage) if multiple_urls: entries = [self.url_result(u, ie='IGN') for u in multiple_urls] @@ -102,22 +119,51 @@ class IGNIE(InfoExtractor): } video_id = self._find_video_id(webpage) - result = self._get_video_info(video_id) - description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', flags=re.DOTALL) - result['description'] = description - return result + if not video_id: + return self.url_result(self._search_regex( + self._EMBED_RE, webpage, 'embed url')) + return self._get_video_info(video_id) def _get_video_info(self, video_id): - config_url = self._CONFIG_URL_TEMPLATE % video_id - config = self._download_json(config_url, video_id) - media = config['playlist']['media'] + api_data = self._download_json( + self._API_URL_TEMPLATE % video_id, video_id) + + formats = [] + m3u8_url = api_data['refs'].get('m3uUrl') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + f4m_url = api_data['refs'].get('f4mUrl') + if f4m_url: + formats.extend(self._extract_f4m_formats( + f4m_url, video_id, f4m_id='hds', fatal=False)) + for asset in api_data['assets']: + formats.append({ + 'url': asset['url'], + 'tbr': asset.get('actual_bitrate_kbps'), + 'fps': asset.get('frame_rate'), + 'height': int_or_none(asset.get('height')), + 'width': int_or_none(asset.get('width')), + }) + self._sort_formats(formats) + + thumbnails = [{ + 'url': thumbnail['url'] + } for thumbnail in api_data.get('thumbnails', [])] + + metadata = api_data['metadata'] return { - 'id': media['metadata']['videoId'], - 'url': media['url'], - 'title': media['metadata']['title'], - 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), + 'id': api_data.get('videoId') or video_id, + 'title': metadata.get('longTitle') or metadata.get('name') or metadata.get['title'], + 'description': metadata.get('description'), + 'timestamp': parse_iso8601(metadata.get('publishDate')), + 'duration': int_or_none(metadata.get('duration')), + 'display_id': metadata.get('slug') or video_id, + 'uploader_id': metadata.get('creator'), + 'thumbnails': thumbnails, + 'formats': formats, } @@ -125,16 +171,17 @@ class OneUPIE(IGNIE): _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html' IE_NAME = '1up.com' - _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>' - _TESTS = [{ 'url': 'http://gamevideos.1up.com/video/id/34976.html', - 'md5': '68a54ce4ebc772e4b71e3123d413163d', + 'md5': 'c9cc69e07acb675c31a16719f909e347', 'info_dict': { 'id': '34976', 'ext': 'mp4', 'title': 'Sniper Elite V2 - Trailer', - 'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf', + 'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826', + 'timestamp': 1313099220, + 'upload_date': '20110811', + 'uploader_id': 'IGN', } }] @@ -143,3 +190,36 @@ class OneUPIE(IGNIE): result = super(OneUPIE, self)._real_extract(url) result['id'] = mobj.group('name_or_id') return result + + +class PCMagIE(IGNIE): + _VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)' + IE_NAME = 'pcmag' + + _EMBED_RE = r'iframe.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content.html?[^"]*url=([^"]+)["&]' + + _TESTS = [{ + 'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data', + 'md5': '212d6154fd0361a2781075f1febbe9ad', + 'info_dict': { + 'id': 'ee10d774b508c9b8ec07e763b9125b91', + 'ext': 'mp4', + 'title': '010615_What\'s New Now: Is GoGo Snooping on Your Data?', + 'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3', + 'timestamp': 1420571160, + 'upload_date': '20150106', + 'uploader_id': 'cozzipix@gmail.com', + } + }, { + 'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp', + 'md5': '94130c1ca07ba0adb6088350681f16c1', + 'info_dict': { + 'id': '042e560ba94823d43afcb12ddf7142ca', + 'ext': 'mp4', + 'title': 'HTC\'s Weird New Re Camera - What\'s New Now', + 'description': 'md5:53433c45df96d2ea5d0fda18be2ca908', + 'timestamp': 1412953920, + 'upload_date': '20141010', + 'uploader_id': 'chris_snyder@pcmag.com', + } + }] diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 70c8ca6..85e9344 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -13,7 +13,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -21,7 +21,7 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$', + 'description': 'Imgur: The most awesome images on the Internet.', }, }, { 'url': 'https://imgur.com/A61SaA1', @@ -29,8 +29,20 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$', + 'description': 'Imgur: The most awesome images on the Internet.', }, + }, { + 'url': 'https://imgur.com/gallery/YcAQlkx', + 'info_dict': { + 'id': 'YcAQlkx', + 'ext': 'mp4', + 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', + 'description': 'Imgur: The most awesome images on the Internet.' + + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, }] def _real_extract(self, url): @@ -100,25 +112,38 @@ class ImgurIE(InfoExtractor): class ImgurAlbumIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{5})(?:[/?