*.pyc
*.pyo
*~
+*.DS_Store
wine-py2exe/
py2exe.log
*.kate-swp
youtube-dl
youtube-dl.exe
youtube-dl.tar.gz
+.coverage
+cover/
+updates_key.pem
+*.egg-info
\ No newline at end of file
python:
- "2.6"
- "2.7"
-# - "3.3"
+ - "3.3"
script: nosetests test --verbose
notifications:
email:
- filippo.valsorda@gmail.com
- irc:
- channels:
- - "irc.freenode.org#youtube-dl"
- skip_join: true
+ - phihag@phihag.de
+ - jaime.marquinez.ferrandiz+travis@gmail.com
+# irc:
+# channels:
+# - "irc.freenode.org#youtube-dl"
+# skip_join: true
--- /dev/null
+2013.01.02 Codename: GIULIA
+
+ * Add support for ComedyCentral clips <nto>
+ * Corrected Vimeo description fetching <Nick Daniels>
+ * Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
+ * --verbose offers more environment info
+ * New info_dict field: uploader_id
+ * New updates system, with signature checking
+ * New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
+ * Fixed IEs: BlipTv
+ * Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
+ * Simplified IEs and test code
+ * Various (Python 3 and other) fixes
+ * Revamped and expanded tests
-9999.99.99
\ No newline at end of file
+2012.12.99
--- /dev/null
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>
include README.md
include test/*.py
-include test/*.json
\ No newline at end of file
+include test/*.json
+include youtube-dl.bash-completion
+include youtube-dl.1
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
clean:
- rm -rf youtube-dl youtube-dl.exe youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/
+ rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
+
+cleanall: clean
+ rm -f youtube-dl youtube-dl.exe
PREFIX=/usr/local
BINDIR=$(PREFIX)/bin
MANDIR=$(PREFIX)/man
-SYSCONFDIR=/etc
+PYTHON=/usr/bin/env python
+
+# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
+ifeq ($(PREFIX),/usr)
+ SYSCONFDIR=/etc
+else
+ ifeq ($(PREFIX),/usr/local)
+ SYSCONFDIR=/etc
+ else
+ SYSCONFDIR=$(PREFIX)/etc
+ endif
+endif
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
install -d $(DESTDIR)$(BINDIR)
install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
test:
- nosetests2 --nocapture test
+ #nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
+ nosetests --verbose test
+
+tar: youtube-dl.tar.gz
-.PHONY: all clean install test
+.PHONY: all clean install test tar bash-completion pypi-files
+
+pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
youtube-dl: youtube_dl/*.py
zip --quiet youtube-dl youtube_dl/*.py
zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
- echo '#!/usr/bin/env python' > youtube-dl
+ echo '#!$(PYTHON)' > youtube-dl
cat youtube-dl.zip >> youtube-dl
rm youtube-dl.zip
chmod a+x youtube-dl
youtube-dl.1: README.md
pandoc -s -f markdown -t man README.md -o youtube-dl.1
-youtube-dl.bash-completion: youtube_dl/*.py devscripts/bash-completion.template
+youtube-dl.bash-completion: youtube_dl/*.py devscripts/bash-completion.in
python devscripts/bash-completion.py
-youtube-dl.tar.gz: all
- tar -czf youtube-dl.tar.gz -s "|^./|./youtube-dl/|" \
- --exclude="*.pyc" --exclude="*.pyo" --exclude="*~" --exclude="youtube-dl.exe" \
- --exclude="wine-py2exe/" --exclude="py2exe.log" --exclude="*.kate-swp" \
- --exclude="build/" --exclude="dist/" --exclude="MANIFEST" --exclude=".git/" .
+bash-completion: youtube-dl.bash-completion
+
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
+ @tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
+ --exclude '*.DS_Store' \
+ --exclude '*.kate-swp' \
+ --exclude '*.pyc' \
+ --exclude '*.pyo' \
+ --exclude '*~' \
+ --exclude '__pycache' \
+ --exclude '.git' \
+ -- \
+ bin devscripts test youtube_dl \
+ CHANGELOG LICENSE README.md README.txt \
+ Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
+ youtube-dl
# DESCRIPTION
**youtube-dl** is a small command-line program to download videos from
YouTube.com and a few more sites. It requires the Python interpreter, version
-2.x (x being at least 6), and it is not platform specific. It should work in
-your Unix box, in Windows or in Mac OS X. It is released to the public domain,
+2.6, 2.7, or 3.3+, and it is not platform specific. It should work on
+your Unix box, on Windows or on Mac OS X. It is released to the public domain,
which means you can modify it, redistribute it or use it however you like.
# OPTIONS
- -h, --help print this help text and exit
- --version print program version and exit
- -U, --update update this program to latest version
- -i, --ignore-errors continue on download errors
- -r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m)
- -R, --retries RETRIES number of retries (default is 10)
- --buffer-size SIZE size of download buffer (e.g. 1024 or 16k) (default
- is 1024)
- --no-resize-buffer do not automatically adjust the buffer size. By
- default, the buffer size is automatically resized
- from an initial value of SIZE.
- --dump-user-agent display the current browser identification
- --user-agent UA specify a custom user agent
- --list-extractors List all supported extractors and the URLs they
- would handle
+ -h, --help print this help text and exit
+ --version print program version and exit
+ -U, --update update this program to latest version
+ -i, --ignore-errors continue on download errors
+ -r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m)
+ -R, --retries RETRIES number of retries (default is 10)
+ --buffer-size SIZE size of download buffer (e.g. 1024 or 16k)
+ (default is 1024)
+ --no-resize-buffer do not automatically adjust the buffer size. By
+ default, the buffer size is automatically resized
+ from an initial value of SIZE.
+ --dump-user-agent display the current browser identification
+ --user-agent UA specify a custom user agent
+ --referer REF specify a custom referer, use if the video access
+ is restricted to one domain
+ --list-extractors List all supported extractors and the URLs they
+ would handle
+ --proxy URL Use the specified HTTP/HTTPS proxy
+ --no-check-certificate Suppress HTTPS certificate validation.
## Video Selection:
- --playlist-start NUMBER playlist video to start at (default is 1)
- --playlist-end NUMBER playlist video to end at (default is last)
- --match-title REGEX download only matching titles (regex or caseless
- sub-string)
- --reject-title REGEX skip download for matching titles (regex or
- caseless sub-string)
- --max-downloads NUMBER Abort after downloading NUMBER files
+ --playlist-start NUMBER playlist video to start at (default is 1)
+ --playlist-end NUMBER playlist video to end at (default is last)
+ --match-title REGEX download only matching titles (regex or caseless
+ sub-string)
+ --reject-title REGEX skip download for matching titles (regex or
+ caseless sub-string)
+ --max-downloads NUMBER Abort after downloading NUMBER files
+ --min-filesize SIZE Do not download any videos smaller than SIZE
+ (e.g. 50k or 44.6m)
+ --max-filesize SIZE Do not download any videos larger than SIZE (e.g.
+ 50k or 44.6m)
+ --date DATE download only videos uploaded in this date
+ --datebefore DATE download only videos uploaded before this date
+ --dateafter DATE download only videos uploaded after this date
## Filesystem Options:
- -t, --title use title in file name
- --id use video ID in file name
- -l, --literal [deprecated] alias of --title
- -A, --auto-number number downloaded files starting from 00000
- -o, --output TEMPLATE output filename template. Use %(title)s to get the
- title, %(uploader)s for the uploader name,
- %(autonumber)s to get an automatically incremented
- number, %(ext)s for the filename extension,
- %(upload_date)s for the upload date (YYYYMMDD),
- %(extractor)s for the provider (youtube, metacafe,
- etc), %(id)s for the video id and %% for a literal
- percent. Use - to output to stdout. Can also be
- used to download to a different directory, for
- example with -o '/my/downloads/%(uploader)s/%(title
- )s-%(id)s.%(ext)s' .
- --restrict-filenames Restrict filenames to only ASCII characters, and
- avoid "&" and spaces in filenames
- -a, --batch-file FILE file containing URLs to download ('-' for stdin)
- -w, --no-overwrites do not overwrite files
- -c, --continue resume partially downloaded files
- --no-continue do not resume partially downloaded files (restart
- from beginning)
- --cookies FILE file to read cookies from and dump cookie jar in
- --no-part do not use .part files
- --no-mtime do not use the Last-modified header to set the file
- modification time
- --write-description write video description to a .description file
- --write-info-json write video metadata to a .info.json file
+ -t, --title use title in file name (default)
+ --id use only video ID in file name
+ -l, --literal [deprecated] alias of --title
+ -A, --auto-number number downloaded files starting from 00000
+ -o, --output TEMPLATE output filename template. Use %(title)s to get
+ the title, %(uploader)s for the uploader name,
+ %(uploader_id)s for the uploader nickname if
+ different, %(autonumber)s to get an automatically
+ incremented number, %(ext)s for the filename
+ extension, %(upload_date)s for the upload date
+ (YYYYMMDD), %(extractor)s for the provider
+ (youtube, metacafe, etc), %(id)s for the video id
+ , %(playlist)s for the playlist the video is in,
+ %(playlist_index)s for the position in the
+ playlist and %% for a literal percent. Use - to
+ output to stdout. Can also be used to download to
+ a different directory, for example with -o '/my/d
+ ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+ --autonumber-size NUMBER Specifies the number of digits in %(autonumber)s
+ when it is present in output filename template or
+ --autonumber option is given
+ --restrict-filenames Restrict filenames to only ASCII characters, and
+ avoid "&" and spaces in filenames
+ -a, --batch-file FILE file containing URLs to download ('-' for stdin)
+ -w, --no-overwrites do not overwrite files
+ -c, --continue resume partially downloaded files
+ --no-continue do not resume partially downloaded files (restart
+ from beginning)
+ --cookies FILE file to read cookies from and dump cookie jar in
+ --no-part do not use .part files
+ --no-mtime do not use the Last-modified header to set the
+ file modification time
+ --write-description write video description to a .description file
+ --write-info-json write video metadata to a .info.json file
+ --write-thumbnail write thumbnail image to disk
## Verbosity / Simulation Options:
- -q, --quiet activates quiet mode
- -s, --simulate do not download the video and do not write anything
- to disk
- --skip-download do not download the video
- -g, --get-url simulate, quiet but print URL
- -e, --get-title simulate, quiet but print title
- --get-thumbnail simulate, quiet but print thumbnail URL
- --get-description simulate, quiet but print video description
- --get-filename simulate, quiet but print output filename
- --get-format simulate, quiet but print output format
- --no-progress do not print progress bar
- --console-title display progress in console titlebar
- -v, --verbose print various debugging information
+ -q, --quiet activates quiet mode
+ -s, --simulate do not download the video and do not write
+ anything to disk
+ --skip-download do not download the video
+ -g, --get-url simulate, quiet but print URL
+ -e, --get-title simulate, quiet but print title
+ --get-id simulate, quiet but print id
+ --get-thumbnail simulate, quiet but print thumbnail URL
+ --get-description simulate, quiet but print video description
+ --get-filename simulate, quiet but print output filename
+ --get-format simulate, quiet but print output format
+ --newline output progress bar as new lines
+ --no-progress do not print progress bar
+ --console-title display progress in console titlebar
+ -v, --verbose print various debugging information
+ --dump-intermediate-pages print downloaded pages to debug problems(very
+ verbose)
## Video Format Options:
- -f, --format FORMAT video format code
- --all-formats download all available video formats
- --prefer-free-formats prefer free video formats unless a specific one is
- requested
- --max-quality FORMAT highest quality format to download
- -F, --list-formats list all available formats (currently youtube only)
- --write-srt write video closed captions to a .srt file
- (currently youtube only)
- --srt-lang LANG language of the closed captions to download
- (optional) use IETF language tags like 'en'
+ -f, --format FORMAT video format code, specifiy the order of
+ preference using slashes: "-f 22/17/18"
+ --all-formats download all available video formats
+ --prefer-free-formats prefer free video formats unless a specific one
+ is requested
+ --max-quality FORMAT highest quality format to download
+ -F, --list-formats list all available formats (currently youtube
+ only)
+ --write-sub write subtitle file (currently youtube only)
+ --only-sub [deprecated] alias of --skip-download
+ --all-subs downloads all the available subtitles of the
+ video (currently youtube only)
+ --list-subs lists all available subtitles for the video
+ (currently youtube only)
+ --sub-format LANG subtitle format [srt/sbv] (default=srt)
+ (currently youtube only)
+ --sub-lang LANG language of the subtitles to download (optional)
+ use IETF language tags like 'en'
## Authentication Options:
- -u, --username USERNAME account username
- -p, --password PASSWORD account password
- -n, --netrc use .netrc authentication data
+ -u, --username USERNAME account username
+ -p, --password PASSWORD account password
+ -n, --netrc use .netrc authentication data
## Post-processing Options:
- -x, --extract-audio convert video files to audio-only files (requires
- ffmpeg or avconv and ffprobe or avprobe)
- --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav";
- best by default
- --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a
- value between 0 (better) and 9 (worse) for VBR or a
- specific bitrate like 128K (default 5)
- -k, --keep-video keeps the video file on disk after the post-
- processing; the video is erased by default
+ -x, --extract-audio convert video files to audio-only files (requires
+ ffmpeg or avconv and ffprobe or avprobe)
+ --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or
+ "wav"; best by default
+ --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert
+ a value between 0 (better) and 9 (worse) for VBR
+ or a specific bitrate like 128K (default 5)
+ --recode-video FORMAT Encode the video to another format if necessary
+ (currently supported: mp4|flv|ogg|webm)
+ -k, --keep-video keeps the video file on disk after the post-
+ processing; the video is erased by default
+ --no-post-overwrites do not overwrite post-processed files; the post-
+ processed files are overwritten by default
# CONFIGURATION
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.local/config/youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`.
# OUTPUT TEMPLATE
- `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 name or the id of the playlist that contains the video.
+ - `playlist_index`: The index of the video in the playlist, a five-digit number.
The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment).
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
youtube-dl_test_video_.mp4 # A simple file name
+# VIDEO SELECTION
+
+Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
+
+ - Absolute dates: Dates in the format `YYYYMMDD`.
+ - Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
+
+Examples:
+
+ $ youtube-dl --dateafter now-6months #will only download the videos uploaded in the last 6 months
+ $ youtube-dl --date 19700101 #will only download the videos uploaded in January 1, 1970
+ $ youtube-dl --dateafter 20000101 --datebefore 20100101 #will only download the videos uploaded between 2000 and 2010
+
# FAQ
### Can you please put the -b option back?
Please include:
* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
+* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us.
* The output of `youtube-dl --version`
* The output of `python --version`
* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
+++ /dev/null
-NAME
-====
-
-youtube-dl
-
-SYNOPSIS
-========
-
-youtube-dl [OPTIONS] URL [URL...]
-
-DESCRIPTION
-===========
-
-youtube-dl is a small command-line program to download videos from
-YouTube.com and a few more sites. It requires the Python interpreter,
-version 2.x (x being at least 6), and it is not platform specific. It
-should work in your Unix box, in Windows or in Mac OS X. It is released
-to the public domain, which means you can modify it, redistribute it or
-use it however you like.
-
-OPTIONS
-=======
-
- -h, --help print this help text and exit
- --version print program version and exit
- -U, --update update this program to latest version
- -i, --ignore-errors continue on download errors
- -r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m)
- -R, --retries RETRIES number of retries (default is 10)
- --buffer-size SIZE size of download buffer (e.g. 1024 or 16k) (default
- is 1024)
- --no-resize-buffer do not automatically adjust the buffer size. By
- default, the buffer size is automatically resized
- from an initial value of SIZE.
- --dump-user-agent display the current browser identification
- --user-agent UA specify a custom user agent
- --list-extractors List all supported extractors and the URLs they
- would handle
-
-Video Selection:
-----------------
-
- --playlist-start NUMBER playlist video to start at (default is 1)
- --playlist-end NUMBER playlist video to end at (default is last)
- --match-title REGEX download only matching titles (regex or caseless
- sub-string)
- --reject-title REGEX skip download for matching titles (regex or
- caseless sub-string)
- --max-downloads NUMBER Abort after downloading NUMBER files
-
-Filesystem Options:
--------------------
-
- -t, --title use title in file name
- --id use video ID in file name
- -l, --literal [deprecated] alias of --title
- -A, --auto-number number downloaded files starting from 00000
- -o, --output TEMPLATE output filename template. Use %(title)s to get the
- title, %(uploader)s for the uploader name,
- %(autonumber)s to get an automatically incremented
- number, %(ext)s for the filename extension,
- %(upload_date)s for the upload date (YYYYMMDD),
- %(extractor)s for the provider (youtube, metacafe,
- etc), %(id)s for the video id and %% for a literal
- percent. Use - to output to stdout. Can also be
- used to download to a different directory, for
- example with -o '/my/downloads/%(uploader)s/%(title
- )s-%(id)s.%(ext)s' .
- --restrict-filenames Restrict filenames to only ASCII characters, and
- avoid "&" and spaces in filenames
- -a, --batch-file FILE file containing URLs to download ('-' for stdin)
- -w, --no-overwrites do not overwrite files
- -c, --continue resume partially downloaded files
- --no-continue do not resume partially downloaded files (restart
- from beginning)
- --cookies FILE file to read cookies from and dump cookie jar in
- --no-part do not use .part files
- --no-mtime do not use the Last-modified header to set the file
- modification time
- --write-description write video description to a .description file
- --write-info-json write video metadata to a .info.json file
-
-Verbosity / Simulation Options:
--------------------------------
-
- -q, --quiet activates quiet mode
- -s, --simulate do not download the video and do not write anything
- to disk
- --skip-download do not download the video
- -g, --get-url simulate, quiet but print URL
- -e, --get-title simulate, quiet but print title
- --get-thumbnail simulate, quiet but print thumbnail URL
- --get-description simulate, quiet but print video description
- --get-filename simulate, quiet but print output filename
- --get-format simulate, quiet but print output format
- --no-progress do not print progress bar
- --console-title display progress in console titlebar
- -v, --verbose print various debugging information
-
-Video Format Options:
----------------------
-
- -f, --format FORMAT video format code
- --all-formats download all available video formats
- --prefer-free-formats prefer free video formats unless a specific one is
- requested
- --max-quality FORMAT highest quality format to download
- -F, --list-formats list all available formats (currently youtube only)
- --write-srt write video closed captions to a .srt file
- (currently youtube only)
- --srt-lang LANG language of the closed captions to download
- (optional) use IETF language tags like 'en'
-
-Authentication Options:
------------------------
-
- -u, --username USERNAME account username
- -p, --password PASSWORD account password
- -n, --netrc use .netrc authentication data
-
-Post-processing Options:
-------------------------
-
- -x, --extract-audio convert video files to audio-only files (requires
- ffmpeg or avconv and ffprobe or avprobe)
- --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav";
- best by default
- --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a
- value between 0 (better) and 9 (worse) for VBR or a
- specific bitrate like 128K (default 5)
- -k, --keep-video keeps the video file on disk after the post-
- processing; the video is erased by default
-
-CONFIGURATION
-=============
-
-You can configure youtube-dl by placing default arguments (such as
---extract-audio --no-mtime to always extract the audio and not copy the
-mtime) into /etc/youtube-dl.conf and/or ~/.local/config/youtube-dl.conf.
-
-OUTPUT TEMPLATE
-===============
-
-The -o option allows users to indicate a template for the output file
-names. The basic usage is not to set any template arguments when
-downloading a single file, like in
-youtube-dl -o funny_video.flv "http://some/video". However, it may
-contain special sequences that will be replaced when downloading each
-video. The special sequences have the format %(NAME)s. To clarify, that
-is a percent symbol followed by a name in parenthesis, followed by a
-lowercase S. Allowed names are:
-
-- 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.
-
-The current default template is %(id)s.%(ext)s, but that will be
-switchted to %(title)s-%(id)s.%(ext)s (which can be requested with -t at
-the moment).
-
-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:
-
- $ 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
-
-FAQ
-===
-
-Can you please put the -b option back?
-
-Most people asking this question are not aware that youtube-dl now
-defaults to downloading the highest available quality as reported by
-YouTube, which will be 1080p or 720p in some cases, so you no longer
-need the -b option. For some specific videos, maybe YouTube does not
-report them to be available in a specific high quality format you''re
-interested in. In that case, simply request it with the -f option and
-youtube-dl will try to download it.
-
-I get HTTP error 402 when trying to download a video. What's this?
-
-Apparently YouTube requires you to pass a CAPTCHA test if you download
-too much. We''re considering to provide a way to let you solve the
-CAPTCHA, but at the moment, your best course of action is pointing a
-webbrowser to the youtube URL, solving the CAPTCHA, and restart
-youtube-dl.
-
-I have downloaded a video but how can I play it?
-
-Once the video is fully downloaded, use any video player, such as vlc or
-mplayer.
-
-The links provided by youtube-dl -g are not working anymore
-
-The URLs youtube-dl outputs require the downloader to have the correct
-cookies. Use the --cookies option to write the required cookies into a
-file, and advise your downloader to read cookies from that file. Some
-sites also require a common user agent to be used, use --dump-user-agent
-to see the one in use by youtube-dl.
-
-ERROR: no fmt_url_map or conn information found in video info
-
-youtube has switched to a new video info format in July 2011 which is
-not supported by old versions of youtube-dl. You can update youtube-dl
-with sudo youtube-dl --update.
-
-ERROR: unable to download video
-
-youtube requires an additional signature since September 2012 which is
-not supported by old versions of youtube-dl. You can update youtube-dl
-with sudo youtube-dl --update.
-
-SyntaxError: Non-ASCII character
-
-The error
-
- File "youtube-dl", line 2
- SyntaxError: Non-ASCII character '\x93' ...
-
-means you're using an outdated version of Python. Please update to
-Python 2.6 or 2.7.
-
-What is this binary file? Where has the code gone?
-
-Since June 2012 (#342) youtube-dl is packed as an executable zipfile,
-simply unzip it (might need renaming to youtube-dl.zip first on some
-systems) or clone the git repository, as laid out above. If you modify
-the code, you can run it by executing the __main__.py file. To recompile
-the executable, run make youtube-dl.
-
-The exe throws a Runtime error from Visual C++
-
-To run the exe you need to install first the Microsoft Visual C++ 2008
-Redistributable Package.
-
-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.
-
-BUGS
-====
-
-Bugs and suggestions should be reported at:
-https://github.com/rg3/youtube-dl/issues
-
-Please include:
-
-- Your exact command line, like
- youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title".
- A common mistake is not to escape the &. Putting URLs in quotes
- should solve this problem.
-- The output of youtube-dl --version
-- The output of python --version
-- The name and version of your Operating System ("Ubuntu 11.04 x64" or
- "Windows 7 x64" is usually enough).
-
-For discussions, join us in the irc channel #youtube-dl on freenode.
+++ /dev/null
-* The retries thing
-* Travis notifications etc.
-* Kill literal and this escaping stuff
-* setup.py and pip etc.
-* Build server e download
-* 2.5 warning
-
-* Modularize tests!!
-
-* listformats
-* IE capabilities?
-* see Wiki pages
-* _WORKING = automatic supported sites list
-
-* look into --no-mtime
-
-https://github.com/rg3/youtube-dl/pull/408
-
-* linting, PEP, and pyflake http://stackoverflow.com/questions/1428872/pylint-pychecker-or-pyflakes
-
-* Why some tests produce output?
-* 2.6 not running download tests
-
-nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose
\ No newline at end of file
import youtube_dl
BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
-BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.template"
+BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
def build_completion(opt_parser):
opts_flag = []
--- /dev/null
+#!/usr/bin/env python3
+
+import json
+import sys
+import hashlib
+import urllib.request
+
+if len(sys.argv) <= 1:
+ print('Specify the version number as parameter')
+ sys.exit()
+version = sys.argv[1]
+
+with open('update/LATEST_VERSION', 'w') as f:
+ f.write(version)
+
+versions_info = json.load(open('update/versions.json'))
+if 'signature' in versions_info:
+ del versions_info['signature']
+
+new_version = {}
+
+filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
+for key, filename in filenames.items():
+ print('Downloading and checksumming %s...' %filename)
+ url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
+ data = urllib.request.urlopen(url).read()
+ sha256sum = hashlib.sha256(data).hexdigest()
+ new_version[key] = (url, sha256sum)
+
+versions_info['versions'][version] = new_version
+versions_info['latest'] = version
+
+json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
\ No newline at end of file
--- /dev/null
+#!/usr/bin/env python3
+import hashlib
+import shutil
+import subprocess
+import tempfile
+import urllib.request
+import json
+
+versions_info = json.load(open('update/versions.json'))
+version = versions_info['latest']
+URL = versions_info['versions'][version]['bin'][0]
+
+data = urllib.request.urlopen(URL).read()
+
+# Read template page
+with open('download.html.in', 'r', encoding='utf-8') as tmplf:
+ template = tmplf.read()
+
+md5sum = hashlib.md5(data).hexdigest()
+sha1sum = hashlib.sha1(data).hexdigest()
+sha256sum = hashlib.sha256(data).hexdigest()
+template = template.replace('@PROGRAM_VERSION@', version)
+template = template.replace('@PROGRAM_URL@', URL)
+template = template.replace('@PROGRAM_MD5SUM@', md5sum)
+template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
+template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
+template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
+template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])
+template = template.replace('@TAR_URL@', versions_info['versions'][version]['tar'][0])
+template = template.replace('@TAR_SHA256SUM@', versions_info['versions'][version]['tar'][1])
+with open('download.html', 'w', encoding='utf-8') as dlf:
+ dlf.write(template)
--- /dev/null
+#!/usr/bin/env python3
+
+import rsa
+import json
+from binascii import hexlify
+
+try:
+ input = raw_input
+except NameError:
+ pass
+
+versions_info = json.load(open('update/versions.json'))
+if 'signature' in versions_info:
+ del versions_info['signature']
+
+print('Enter the PKCS1 private key, followed by a blank line:')
+privkey = b''
+while True:
+ try:
+ line = input()
+ except EOFError:
+ break
+ if line == '':
+ break
+ privkey += line.encode('ascii') + b'\n'
+privkey = rsa.PrivateKey.load_pkcs1(privkey)
+
+signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()
+print('signature: ' + signature)
+
+versions_info['signature'] = signature
+json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
\ No newline at end of file
--- /dev/null
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import with_statement
+
+import datetime
+import glob
+import io # For Python 2 compatibilty
+import os
+import re
+
+year = str(datetime.datetime.now().year)
+for fn in glob.glob('*.html*'):
+ with io.open(fn, encoding='utf-8') as f:
+ content = f.read()
+ newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content)
+ if content != newc:
+ tmpFn = fn + '.part'
+ with io.open(tmpFn, 'wt', encoding='utf-8') as outf:
+ outf.write(newc)
+ os.rename(tmpFn, fn)
--- /dev/null
+#!/usr/bin/env python3
+
+import datetime
+
+import textwrap
+
+import json
+
+atom_template=textwrap.dedent("""\
+ <?xml version='1.0' encoding='utf-8'?>
+ <atom:feed xmlns:atom="http://www.w3.org/2005/Atom">
+ <atom:title>youtube-dl releases</atom:title>
+ <atom:id>youtube-dl-updates-feed</atom:id>
+ <atom:updated>@TIMESTAMP@</atom:updated>
+ @ENTRIES@
+ </atom:feed>""")
+
+entry_template=textwrap.dedent("""
+ <atom:entry>
+ <atom:id>youtube-dl-@VERSION@</atom:id>
+ <atom:title>New version @VERSION@</atom:title>
+ <atom:link href="http://rg3.github.io/youtube-dl" />
+ <atom:content type="xhtml">
+ <div xmlns="http://www.w3.org/1999/xhtml">
+ Downloads available at <a href="http://youtube-dl.org/downloads/@VERSION@/">http://youtube-dl.org/downloads/@VERSION@/</a>
+ </div>
+ </atom:content>
+ <atom:author>
+ <atom:name>The youtube-dl maintainers</atom:name>
+ </atom:author>
+ <atom:updated>@TIMESTAMP@</atom:updated>
+ </atom:entry>
+ """)
+
+now = datetime.datetime.now()
+now_iso = now.isoformat()
+
+atom_template = atom_template.replace('@TIMESTAMP@',now_iso)
+
+entries=[]
+
+versions_info = json.load(open('update/versions.json'))
+versions = list(versions_info['versions'].keys())
+versions.sort()
+
+for v in versions:
+ entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-'))
+ entry = entry.replace('@VERSION@',v)
+ entries.append(entry)
+
+entries_str = textwrap.indent(''.join(entries), '\t')
+atom_template = atom_template.replace('@ENTRIES@', entries_str)
+
+with open('update/releases.atom','w',encoding='utf-8') as atom_file:
+ atom_file.write(atom_template)
+
+
-#!/bin/sh
+#!/bin/bash
+
+# IMPORTANT: the following assumptions are made
+# * the GH repo is on the origin remote
+# * the gh-pages branch is named so locally
+# * the git config user.signingkey is properly set
+
+# You will need
+# pip install coverage nose rsa
+
+# TODO
+# release notes
+# make hash on local files
+
+set -e
if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
version="$1"
if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
-if [ ! -z "`git status --porcelain`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
-sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/__init__.py
-make all
-git add -A
+if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
+if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
+
+/bin/echo -e "\n### First of all, testing..."
+make cleanall
+nosetests --with-coverage --cover-package=youtube_dl --cover-html test --stop || exit 1
+
+/bin/echo -e "\n### Changing version in version.py..."
+sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
+
+/bin/echo -e "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
+make README.md
+git add CHANGELOG README.md youtube_dl/version.py
git commit -m "release $version"
-git tag -m "Release $version" "$version"
\ No newline at end of file
+
+/bin/echo -e "\n### Now tagging, signing and pushing..."
+git tag -s -m "Release $version" "$version"
+git show "$version"
+read -p "Is it good, can I push? (y/n) " -n 1
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
+echo
+MASTER=$(git rev-parse --abbrev-ref HEAD)
+git push origin $MASTER:master
+git push origin "$version"
+
+/bin/echo -e "\n### OK, now it is time to build the binaries..."
+REV=$(git rev-parse HEAD)
+make youtube-dl youtube-dl.tar.gz
+wget "http://jeromelaheurte.net:8142/download/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe || \
+ wget "http://jeromelaheurte.net:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
+mkdir -p "build/$version"
+mv youtube-dl youtube-dl.exe "build/$version"
+mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"
+RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
+(cd build/$version/ && md5sum $RELEASE_FILES > MD5SUMS)
+(cd build/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
+(cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
+(cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
+git checkout HEAD -- youtube-dl youtube-dl.exe
+
+/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
+for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
+scp -r "build/$version" ytdl@youtube-dl.org:html/downloads/
+
+/bin/echo -e "\n### Now switching to gh-pages..."
+git clone --branch gh-pages --single-branch . build/gh-pages
+ROOT=$(pwd)
+(
+ set -e
+ ORIGIN_URL=$(git config --get remote.origin.url)
+ cd build/gh-pages
+ "$ROOT/devscripts/gh-pages/add-version.py" $version
+ "$ROOT/devscripts/gh-pages/update-feed.py"
+ "$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem"
+ "$ROOT/devscripts/gh-pages/generate-download.py"
+ "$ROOT/devscripts/gh-pages/update-copyright.py"
+ git add *.html *.html.in update
+ git commit -m "release $version"
+ git show HEAD
+ read -p "Is it good, can I push? (y/n) " -n 1
+ if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
+ echo
+ git push "$ROOT" gh-pages
+ git push "$ORIGIN_URL" gh-pages
+)
+rm -rf build
+
+make pypi-files
+echo "Uploading to PyPi ..."
+python setup.py sdist upload
+make clean
+
+/bin/echo -e "\n### DONE!"
import sys, os
import urllib2
+import json, hashlib
+
+def rsa_verify(message, signature, key):
+ from struct import pack
+ from hashlib import sha256
+ from sys import version_info
+ def b(x):
+ if version_info[0] == 2: return x
+ else: return x.encode('latin1')
+ assert(type(message) == type(b('')))
+ block_size = 0
+ n = key[0]
+ while n:
+ block_size += 1
+ n >>= 8
+ signature = pow(int(signature, 16), key[1], key[0])
+ raw_bytes = []
+ while signature:
+ raw_bytes.insert(0, pack("B", signature & 0xFF))
+ signature >>= 8
+ signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
+ if signature[0:2] != b('\x00\x01'): return False
+ signature = signature[2:]
+ if not b('\x00') in signature: return False
+ signature = signature[signature.index(b('\x00'))+1:]
+ if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
+ signature = signature[19:]
+ if signature != sha256(message).digest(): return False
+ return True
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
-sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
+sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
raw_input()
filename = sys.argv[0]
-API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
-EXE_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl.exe"
+UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
+VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
+JSON_URL = UPDATE_URL + 'versions.json'
+UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
sys.exit('ERROR: no write permissions on %s' % directory)
try:
- urlh = urllib2.urlopen(EXE_URL)
+ versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
+ versions_info = json.loads(versions_info)
+except:
+ sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
+if not 'signature' in versions_info:
+ sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
+signature = versions_info['signature']
+del versions_info['signature']
+if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
+ sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
+
+version = versions_info['versions'][versions_info['latest']]
+
+try:
+ urlh = urllib2.urlopen(version['exe'][0])
newcontent = urlh.read()
urlh.close()
+except (IOError, OSError) as err:
+ sys.exit('ERROR: unable to download latest version')
+
+newcontent_hash = hashlib.sha256(newcontent).hexdigest()
+if newcontent_hash != version['exe'][1]:
+ sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
+
+try:
with open(exe + '.new', 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
- sys.exit('ERROR: unable to download latest version')
+ sys.exit(u'ERROR: unable to write the new version')
try:
bat = os.path.join(directory, 'youtube-dl-updater.bat')
# -*- coding: utf-8 -*-
from __future__ import print_function
-from distutils.core import setup
import pkg_resources
import sys
+try:
+ from setuptools import setup
+except ImportError:
+ from distutils.core import setup
+
try:
import py2exe
"""This will create an exe that needs Microsoft Visual C++ 2008 Redistributable Package"""
+++ /dev/null
-#!/usr/bin/env python3
-
-import io # for python 2
-import json
-import os
-import sys
-import unittest
-
-# Allow direct execution
-import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-import youtube_dl.InfoExtractors
-
-HEADER = u'''#!/usr/bin/env python
-
-# DO NOT EDIT THIS FILE BY HAND!
-# It is auto-generated from tests.json and gentests.py.
-
-import hashlib
-import io
-import os
-import json
-import unittest
-import sys
-import socket
-
-# Allow direct execution
-import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-import youtube_dl.FileDownloader
-import youtube_dl.InfoExtractors
-from youtube_dl.utils import *
-
-# General configuration (from __init__, not very elegant...)
-jar = compat_cookiejar.CookieJar()
-cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
-proxy_handler = compat_urllib_request.ProxyHandler()
-opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
-compat_urllib_request.install_opener(opener)
-socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-
-class FileDownloader(youtube_dl.FileDownloader):
- def __init__(self, *args, **kwargs):
- youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
- self.to_stderr = self.to_screen
-
-def _file_md5(fn):
- with open(fn, 'rb') as f:
- return hashlib.md5(f.read()).hexdigest()
-try:
- _skip_unless = unittest.skipUnless
-except AttributeError: # Python 2.6
- def _skip_unless(cond, reason='No reason given'):
- def resfunc(f):
- # Start the function name with test to appease nosetests-2.6
- def test_wfunc(*args, **kwargs):
- if cond:
- return f(*args, **kwargs)
- else:
- print('Skipped test')
- return
- return test_wfunc
- return resfunc
-_skip = lambda *args, **kwargs: _skip_unless(False, *args, **kwargs)
-
-class DownloadTest(unittest.TestCase):
- PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
-
- def setUp(self):
- # Clear old files
- self.tearDown()
-
- with io.open(self.PARAMETERS_FILE, encoding='utf-8') as pf:
- self.parameters = json.load(pf)
-'''
-
-FOOTER = u'''
-
-if __name__ == '__main__':
- unittest.main()
-'''
-
-DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
-TEST_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'test_download.py')
-
-def gentests():
- with io.open(DEF_FILE, encoding='utf-8') as deff:
- defs = json.load(deff)
- with io.open(TEST_FILE, 'w', encoding='utf-8') as testf:
- testf.write(HEADER)
- spaces = ' ' * 4
- write = lambda l: testf.write(spaces + l + u'\n')
-
- for d in defs:
- name = d['name']
- ie = getattr(youtube_dl.InfoExtractors, name + 'IE')
- testf.write(u'\n')
- write('@_skip_unless(youtube_dl.InfoExtractors.' + name + 'IE._WORKING, "IE marked as not _WORKING")')
- if not d['file']:
- write('@_skip("No output file specified")')
- elif 'skip' in d:
- write('@_skip(' + repr(d['skip']) + ')')
- write('def test_' + name + '(self):')
- write(' filename = ' + repr(d['file']))
- write(' params = self.parameters')
- for p in d.get('params', {}):
- write(' params["' + p + '"] = ' + repr(d['params'][p]))
- write(' fd = FileDownloader(params)')
- write(' fd.add_info_extractor(youtube_dl.InfoExtractors.' + name + 'IE())')
- for ien in d.get('addIEs', []):
- write(' fd.add_info_extractor(youtube_dl.InfoExtractors.' + ien + 'IE())')
- write(' fd.download([' + repr(d['url']) + '])')
- write(' self.assertTrue(os.path.exists(filename))')
- if 'md5' in d:
- write(' md5_for_file = _file_md5(filename)')
- write(' self.assertEqual(md5_for_file, ' + repr(d['md5']) + ')')
-
- testf.write(u'\n\n')
- write('def tearDown(self):')
- for d in defs:
- if d['file']:
- write(' if os.path.exists(' + repr(d['file']) + '):')
- write(' os.remove(' + repr(d['file']) + ')')
- else:
- write(' # No file specified for ' + d['name'])
- testf.write(u'\n')
- testf.write(FOOTER)
-
-if __name__ == '__main__':
- gentests()
"simulate": false,
"skip_download": false,
"subtitleslang": null,
+ "subtitlesformat": "srt",
"test": true,
"updatetime": true,
"usenetrc": false,
"username": null,
"verbose": true,
"writedescription": false,
- "writeinfojson": false,
- "writesubtitles": false
-}
\ No newline at end of file
+ "writeinfojson": true,
+ "writesubtitles": false,
+ "onlysubtitles": false,
+ "allsubtitles": false,
+ "listssubtitles": false
+}
--- /dev/null
+#!/usr/bin/env python
+
+import sys
+import unittest
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE
+
+class TestAllURLsMatching(unittest.TestCase):
+ def test_youtube_playlist_matching(self):
+ self.assertTrue(YoutubePlaylistIE.suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
+ self.assertTrue(YoutubePlaylistIE.suitable(u'UUBABnxM4Ar9ten8Mdjj1j0Q')) #585
+ self.assertTrue(YoutubePlaylistIE.suitable(u'PL63F0C78739B09958'))
+ self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q'))
+ self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
+ self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC'))
+ self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+ self.assertFalse(YoutubePlaylistIE.suitable(u'PLtS2H6bU1M'))
+
+ def test_youtube_matching(self):
+ self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
+ self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+
+ def test_youtube_channel_matching(self):
+ self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM'))
+ self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec'))
+ self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos'))
+
+ def test_youtube_extract(self):
+ self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
+ self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
+ self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
+
+if __name__ == '__main__':
+ unittest.main()
#!/usr/bin/env python
-# DO NOT EDIT THIS FILE BY HAND!