#&]+)?$' - _TEST = { + _TESTS = [{ 'url': 'http://imgur.com/gallery/Q95ko', 'info_dict': { 'id': 'Q95ko', }, 'playlist_count': 25, - } + }, { + 'url': 'http://imgur.com/a/j6Orj', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'only_matching': True, + }] def _real_extract(self, url): album_id = self._match_id(url) album_images = self._download_json( 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, - album_id)['data']['images'] - - entries = [ - self.url_result('http://imgur.com/%s' % image['hash']) - for image in album_images if image.get('hash')] - - return self.playlist_result(entries, album_id) + album_id, fatal=False) + + if album_images: + data = album_images.get('data') + if data and isinstance(data, dict): + images = data.get('images') + if images and isinstance(images, list): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash']) + for image in images if image.get('hash')] + return self.playlist_result(entries, album_id) + + # Fallback to single video + return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key()) diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 71cfd12..016af20 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,3 +1,5 @@ +# coding: utf-8 + from __future__ import unicode_literals import base64 @@ -5,8 +7,9 @@ import base64 from .common import InfoExtractor from ..compat import ( compat_urllib_parse_unquote, - compat_urlparse, + compat_parse_qs, ) +from ..utils import determine_ext class InfoQIE(InfoExtractor): @@ -16,7 +19,7 @@ class InfoQIE(InfoExtractor): 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2', 'info_dict': { - 'id': '12-jan-pythonthings', + 'id': 'A-Few-of-My-Favorite-Python-Things', 'ext': 'mp4', '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', @@ -24,40 +27,84 @@ class InfoQIE(InfoExtractor): }, { 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript', 'only_matching': True, + }, { + 'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery', + 'md5': '4918d0cca1497f2244572caf626687ef', + 'info_dict': { + 'id': 'openstack-continued-delivery', + 'title': 'OpenStack持续交付之路', + 'ext': 'flv', + 'description': 'md5:308d981fb28fa42f49f9568322c683ff', + }, }] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + def _extract_bokecc_videos(self, webpage, video_id): + # TODO: bokecc.com is a Chinese video cloud platform + # It should have an independent extractor but I don't have other + # examples using bokecc + player_params_str = self._html_search_regex( + r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', + webpage, 'player params', default=None) - video_title = self._html_search_regex(r'<title>(.*?)', webpage, 'title') - video_description = self._html_search_meta('description', webpage, 'description') + player_params = compat_parse_qs(player_params_str) + + info_xml = self._download_xml( + 'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % ( + player_params['siteid'][0], player_params['vid'][0]), video_id) + + return [{ + 'format_id': 'bokecc', + 'url': quality.find('./copy').attrib['playurl'], + 'preference': int(quality.attrib['value']), + } for quality in info_xml.findall('./video/quality')] + def _extract_rtmp_videos(self, webpage): # The server URL is hardcoded video_url = 'rtmpe://video.infoq.com/cfx/st/' # Extract video URL encoded_id = self._search_regex( - r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id') + r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None) + 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( - r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage, - 'HTTP base URL') - - formats = [{ + return [{ 'format_id': 'rtmp', 'url': video_url, - 'ext': extension, + 'ext': determine_ext(playpath), 'play_path': playpath, - }, { + }] + + def _extract_http_videos(self, webpage): + http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL') + + policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy') + signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature') + key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id') + + return [{ 'format_id': 'http', - 'url': compat_urlparse.urljoin(url, http_base) + real_id, + 'url': http_video_url, + 'http_headers': { + 'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % ( + policy, signature, key_pair_id), + }, }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'(.*?)', webpage, 'title') + video_description = self._html_search_meta('description', webpage, 'description') + + if '/cn/' in url: + # for China videos, HTTP video URL exists but always fails with 403 + formats = self._extract_bokecc_videos(webpage, video_id) + else: + formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index c158f20..ed3e071 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -21,6 +21,18 @@ class InstagramIE(InfoExtractor): 'title': 'Video by naomipq', 'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8', } + }, { + # missing description + 'url': 'https://www.instagram.com/p/BA-pQFBG8HZ/?taken-by=britneyspears', + 'info_dict': { + 'id': 'BA-pQFBG8HZ', + 'ext': 'mp4', + 'uploader_id': 'britneyspears', + 'title': 'Video by britneyspears', + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://instagram.com/p/-Cmh1cukG2/', 'only_matching': True, @@ -32,8 +44,8 @@ class InstagramIE(InfoExtractor): webpage = self._download_webpage(url, video_id) uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"', webpage, 'uploader id', fatal=False) - desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description', - fatal=False) + desc = self._search_regex( + r'"caption":"(.+?)"', webpage, 'description', default=None) return { 'id': video_id, @@ -47,7 +59,7 @@ class InstagramIE(InfoExtractor): class InstagramUserIE(InfoExtractor): - _VALID_URL = r'https://instagram\.com/(?P[^/]{2,})/?(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' _TEST = { diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 36baf32..61a0de4 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -2,45 +2,30 @@ from __future__ import unicode_literals import re -from random import random -from math import floor +import time from .common import InfoExtractor from ..utils import ( - ExtractorError, - remove_end, sanitized_Request, ) class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P[^?#]+)' + _VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P[^?#]+)' _TESTS = [{ - 'url': 'http://play.iprima.cz/particka/particka-92', + 'url': 'http://play.iprima.cz/gondici-s-r-o-33', 'info_dict': { - 'id': '39152', - 'ext': 'flv', - 'title': 'Partička (92)', - 'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45', - 'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg', + 'id': 'p136534', + 'ext': 'mp4', + 'title': 'Gondíci s. r. o. (34)', + 'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd', }, 'params': { - 'skip_download': True, # requires rtmpdump + 'skip_download': True, # m3u8 download }, }, { - 'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda', - 'info_dict': { - 'id': '9718337', - 'ext': 'flv', - 'title': 'Tchibo Partička - Jarní móda', - 'thumbnail': 're:^http:.*\.jpg$', - }, - 'params': { - 'skip_download': True, # requires rtmpdump - }, - }, { - 'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015', + 'url': 'http://play.iprima.cz/particka/particka-92', 'only_matching': True, }] @@ -50,62 +35,24 @@ class IPrimaIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*', webpage): - raise ExtractorError( - '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True) + video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id') - player_url = ( - 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % - (floor(random() * 1073741824), floor(random() * 1073741824)) - ) - - req = sanitized_Request(player_url) + req = sanitized_Request( + 'http://play.iprima.cz/prehravac/init?_infuse=1' + '&_ts=%s&productId=%s' % (round(time.time()), video_id)) req.add_header('Referer', url) - playerpage = self._download_webpage(req, video_id) - - base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1]) - - zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO') - if zoneGEO != '0': - base_url = base_url.replace('token', 'token_' + zoneGEO) - - formats = [] - for format_id in ['lq', 'hq', 'hd']: - filename = self._html_search_regex( - r'"%s_id":(.