-# It is auto-generated from tests.json and gentests.py.
-
+import errno
import hashlib
import io
import os
import json
import unittest
import sys
+import hashlib
import socket
# Allow direct execution
-import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import youtube_dl.FileDownloader
import youtube_dl.InfoExtractors
from youtube_dl.utils import *
+DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
+PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+
+RETRIES = 3
+
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
-socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+socket.setdefaulttimeout(10)
+
+def _try_rm(filename):
+ """ Remove a file if it exists """
+ try:
+ os.remove(filename)
+ except OSError as ose:
+ if ose.errno != errno.ENOENT:
+ raise
class FileDownloader(youtube_dl.FileDownloader):
def __init__(self, *args, **kwargs):
- youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
self.to_stderr = self.to_screen
+ self.processed_info_dicts = []
+ return youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
+ def process_info(self, info_dict):
+ self.processed_info_dicts.append(info_dict)
+ return youtube_dl.FileDownloader.process_info(self, info_dict)
def _file_md5(fn):
with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest()
-try:
- _skip_unless = unittest.skipUnless
-except AttributeError: # Python 2.6
- def _skip_unless(cond, reason='No reason given'):
- def resfunc(f):
- # Start the function name with test to appease nosetests-2.6
- def test_wfunc(*args, **kwargs):
- if cond:
- return f(*args, **kwargs)
- else:
- print('Skipped test')
- return
- return test_wfunc
- return resfunc
-_skip = lambda *args, **kwargs: _skip_unless(False, *args, **kwargs)
-class DownloadTest(unittest.TestCase):
- PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+with io.open(DEF_FILE, encoding='utf-8') as deff:
+ defs = json.load(deff)
+with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ parameters = json.load(pf)
- def setUp(self):
- # Clear old files
- self.tearDown()
- with io.open(self.PARAMETERS_FILE, encoding='utf-8') as pf:
- self.parameters = json.load(pf)
+class TestDownload(unittest.TestCase):
+ maxDiff = None
+ def setUp(self):
+ self.parameters = parameters
+ self.defs = defs
+
+### Dynamically generate tests
+def generator(test_case):
+
+ def test_template(self):
+ ie = youtube_dl.InfoExtractors.get_info_extractor(test_case['name'])
+ if not ie._WORKING:
+ print('Skipping: IE marked as not _WORKING')
+ return
+ if 'playlist' not in test_case and not test_case['file']:
+ print('Skipping: No output file specified')
+ return
+ if 'skip' in test_case:
+ print('Skipping: {0}'.format(test_case['skip']))
+ return
+
+ params = self.parameters.copy()
+ params.update(test_case.get('params', {}))
- @_skip_unless(youtube_dl.InfoExtractors.YoutubeIE._WORKING, "IE marked as not _WORKING")
- def test_Youtube(self):
- filename = u'BaW_jenozKc.mp4'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
- fd.download([u'http://www.youtube.com/watch?v=BaW_jenozKc'])
- self.assertTrue(os.path.exists(filename))
-
- @_skip_unless(youtube_dl.InfoExtractors.DailymotionIE._WORKING, "IE marked as not _WORKING")
- def test_Dailymotion(self):
- filename = u'x33vw9.mp4'
- params = self.parameters
fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.DailymotionIE())
- fd.download([u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'392c4b85a60a90dc4792da41ce3144eb')
-
- @_skip_unless(youtube_dl.InfoExtractors.MetacafeIE._WORKING, "IE marked as not _WORKING")
- def test_Metacafe(self):
- filename = u'_aUehQsCQtM.flv'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.MetacafeIE())
- fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
- fd.download([u'http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/'])
- self.assertTrue(os.path.exists(filename))
-
- @_skip_unless(youtube_dl.InfoExtractors.BlipTVIE._WORKING, "IE marked as not _WORKING")
- def test_BlipTV(self):
- filename = u'5779306.m4v'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.BlipTVIE())
- fd.download([u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'b2d849efcf7ee18917e4b4d9ff37cafe')
-
- @_skip_unless(youtube_dl.InfoExtractors.XVideosIE._WORKING, "IE marked as not _WORKING")
- def test_XVideos(self):
- filename = u'939581.flv'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.XVideosIE())
- fd.download([u'http://www.xvideos.com/video939581/funny_porns_by_s_-1'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'1d0c835822f0a71a7bf011855db929d0')
-
- @_skip_unless(youtube_dl.InfoExtractors.VimeoIE._WORKING, "IE marked as not _WORKING")
- def test_Vimeo(self):
- filename = u'14160053.mp4'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.VimeoIE())
- fd.download([u'http://vimeo.com/14160053'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'60540a4ec7cc378ec84b919c0aed5023')
-
- @_skip_unless(youtube_dl.InfoExtractors.SoundcloudIE._WORKING, "IE marked as not _WORKING")
- def test_Soundcloud(self):
- filename = u'62986583.mp3'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.SoundcloudIE())
- fd.download([u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'ebef0a451b909710ed1d7787dddbf0d7')
-
- @_skip_unless(youtube_dl.InfoExtractors.StanfordOpenClassroomIE._WORKING, "IE marked as not _WORKING")
- def test_StanfordOpenClassroom(self):
- filename = u'PracticalUnix_intro-environment.mp4'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.StanfordOpenClassroomIE())
- fd.download([u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'544a9468546059d4e80d76265b0443b8')
-
- @_skip_unless(youtube_dl.InfoExtractors.XNXXIE._WORKING, "IE marked as not _WORKING")
- def test_XNXX(self):
- filename = u'1135332.flv'
- params = self.parameters
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.XNXXIE())
- fd.download([u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'0831677e2b4761795f68d417e0b7b445')
-
- @_skip_unless(youtube_dl.InfoExtractors.YoukuIE._WORKING, "IE marked as not _WORKING")
- def test_Youku(self):
- filename = u'XNDgyMDQ2NTQw_part00.flv'
- params = self.parameters
- params["test"] = False
- fd = FileDownloader(params)
- fd.add_info_extractor(youtube_dl.InfoExtractors.YoukuIE())
- fd.download([u'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html'])
- self.assertTrue(os.path.exists(filename))
- md5_for_file = _file_md5(filename)
- self.assertEqual(md5_for_file, u'ffe3f2e435663dc2d1eea34faeff5b5b')
-
-
- def tearDown(self):
- if os.path.exists(u'BaW_jenozKc.mp4'):
- os.remove(u'BaW_jenozKc.mp4')
- if os.path.exists(u'x33vw9.mp4'):
- os.remove(u'x33vw9.mp4')
- if os.path.exists(u'_aUehQsCQtM.flv'):
- os.remove(u'_aUehQsCQtM.flv')
- if os.path.exists(u'5779306.m4v'):
- os.remove(u'5779306.m4v')
- if os.path.exists(u'939581.flv'):
- os.remove(u'939581.flv')
- if os.path.exists(u'14160053.mp4'):
- os.remove(u'14160053.mp4')
- if os.path.exists(u'62986583.mp3'):
- os.remove(u'62986583.mp3')
- if os.path.exists(u'PracticalUnix_intro-environment.mp4'):
- os.remove(u'PracticalUnix_intro-environment.mp4')
- if os.path.exists(u'1135332.flv'):
- os.remove(u'1135332.flv')
- if os.path.exists(u'XNDgyMDQ2NTQw_part00.flv'):
- os.remove(u'XNDgyMDQ2NTQw_part00.flv')
-
+ for ie in youtube_dl.InfoExtractors.gen_extractors():
+ fd.add_info_extractor(ie)
+ finished_hook_called = set()
+ def _hook(status):
+ if status['status'] == 'finished':
+ finished_hook_called.add(status['filename'])
+ fd.add_progress_hook(_hook)
+
+ test_cases = test_case.get('playlist', [test_case])
+ for tc in test_cases:
+ _try_rm(tc['file'])
+ _try_rm(tc['file'] + '.part')
+ _try_rm(tc['file'] + '.info.json')
+ try:
+ for retry in range(1, RETRIES + 1):
+ try:
+ fd.download([test_case['url']])
+ except (DownloadError, ExtractorError) as err:
+ if retry == RETRIES: raise
+
+ # Check if the exception is not a network related one
+ if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
+ raise
+
+ print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry))
+ else:
+ break
+
+ for tc in test_cases:
+ if not test_case.get('params', {}).get('skip_download', False):
+ self.assertTrue(os.path.exists(tc['file']), msg='Missing file ' + tc['file'])
+ self.assertTrue(tc['file'] in finished_hook_called)
+ self.assertTrue(os.path.exists(tc['file'] + '.info.json'))
+ if 'md5' in tc:
+ md5_for_file = _file_md5(tc['file'])
+ self.assertEqual(md5_for_file, tc['md5'])
+ with io.open(tc['file'] + '.info.json', encoding='utf-8') as infof:
+ info_dict = json.load(infof)
+ for (info_field, value) in tc.get('info_dict', {}).items():
+ self.assertEqual(value, info_dict.get(info_field))
+ finally:
+ for tc in test_cases:
+ _try_rm(tc['file'])
+ _try_rm(tc['file'] + '.part')
+ _try_rm(tc['file'] + '.info.json')
+
+ return test_template
+
+### And add them to TestDownload
+for test_case in defs:
+ test_method = generator(test_case)
+ test_method.__name__ = "test_{0}".format(test_case["name"])
+ setattr(TestDownload, test_method.__name__, test_method)
+ del test_method
if __name__ == '__main__':
from youtube_dl.utils import sanitize_filename
from youtube_dl.utils import unescapeHTML
from youtube_dl.utils import orderedSet
+from youtube_dl.utils import DateRange
+from youtube_dl.utils import unified_strdate
if sys.version_info < (3, 0):
_compat_str = lambda b: b.decode('unicode-escape')
self.assertTrue(sanitize_filename(':', restricted=True) != '')
def test_sanitize_ids(self):
- self.assertEquals(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
- self.assertEquals(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
- self.assertEquals(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
+ self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
+ self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
+ self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
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])
def test_unescape_html(self):
self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
+
+ def test_daterange(self):
+ _20century = DateRange("19000101","20000101")
+ self.assertFalse("17890714" in _20century)
+ _ac = DateRange("00010101")
+ self.assertTrue("19690721" in _ac)
+ _firstmilenium = DateRange(end="10000101")
+ self.assertTrue("07110427" in _firstmilenium)
+
+ def test_unified_dates(self):
+ self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
+ self.assertEqual(unified_strdate('8/7/2009'), '20090708')
+ self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
+ self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
if __name__ == '__main__':
unittest.main()
--- /dev/null
+#!/usr/bin/env python
+# coding: utf-8
+
+import json
+import os
+import sys
+import unittest
+
+# Allow direct execution
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl.FileDownloader
+import youtube_dl.InfoExtractors
+from youtube_dl.utils import *
+
+PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+
+class FileDownloader(youtube_dl.FileDownloader):
+ def __init__(self, *args, **kwargs):
+ youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
+ self.to_stderr = self.to_screen
+
+with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ params = json.load(pf)
+params['writeinfojson'] = True
+params['skip_download'] = True
+params['writedescription'] = True
+
+TEST_ID = 'BaW_jenozKc'
+INFO_JSON_FILE = TEST_ID + '.mp4.info.json'
+DESCRIPTION_FILE = TEST_ID + '.mp4.description'
+EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐
+
+This is a test video for youtube-dl.
+
+For more information, contact phihag@phihag.de .'''
+
+class TestInfoJSON(unittest.TestCase):
+ def setUp(self):
+ # Clear old files
+ self.tearDown()
+
+ def test_info_json(self):
+ ie = youtube_dl.InfoExtractors.YoutubeIE()
+ fd = FileDownloader(params)
+ fd.add_info_extractor(ie)
+ fd.download([TEST_ID])
+ self.assertTrue(os.path.exists(INFO_JSON_FILE))
+ with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
+ jd = json.load(jsonf)
+ self.assertEqual(jd['upload_date'], u'20121002')
+ self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
+ self.assertEqual(jd['id'], TEST_ID)
+ self.assertEqual(jd['extractor'], 'youtube')
+ self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
+ self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
+
+ self.assertTrue(os.path.exists(DESCRIPTION_FILE))
+ with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
+ descr = descf.read()
+ self.assertEqual(descr, EXPECTED_DESCRIPTION)
+
+ def tearDown(self):
+ if os.path.exists(INFO_JSON_FILE):
+ os.remove(INFO_JSON_FILE)
+ if os.path.exists(DESCRIPTION_FILE):
+ os.remove(DESCRIPTION_FILE)
+
+if __name__ == '__main__':
+ unittest.main()
import sys
import unittest
-import socket
+import json
# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from youtube_dl.InfoExtractors import YoutubePlaylistIE
+from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE
from youtube_dl.utils import *
+from youtube_dl.FileDownloader import FileDownloader
+
+PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ parameters = json.load(pf)
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
-socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-class FakeDownloader(object):
+class FakeDownloader(FileDownloader):
def __init__(self):
self.result = []
- self.params = {}
+ self.params = parameters
def to_screen(self, s):
print(s)
- def trouble(self, s):
+ def trouble(self, s, tb=None):
raise Exception(s)
- def download(self, x):
- self.result.append(x)
+ def extract_info(self, url):
+ self.result.append(url)
+ return url
class TestYoutubeLists(unittest.TestCase):
+ def assertIsPlaylist(self,info):
+ """Make sure the info has '_type' set to 'playlist'"""
+ self.assertEqual(info['_type'], 'playlist')
+
def test_youtube_playlist(self):
- DL = FakeDownloader()
- IE = YoutubePlaylistIE(DL)
- IE.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
- self.assertEqual(DL.result, [
- ['http://www.youtube.com/watch?v=bV9L5Ht9LgY'],
- ['http://www.youtube.com/watch?v=FXxLjLQi3Fg'],
- ['http://www.youtube.com/watch?v=tU3Bgo5qJZE']
- ])
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0]
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], 'ytdl test PL')
+ ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+ self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
+
+ def test_issue_673(self):
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('PLBB231211A4F62143')[0]
+ self.assertEqual(result['title'], 'Team Fortress 2')
+ self.assertTrue(len(result['entries']) > 40)
def test_youtube_playlist_long(self):
- DL = FakeDownloader()
- IE = YoutubePlaylistIE(DL)
- IE.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
- self.assertTrue(len(DL.result) >= 799)
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0]
+ self.assertIsPlaylist(result)
+ self.assertTrue(len(result['entries']) >= 799)
+
+ def test_youtube_playlist_with_deleted(self):
+ #651
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0]
+ ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+ self.assertFalse('pElCt5oNDuI' in ytie_results)
+ self.assertFalse('KdPEApIVdWM' in ytie_results)
+
+ def test_youtube_playlist_empty(self):
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0]
+ self.assertIsPlaylist(result)
+ self.assertEqual(len(result['entries']), 0)
def test_youtube_course(self):
- DL = FakeDownloader()
- IE = YoutubePlaylistIE(DL)
+ dl = FakeDownloader()
+ ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
- IE.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
- self.assertEqual(DL.result[0], ['http://www.youtube.com/watch?v=j9WZyLZCBzs'])
- self.assertEqual(len(DL.result), 25)
- self.assertEqual(DL.result[-1], ['http://www.youtube.com/watch?v=rYefUsYuEp0'])
+ result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0]
+ entries = 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')
def test_youtube_channel(self):
- """I give up, please find a channel that does paginate and test this like test_youtube_playlist_long"""
- pass # TODO
+ dl = FakeDownloader()
+ ie = YoutubeChannelIE(dl)
+ #test paginated channel
+ result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0]
+ self.assertTrue(len(result['entries']) > 90)
+ #test autogenerated channel
+ result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')[0]
+ self.assertTrue(len(result['entries']) >= 18)
def test_youtube_user(self):
- DL = FakeDownloader()
- IE = YoutubePlaylistIE(DL)
- IE.extract('https://www.youtube.com/user/TheLinuxFoundation')
- self.assertTrue(len(DL.result) >= 320)
+ dl = FakeDownloader()
+ ie = YoutubeUserIE(dl)
+ result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0]
+ self.assertTrue(len(result['entries']) >= 320)
if __name__ == '__main__':
unittest.main()
+++ /dev/null
-#!/usr/bin/env python
-
-import sys
-import unittest
-
-# Allow direct execution
-import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
-
-class TestYoutubePlaylistMatching(unittest.TestCase):
- def test_playlist_matching(self):
- self.assertTrue(YoutubePlaylistIE().suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
- self.assertTrue(YoutubePlaylistIE().suitable(u'PL63F0C78739B09958'))
- self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M'))
-
- def test_youtube_matching(self):
- self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M'))
-