+?),' % format_id, webpage, 'filename') - - if filename == 'null': - continue - - real_id = self._search_regex( - r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]', - filename, 'real video id') + playerpage = self._download_webpage(req, video_id, note='Downloading player') - if format_id == 'lq': - quality = 0 - elif format_id == 'hq': - quality = 1 - elif format_id == 'hd': - quality = 2 - filename = 'hq/' + filename + m3u8_url = self._search_regex(r"'src': '([^']+\.m3u8)'", playerpage, 'm3u8 url') - formats.append({ - 'format_id': format_id, - 'url': base_url, - 'quality': quality, - 'play_path': 'mp4:' + filename.replace('"', '')[:-4], - 'rtmp_live': True, - 'ext': 'flv', - }) + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') self._sort_formats(formats) return { - 'id': real_id, - 'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'), + 'id': video_id, + 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, - 'description': self._search_regex( - r']+itemprop="description"[^>]*>([^<]+)', - webpage, 'description', default=None), + 'description': self._og_search_description(webpage), } diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 2df1da3..c3e3300 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -2,21 +2,203 @@ from __future__ import unicode_literals import hashlib +import itertools import math +import os import random +import re import time import uuid from .common import InfoExtractor -from ..compat import compat_urllib_parse -from ..utils import ExtractorError +from ..compat import ( + compat_parse_qs, + compat_str, + compat_urllib_parse, + compat_urllib_parse_urlparse, +) +from ..utils import ( + ExtractorError, + ohdave_rsa_encrypt, + remove_start, + sanitized_Request, + urlencode_postdata, + url_basename, +) + + +def md5_text(text): + return hashlib.md5(text.encode('utf-8')).hexdigest() + + +class IqiyiSDK(object): + def __init__(self, target, ip, timestamp): + self.target = target + self.ip = ip + self.timestamp = timestamp + + @staticmethod + def split_sum(data): + return compat_str(sum(map(lambda p: int(p, 16), list(data)))) + + @staticmethod + def digit_sum(num): + if isinstance(num, int): + num = compat_str(num) + return compat_str(sum(map(int, num))) + + def even_odd(self): + even = self.digit_sum(compat_str(self.timestamp)[::2]) + odd = self.digit_sum(compat_str(self.timestamp)[1::2]) + return even, odd + + def preprocess(self, chunksize): + self.target = md5_text(self.target) + chunks = [] + for i in range(32 // chunksize): + chunks.append(self.target[chunksize * i:chunksize * (i + 1)]) + if 32 % chunksize: + chunks.append(self.target[32 - 32 % chunksize:]) + return chunks, list(map(int, self.ip.split('.'))) + + def mod(self, modulus): + chunks, ip = self.preprocess(32) + self.target = chunks[0] + ''.join(map(lambda p: compat_str(p % modulus), ip)) + + def split(self, chunksize): + modulus_map = { + 4: 256, + 5: 10, + 8: 100, + } + + chunks, ip = self.preprocess(chunksize) + ret = '' + for i in range(len(chunks)): + ip_part = compat_str(ip[i] % modulus_map[chunksize]) if i < 4 else '' + if chunksize == 8: + ret += ip_part + chunks[i] + else: + ret += chunks[i] + ip_part + self.target = ret + + def handle_input16(self): + self.target = md5_text(self.target) + self.target = self.split_sum(self.target[:16]) + self.target + self.split_sum(self.target[16:]) + + def handle_input8(self): + self.target = md5_text(self.target) + ret = '' + for i in range(4): + part = self.target[8 * i:8 * (i + 1)] + ret += self.split_sum(part) + part + self.target = ret + + def handleSum(self): + self.target = md5_text(self.target) + self.target = self.split_sum(self.target) + self.target + + def date(self, scheme): + self.target = md5_text(self.target) + d = time.localtime(self.timestamp) + strings = { + 'y': compat_str(d.tm_year), + 'm': '%02d' % d.tm_mon, + 'd': '%02d' % d.tm_mday, + } + self.target += ''.join(map(lambda c: strings[c], list(scheme))) + + def split_time_even_odd(self): + even, odd = self.even_odd() + self.target = odd + md5_text(self.target) + even + + def split_time_odd_even(self): + even, odd = self.even_odd() + self.target = even + md5_text(self.target) + odd + + def split_ip_time_sum(self): + chunks, ip = self.preprocess(32) + self.target = compat_str(sum(ip)) + chunks[0] + self.digit_sum(self.timestamp) + + def split_time_ip_sum(self): + chunks, ip = self.preprocess(32) + self.target = self.digit_sum(self.timestamp) + chunks[0] + compat_str(sum(ip)) + + +class IqiyiSDKInterpreter(object): + BASE62_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' + + def __init__(self, sdk_code): + self.sdk_code = sdk_code + + @classmethod + def base62(cls, num): + if num == 0: + return '0' + ret = '' + while num: + ret = cls.BASE62_TABLE[num % 62] + ret + num = num // 62 + return ret + + def decode_eval_codes(self): + self.sdk_code = self.sdk_code[5:-3] + + mobj = re.search( + r"'([^']+)',62,(\d+),'([^']+)'\.split\('\|'\),[^,]+,{}", + self.sdk_code) + obfucasted_code, count, symbols = mobj.groups() + count = int(count) + symbols = symbols.split('|') + symbol_table = {} + + while count: + count -= 1 + b62count = self.base62(count) + symbol_table[b62count] = symbols[count] or b62count + + self.sdk_code = re.sub( + r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)], + obfucasted_code) + + def run(self, target, ip, timestamp): + self.decode_eval_codes() + + functions = re.findall(r'input=([a-zA-Z0-9]+)\(input', self.sdk_code) + + sdk = IqiyiSDK(target, ip, timestamp) + + other_functions = { + 'handleSum': sdk.handleSum, + 'handleInput8': sdk.handle_input8, + 'handleInput16': sdk.handle_input16, + 'splitTimeEvenOdd': sdk.split_time_even_odd, + 'splitTimeOddEven': sdk.split_time_odd_even, + 'splitIpTimeSum': sdk.split_ip_time_sum, + 'splitTimeIpSum': sdk.split_time_ip_sum, + } + for function in functions: + if re.match(r'mod\d+', function): + sdk.mod(int(function[3:])) + elif re.match(r'date[ymd]{3}', function): + sdk.date(function[4:]) + elif re.match(r'split\d+', function): + sdk.split(int(function[5:])) + elif function in other_functions: + other_functions[function]() + else: + raise ExtractorError('Unknown funcion %s' % function) + + return sdk.target class IqiyiIE(InfoExtractor): IE_NAME = 'iqiyi' IE_DESC = '爱奇艺' - _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html' + _VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html' + + _NETRC_MACHINE = 'iqiyi' _TESTS = [{ 'url': 'http://www.iqiyi.com/v_19rrojlavg.html', @@ -84,6 +266,44 @@ class IqiyiIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'http://www.iqiyi.com/w_19rt6o8t9p.html', + 'only_matching': True, + }, { + 'url': 'http://www.iqiyi.com/a_19rrhbc6kt.html', + 'only_matching': True, + }, { + 'url': 'http://yule.iqiyi.com/pcb.html', + 'only_matching': True, + }, { + # VIP-only video. The first 2 parts (6 minutes) are available without login + # MD5 sums omitted as values are different on Travis CI and my machine + 'url': 'http://www.iqiyi.com/v_19rrny4w8w.html', + 'info_dict': { + 'id': 'f3cf468b39dddb30d676f89a91200dc1', + 'title': '泰坦尼克号', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'f3cf468b39dddb30d676f89a91200dc1_part1', + 'ext': 'f4v', + 'title': '泰坦尼克号', + }, + }, { + 'info_dict': { + 'id': 'f3cf468b39dddb30d676f89a91200dc1_part2', + 'ext': 'f4v', + 'title': '泰坦尼克号', + }, + }], + 'expected_warnings': ['Needs a VIP account for full video'], + }, { + 'url': 'http://www.iqiyi.com/a_19rrhb8ce1.html', + 'info_dict': { + 'id': '202918101', + 'title': '灌篮高手 国语版', + }, + 'playlist_count': 101, }] _FORMATS_MAP = [ @@ -95,11 +315,98 @@ class IqiyiIE(InfoExtractor): ('10', 'h1'), ] + def _real_initialize(self): + self._login() + @staticmethod - def md5_text(text): - return hashlib.md5(text.encode('utf-8')).hexdigest() + def _rsa_fun(data): + # public key extracted from http://static.iqiyi.com/js/qiyiV2/20160129180840/jobs/i18n/i18nIndex.js + N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd + e = 65537 + + return ohdave_rsa_encrypt(data, e, N) + + def _login(self): + (username, password) = self._get_login_info() + + # No authentication to be performed + if not username: + return True + + data = self._download_json( + 'http://kylin.iqiyi.com/get_token', None, + note='Get token for logging', errnote='Unable to get token for logging') + sdk = data['sdk'] + timestamp = int(time.time()) + target = '/apis/reglogin/login.action?lang=zh_TW&area_code=null&email=%s&passwd=%s&agenttype=1&from=undefined&keeplogin=0&piccode=&fromurl=&_pos=1' % ( + username, self._rsa_fun(password.encode('utf-8'))) + + interp = IqiyiSDKInterpreter(sdk) + sign = interp.run(target, data['ip'], timestamp) + + validation_params = { + 'target': target, + 'server': 'BEA3AA1908656AABCCFF76582C4C6660', + 'token': data['token'], + 'bird_src': 'f8d91d57af224da7893dd397d52d811a', + 'sign': sign, + 'bird_t': timestamp, + } + validation_result = self._download_json( + 