-if __name__ == '__main__':
- unittest.main()
--- /dev/null
+#!/usr/bin/env python
+
+import sys
+import unittest
+import json
+import io
+import hashlib
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.InfoExtractors import YoutubeIE
+from youtube_dl.utils import *
+from youtube_dl import FileDownloader
+
+PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ parameters = json.load(pf)
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+
+class FakeDownloader(FileDownloader):
+ def __init__(self):
+ self.result = []
+ self.params = parameters
+ def to_screen(self, s):
+ print(s)
+ def trouble(self, s, tb=None):
+ raise Exception(s)
+ def download(self, x):
+ self.result.append(x)
+
+md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+class TestYoutubeSubtitles(unittest.TestCase):
+ def setUp(self):
+ DL = FakeDownloader()
+ DL.params['allsubtitles'] = False
+ DL.params['writesubtitles'] = False
+ DL.params['subtitlesformat'] = 'srt'
+ DL.params['listsubtitles'] = False
+ def test_youtube_no_subtitles(self):
+ DL = FakeDownloader()
+ DL.params['writesubtitles'] = False
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ subtitles = info_dict[0]['subtitles']
+ self.assertEqual(subtitles, None)
+ def test_youtube_subtitles(self):
+ DL = FakeDownloader()
+ DL.params['writesubtitles'] = True
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ sub = info_dict[0]['subtitles'][0]
+ self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
+ def test_youtube_subtitles_it(self):
+ DL = FakeDownloader()
+ DL.params['writesubtitles'] = True
+ DL.params['subtitleslang'] = 'it'
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ sub = info_dict[0]['subtitles'][0]
+ self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
+ def test_youtube_onlysubtitles(self):
+ DL = FakeDownloader()
+ DL.params['writesubtitles'] = True
+ DL.params['onlysubtitles'] = True
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ sub = info_dict[0]['subtitles'][0]
+ self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
+ def test_youtube_allsubtitles(self):
+ DL = FakeDownloader()
+ DL.params['allsubtitles'] = True
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ subtitles = info_dict[0]['subtitles']
+ self.assertEqual(len(subtitles), 13)
+ def test_youtube_subtitles_format(self):
+ DL = FakeDownloader()
+ DL.params['writesubtitles'] = True
+ DL.params['subtitlesformat'] = 'sbv'
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ sub = info_dict[0]['subtitles'][0]
+ self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b')
+ def test_youtube_list_subtitles(self):
+ DL = FakeDownloader()
+ DL.params['listsubtitles'] = True
+ IE = YoutubeIE(DL)
+ info_dict = IE.extract('QRS8MkLhQmM')
+ self.assertEqual(info_dict, None)
+
+if __name__ == '__main__':
+ unittest.main()
{
"name": "Youtube",
"url": "http://www.youtube.com/watch?v=BaW_jenozKc",
- "file": "BaW_jenozKc.mp4"
+ "file": "BaW_jenozKc.mp4",
+ "info_dict": {
+ "title": "youtube-dl test video \"'/\\ä↭𝕐",
+ "uploader": "Philipp Hagemeister",
+ "uploader_id": "phihag",
+ "upload_date": "20121002",
+ "description": "test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
+ }
},
{
"name": "Dailymotion",
},
{
"name": "Metacafe",
- "addIEs": ["Youtube"],
- "url": "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
+ "add_ie": ["Youtube"],
+ "url": "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
"file": "_aUehQsCQtM.flv"
},
{
"url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
"file": "939581.flv"
},
+ {
+ "name": "YouPorn",
+ "md5": "c37ddbaaa39058c76a7e86c6813423c1",
+ "url": "http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/",
+ "file": "505835.mp4"
+ },
+ {
+ "name": "Pornotube",
+ "md5": "374dd6dcedd24234453b295209aa69b6",
+ "url": "http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing",
+ "file": "1689755.flv"
+ },
+ {
+ "name": "YouJizz",
+ "md5": "07e15fa469ba384c7693fd246905547c",
+ "url": "http://www.youjizz.com/videos/zeichentrick-1-2189178.html",
+ "file": "2189178.flv"
+ },
{
"name": "Vimeo",
- "md5": "60540a4ec7cc378ec84b919c0aed5023",
- "url": "http://vimeo.com/14160053",
- "file": "14160053.mp4"
+ "md5": "8879b6cc097e987f02484baf890129e5",
+ "url": "http://vimeo.com/56015672",
+ "file": "56015672.mp4",
+ "info_dict": {
+ "title": "youtube-dl test video - ★ \" ' 幸 / \\ ä ↭ 𝕐",
+ "uploader": "Filippo Valsorda",
+ "uploader_id": "user7108434",
+ "upload_date": "20121220",
+ "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: ★ \" ' 幸 / \\ ä ↭ 𝕐"
+ }
},
{
"name": "Soundcloud",
"file": "XNDgyMDQ2NTQw_part00.flv",
"md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
"params": { "test": false }
+ },
+ {
+ "name": "NBA",
+ "url": "http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html",
+ "file": "0021200253-okc-bkn-recap.nba.mp4",
+ "md5": "c0edcfc37607344e2ff8f13c378c88a4"
+ },
+ {
+ "name": "JustinTV",
+ "url": "http://www.twitch.tv/thegamedevhub/b/296128360",
+ "file": "296128360.flv",
+ "md5": "ecaa8a790c22a40770901460af191c9a"
+ },
+ {
+ "name": "MyVideo",
+ "url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
+ "file": "8229274.flv",
+ "md5": "2d2753e8130479ba2cb7e0a37002053e"
+ },
+ {
+ "name": "Escapist",
+ "url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
+ "file": "6618-Breaking-Down-Baldurs-Gate.mp4",
+ "md5": "c6793dbda81388f4264c1ba18684a74d"
+ },
+ {
+ "name": "GooglePlus",
+ "url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
+ "file": "ZButuJc6CtH.flv"
+ },
+ {
+ "name": "FunnyOrDie",
+ "url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
+ "file": "0732f586d7.mp4",
+ "md5": "f647e9e90064b53b6e046e75d0241fbd"
+ },
+ {
+ "name": "Steam",
+ "url": "http://store.steampowered.com/video/105600/",
+ "playlist": [
+ {
+ "file": "81300.flv",
+ "md5": "f870007cee7065d7c76b88f0a45ecc07",
+ "info_dict": {
+ "title": "Terraria 1.1 Trailer"
+ }
+ },
+ {
+ "file": "80859.flv",
+ "md5": "61aaf31a5c5c3041afb58fb83cbb5751",
+ "info_dict": {
+ "title": "Terraria Trailer"
+ }
+ }
+ ]
+ },
+ {
+ "name": "Ustream",
+ "url": "http://www.ustream.tv/recorded/20274954",
+ "file": "20274954.flv",
+ "md5": "088f151799e8f572f84eb62f17d73e5c",
+ "info_dict": {
+ "title": "Young Americans for Liberty February 7, 2012 2:28 AM"
+ }
+ },
+ {
+ "name": "InfoQ",
+ "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
+ "file": "12-jan-pythonthings.mp4",
+ "info_dict": {
+ "title": "A Few of My Favorite [Python] Things"
+ },
+ "params": {
+ "skip_download": true
+ }
+ },
+ {
+ "name": "ComedyCentral",
+ "url": "http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart",
+ "file": "422212.mp4",
+ "md5": "4e2f5cb088a83cd8cdb7756132f9739d",
+ "info_dict": {
+ "title": "thedailyshow-kristen-stewart part 1"
+ }
+ },
+ {
+ "name": "RBMARadio",
+ "url": "http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011",
+ "file": "ford-lopatin-live-at-primavera-sound-2011.mp3",
+ "md5": "6bc6f9bcb18994b4c983bc3bf4384d95",
+ "info_dict": {
+ "title": "Live at Primavera Sound 2011",
+ "description": "Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
+ "uploader": "Ford & Lopatin",
+ "uploader_id": "ford-lopatin",
+ "location": "Spain"
+ }
+ },
+ {
+ "name": "Facebook",
+ "url": "https://www.facebook.com/photo.php?v=120708114770723",
+ "file": "120708114770723.mp4",
+ "md5": "48975a41ccc4b7a581abd68651c1a5a8",
+ "info_dict": {
+ "title": "PEOPLE ARE AWESOME 2013",
+ "duration": 279
+ }
+ },
+ {
+ "name": "EightTracks",
+ "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
+ "playlist": [
+ {
+ "file": "11885610.m4a",
+ "md5": "96ce57f24389fc8734ce47f4c1abcc55",
+ "info_dict": {
+ "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
+ "uploader_id": "ytdl"
+ }
+ },
+ {
+ "file": "11885608.m4a",
+ "md5": "4ab26f05c1f7291ea460a3920be8021f",
+ "info_dict": {
+ "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
+ "uploader_id": "ytdl"
+
+ }
+ },
+ {
+ "file": "11885679.m4a",
+ "md5": "d30b5b5f74217410f4689605c35d1fd7",
+ "info_dict": {
+ "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad"
+ }
+ },
+ {
+ "file": "11885680.m4a",
+ "md5": "4eb0a669317cd725f6bbd336a29f923a",
+ "info_dict": {
+ "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad"
+ }
+ },
+ {
+ "file": "11885682.m4a",
+ "md5": "1893e872e263a2705558d1d319ad19e8",
+ "info_dict": {
+ "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad"
+ }
+ },
+ {
+ "file": "11885683.m4a",
+ "md5": "b673c46f47a216ab1741ae8836af5899",
+ "info_dict": {
+ "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad"
+ }
+ },
+ {
+ "file": "11885684.m4a",
+ "md5": "1d74534e95df54986da7f5abf7d842b7",
+ "info_dict": {
+ "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad"
+ }
+ },
+ {
+ "file": "11885685.m4a",
+ "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
+ "info_dict": {
+ "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad"
+ }
+ }
+ ]
+ },
+ {
+ "name": "Keek",
+ "url": "http://www.keek.com/ytdl/keeks/NODfbab",
+ "file": "NODfbab.mp4",
+ "md5": "9b0636f8c0f7614afa4ea5e4c6e57e83",
+ "info_dict": {
+ "title": "test chars: \"'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
+ }
+
+ },
+ {
+ "name": "TED",
+ "url": "http://www.ted.com/talks/dan_dennett_on_our_consciousness.html",
+ "file": "102.mp4",
+ "md5": "7bc087e71d16f18f9b8ab9fa62a8a031",
+ "info_dict": {
+ "title": "Dan Dennett: The illusion of consciousness",
+ "thumbnail": "http://images.ted.com/images/ted/488_389x292.jpg"
+ }
+ },
+ {
+ "name": "MySpass",
+ "url": "http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/",
+ "file": "11741.mp4",
+ "md5": "0b49f4844a068f8b33f4b7c88405862b",
+ "info_dict": {
+ "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
+ }
+ },
+ {
+ "name": "Generic",
+ "url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html",
+ "file": "13601338388002.mp4",
+ "md5": "85b90ccc9d73b4acd9138d3af4c27f89"
+ },
+ {
+ "name": "Spiegel",
+ "url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html",
+ "file": "1259285.mp4",
+ "md5": "2c2754212136f35fb4b19767d242f66e",
+ "info_dict": {
+ "title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
+ }
+ },
+ {
+ "name": "LiveLeak",
+ "md5": "0813c2430bea7a46bf13acf3406992f4",
+ "url": "http://www.liveleak.com/view?i=757_1364311680",
+ "file": "757_1364311680.mp4",
+ "info_dict": {
+ "title": "Most unlucky car accident",
+ "description": "extremely bad day for this guy..!",
+ "uploader": "ljfriel2"
+ }
+ },
+ {
+ "name": "WorldStarHipHop",
+ "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
+ "file": "wshh6a7q1ny0G34ZwuIO.mp4",
+ "md5": "9d04de741161603bf7071bbf4e883186",
+ "info_dict": {
+ "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! "
+ }
+ },
+ {
+ "name": "ARD",
+ "url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640",
+ "file": "14077640.mp4",
+ "md5": "6ca8824255460c787376353f9e20bbd8",
+ "info_dict": {
+ "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+ },
+ "skip": "Requires rtmpdump"
+ },
+ {
+ "name": "Tumblr",
+ "url": "http://birthdayproject2012.tumblr.com/post/17258355236/a-sample-video-from-leeann-if-you-need-an-idea",
+ "file": "17258355236.mp4",
+ "md5": "7c6a514d691b034ccf8567999e9e88a3",
+ "info_dict": {
+ "title": "Calling all Pris! - A sample video from LeeAnn. (If you need an idea..."
+ }
+ },
+ {
+ "name": "SoundcloudSet",
+ "url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
+ "playlist":[
+ {
+ "file":"30510138.mp3",
+ "md5":"f9136bf103901728f29e419d2c70f55d",
+ "info_dict": {
+ "title":"D-D-Dance"
+ }
+ },
+ {
+ "file":"47127625.mp3",
+ "md5":"09b6758a018470570f8fd423c9453dd8",
+ "info_dict": {
+ "title":"The Royal Concept - Gimme Twice"
+ }
+ },
+ {
+ "file":"47127627.mp3",
+ "md5":"154abd4e418cea19c3b901f1e1306d9c",
+ "info_dict": {
+ "title":"Goldrushed"
+ }
+ },
+ {
+ "file":"47127629.mp3",
+ "md5":"2f5471edc79ad3f33a683153e96a79c1",
+ "info_dict": {
+ "title":"In the End"
+ }
+ },
+ {
+ "file":"47127631.mp3",
+ "md5":"f9ba87aa940af7213f98949254f1c6e2",
+ "info_dict": {
+ "title":"Knocked Up"
+ }
+ },
+ {
+ "file":"75206121.mp3",
+ "md5":"f9d1fe9406717e302980c30de4af9353",
+ "info_dict": {
+ "title":"World On Fire"
+ }
+ }
+ ]
+ },
+ {
+ "name":"Bandcamp",
+ "url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
+ "file":"1812978515.mp3",
+ "md5":"cdeb30cdae1921719a3cbcab696ef53c",
+ "info_dict": {
+ "title":"youtube-dl test song \"'/\\ä↭"
+ },
+ "skip": "There is a limit of 200 free downloads / month for the test song"
+ },
+ {
+ "name": "RedTube",
+ "url": "http://www.redtube.com/66418",
+ "file": "66418.mp4",
+ "md5": "7b8c22b5e7098a3e1c09709df1126d2d",
+ "info_dict":{
+ "title":"Sucked on a toilet"
+ }
+ },
+ {
+ "name": "Photobucket",
+ "url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0",
+ "file": "zpsc0c3b9fa.mp4",
+ "md5": "7dabfb92b0a31f6c16cebc0f8e60ff99",
+ "info_dict":{
+ "title":"Tired of Link Building? Try BacklinkMyDomain.com!"
+ }
+ },
+ {
+ "name": "Ina",
+ "url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
+ "file": "I12055569.mp4",
+ "md5": "a667021bf2b41f8dc6049479d9bb38a3",
+ "info_dict":{
+ "title":"François Hollande \"Je crois que c'est clair\""
+ }
+ },
+ {
+ "name": "Yahoo",
+ "url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html",
+ "file": "27592561.flv",
+ "md5": "c6179bed843512823fd284fa2e7f012d",
+ "info_dict": {
+ "title": "Obama Celebrates Iraq Victory"
+ },
+ "skip": "Requires rtmpdump"
}
]
+++ /dev/null
-.TH YOUTUBE-DL 1 ""
-.SH NAME
-.PP
-youtube-dl
-.SH SYNOPSIS
-.PP
-\f[B]youtube-dl\f[] [OPTIONS] URL [URL...]
-.SH DESCRIPTION
-.PP
-\f[B]youtube-dl\f[] is a small command-line program to download videos
-from YouTube.com and a few more sites.
-It requires the Python interpreter, version 2.x (x being at least 6),
-and it is not platform specific.
-It should work in your Unix box, in Windows or in Mac OS X.
-It is released to the public domain, which means you can modify it,
-redistribute it or use it however you like.
-.SH OPTIONS
-.IP
-.nf
-\f[C]
--h,\ --help\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ this\ help\ text\ and\ exit
---version\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ program\ version\ and\ exit
--U,\ --update\ \ \ \ \ \ \ \ \ \ \ \ \ update\ this\ program\ to\ latest\ version
--i,\ --ignore-errors\ \ \ \ \ \ continue\ on\ download\ errors
--r,\ --rate-limit\ LIMIT\ \ \ download\ rate\ limit\ (e.g.\ 50k\ or\ 44.6m)
--R,\ --retries\ RETRIES\ \ \ \ number\ of\ retries\ (default\ is\ 10)
---buffer-size\ SIZE\ \ \ \ \ \ \ size\ of\ download\ buffer\ (e.g.\ 1024\ or\ 16k)\ (default
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ is\ 1024)
---no-resize-buffer\ \ \ \ \ \ \ do\ not\ automatically\ adjust\ the\ buffer\ size.\ By
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default,\ the\ buffer\ size\ is\ automatically\ resized
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ an\ initial\ value\ of\ SIZE.
---dump-user-agent\ \ \ \ \ \ \ \ display\ the\ current\ browser\ identification
---user-agent\ UA\ \ \ \ \ \ \ \ \ \ specify\ a\ custom\ user\ agent
---list-extractors\ \ \ \ \ \ \ \ List\ all\ supported\ extractors\ and\ the\ URLs\ they
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ would\ handle
-\f[]
-.fi
-.SS Video Selection:
-.IP
-.nf
-\f[C]
---playlist-start\ NUMBER\ \ playlist\ video\ to\ start\ at\ (default\ is\ 1)
---playlist-end\ NUMBER\ \ \ \ playlist\ video\ to\ end\ at\ (default\ is\ last)
---match-title\ REGEX\ \ \ \ \ \ download\ only\ matching\ titles\ (regex\ or\ caseless
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ sub-string)
---reject-title\ REGEX\ \ \ \ \ skip\ download\ for\ matching\ titles\ (regex\ or
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ caseless\ sub-string)
---max-downloads\ NUMBER\ \ \ Abort\ after\ downloading\ NUMBER\ files
-\f[]
-.fi
-.SS Filesystem Options:
-.IP
-.nf
-\f[C]
--t,\ --title\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ title\ in\ file\ name
---id\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ video\ ID\ in\ file\ name
--l,\ --literal\ \ \ \ \ \ \ \ \ \ \ \ [deprecated]\ alias\ of\ --title
--A,\ --auto-number\ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000
--o,\ --output\ TEMPLATE\ \ \ \ output\ filename\ template.\ Use\ %(title)s\ to\ get\ the
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ title,\ %(uploader)s\ for\ the\ uploader\ name,
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(autonumber)s\ to\ get\ an\ automatically\ incremented
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ number,\ %(ext)s\ for\ the\ filename\ extension,
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(upload_date)s\ for\ the\ upload\ date\ (YYYYMMDD),
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(extractor)s\ for\ the\ provider\ (youtube,\ metacafe,
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ etc),\ %(id)s\ for\ the\ video\ id\ and\ %%\ for\ a\ literal
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ percent.\ Use\ -\ to\ output\ to\ stdout.\ Can\ also\ be
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ used\ to\ download\ to\ a\ different\ directory,\ for
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ example\ with\ -o\ \[aq]/my/downloads/%(uploader)s/%(title
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ )s-%(id)s.%(ext)s\[aq]\ .
---restrict-filenames\ \ \ \ \ Restrict\ filenames\ to\ only\ ASCII\ characters,\ and
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ avoid\ "&"\ and\ spaces\ in\ filenames
--a,\ --batch-file\ FILE\ \ \ \ file\ containing\ URLs\ to\ download\ (\[aq]-\[aq]\ for\ stdin)
--w,\ --no-overwrites\ \ \ \ \ \ do\ not\ overwrite\ files
--c,\ --continue\ \ \ \ \ \ \ \ \ \ \ resume\ partially\ downloaded\ files
---no-continue\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ resume\ partially\ downloaded\ files\ (restart
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ beginning)
---cookies\ FILE\ \ \ \ \ \ \ \ \ \ \ file\ to\ read\ cookies\ from\ and\ dump\ cookie\ jar\ in
---no-part\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ .part\ files
---no-mtime\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ the\ Last-modified\ header\ to\ set\ the\ file
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ modification\ time
---write-description\ \ \ \ \ \ write\ video\ description\ to\ a\ .description\ file
---write-info-json\ \ \ \ \ \ \ \ write\ video\ metadata\ to\ a\ .info.json\ file
-\f[]
-.fi
-.SS Verbosity / Simulation Options:
-.IP
-.nf
-\f[C]
--q,\ --quiet\ \ \ \ \ \ \ \ \ \ \ \ \ \ activates\ quiet\ mode
--s,\ --simulate\ \ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video\ and\ do\ not\ write\ anything
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ disk
---skip-download\ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video
--g,\ --get-url\ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ URL
--e,\ --get-title\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ title
---get-thumbnail\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ thumbnail\ URL
---get-description\ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ video\ description
---get-filename\ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ filename
---get-format\ \ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ format
---no-progress\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ print\ progress\ bar
---console-title\ \ \ \ \ \ \ \ \ \ display\ progress\ in\ console\ titlebar
--v,\ --verbose\ \ \ \ \ \ \ \ \ \ \ \ print\ various\ debugging\ information
-\f[]
-.fi
-.SS Video Format Options:
-.IP
-.nf
-\f[C]
--f,\ --format\ FORMAT\ \ \ \ \ \ video\ format\ code
---all-formats\ \ \ \ \ \ \ \ \ \ \ \ download\ all\ available\ video\ formats
---prefer-free-formats\ \ \ \ prefer\ free\ video\ formats\ unless\ a\ specific\ one\ is
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ requested
---max-quality\ FORMAT\ \ \ \ \ highest\ quality\ format\ to\ download
--F,\ --list-formats\ \ \ \ \ \ \ list\ all\ available\ formats\ (currently\ youtube\ only)
---write-srt\ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ closed\ captions\ to\ a\ .srt\ file
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (currently\ youtube\ only)
---srt-lang\ LANG\ \ \ \ \ \ \ \ \ \ language\ of\ the\ closed\ captions\ to\ download
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (optional)\ use\ IETF\ language\ tags\ like\ \[aq]en\[aq]
-\f[]
-.fi
-.SS Authentication Options:
-.IP
-.nf
-\f[C]
--u,\ --username\ USERNAME\ \ account\ username
--p,\ --password\ PASSWORD\ \ account\ password
--n,\ --netrc\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ .netrc\ authentication\ data
-\f[]
-.fi
-.SS Post-processing Options:
-.IP
-.nf
-\f[C]
--x,\ --extract-audio\ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ffmpeg\ or\ avconv\ and\ ffprobe\ or\ avprobe)
---audio-format\ FORMAT\ \ \ \ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ or\ "wav";
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ best\ by\ default
---audio-quality\ QUALITY\ \ ffmpeg/avconv\ audio\ quality\ specification,\ insert\ a
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ value\ between\ 0\ (better)\ and\ 9\ (worse)\ for\ VBR\ or\ a
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ specific\ bitrate\ like\ 128K\ (default\ 5)
--k,\ --keep-video\ \ \ \ \ \ \ \ \ keeps\ the\ video\ file\ on\ disk\ after\ the\ post-
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ processing;\ the\ video\ is\ erased\ by\ default
-\f[]
-.fi
-.SH CONFIGURATION
-.PP
-You can configure youtube-dl by placing default arguments (such as
-\f[C]--extract-audio\ --no-mtime\f[] to always extract the audio and not
-copy the mtime) into \f[C]/etc/youtube-dl.conf\f[] and/or
-\f[C]~/.local/config/youtube-dl.conf\f[].
-.SH OUTPUT TEMPLATE
-.PP
-The \f[C]-o\f[] 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
-\f[C]youtube-dl\ -o\ funny_video.flv\ "http://some/video"\f[].
-However, it may contain special sequences that will be replaced when
-downloading each video.
-The special sequences have the format \f[C]%(NAME)s\f[].
-To clarify, that is a percent symbol followed by a name in parenthesis,
-followed by a lowercase S.
-Allowed names are:
-.IP \[bu] 2
-\f[C]id\f[]: The sequence will be replaced by the video identifier.
-.IP \[bu] 2
-\f[C]url\f[]: The sequence will be replaced by the video URL.
-.IP \[bu] 2
-\f[C]uploader\f[]: The sequence will be replaced by the nickname of the
-person who uploaded the video.
-.IP \[bu] 2
-\f[C]upload_date\f[]: The sequence will be replaced by the upload date
-in YYYYMMDD format.
-.IP \[bu] 2
-\f[C]title\f[]: The sequence will be replaced by the video title.
-.IP \[bu] 2
-\f[C]ext\f[]: The sequence will be replaced by the appropriate extension
-(like flv or mp4).
-.IP \[bu] 2
-\f[C]epoch\f[]: The sequence will be replaced by the Unix epoch when
-creating the file.
-.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.
-.PP
-The current default template is \f[C]%(id)s.%(ext)s\f[], but that will
-be switchted to \f[C]%(title)s-%(id)s.%(ext)s\f[] (which can be
-requested with \f[C]-t\f[] at the moment).
-.PP
-In some cases, you don\[aq]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 \f[C]--restrict-filenames\f[] flag to get a
-shorter title:
-.IP
-.nf
-\f[C]
-$\ youtube-dl\ --get-filename\ -o\ "%(title)s.%(ext)s"\ 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_test_video_.mp4\ \ \ \ \ \ \ \ \ \ #\ A\ simple\ file\ name
-\f[]
-.fi
-.SH FAQ
-.SS Can you please put the -b option back?
-.PP
-Most people asking this question are not aware that youtube-dl now
-defaults to downloading the highest available quality as reported by
-YouTube, which will be 1080p or 720p in some cases, so you no longer
-need the -b option.
-For some specific videos, maybe YouTube does not report them to be
-available in a specific high quality format you\[aq]\[aq]re interested
-in.
-In that case, simply request it with the -f option and youtube-dl will
-try to download it.
-.SS I get HTTP error 402 when trying to download a video. What\[aq]s
-this?
-.PP
-Apparently YouTube requires you to pass a CAPTCHA test if you download
-too much.
-We\[aq]\[aq]re considering to provide a way to let you solve the
-CAPTCHA (https://github.com/rg3/youtube-dl/issues/154), but at the
-moment, your best course of action is pointing a webbrowser to the
-youtube URL, solving the CAPTCHA, and restart youtube-dl.
-.SS I have downloaded a video but how can I play it?
-.PP
-Once the video is fully downloaded, use any video player, such as
-vlc (http://www.videolan.org) or mplayer (http://www.mplayerhq.hu/).
-.SS The links provided by youtube-dl -g are not working anymore
-.PP
-The URLs youtube-dl outputs require the downloader to have the correct
-cookies.
-Use the \f[C]--cookies\f[] option to write the required cookies into a
-file, and advise your downloader to read cookies from that file.
-Some sites also require a common user agent to be used, use
-\f[C]--dump-user-agent\f[] to see the one in use by youtube-dl.
-.SS ERROR: no fmt_url_map or conn information found in video info
-.PP
-youtube has switched to a new video info format in July 2011 which is
-not supported by old versions of youtube-dl.
-You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[].
-.SS ERROR: unable to download video
-.PP
-youtube requires an additional signature since September 2012 which is
-not supported by old versions of youtube-dl.
-You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[].
-.SS SyntaxError: Non-ASCII character
-.PP
-The error
-.IP
-.nf
-\f[C]
-File\ "youtube-dl",\ line\ 2
-SyntaxError:\ Non-ASCII\ character\ \[aq]\\x93\[aq]\ ...
-\f[]
-.fi
-.PP
-means you\[aq]re using an outdated version of Python.
-Please update to Python 2.6 or 2.7.
-.SS What is this binary file? Where has the code gone?
-.PP
-Since June 2012 (#342) youtube-dl is packed as an executable zipfile,
-simply unzip it (might need renaming to \f[C]youtube-dl.zip\f[] first on
-some systems) or clone the git repository, as laid out above.
-If you modify the code, you can run it by executing the
-\f[C]__main__.py\f[] file.
-To recompile the executable, run \f[C]make\ youtube-dl\f[].
-.SS The exe throws a \f[I]Runtime error from Visual C++\f[]
-.PP
-To run the exe you need to install first the Microsoft Visual C++ 2008
-Redistributable
-Package (http://www.microsoft.com/en-us/download/details.aspx?id=29).
-.SH COPYRIGHT
-.PP
-youtube-dl is released into the public domain by the copyright holders.
-.PP
-This README file was originally written by Daniel Bolton
-(<https://github.com/dbbolton>) and is likewise released into the public
-domain.
-.SH BUGS
-.PP
-Bugs and suggestions should be reported at:
-<https://github.com/rg3/youtube-dl/issues>
-.PP
-Please include:
-.IP \[bu] 2
-Your exact command line, like
-\f[C]youtube-dl\ -t\ "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"\f[].
-A common mistake is not to escape the \f[C]&\f[].
-Putting URLs in quotes should solve this problem.
-.IP \[bu] 2
-The output of \f[C]youtube-dl\ --version\f[]
-.IP \[bu] 2
-The output of \f[C]python\ --version\f[]
-.IP \[bu] 2
-The name and version of your Operating System ("Ubuntu 11.04 x64" or
-"Windows 7 x64" is usually enough).
-.PP
-For discussions, join us in the irc channel #youtube-dl on freenode.
+++ /dev/null
-__youtube-dl()
-{
- local cur prev opts
- COMPREPLY=()
- cur="${COMP_WORDS[COMP_CWORD]}"
- opts="--help --version --update --ignore-errors --rate-limit --retries --buffer-size --no-resize-buffer --dump-user-agent --user-agent --list-extractors --playlist-start --playlist-end --match-title --reject-title --max-downloads --title --id --literal --auto-number --output --restrict-filenames --batch-file --no-overwrites --continue --no-continue --cookies --no-part --no-mtime --write-description --write-info-json --quiet --simulate --skip-download --get-url --get-title --get-thumbnail --get-description --get-filename --get-format --no-progress --console-title --verbose --format --all-formats --prefer-free-formats --max-quality --list-formats --write-srt --srt-lang --username --password --netrc --extract-audio --audio-format --audio-quality --keep-video"
-
- if [[ ${cur} == * ]] ; then
- COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
- return 0
- fi
-}
-
-complete -F __youtube-dl youtube-dl
from __future__ import absolute_import
import math
+import io
import os
import re
+import shutil
import socket
import subprocess
import sys
import ctypes
from .utils import *
+from .InfoExtractors import get_info_extractor
class FileDownloader(object):
quiet: Do not print messages to stdout.
forceurl: Force printing final URL.
forcetitle: Force printing title.
+ forceid: Force printing ID.
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
forcefilename: Force printing final filename.
updatetime: Use the Last-modified header to set output file timestamps.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
- writesubtitles: Write the video subtitles to a .srt file
+ writethumbnail: Write the thumbnail image to a file
+ writesubtitles: Write the video subtitles to a file
+ allsubtitles: Downloads all the subtitles of the video
+ listsubtitles: Lists all available subtitles for the video
+ subtitlesformat: Subtitle format [sbv/srt] (default=srt)
subtitleslang: Language of the subtitles to download
test: Download only first bytes to test the downloader.
+ keepvideo: Keep the video file after post-processing
+ min_filesize: Skip files smaller than this size
+ max_filesize: Skip files larger than this size
+ daterange: A DateRange object, download only if the upload_date is in the range.
+ skip_download: Skip the actual download of the video file
"""
params = None
"""Create a FileDownloader object with the given options."""
self._ies = []
self._pps = []
+ self._progress_hooks = []
self._download_retcode = 0
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params
if '%(stitle)s' in self.params['outtmpl']:
- self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+ self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
@staticmethod
def format_bytes(bytes):
exponent = 0
else:
exponent = int(math.log(bytes, 1024.0))
- suffix = 'bkMGTPEZY'[exponent]
+ suffix = ['B','KiB','MiB','GiB','TiB','PiB','EiB','ZiB','YiB'][exponent]
converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ:
- sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
+ self.to_screen('\033]0;%s\007' % message, skip_eol=True)
def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
- def trouble(self, message=None):
+ def trouble(self, message=None, tb=None):
"""Determine action to take when a download problem appears.
Depending on if the downloader has been configured to ignore
download errors or not, this method may throw an exception or
not when errors are found, after printing the message.
+
+ tb, if given, is additional traceback information.
"""
if message is not None:
self.to_stderr(message)
if self.params.get('verbose'):
- self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack())))
+ if tb is None:
+ if sys.exc_info()[0]: # if .trouble has been called from an except block
+ tb = u''
+ if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
+ tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
+ tb += compat_str(traceback.format_exc())
+ else:
+ tb_data = traceback.format_list(traceback.extract_stack())
+ tb = u''.join(tb_data)
+ self.to_stderr(tb)
if not self.params.get('ignoreerrors', False):
- raise DownloadError(message)
+ if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
+ exc_info = sys.exc_info()[1].exc_info
+ else:
+ exc_info = sys.exc_info()
+ raise DownloadError(message, exc_info)
self._download_retcode = 1
+ def report_warning(self, message):
+ '''
+ Print the message to stderr, it will be prefixed with 'WARNING:'
+ If stderr is a tty file the 'WARNING:' will be colored
+ '''
+ if sys.stderr.isatty() and os.name != 'nt':
+ _msg_header=u'\033[0;33mWARNING:\033[0m'
+ else:
+ _msg_header=u'WARNING:'
+ warning_message=u'%s %s' % (_msg_header,message)
+ self.to_stderr(warning_message)
+
+ def report_error(self, message, tb=None):
+ '''
+ Do the same as trouble, but prefixes the message with 'ERROR:', colored
+ in red if stderr is a tty file.
+ '''
+ if sys.stderr.isatty() and os.name != 'nt':
+ _msg_header = u'\033[0;31mERROR:\033[0m'
+ else:
+ _msg_header = u'ERROR:'
+ error_message = u'%s %s' % (_msg_header, message)
+ self.trouble(error_message, tb)
+
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err:
- self.trouble(u'ERROR: unable to rename file')
+ self.report_error(u'unable to rename file')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
""" Report that the description file is being written """
self.to_screen(u'[info] Writing video description to: ' + descfn)
- def report_writesubtitles(self, srtfn):
+ def report_writesubtitles(self, sub_filename):
""" Report that the subtitles file is being written """
- self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
+ self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
def report_writeinfojson(self, infofn):
""" Report that the metadata file has been written """
"""Report download progress."""
if self.params.get('noprogress', False):
return
- self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
- (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+ clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+ if self.params.get('progress_with_newline', False):
+ self.to_screen(u'[download] %s of %s at %s ETA %s' %
+ (percent_str, data_len_str, speed_str, eta_str))
+ else:
+ self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
+ (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
template_dict = dict(info_dict)
template_dict['epoch'] = int(time.time())
- template_dict['autonumber'] = u'%05d' % self._num_downloads
+ autonumber_size = self.params.get('autonumber_size')
+ if autonumber_size is None:
+ autonumber_size = 5
+ autonumber_templ = u'%0' + str(autonumber_size) + u'd'
+ template_dict['autonumber'] = autonumber_templ % self._num_downloads
+ if template_dict['playlist_index'] is not None:
+ template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
sanitize = lambda k,v: sanitize_filename(
u'NA' if v is None else compat_str(v),
filename = self.params['outtmpl'] % template_dict
return filename
- except (ValueError, KeyError) as err:
- self.trouble(u'ERROR: invalid system charset or erroneous output template')
+ except KeyError as err:
+ self.report_error(u'Erroneous output template')
+ return None
+ except ValueError as err:
+ self.report_error(u'Insufficient system charset ' + repr(preferredencoding()))
return None
def _match_entry(self, info_dict):
title = info_dict['title']
matchtitle = self.params.get('matchtitle', False)
if matchtitle:
- matchtitle = matchtitle.decode('utf8')
if not re.search(matchtitle, title, re.IGNORECASE):
return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
rejecttitle = self.params.get('rejecttitle', False)
if rejecttitle:
- rejecttitle = rejecttitle.decode('utf8')
if re.search(rejecttitle, title, re.IGNORECASE):
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ date = info_dict.get('upload_date', None)
+ if date is not None:
+ dateRange = self.params.get('daterange', DateRange())
+ if date not in dateRange:
+ return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
return None
+
+ def extract_info(self, url, download=True, ie_key=None):
+ '''
+ Returns a list with a dictionary for each video we find.
+ If 'download', also downloads the videos.
+ '''
+
+ if ie_key:
+ ie = get_info_extractor(ie_key)()
+ ie.set_downloader(self)
+ ies = [ie]
+ else:
+ ies = self._ies
+
+ for ie in ies:
+ if not ie.suitable(url):
+ continue
+
+ if not ie.working():
+ self.report_warning(u'The program functionality for this site has been marked as broken, '
+ u'and will probably not work.')
+
+ try:
+ ie_result = ie.extract(url)
+ if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
+ break
+ if isinstance(ie_result, list):
+ # Backwards compatibility: old IE result format
+ ie_result = {
+ '_type': 'compat_list',
+ 'entries': ie_result,
+ }
+ if 'extractor' not in ie_result:
+ ie_result['extractor'] = ie.IE_NAME
+ return self.process_ie_result(ie_result, download=download)
+ except ExtractorError as de: # An error we somewhat expected
+ self.report_error(compat_str(de), de.format_traceback())
+ break
+ except Exception as e:
+ if self.params.get('ignoreerrors', False):
+ self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
+ break
+ else:
+ raise
+ else:
+ self.report_error(u'no suitable InfoExtractor: %s' % url)
+
+ def process_ie_result(self, ie_result, download=True):
+ """
+ Take the result of the ie(may be modified) and resolve all unresolved
+ references (URLs, playlist items).
+
+ It will also download the videos if 'download'.
+ Returns the resolved ie_result.