'http://kylin.iqiyi.com/validate?' + compat_urllib_parse.urlencode(validation_params), None, + note='Validate credentials', errnote='Unable to validate credentials') + + MSG_MAP = { + 'P00107': 'please login via the web interface and enter the CAPTCHA code', + 'P00117': 'bad username or password', + } + + code = validation_result['code'] + if code != 'A00000': + msg = MSG_MAP.get(code) + if not msg: + msg = 'error %s' % code + if validation_result.get('msg'): + msg += ': ' + validation_result['msg'] + self._downloader.report_warning('unable to log in: ' + msg) + return False + + return True + + def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning): + auth_params = { + # version and platform hard-coded in com/qiyi/player/core/model/remote/AuthenticationRemote.as + 'version': '2.0', + 'platform': 'b6c13e26323c537d', + 'aid': tvid, + 'tvid': tvid, + 'uid': '', + 'deviceId': _uuid, + 'playType': 'main', # XXX: always main? + 'filename': os.path.splitext(url_basename(api_video_url))[0], + } - def construct_video_urls(self, data, video_id, _uuid): + qd_items = compat_parse_qs(compat_urllib_parse_urlparse(api_video_url).query) + for key, val in qd_items.items(): + auth_params[key] = val[0] + + auth_req = sanitized_Request( + 'http://api.vip.iqiyi.com/services/ckn.action', + urlencode_postdata(auth_params)) + # iQiyi server throws HTTP 405 error without the following header + auth_req.add_header('Content-Type', 'application/x-www-form-urlencoded') + auth_result = self._download_json( + auth_req, video_id, + note='Downloading video authentication JSON', + errnote='Unable to download video authentication JSON') + if auth_result['code'] == 'Q00506': # requires a VIP account + if do_report_warning: + self.report_warning('Needs a VIP account for full video') + return False + + return auth_result + + def construct_video_urls(self, data, video_id, _uuid, tvid): def do_xor(x, y): a = y % 3 if a == 1: @@ -125,9 +432,10 @@ class IqiyiIE(InfoExtractor): 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 self.md5_text(t + mg + x) + return md5_text(t + mg + x) video_urls_dict = {} + need_vip_warning_report = True for format_item in data['vp']['tkl'][0]['vs']: if 0 < int(format_item['bid']) <= 10: format_id = self.get_format(format_item['bid']) @@ -146,11 +454,13 @@ class IqiyiIE(InfoExtractor): 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) + is_vip_video = '/vip/' in vl filesize = segment['b'] base_url = data['vp']['du'].split('/') - base_url.insert(-1, key) + if not is_vip_video: + key = get_path_key( + vl.split('/')[-1].split('.')[0], format_id, segment_index) + base_url.insert(-1, key) base_url = '/'.join(base_url) param = { 'su': _uuid, @@ -161,8 +471,23 @@ class IqiyiIE(InfoExtractor): 'ct': '', 'tn': str(int(time.time())) } - api_video_url = base_url + vl + '?' + \ - compat_urllib_parse.urlencode(param) + api_video_url = base_url + vl + if is_vip_video: + api_video_url = api_video_url.replace('.f4v', '.hml') + auth_result = self._authenticate_vip_video( + api_video_url, video_id, tvid, _uuid, need_vip_warning_report) + if auth_result is False: + need_vip_warning_report = False + break + param.update({ + 't': auth_result['data']['t'], + # cid is hard-coded in com/qiyi/player/core/player/RuntimeData.as + 'cid': 'afbe8fd3d73448c9', + 'vid': video_id, + 'QY00001': auth_result['data']['u'], + }) + api_video_url += '?' if '?' not in api_video_url else '&' + api_video_url += 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)) @@ -186,16 +511,17 @@ class IqiyiIE(InfoExtractor): tail = tm + tvid param = { 'key': 'fvip', - 'src': self.md5_text('youtube-dl'), + 'src': md5_text('youtube-dl'), 'tvId': tvid, 'vid': video_id, 'vinfo': 1, 'tm': tm, - 'enc': self.md5_text(enc_key + tail), + 'enc': md5_text(enc_key + tail), 'qyid': _uuid, 'tn': random.random(), 'um': 0, - 'authkey': self.md5_text(self.md5_text('') + tail), + 'authkey': md5_text(md5_text('') + tail), + 'k_tag': 1, } api_url = 'http://cache.video.qiyi.com/vms' + '?' + \ @@ -205,14 +531,53 @@ class IqiyiIE(InfoExtractor): def get_enc_key(self, swf_url, video_id): # TODO: automatic key extraction - # last update at 2015-10-22 for Zombie::bite - # '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2] - enc_key = '2c76de15dcb44bd28ff0927d50d31620' + # last update at 2016-01-22 for Zombie::bite + enc_key = '6ab6d0280511493ba85594779759d4ed' return enc_key + def _extract_playlist(self, webpage): + PAGE_SIZE = 50 + + links = re.findall( + r']+class="site-piclist_pic_link"[^>]+href="(http://www\.iqiyi\.com/.+\.html)"', + webpage) + if not links: + return + + album_id = self._search_regex( + r'albumId\s*:\s*(\d+),', webpage, 'album ID') + album_title = self._search_regex( + r'data-share-title="([^"]+)"', webpage, 'album title', fatal=False) + + entries = list(map(self.url_result, links)) + + # Start from 2 because links in the first page are already on webpage + for page_num in itertools.count(2): + pagelist_page = self._download_webpage( + 'http://cache.video.qiyi.com/jp/avlist/%s/%d/%d/' % (album_id, page_num, PAGE_SIZE), + album_id, + note='Download playlist page %d' % page_num, + errnote='Failed to download playlist page %d' % page_num) + pagelist = self._parse_json( + remove_start(pagelist_page, 'var tvInfoJs='), album_id) + vlist = pagelist['data']['vlist'] + for item in vlist: + entries.append(self.url_result(item['vurl'])) + if len(vlist) < PAGE_SIZE: + break + + return self.playlist_result(entries, album_id, album_title) + def _real_extract(self, url): webpage = self._download_webpage( url, 'temp_id', note='download video page') + + # There's no simple way to determine whether an URL is a playlist or not + # So detect it + playlist_result = self._extract_playlist(webpage) + if playlist_result: + return playlist_result + tvid = self._search_regex( r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid') video_id = self._search_regex( @@ -228,16 +593,13 @@ class IqiyiIE(InfoExtractor): 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) + data, video_id, _uuid, tvid) # construct info entries = [] diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 029878d..472d72b 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -7,6 +7,7 @@ import json from .common import InfoExtractor from ..utils import ( ExtractorError, + int_or_none, sanitized_Request, ) @@ -27,44 +28,36 @@ class IviIE(InfoExtractor): 'title': 'Иван Васильевич меняет профессию', 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f', 'duration': 5498, - 'thumbnail': 'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg', + 'thumbnail': 're:^https?://.*\.jpg$', }, 'skip': 'Only works from Russia', }, - # Serial's serie + # Serial's series { 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549', 'md5': '221f56b35e3ed815fde2df71032f4b3e', 'info_dict': { 'id': '9549', 'ext': 'mp4', - 'title': 'Двое из ларца - Серия 1', + 'title': 'Двое из ларца - Дело Гольдберга (1 часть)', + 'series': 'Двое из ларца', + 'season': 'Сезон 1', + 'season_number': 1, + 'episode': 'Дело Гольдберга (1 часть)', + 'episode_number': 1, 'duration': 2655, - 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg', + 'thumbnail': 're:^https?://.*\.jpg$', }, 'skip': 'Only works from Russia', } ] # Sorted by quality - _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ'] - - # Sorted by size - _known_thumbnails = ['Thumb-120x90', 'Thumb-160', 'Thumb-640x480'] - - def _extract_description(self, html): - m = re.search(r'', html) - return m.group('description') if m is not None else None - - def _extract_comment_count(self, html): - m = re.search('(?s)\s*Комментарии:\s*(?P\d+)\s*', html) - return int(m.group('commentcount')) if m is not None else 0 + _KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ'] def _real_extract(self, url): video_id = self._match_id(url) - api_url = 'http://api.digitalaccess.ru/api/json/' - data = { 'method': 'da.content.get', 'params': [ @@ -76,11 +69,10 @@ class IviIE(InfoExtractor): ] } - request = sanitized_Request(api_url, json.dumps(data)) - - video_json_page = self._download_webpage( + request = sanitized_Request( + 'http://api.digitalaccess.ru/api/json/', json.dumps(data)) + video_json = self._download_json( request, video_id, 'Downloading video JSON') - video_json = json.loads(video_json_page) if 'error' in video_json: error = video_json['error'] @@ -95,35 +87,51 @@ class IviIE(InfoExtractor): formats = [{ 'url': x['url'], 'format_id': x['content_format'], - 'preference': self._known_formats.index(x['content_format']), - } for x in result['files'] if x['content_format'] in self._known_formats] + 'preference': self._KNOWN_FORMATS.index(x['content_format']), + } for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS] self._sort_formats(formats) - if not formats: - raise ExtractorError('No media links