+ """
+
+ result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
+ if result_type == 'video':
+ if 'playlist' not in ie_result:
+ # It isn't part of a playlist
+ ie_result['playlist'] = None
+ ie_result['playlist_index'] = None
+ if download:
+ self.process_info(ie_result)
+ return ie_result
+ elif result_type == 'url':
+ return self.extract_info(ie_result['url'], download, ie_key=ie_result.get('ie_key'))
+ elif result_type == 'playlist':
+ # We process each entry in the playlist
+ playlist = ie_result.get('title', None) or ie_result.get('id', None)
+ self.to_screen(u'[download] Downloading playlist: %s' % playlist)
+
+ playlist_results = []
+
+ n_all_entries = len(ie_result['entries'])
+ playliststart = self.params.get('playliststart', 1) - 1
+ playlistend = self.params.get('playlistend', -1)
+
+ if playlistend == -1:
+ entries = ie_result['entries'][playliststart:]
+ else:
+ entries = ie_result['entries'][playliststart:playlistend]
+
+ n_entries = len(entries)
+
+ self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
+ (ie_result['extractor'], playlist, n_all_entries, n_entries))
+
+ for i,entry in enumerate(entries,1):
+ self.to_screen(u'[download] Downloading video #%s of %s' %(i, n_entries))
+ entry['playlist'] = playlist
+ entry['playlist_index'] = i + playliststart
+ entry_result = self.process_ie_result(entry, download=download)
+ playlist_results.append(entry_result)
+ ie_result['entries'] = playlist_results
+ return ie_result
+ elif result_type == 'compat_list':
+ def _fixup(r):
+ r.setdefault('extractor', ie_result['extractor'])
+ return r
+ ie_result['entries'] = [
+ self.process_ie_result(_fixup(r), download=download)
+ for r in ie_result['entries']
+ ]
+ return ie_result
+ else:
+ raise Exception('Invalid result type: %s' % result_type)
def process_info(self, info_dict):
- """Process a single dictionary returned by an InfoExtractor."""
+ """Process a single resolved IE result."""
+
+ assert info_dict.get('_type', 'video') == 'video'
+ #We increment the download the download count here to match the previous behaviour.
+ self.increment_downloads()
+
+ info_dict['fulltitle'] = info_dict['title']
+ if len(info_dict['title']) > 200:
+ info_dict['title'] = info_dict['title'][:197] + u'...'
# Keep for backwards compatibility
info_dict['stitle'] = info_dict['title']
# Forced printings
if self.params.get('forcetitle', False):
compat_print(info_dict['title'])
+ if self.params.get('forceid', False):
+ compat_print(info_dict['id'])
if self.params.get('forceurl', False):
compat_print(info_dict['url'])
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
try:
dn = os.path.dirname(encodeFilename(filename))
- if dn != '' and not os.path.exists(dn): # dn is already encoded
+ if dn != '' and not os.path.exists(dn):
os.makedirs(dn)
except (OSError, IOError) as err:
- self.trouble(u'ERROR: unable to create directory ' + compat_str(err))
+ self.report_error(u'unable to create directory ' + compat_str(err))
return
if self.params.get('writedescription', False):
try:
descfn = filename + u'.description'
self.report_writedescription(descfn)
- descfile = open(encodeFilename(descfn), 'wb')
- try:
- descfile.write(info_dict['description'].encode('utf-8'))
- finally:
- descfile.close()
+ with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+ descfile.write(info_dict['description'])
except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write description file ' + descfn)
+ self.report_error(u'Cannot write description file ' + descfn)
return
if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
- try:
- srtfn = filename.rsplit('.', 1)[0] + u'.srt'
- self.report_writesubtitles(srtfn)
- srtfile = open(encodeFilename(srtfn), 'wb')
+ subtitle = info_dict['subtitles'][0]
+ (sub_error, sub_lang, sub) = subtitle
+ sub_format = self.params.get('subtitlesformat')
+ if sub_error:
+ self.report_warning("Some error while getting the subtitles")
+ else:
try:
- srtfile.write(info_dict['subtitles'].encode('utf-8'))
- finally:
- srtfile.close()
- except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
- return
+ sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+ self.report_writesubtitles(sub_filename)
+ with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+ subfile.write(sub)
+ except (OSError, IOError):
+ self.report_error(u'Cannot write subtitles file ' + descfn)
+ return
+
+ if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
+ subtitles = info_dict['subtitles']
+ sub_format = self.params.get('subtitlesformat')
+ for subtitle in subtitles:
+ (sub_error, sub_lang, sub) = subtitle
+ if sub_error:
+ self.report_warning("Some error while getting the subtitles")
+ else:
+ try:
+ sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+ self.report_writesubtitles(sub_filename)
+ with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+ subfile.write(sub)
+ except (OSError, IOError):
+ self.report_error(u'Cannot write subtitles file ' + descfn)
+ return
if self.params.get('writeinfojson', False):
infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)
try:
- json.dump
- except (NameError,AttributeError):
- self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
- return
- try:
- infof = open(encodeFilename(infofn), 'wb')
- try:
- json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
- json.dump(json_info_dict, infof)
- finally:
- infof.close()
+ json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle'])
+ write_json_file(json_info_dict, encodeFilename(infofn))
except (OSError, IOError):
- self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+ self.report_error(u'Cannot write metadata to JSON file ' + infofn)
return
+ if self.params.get('writethumbnail', False):
+ if 'thumbnail' in info_dict:
+ thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
+ if not thumb_format:
+ thumb_format = 'jpg'
+ thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
+ self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
+ (info_dict['extractor'], info_dict['id']))
+ uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+ with open(thumb_filename, 'wb') as thumbf:
+ shutil.copyfileobj(uf, thumbf)
+ self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
+ (info_dict['extractor'], info_dict['id'], thumb_filename))
+
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
success = True
except (OSError, IOError) as err:
raise UnavailableVideoError()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+ self.report_error(u'unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ) as err:
- self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError) as err:
- self.trouble(u'ERROR: postprocessing: %s' % str(err))
+ self.report_error(u'postprocessing: %s' % str(err))
return
def download(self, url_list):
raise SameFileError(self.params['outtmpl'])
for url in url_list:
- suitable_found = False
- for ie in self._ies:
- # Go to next InfoExtractor if not suitable
- if not ie.suitable(url):
- continue
-
- # Warn if the _WORKING attribute is False
- if not ie.working():
- self.trouble(u'WARNING: the program functionality for this site has been marked as broken, '
- u'and will probably not work. If you want to go on, use the -i option.')
-
- # Suitable InfoExtractor found
- suitable_found = True
-
- # Extract information from URL and process it
- videos = ie.extract(url)
- for video in videos or []:
- video['extractor'] = ie.IE_NAME
- try:
- self.increment_downloads()
- self.process_info(video)
- except UnavailableVideoError:
- self.trouble(u'\nERROR: unable to download video')
-
- # Suitable InfoExtractor had been found; go to next URL
- break
-
- if not suitable_found:
- self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
+ try:
+ #It also downloads the videos
+ videos = self.extract_info(url)
+ except UnavailableVideoError:
+ self.report_error(u'unable to download video')
+ except MaxDownloadsReached:
+ self.to_screen(u'[info] Maximum number of downloaded files reached.')
+ raise
return self._download_retcode
def post_process(self, filename, ie_info):
- """Run the postprocessing chain on the given file."""
+ """Run all the postprocessors on the given file."""
info = dict(ie_info)
info['filepath'] = filename
+ keep_video = None
for pp in self._pps:
- info = pp.run(info)
- if info is None:
- break
+ try:
+ keep_video_wish,new_info = pp.run(info)
+ if keep_video_wish is not None:
+ if keep_video_wish:
+ keep_video = keep_video_wish
+ elif keep_video is None:
+ # No clear decision yet, let IE decide
+ keep_video = keep_video_wish
+ except PostProcessingError as e:
+ self.to_stderr(u'ERROR: ' + e.msg)
+ if keep_video is False and not self.params.get('keepvideo', False):
+ try:
+ self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename)
+ os.remove(encodeFilename(filename))
+ except (IOError, OSError):
+ self.report_warning(u'Unable to remove downloaded video file')
- def _download_with_rtmpdump(self, filename, url, player_url):
+ def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
# Check for rtmpdump first
try:
- subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
- self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+ self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
- basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
+ basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename]
+ if player_url is not None:
+ basic_args += ['-W', player_url]
+ if page_url is not None:
+ basic_args += ['--pageUrl', page_url]
+ if play_path is not None:
+ basic_args += ['-y', play_path]
args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
if self.params.get('verbose', False):
try:
retval = 0
break
if retval == 0:
- self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename)))
+ fsize = os.path.getsize(encodeFilename(tmpfilename))
+ self.to_screen(u'\r[rtmpdump] %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
+ self._hook_progress({
+ 'downloaded_bytes': fsize,
+ 'total_bytes': fsize,
+ 'filename': filename,
+ 'status': 'finished',
+ })
return True
else:
- self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
+ self.to_stderr(u"\n")
+ self.report_error(u'rtmpdump exited with code %d' % retval)
return False
def _do_download(self, filename, info_dict):
url = info_dict['url']
- player_url = info_dict.get('player_url', None)
# Check file already present
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
+ self._hook_progress({
+ 'filename': filename,
+ 'status': 'finished',
+ })
return True
# Attempt to download using rtmpdump
if url.startswith('rtmp'):
- return self._download_with_rtmpdump(filename, url, player_url)
+ return self._download_with_rtmpdump(filename, url,
+ info_dict.get('player_url', None),
+ info_dict.get('page_url', None),
+ info_dict.get('play_path', None))
tmpfilename = self.temp_name(filename)
stream = None
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
+ if 'user_agent' in info_dict:
+ headers['Youtubedl-user-agent'] = info_dict['user_agent']
basic_request = compat_urllib_request.Request(url, None, headers)
request = compat_urllib_request.Request(url, None, headers)
# the one in the hard drive.
self.report_file_already_downloaded(filename)
self.try_rename(tmpfilename, filename)
+ self._hook_progress({
+ 'filename': filename,
+ 'status': 'finished',
+ })
return True
else:
# The length does not match, we start the download over
self.report_retry(count, retries)
if count > retries:
- self.trouble(u'ERROR: giving up after %s retries' % retries)
+ self.report_error(u'giving up after %s retries' % retries)
return False
data_len = data.info().get('Content-length', None)
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)
+ if min_data_len is not None and data_len < min_data_len:
+ self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
+ return False
+ if max_data_len is not None and data_len > max_data_len:
+ self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
+ return False
+
data_len_str = self.format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError) as err:
- self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
+ self.report_error(u'unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError) as err:
- self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+ self.to_stderr(u"\n")
+ self.report_error(u'unable to write data: %s' % str(err))
return False
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+ self._hook_progress({
+ 'downloaded_bytes': byte_counter,
+ 'total_bytes': data_len,
+ 'tmpfilename': tmpfilename,
+ 'filename': filename,
+ 'status': 'downloading',
+ })
+
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
if stream is None:
- self.trouble(u'\nERROR: Did not get any data blocks')
+ self.to_stderr(u"\n")
+ self.report_error(u'Did not get any data blocks')
return False
stream.close()
self.report_finish()
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
+ self._hook_progress({
+ 'downloaded_bytes': byte_counter,
+ 'total_bytes': byte_counter,
+ 'filename': filename,
+ 'status': 'finished',
+ })
+
return True
+
+ def _hook_progress(self, status):
+ for ph in self._progress_hooks:
+ ph(status)
+
+ def add_progress_hook(self, ph):
+ """ ph gets called on download progress, with a dictionary with the entries
+ * filename: The final filename
+ * status: One of "downloading" and "finished"
+
+ It can also have some of the following entries:
+
+ * downloaded_bytes: Bytes on disks
+ * total_bytes: Total bytes, None if unknown
+ * tmpfilename: The filename we're currently writing to
+
+ Hooks are guaranteed to be called at least once (with status "finished")
+ if the download is successful.
+ """
+ self._progress_hooks.append(ph)
from __future__ import absolute_import
+import base64
import datetime
+import itertools
import netrc
import os
import re
import xml.etree.ElementTree
import random
import math
+import operator
from .utils import *
Information extractors are the classes that, given a URL, extract
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video title, author and
- others. The information is stored in a dictionary which is then
+ others. The information is stored in a dictionary which is then
passed to the FileDownloader. The FileDownloader processes this
information possibly downloading the video to the file system, among
other possible outcomes.
id: Video identifier.
url: Final video URL.
- uploader: Nickname of the video uploader, unescaped.
- upload_date: Video upload date (YYYYMMDD).
title: Video title, unescaped.
ext: Video filename extension.
format: The video format, defaults to ext (used for --get-format)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
+ uploader: Full name of the video uploader.
+ upload_date: Video upload date (YYYYMMDD).
+ uploader_id: Nickname or id of the video uploader.
+ location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
+ subtitles: The subtitle file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
self._ready = False
self.set_downloader(downloader)
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
+ return re.match(cls._VALID_URL, url) is not None
- def working(self):
+ @classmethod
+ def working(cls):
"""Getter method for _WORKING."""
- return self._WORKING
+ return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
"""Real extraction process. Redefine in subclasses."""
pass
+ @property
+ def IE_NAME(self):
+ return type(self).__name__[:-2]
+
+ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the response handle """
+ if note is None:
+ self.report_download_webpage(video_id)
+ elif note is not False:
+ self.to_screen(u'%s: %s' % (video_id, note))
+ try:
+ return compat_urllib_request.urlopen(url_or_request)
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is None:
+ errnote = u'Unable to download webpage'
+ raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+
+ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns a tuple (page content as string, URL handle) """
+ urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+ content_type = urlh.headers.get('Content-Type', '')
+ m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
+ if m:
+ encoding = m.group(1)
+ else:
+ encoding = 'utf-8'
+ webpage_bytes = urlh.read()
+ if self._downloader.params.get('dump_intermediate_pages', False):
+ try:
+ url = url_or_request.get_full_url()
+ except AttributeError:
+ url = url_or_request
+ self.to_screen(u'Dumping request to ' + url)
+ dump = base64.b64encode(webpage_bytes).decode('ascii')
+ self._downloader.to_screen(dump)
+ content = webpage_bytes.decode(encoding, 'replace')
+ return (content, urlh)
+
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the data of the page as a string """
+ return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
+
+ def to_screen(self, msg):
+ """Print msg to screen, prefixing it with '[ie_name]'"""
+ self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+
+ def report_extraction(self, id_or_name):
+ """Report information extraction."""
+ self.to_screen(u'%s: Extracting information' % id_or_name)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self.to_screen(u'%s: Downloading webpage' % video_id)
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self.to_screen(u'Confirming age')
+
+ #Methods for following #608
+ #They set the correct value of the '_type' key
+ def video_result(self, video_info):
+ """Returns a video"""
+ video_info['_type'] = 'video'
+ return video_info
+ def url_result(self, url, ie=None):
+ """Returns a url that points to a page that should be processed"""
+ #TODO: ie should be the class used for getting the info
+ video_info = {'_type': 'url',
+ 'url': url,
+ 'ie_key': ie}
+ return video_info
+ def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+ """Returns a playlist"""
+ video_info = {'_type': 'playlist',
+ 'entries': entries}
+ if playlist_id:
+ video_info['id'] = playlist_id
+ if playlist_title:
+ video_info['title'] = playlist_title
+ return video_info
+
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
- (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
+ (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
)
)? # optional -> youtube.com/xxxx is OK
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
'44': '480x854',
'45': '720x1280',
'46': '1080x1920',
- }
+ }
IE_NAME = u'youtube'
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ if YoutubePlaylistIE.suitable(url): return False
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
+ self.to_screen(u'Setting language')
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
+ self.to_screen(u'Logging in')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
+ self.to_screen(u'%s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+ self.to_screen(u'%s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
+ self.to_screen(u'%s: Checking available subtitles' % video_id)
+
+ def report_video_subtitles_request(self, video_id, sub_lang, format):
+ """Report attempt to download video info webpage."""
+ self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
+
+ def report_video_subtitles_available(self, video_id, sub_lang_list):
+ """Report available subtitles."""