available for %s' % video_id) - - duration = result['duration'] - compilation = result['compilation'] title = result['title'] + duration = int_or_none(result.get('duration')) + compilation = result.get('compilation') + episode = title if compilation else None + title = '%s - %s' % (compilation, title) if compilation is not None else title - previews = result['preview'] - previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format'])) - thumbnail = previews[-1]['url'] if len(previews) > 0 else None + thumbnails = [{ + 'url': preview['url'], + 'id': preview.get('content_format'), + } for preview in result.get('preview', []) if preview.get('url')] + + webpage = self._download_webpage(url, video_id) + + season = self._search_regex( + r']+class="season active"[^>]*>]+>([^<]+)', + webpage, 'season', default=None) + season_number = int_or_none(self._search_regex( + r']+class="season active"[^>]*>]+data-season(?:-index)?="(\d+)"', + webpage, 'season number', default=None)) + + episode_number = int_or_none(self._search_regex( + r']+itemprop="episode"[^>]*>\s*]+itemprop="episodeNumber"[^>]+content="(\d+)', + webpage, 'episode number', default=None)) - video_page = self._download_webpage(url, video_id, 'Downloading video page') - description = self._extract_description(video_page) - comment_count = self._extract_comment_count(video_page) + description = self._og_search_description(webpage, default=None) or self._html_search_meta( + 'description', webpage, 'description', default=None) return { 'id': video_id, 'title': title, - 'thumbnail': thumbnail, + 'series': compilation, + 'season': season, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + 'thumbnails': thumbnails, 'description': description, 'duration': duration, - 'comment_count': comment_count, 'formats': formats, } @@ -149,8 +157,11 @@ class IviCompilationIE(InfoExtractor): }] def _extract_entries(self, html, compilation_id): - return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') - for serie in re.findall(r'(?:[^<]+)' % compilation_id, html)] + return [ + self.url_result( + 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key()) + for serie in re.findall( + r']+data-id="\1"' % compilation_id, html)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -158,7 +169,8 @@ class IviCompilationIE(InfoExtractor): season_id = mobj.group('seasonid') if season_id is not None: # Season link - season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) + season_page = self._download_webpage( + url, compilation_id, 'Downloading season %s web page' % season_id) playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_title = self._html_search_meta('title', season_page, 'title') entries = self._extract_entries(season_page, compilation_id) @@ -166,8 +178,9 @@ class IviCompilationIE(InfoExtractor): compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') playlist_id = compilation_id playlist_title = self._html_search_meta('title', compilation_page, 'title') - seasons = re.findall(r'[^<]+' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + seasons = re.findall( + r']*>([^<]+)', webpage, 'camera name', default=None) + + quality = qualities(self._QUALITIES) + + formats = [{ + 'url': 'https://streaming.ivideon.com/flv/live?%s' % compat_urllib_parse.urlencode({ + 'server': server_id, + 'camera': camera_id, + 'sessionId': 'demo', + 'q': quality(format_id), + }), + 'format_id': format_id, + 'ext': 'flv', + 'quality': quality(format_id), + } for format_id in self._QUALITIES] + self._sort_formats(formats) + + return { + 'id': server_id, + 'title': self._live_title(camera_name or server_id), + 'description': description, + 'is_live': True, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jukebox.py b/youtube_dl/extractor/jukebox.py deleted file mode 100644 index da8068e..0000000 --- a/youtube_dl/extractor/jukebox.py +++ /dev/null @@ -1,59 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - RegexNotFoundError, - unescapeHTML, -) - - -class JukeboxIE(InfoExtractor): - _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P[a-z0-9\-]+)\.html' - _TEST = { - 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html', - 'info_dict': { - 'id': 'r303r', - 'ext': 'flv', - 'title': 'Kosheen-En Vivo Pride', - 'uploader': 'Kosheen', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - html = self._download_webpage(url, video_id) - iframe_url = unescapeHTML(self._search_regex(r'