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
+ self.to_screen(u'%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+ self.to_screen(u'%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
+ self.to_screen(u'RTMP download detected')
+
+ def _get_available_subtitles(self, video_id):
+ self.report_video_subtitles_download(video_id)
+ request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
+ try:
+ sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ return (u'unable to download video subtitles: %s' % compat_str(err), None)
+ sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+ sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
+ if not sub_lang_list:
+ return (u'video doesn\'t have subtitles', None)
+ return sub_lang_list
+
+ def _list_available_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ self.report_video_subtitles_available(video_id, sub_lang_list)
+
+ def _request_subtitle(self, sub_lang, sub_name, video_id, format):
+ """
+ Return tuple:
+ (error_message, sub_lang, sub)
+ """
+ self.report_video_subtitles_request(video_id, sub_lang, format)
+ params = compat_urllib_parse.urlencode({
+ 'lang': sub_lang,
+ 'name': sub_name,
+ 'v': video_id,
+ 'fmt': format,
+ })
+ url = 'http://www.youtube.com/api/timedtext?' + params
+ try:
+ sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
+ if not sub:
+ return (u'Did not fetch video subtitles', None, None)
+ return (None, sub_lang, sub)
+
+ def _extract_subtitle(self, video_id):
+ """
+ Return a list with a tuple:
+ [(error_message, sub_lang, sub)]
+ """
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ if self._downloader.params.get('subtitleslang', False):
+ sub_lang = self._downloader.params.get('subtitleslang')
+ elif 'en' in sub_lang_list:
+ sub_lang = 'en'
+ else:
+ sub_lang = list(sub_lang_list.keys())[0]
+ if not sub_lang in sub_lang_list:
+ return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
+
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ return [subtitle]
+
+ def _extract_all_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ subtitles = []
+ for sub_lang in sub_lang_list:
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ subtitles.append(subtitle)
+ return subtitles
def _print_formats(self, formats):
print('Available formats:')
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
# Set language
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
# No authentication to be performed
if username is None:
return
+ request = compat_urllib_request.Request(self._LOGIN_URL)
+ try:
+ login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
+ return
+
+ galx = None
+ dsh = None
+ match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
+ if match:
+ galx = match.group(1)
+
+ match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
+ if match:
+ dsh = match.group(1)
+
# Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+ login_form_strs = {
+ u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+ u'Email': username,
+ u'GALX': galx,
+ u'Passwd': password,
+ u'PersistentCookie': u'yes',
+ u'_utf8': u'霱',
+ u'bgresponse': u'js_disabled',
+ u'checkConnection': u'',
+ u'checkedDomains': u'youtube',
+ u'dnConn': u'',
+ u'dsh': dsh,
+ u'pstMsg': u'0',
+ u'rmShown': u'1',
+ u'secTok': u'',
+ u'signIn': u'Sign in',
+ u'timeStmp': u'',
+ u'service': u'youtube',
+ u'uilel': u'3',
+ u'hl': u'en_US',
+ }
+ # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+ # chokes on unicode
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
+ request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
try:
self.report_login()
- login_results = compat_urllib_request.urlopen(request).read()
- if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
+ self._downloader.report_warning(u'unable to log in: bad username or password')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
# Confirm age
request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
try:
self.report_age_confirmation()
- age_results = compat_urllib_request.urlopen(request).read()
+ age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
+
+ def _extract_id(self, url):
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group(2)
+ return video_id
def _real_extract(self, url):
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
- url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
-
- # Extract video id from URL
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(2)
+ url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
+ video_id = self._extract_id(url)
# Get video webpage
self.report_video_webpage_download(video_id)
- request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
+ url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
+ request = compat_urllib_request.Request(url)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
# Get video info
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type))
- request = compat_urllib_request.Request(video_info_url)
- try:
- video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
- video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
- video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
- return
+ video_info_webpage = self._download_webpage(video_info_url, video_id,
+ note=False,
+ errnote='unable to download video info webpage')
+ video_info = compat_parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
if 'token' not in video_info:
if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
+ raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
- return
+ raise ExtractorError(u'"token" parameter not in video info for unknown reason')
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.trouble(u'ERROR: "rental" videos not supported')
- return
+ raise ExtractorError(u'"rental" videos not supported')
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
+ raise ExtractorError(u'Unable to extract uploader name')
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
+ # uploader_id
+ video_uploader_id = None
+ mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
+ if mobj is not None:
+ video_uploader_id = mobj.group(1)
+ else:
+ self._downloader.report_warning(u'unable to extract uploader nickname')
+
# title
if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
+ raise ExtractorError(u'Unable to extract video title')
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
+ upload_date = unified_strdate(upload_date)
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
video_description = clean_html(video_description)
else:
- video_description = ''
+ fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
+ if fd_mobj:
+ video_description = unescapeHTML(fd_mobj.group(1))
+ else:
+ video_description = u''
- # closed captions
+ # subtitles
video_subtitles = None
+
if self._downloader.params.get('writesubtitles', False):
- try:
- self.report_video_subtitles_download(video_id)
- request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
- try:
- srt_list = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- raise Trouble(u'WARNING: video has no closed captions')
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = srt_lang_list.keys()[0]
- if not srt_lang in srt_lang_list:
- raise Trouble(u'WARNING: no closed captions found in the specified language')
- request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
- try:
- srt_xml = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
- if not srt_xml:
- raise Trouble(u'WARNING: unable to download video subtitles')
- video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
- except Trouble as trouble:
- self._downloader.trouble(trouble[0])
+ video_subtitles = self._extract_subtitle(video_id)
+ if video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitles[0]
+ if sub_error:
+ self._downloader.report_error(sub_error)
+
+ if self._downloader.params.get('allsubtitles', False):
+ video_subtitles = self._extract_all_subtitles(video_id)
+ for video_subtitle in video_subtitles:
+ (sub_error, sub_lang, sub) = video_subtitle
+ if sub_error:
+ self._downloader.report_error(sub_error)
+
+ if self._downloader.params.get('listsubtitles', False):
+ sub_lang_list = self._list_available_subtitles(video_id)
+ return
if 'length_seconds' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video duration')
+ self._downloader.report_warning(u'unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
- url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
- url_data = [compat_parse_qs(uds) for uds in url_data_strs]
- url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
- url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
+ url_map = {}
+ for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
+ url_data = compat_parse_qs(url_data_str)
+ if 'itag' in url_data and 'url' in url_data:
+ url = url_data['url'][0] + '&signature=' + url_data['sig'][0]
+ if not 'ratebypass' in url: url += '&ratebypass=yes'
+ url_map[url_data['itag'][0]] = url
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
+ raise ExtractorError(u'no known formats available for video')
if self._downloader.params.get('listformats', None):
self._print_formats(existing_formats)
return
video_url_list = [(rf, url_map[rf])]
break
if video_url_list is None:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
+ raise ExtractorError(u'requested format not available')
else:
- self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
- return
+ raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
results = []
for format_param, video_real_url in video_url_list:
'id': video_id,
'url': video_real_url,
'uploader': video_uploader,
+ 'uploader_id': video_uploader_id,
'upload_date': upload_date,
'title': video_title,
'ext': video_extension,
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = u'metacafe'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_disclaimer(self):
"""Report disclaimer retrieval."""
- self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[metacafe] Confirming age')
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
+ self.to_screen(u'Retrieving disclaimer')
def _real_initialize(self):
# Retrieve disclaimer
self.report_disclaimer()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
# Confirm age
disclaimer_form = {
self.report_age_confirmation()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
- return
+ return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
else:
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
vardict = compat_parse_qs(mobj.group(1))
if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+ raise ExtractorError(u'Unable to extract media URL')
+ mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = mobj.group(1).replace('\\/', '/')
+ raise ExtractorError(u'Unable to extract media URL')
+ mediaURL = mobj.group('mediaURL').replace('\\/', '/')
video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
+ video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'submitter=(.*?);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
+ raise ExtractorError(u'Unable to extract uploader nickname')
video_uploader = mobj.group(1)
return [{
'ext': video_extension.decode('utf-8'),
}]
-
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1).split('_')[0].split('?')[0]
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
flashvars = compat_urllib_parse.unquote(mobj.group(1))
for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
if key in flashvars:
max_quality = key
- self._downloader.to_screen(u'[dailymotion] Using %s' % key)
+ self.to_screen(u'Using %s' % key)
break
else:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
+ raise ExtractorError(u'Unable to extract video URL')
mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
+ raise ExtractorError(u'Unable to extract video URL')
video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
+ raise ExtractorError(u'Unable to extract title')
+ video_title = unescapeHTML(mobj.group('title'))
video_uploader = None
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
# lookin for official user
mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
if mobj_official is None:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ self._downloader.report_warning(u'unable to extract uploader nickname')
else:
video_uploader = mobj_official.group(1)
else:
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
'upload_date': video_upload_date,
'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- }]
-
-
-class GoogleIE(InfoExtractor):
- """Information extractor for video.google.com."""
-
- _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
- IE_NAME = u'video.google'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- video_extension = 'mp4'
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r"download_url:'([^']+)'", webpage)
- if mobj is None:
- video_extension = 'flv'
- mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
- mediaURL = mediaURL.replace('\\x3d', '\x3d')
- mediaURL = mediaURL.replace('\\x26', '\x26')
-
- video_url = mediaURL
-
- mobj = re.search(r'<title>(.*)</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video thumbnail
- if self._downloader.params.get('forcethumbnail', False):
- request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
- mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1)
- else: # we need something to pass to process_info
- video_thumbnail = ''
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
+ 'ext': video_extension,
}]
class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com."""
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ # TODO: the original _VALID_URL was:
+ # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ # Check if it's necessary to keep the old extracion process
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
IE_NAME = u'photobucket'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group(1)
+ video_id = mobj.group('id')
- video_extension = 'flv'
+ video_extension = mobj.group('ext')
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
+ # We try first by looking the javascript code:
+ mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage)
+ if mobj is not None:
+ info = json.loads(mobj.group('json'))
+ return [{
+ 'id': video_id,
+ 'url': info[u'downloadUrl'],
+ 'uploader': info[u'username'],
+ 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
+ 'title': info[u'title'],
+ 'ext': video_extension,
+ 'thumbnail': info[u'thumbUrl'],
+ }]
+
+ # We try looking in other parts of the webpage
mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
mediaURL = compat_urllib_parse.unquote(mobj.group(1))
video_url = mediaURL
mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
video_uploader = mobj.group(2).decode('utf-8')
class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
+ """Information extractor for screen.yahoo.com."""
+ _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
+
+ if m_id is None:
+ # TODO: Check which url parameters are required
+ info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
+ webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
+ info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
+ <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
+ <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
+ <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
+ '''
+ self.report_extraction(video_id)
+ m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
+ if m_info is None:
+ raise ExtractorError(u'Unable to extract video info')
+ video_title = m_info.group('title')
+ video_description = m_info.group('description')
+ video_thumb = m_info.group('thumb')
+ video_date = m_info.group('date')
+ video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
+
+ # TODO: Find a way to get mp4 videos
+ rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
+ webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
+ m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
+ video_url = m_rest.group('url')
+ video_path = m_rest.group('path')
+ if m_rest is None:
+ raise ExtractorError(u'Unable to extract video url')
+
+ else: # We have to use a different method if another id is defined
+ long_id = m_id.group('new_id')
+ info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
+ webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
+ json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
+ info = json.loads(json_str)
+ res = info[u'query'][u'results'][u'mediaObj'][0]
+ stream = res[u'streams'][0]
+ video_path = stream[u'path']
+ video_url = stream[u'host']
+ meta = res[u'meta']
+ video_title = meta[u'title']
+ video_description = meta[u'description']
+ video_thumb = meta[u'thumbnail']
+ video_date = None # I can't find it
+
+ info_dict = {
+ 'id': video_id,
+ 'url': video_url,
+ 'play_path': video_path,
+ 'title':video_title,
+ 'description': video_description,
+ 'thumbnail': video_thumb,
+ 'upload_date': video_date,
+ 'ext': 'flv',
+ }
+ return info_dict
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
+class VimeoIE(InfoExtractor):
+ """Information extractor for vimeo.com."""
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
+ IE_NAME = u'vimeo'
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
+ raise ExtractorError(u'Invalid URL: %s' % url)
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
+ video_id = mobj.group('id')
+ if not mobj.group('proto'):
+ url = 'https://' + url
+ if mobj.group('direct_link'):
+ url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ request = compat_urllib_request.Request(url, None, std_headers)
+ webpage = self._download_webpage(request, video_id)
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract media URL')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = unescapeHTML(video_url)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- }]
-
-
-class VimeoIE(InfoExtractor):
- """Information extractor for vimeo.com."""
-
- # _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
- IE_NAME = u'vimeo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Now we begin extracting as much information as we can from what we
- # retrieved. First we extract the information common to all extractors,
- # and latter we extract those that are Vimeo specific.
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
# Extract the config JSON
config = webpage.split(' = {config:')[1].split(',assets:')[0]
config = json.loads(config)
except:
- self._downloader.trouble(u'ERROR: unable to extract info section')
- return
-
+ if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
+ raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
+ else:
+ raise ExtractorError(u'Unable to extract info section')
+
# Extract title
video_title = config["video"]["title"]
- # Extract uploader
+ # Extract uploader and uploader_id
video_uploader = config["video"]["owner"]["name"]
+ video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
# Extract video thumbnail
video_thumbnail = config["video"]["thumbnail"]
# Extract video description
- video_description = get_element_by_id("description", webpage.decode('utf8'))
+ video_description = get_element_by_attribute("itemprop", "description", webpage)
if video_description: video_description = clean_html(video_description)
- else: video_description = ''
+ else: video_description = u''
# Extract upload date
video_upload_date = None
- mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
+ mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
if mobj is not None:
- video_upload_date = mobj.group(1)
+ video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
# Vimeo specific: extract request signature and timestamp
sig = config['request']['signature']
video_quality = files[quality][0][2]
video_codec = files[quality][0][0]
video_extension = files[quality][0][1]
- self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
+ self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
break
else:
- self._downloader.trouble(u'ERROR: no known codec found')
- return
+ raise ExtractorError(u'No known codec found')
video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
%(video_id, sig, timestamp, video_quality, video_codec.upper())
'id': video_id,
'url': video_url,
'uploader': video_uploader,
+ 'uploader_id': video_uploader_id,
'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension,
IE_NAME = u'arte.tv'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
-
def fetch_webpage(self, url):
- self._downloader.increment_downloads()
request = compat_urllib_request.Request(url)
try:
self.report_download_webpage(url)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
except ValueError as err:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
return webpage
def grep_webpage(self, url, regex, regexFlags, matchTuples):
info = {}
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
for (i, key, err) in matchTuples:
if mobj.group(i) is None:
- self._downloader.trouble(err)
- return
+ raise ExtractorError(err)
else:
info[key] = mobj.group(i)
r'src="(.*?/videothek_js.*?\.js)',
0,
[
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ (1, 'url', u'Invalid URL: %s' % url)
]
)
http_host = url.split('/')[2]
'(rtmp://.*?)\'',
re.DOTALL,
[
- (1, 'path', u'ERROR: could not extract video path: %s' % url),
- (2, 'player', u'ERROR: could not extract video player: %s' % url),
- (3, 'url', u'ERROR: could not extract video url: %s' % url)
+ (1, 'path', u'could not extract video path: %s' % url),
+ (2, 'player', u'could not extract video player: %s' % url),
+ (3, 'url', u'could not extract video url: %s' % url)
]
)
video_url = u'%s/%s' % (info.get('url'), info.get('path'))
r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
0,
[
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ (1, 'url', u'Invalid URL: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
0,
[
- (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+ (1, 'url', u'Could not find <video> tag: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
'<url quality="hd">(.*?)</url>',
re.DOTALL,
[
- (1, 'id', u'ERROR: could not extract video id: %s' % url),
- (2, 'title', u'ERROR: could not extract video title: %s' % url),
- (3, 'date', u'ERROR: could not extract video date: %s' % url),
- (4, 'url', u'ERROR: could not extract video url: %s' % url)
+ (1, 'id', u'could not extract video id: %s' % url),
+ (2, 'title', u'could not extract video title: %s' % url),
+ (3, 'date', u'could not extract video date: %s' % url),
+ (4, 'url', u'could not extract video url: %s' % url)
]
)
'id': info.get('id'),
'url': compat_urllib_parse.unquote(info.get('url')),
'uploader': u'arte.tv',
- 'upload_date': info.get('date'),
- 'title': info.get('title'),
+ 'upload_date': unified_strdate(info.get('date')),
+ 'title': info.get('title').decode('utf-8'),
'ext': u'mp4',
'format': u'NA',
'player_url': None,
_VALID_URL = r'.*'
IE_NAME = u'generic'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+ if not self._downloader.params.get('test', False):
+ self._downloader.report_warning(u'Falling back on generic information extractor.')
+ super(GenericIE, self).report_download_webpage(video_id)
def report_following_redirect(self, new_url):
"""Report information extraction."""
self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
-
+
def _test_redirect(self, url):
- """Check if it is a redirect, like url shorteners, in case restart chain."""
+ """Check if it is a redirect, like url shorteners, in case return the new url."""
class HeadRequest(compat_urllib_request.Request):
def get_method(self):
return "HEAD"
class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
"""
- Subclass the HTTPRedirectHandler to make it use our
+ Subclass the HTTPRedirectHandler to make it use our
HeadRequest also on the redirected URL
"""
- def redirect_request(self, req, fp, code, msg, headers, newurl):
+ def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
+ newurl = newurl.replace(' ', '%20')
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
+ return HeadRequest(newurl,
headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True)
- else:
- raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
+ origin_req_host=req.get_origin_req_host(),
+ unverifiable=True)
+ else:
+ raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
class HTTPMethodFallback(compat_urllib_request.BaseHandler):
"""
Fallback to GET if HEAD is not allowed (405 HTTP error)
"""
- def http_error_405(self, req, fp, code, msg, headers):
+ def http_error_405(self, req, fp, code, msg, headers):
fp.read()
fp.close()
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
+ return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
+ headers=newheaders,
+ origin_req_host=req.get_origin_req_host(),
unverifiable=True))
# Build our opener
- opener = compat_urllib_request.OpenerDirector()
+ opener = compat_urllib_request.OpenerDirector()
for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
HTTPMethodFallback, HEADRedirectHandler,
- compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
+ compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
response = opener.open(HeadRequest(url))
return False
self.report_following_redirect(new_url)
- self._downloader.download([new_url])
- return True
+ return new_url
def _real_extract(self, url):
- if self._test_redirect(url): return
+ new_url = self._test_redirect(url)
+ if new_url: return [self.url_result(new_url)]
video_id = url.split('/')[-1]
- request = compat_urllib_request.Request(url)
try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
except ValueError as err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
self.report_extraction(video_id)
# Start with something easy: JW Player in SWFObject
# Broaden the search a little bit
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ # Broaden the search a little bit: JWPlayer JS loader
+ mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_url = compat_urllib_parse.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# and so on and so forth; it's just not practical
mobj = re.search(r'<title>(.*)</title>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract title')
+ video_title = mobj.group(1)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_uploader = mobj.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract title')
+ video_uploader = mobj.group(1)
return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
+ 'id': video_id,
+ 'url': video_url,
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
- 'ext': video_extension.decode('utf-8'),
+ 'ext': video_extension,
}]
_max_youtube_results = 1000
IE_NAME = u'youtube:search'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_download_page(self, query, pagenum):
"""Report attempt to download search page with given number."""
query = query.decode(preferredencoding())
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
+ raise ExtractorError(u'Invalid search query "%s"' % query)
prefix, query = query.split(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
+ self._get_n_results(query, self._max_youtube_results)
else:
try:
n = int(prefix)
if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
+ raise ExtractorError(u'Invalid download number %s for query "%s"' % (n, query))
elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
- self._download_n_results(query, n)
- return
+ return self._get_n_results(query, n)
except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
video_ids = []
pagenum = 0
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
request = compat_urllib_request.Request(result_url)
try:
- data = compat_urllib_request.urlopen(request).read()
+ data = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download API page: %s' % compat_str(err))
api_response = json.loads(data)['data']
+ if not 'items' in api_response:
+ raise ExtractorError(u'[youtube] No video results')
+
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
if len(video_ids) > n:
video_ids = video_ids[:n]
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
+ return self.playlist_result(videos, query)
class GoogleSearchIE(InfoExtractor):
"""Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
- _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
+ _VALID_URL = r'gvsearch(?P<prefix>|\d+|all):(?P<query>[\s\S]+)'
+ _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
_max_google_results = 1000
IE_NAME = u'video.google:search'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
-
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
+ prefix = mobj.group('prefix')
+ query = mobj.group('query')
if prefix == '':
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
elif prefix == 'all':
- self._download_n_results(query, self._max_google_results)
- return
+ return self._get_n_results(query, self._max_google_results)
else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ n = int(prefix)
+ if n <= 0:
+ raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+ elif n > self._max_google_results:
+ self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ n = self._max_google_results
+ return self._get_n_results(query, n)
+
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
+
+ res = {
+ '_type': 'playlist',
+ 'id': query,
+ 'entries': []
+ }
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in video_ids:
- video_ids.append(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
+ for pagenum in itertools.count(1):
+ result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
+ webpage = self._download_webpage(result_url, u'gvsearch:' + query,
+ note='Downloading result page ' + str(pagenum))
- pagenum = pagenum + 1
+ for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
+ e = {
+ '_type': 'url',
+ 'url': mobj.group(1)
+ }
+ res['entries'].append(e)
+ if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
+ return res
class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+ _max_yahoo_results = 1000
+ IE_NAME = u'screen.yahoo:search'
def _real_extract(self, query):
mobj = re.match(self._VALID_URL, query)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
+ raise ExtractorError(u'Invalid search query "%s"' % query)
prefix, query = query.split(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
+ return self._get_n_results(query, self._max_yahoo_results)
else:
try:
n = int(prefix)
if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
+ raise ExtractorError(u'Invalid download number %s for query "%s"' % (n, query))
elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
+ return self._get_n_results(query, n)
except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
+ return self._get_n_results(query, 1)
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
+ res = {
+ '_type': 'playlist',
+ 'id': query,
+ 'entries': []
+ }
+ for pagenum in itertools.count(0):
+ result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
+ webpage = self._download_webpage(result_url, query,
+ note='Downloading results page '+str(pagenum+1))
+ info = json.loads(webpage)
+ m = info[u'm']
+ results = info[u'results']
+
+ for (i, r) in enumerate(results):
+ if (pagenum * 30) +i >= n:
+ break
+ mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
+ e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
+ res['entries'].append(e)
+ if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
+ break
- pagenum = pagenum + 1
+ return res
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
+ _VALID_URL = r"""(?:
+ (?:https?://)?
+ (?:\w+\.)?
+ youtube\.com/
+ (?:
+ (?:course|view_play_list|my_playlists|artist|playlist|watch)
+ \? (?:.*?&)*? (?:p|a|list)=
+ | p/
+ )
+ ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
+ .*
+ |
+ ((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
+ )"""
+ _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
+ _MAX_RESULTS = 50
IE_NAME = u'youtube:playlist'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url):
# Extract playlist id
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- # Single video case
- if mobj.group(3) is not None:
- self._downloader.download([mobj.group(3)])
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
- # Download playlist pages
- # prefix is 'p' as default for playlists but there are other types that need extra care
- playlist_prefix = mobj.group(1)
- if playlist_prefix == 'a':
- playlist_access = 'artist'
- else:
- playlist_prefix = 'p'
- playlist_access = 'view_play_list'
- playlist_id = mobj.group(2)
- video_ids = []
- pagenum = 1
+ # Download playlist videos from API
+ playlist_id = mobj.group(1) or mobj.group(2)
+ page_num = 1
+ videos = []
while True:
- self.report_download_page(playlist_id, pagenum)
- url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
-
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
+ page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
- if self._MORE_PAGES_INDICATOR not in page:
+ try:
+ response = json.loads(page)
+ except ValueError as err:
+ raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
+
+ if 'feed' not in response:
+ raise ExtractorError(u'Got a malformed response from YouTube API')
+ playlist_title = response['feed']['title']['$t']
+ if 'entry' not in response['feed']:
+ # Number of videos is a multiple of self._MAX_RESULTS
break
- pagenum = pagenum + 1
- total = len(video_ids)
+ videos += [ (entry['yt$position']['$t'], entry['content']['src'])
+ for entry in response['feed']['entry']
+ if 'content' in entry ]
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
+ if len(response['feed']['entry']) < self._MAX_RESULTS:
+ break
+ page_num += 1
- if len(video_ids) == total:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
- else:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids)))
+ videos = [v[1] for v in sorted(videos)]
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ url_results = [self.url_result(url, 'Youtube') for url in videos]
+ return [self.playlist_result(url_results, playlist_id, playlist_title)]
class YoutubeChannelIE(InfoExtractor):
"""Information Extractor for YouTube channels."""
- _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+ _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
+ _MORE_PAGES_INDICATOR = 'yt-uix-load-more'
+ _MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
- def report_download_page(self, channel_id, pagenum):
- """Report attempt to download channel page with given number."""
- self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+ def extract_videos_from_page(self, page):
+ ids_in_page = []
+ for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ return ids_in_page
def _real_extract(self, url):
# Extract channel id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
- # Download channel pages
+ # Download channel page
channel_id = mobj.group(1)
video_ids = []
pagenum = 1
- while True:
- self.report_download_page(channel_id, pagenum)
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ url = self._TEMPLATE_URL % (channel_id, pagenum)
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ # Extract video identifiers
+ ids_in_page = self.extract_videos_from_page(page)
+ video_ids.extend(ids_in_page)
- if self._MORE_PAGES_INDICATOR not in page:
- break
- pagenum = pagenum + 1
+ # Download any subsequent channel pages using the json-based channel_ajax query
+ if self._MORE_PAGES_INDICATOR in page:
+ while True:
+ pagenum = pagenum + 1
+
+ url = self._MORE_PAGES_URL % (pagenum, channel_id)
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
+
+ page = json.loads(page)
+
+ ids_in_page = self.extract_videos_from_page(page['content_html'])
+ video_ids.extend(ids_in_page)
+
+ if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
+ break
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
+ urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
+ url_entries = [self.url_result(url, 'Youtube') for url in urls]
+ return [self.playlist_result(url_entries, channel_id)]
class YoutubeUserIE(InfoExtractor):
_VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
IE_NAME = u'youtube:user'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
username = mobj.group(1)
while True:
start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
-
- request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
+ page = self._download_webpage(gdata_url, username,
+ u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
# Extract video identifiers
ids_in_page = []
pagenum += 1
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
-
- for video_id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
+ urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
+ url_results = [self.url_result(url, 'Youtube') for url in urls]
+ return [self.playlist_result(url_results, playlist_title = username)]
class BlipTVUserIE(InfoExtractor):
_PAGE_SIZE = 12
IE_NAME = u'blip.tv:user'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, pagenum):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
- (self.IE_NAME, username, pagenum))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
- request = compat_urllib_request.Request(url)
-
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- mobj = re.search(r'data-users-id="([^"]+)"', page)
- page_base = page_base % mobj.group(1)
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, username, u'Downloading user page')
+ mobj = re.search(r'data-users-id="([^"]+)"', page)
+ page_base = page_base % mobj.group(1)
# Download video ids using BlipTV Ajax calls. Result size per
pagenum = 1
while True:
- self.report_download_page(username, pagenum)
-
- request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
-
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
+ url = page_base + "&page=" + str(pagenum)
+ page = self._download_webpage(url, username,
+ u'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
pagenum += 1
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
- (self.IE_NAME, username, all_ids_count, len(video_ids)))
-
- for video_id in video_ids:
- self._downloader.download([u'http://blip.tv/'+video_id])
+ urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
+ url_entries = [self.url_result(url, 'BlipTV') for url in urls]
+ return [self.playlist_result(url_entries, playlist_title = username)]
class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com"""
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
- IE_NAME = u'DepositFiles'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, file_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
def _real_extract(self, url):
file_id = url.split('/')[-1]
self.report_download_webpage(file_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err))
# Search for the real file URL
mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
if (mobj is not None) and (mobj.group(1) is not None):
restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
- self._downloader.trouble(u'ERROR: %s' % restriction_message)
+ raise ExtractorError(u'%s' % restriction_message)
else:
- self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
- return
+ raise ExtractorError(u'Unable to extract download URL from: %s' % url)
file_url = mobj.group(1)
file_extension = os.path.splitext(file_url)[1][1:]
# Search for file title
mobj = re.search(r'<b title="(.*?)">', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
file_title = mobj.group(1).decode('utf-8')
return [{
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _WORKING = False
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
- _available_formats = ['video', 'highqual', 'lowqual']
- _video_extensions = {
- 'video': 'mp4',
- 'highqual': 'mp4',
- 'lowqual': 'mp4',
- }
IE_NAME = u'facebook'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def _reporter(self, message):
- """Add header and report message."""
- self._downloader.to_screen(u'[facebook] %s' % message)
-
def report_login(self):
"""Report attempt to log in."""
- self._reporter(u'Logging in')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._reporter(u'%s: Downloading video webpage' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._reporter(u'%s: Extracting video information' % video_id)
-
- def _parse_page(self, video_webpage):
- """Extract video information from page"""
- # General data
- data = {'title': r'\("video_title", "(.*?)"\)',
- 'description': r'<div class="datawrap">(.*?)</div>',
- 'owner': r'\("video_owner_name", "(.*?)"\)',
- 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
- }
- video_info = {}
- for piece in data.keys():
- mobj = re.search(data[piece], video_webpage)
- if mobj is not None:
- video_info[piece] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
-
- # Video urls
- video_urls = {}
- for fmt in self._available_formats:
- mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
- if mobj is not None:
- # URL is in a Javascript segment inside an escaped Unicode format within
- # the generally utf-8 page
- video_urls[fmt] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
- video_info['video_urls'] = video_urls
-
- return video_info
+ self.to_screen(u'Logging in')
def _real_initialize(self):
if self._downloader is None:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
if useremail is None:
self.report_login()
login_results = compat_urllib_request.urlopen(request).read()
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+ self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('ID')
- # Get video webpage
- self.report_video_webpage_download(video_id)
- request = compat_urllib_request.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
- try:
- page = compat_urllib_request.urlopen(request)
- video_webpage = page.read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # Extract information
- video_info = self._parse_page(video_webpage)
-
- # uploader
- if 'owner' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = video_info['owner']
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = video_info['title']
- video_title = video_title.decode('utf-8')
-
- # thumbnail image
- if 'thumbnail' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else:
- video_thumbnail = video_info['thumbnail']
-
- # upload date
- upload_date = None
- if 'upload_date' in video_info:
- upload_time = video_info['upload_date']
- timetuple = email.utils.parsedate_tz(upload_time)
- if timetuple is not None:
- try:
- upload_date = time.strftime('%Y%m%d', timetuple[0:9])
- except:
- pass
-
- # description
- video_description = video_info.get('description', 'No description available.')
-
- url_map = video_info['video_urls']
- if len(url_map.keys()) > 0:
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
- format_limit = self._downloader.params.get('format_limit', None)
-
- if format_limit is not None and format_limit in self._available_formats:
- format_list = self._available_formats[self._available_formats.index(format_limit):]
- else:
- format_list = self._available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if req_format is None:
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format == '-1':
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific format
- if req_format not in url_map:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- video_url_list = [(req_format, url_map[req_format])] # Specific format
+ url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
+ webpage = self._download_webpage(url, video_id)
+
+ 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:
+ raise ExtractorError(u'Cannot parse data')
+ data = dict(json.loads(m.group(1)))
+ params_raw = compat_urllib_parse.unquote(data['params'])
+ params = json.loads(params_raw)
+ video_data = params['video_data'][0]
+ video_url = video_data.get('hd_src')
+ if not video_url:
+ video_url = video_data['sd_src']
+ if not video_url:
+ raise ExtractorError(u'Cannot find video URL')
+ video_duration = int(video_data['video_duration'])
+ thumbnail = video_data['thumbnail_src']
+
+ m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title in webpage')
+ video_title = unescapeHTML(m.group(1))
- results = []
- for format_param, video_real_url in video_url_list:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'mp4')
+ info = {
+ 'id': video_id,
+ 'title': video_title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'duration': video_duration,
+ 'thumbnail': thumbnail,
+ }
+ return [info]
- results.append({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description.decode('utf-8'),
- })
- return results
class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv"""
_URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv'
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
-
def report_direct_download(self, title):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
+ self.to_screen(u'%s: Direct download detected' % title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ urlp = compat_urllib_parse_urlparse(url)
+ if urlp.path.startswith('/play/'):
+ request = compat_urllib_request.Request(url)
+ response = compat_urllib_request.urlopen(request)
+ redirecturl = response.geturl()
+ rurlp = compat_urllib_parse_urlparse(redirecturl)
+ file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
+ url = 'http://blip.tv/a/a-' + file_id
+ return self._real_extract(url)
+
if '?' in url:
cchar = '&'
else:
cchar = '?'
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
- request = compat_urllib_request.Request(json_url.encode('utf-8'))
+ request = compat_urllib_request.Request(json_url)
+ request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1))
info = None
try:
'urlhandle': urlh
}
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
if info is None: # Regular URL
try:
- json_code = urlh.read()
+ json_code_bytes = urlh.read()
+ json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
try:
json_data = json.loads(json_code)
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
- 'player_url': data['embedUrl']
+ 'player_url': data['embedUrl'],
+ 'user_agent': 'iTunes/10.6.1',
}
except (ValueError,KeyError) as err:
- self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
- return
+ raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
- std_headers['User-Agent'] = 'iTunes/10.6.1'
return [info]
_VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
IE_NAME = u'myvideo'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
-
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._download.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
# Get video webpage
- request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
+ webpage = self._download_webpage(webpage_url, video_id)
self.report_extraction(video_id)
- mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'',
webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
video_url = mobj.group(1) + ('/%s.flv' % video_id)
mobj = re.search('<title>([^<]+)</title>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1)
class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """
- _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
- IE_NAME = u'comedycentral'
+ # urls can be abbreviations like :thedailyshow or :colbert
+ # urls for episodes like:
+ # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
+ # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
+ # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
+ _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+ |(https?://)?(www\.)?
+ (?P<showname>thedailyshow|colbertnation)\.com/
+ (full-episodes/(?P<episode>.*)|
+ (?P<clip>
+ (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
+ |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
+ $"""
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
'400': '384x216',
}
- def report_extraction(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
-
- def report_config_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
-
- def report_index_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
-
- def report_player_url(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
-
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _print_formats(self, formats):
print('Available formats:')
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
url = u'http://www.thedailyshow.com/full-episodes/'
else:
url = u'http://www.colbertnation.com/full-episodes/'
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
assert mobj is not None
- dlNewest = not mobj.group('episode')
- if dlNewest:
- epTitle = mobj.group('showname')
+ if mobj.group('clip'):
+ if mobj.group('showname') == 'thedailyshow':
+ epTitle = mobj.group('tdstitle')
+ else:
+ epTitle = mobj.group('cntitle')
+ dlNewest = False
else:
- epTitle = mobj.group('episode')
+ dlNewest = not mobj.group('episode')
+ if dlNewest:
+ epTitle = mobj.group('showname')
+ else:
+ epTitle = mobj.group('episode')
- req = compat_urllib_request.Request(url)
self.report_extraction(epTitle)
- try:
- htmlHandle = compat_urllib_request.urlopen(req)
- html = htmlHandle.read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest:
url = htmlHandle.geturl()
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
- return
+ raise ExtractorError(u'Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
- self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
- return
+ raise ExtractorError(u'Redirected URL is still not specific: ' + url)
epTitle = mobj.group('episode')
- mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
+ mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
- altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html)
+ altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
- self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
- return
+ raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
-
- playerUrl_raw = mMovieParams[0][0]
- self.report_player_url(epTitle)
- try:
- urlHandle = compat_urllib_request.urlopen(playerUrl_raw)
- playerUrl = urlHandle.geturl()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err))
- return
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
- self.report_index_download(epTitle)
- try:
- indexXml = compat_urllib_request.urlopen(indexUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err))
- return
+ indexXml = self._download_webpage(indexUrl, epTitle,
+ u'Downloading show index',
+ u'unable to download episode index')
results = []
idoc = xml.etree.ElementTree.fromstring(indexXml)
itemEls = idoc.findall('.//item')
- for itemEl in itemEls:
+ for partNum,itemEl in enumerate(itemEls):
mediaId = itemEl.findall('./guid')[0].text
shortMediaId = mediaId.split(':')[-1]
showId = mediaId.split(':')[-2].replace('.com', '')
officialTitle = itemEl.findall('./title')[0].text
- officialDate = itemEl.findall('./pubDate')[0].text
+ officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
compat_urllib_parse.urlencode({'uri': mediaId}))
- configReq = compat_urllib_request.Request(configUrl)
- self.report_config_download(epTitle)
- try:
- configXml = compat_urllib_request.urlopen(configReq).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ configXml = self._download_webpage(configUrl, epTitle,
+ u'Downloading configuration for %s' % shortMediaId)
cdoc = xml.etree.ElementTree.fromstring(configXml)
turls = []
turls.append(finfo)
if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+ self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
continue
-
+
if self._downloader.params.get('listformats', None):
self._print_formats([i[0] for i in turls])
return
# For now, just pick the highest bitrate
- format,video_url = turls[-1]
+ format,rtmp_video_url = turls[-1]
# Get the format arg from the arg stream
req_format = self._downloader.params.get('format', None)
# Select format if we can find one
for f,v in turls:
if f == req_format:
- format, video_url = f, v
+ format, rtmp_video_url = f, v
break
- # Patch to download from alternative CDN, which does not
- # break on current RTMPDump builds
- broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
- better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
-
- if video_url.startswith(broken_cdn):
- video_url = video_url.replace(broken_cdn, better_cdn)
+ m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+ if not m:
+ raise ExtractorError(u'Cannot transform RTMP url')
+ base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+ video_url = base + m.group('finalid')
- effTitle = showId + u'-' + epTitle
+ effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
info = {
'id': shortMediaId,
'url': video_url,
'format': format,
'thumbnail': None,
'description': officialTitle,
- 'player_url': None #playerUrl
}
-
results.append(info)
-
+
return results
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
IE_NAME = u'escapist'
- def report_extraction(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
-
- def report_config_download(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(showName)
- try:
- webPage = compat_urllib_request.urlopen(url)
- webPageBytes = webPage.read()
- m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
- webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err))
- return
+ webPage = self._download_webpage(url, showName)
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
description = unescapeHTML(descMatch.group(1))
configUrlMatch = re.search('config=(.*)$', playerUrl)
configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
- self.report_config_download(showName)
- try:
- configJSON = compat_urllib_request.urlopen(configUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err))
- return
+ configJSON = self._download_webpage(configUrl, showName,
+ u'Downloading configuration',
+ u'unable to download configuration')
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
- self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + compat_str(err))
- return
+ raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
videoUrl = playlist[1]['url']
'uploader': showName,
'upload_date': None,
'title': showName,
- 'ext': 'flv',
+ 'ext': 'mp4',
'thumbnail': imgUrl,
'description': description,
'player_url': playerUrl,
return [info]
-
class CollegeHumorIE(InfoExtractor):
"""Information extractor for collegehumor.com"""
def report_manifest(self, video_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+ self.to_screen(u'%s: Downloading XML manifest' % video_id)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
info = {
try:
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text
except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
- return
+ raise ExtractorError(u'Invalid metadata XML file')
manifest_url += '?hdcore=2.10.3'
self.report_manifest(video_id)
try:
manifestXml = compat_urllib_request.urlopen(manifest_url).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
- self._downloader.trouble(u'\nERROR: Invalid manifest file')
- return
+ raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(manifest_url)
url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
IE_NAME = u'xvideos'
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(1).decode('utf-8')
-
- self.report_webpage(video_id)
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group(1)
- request = compat_urllib_request.Request(r'http://www.xvideos.com/video' + video_id)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
# Extract video URL
mobj = re.search(r'flv_url=(.+?)&', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1).decode('utf-8'))
+ raise ExtractorError(u'Unable to extract video url')
+ video_url = compat_urllib_parse.unquote(mobj.group(1))
# Extract title
mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = mobj.group(1)
# Extract video thumbnail
mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(0).decode('utf-8')
+ raise ExtractorError(u'Unable to extract video thumbnail')
+ video_thumbnail = mobj.group(0)
info = {
'id': video_id,
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'soundcloud'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_resolve(self, video_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id))
+ self.to_screen(u'%s: Resolving id' % video_id)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader (which is in the url)
uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
slug_title = mobj.group(2)
simple_title = uploader + u'-' + slug_title
+ full_title = '%s/%s' % (uploader, slug_title)
- self.report_resolve('%s/%s' % (uploader, slug_title))
+ self.report_resolve(full_title)
url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(resolv_url)
- try:
- info_json_bytes = compat_urllib_request.urlopen(request).read()
- info_json = info_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
info = json.loads(info_json)
video_id = info['id']
- self.report_extraction('%s/%s' % (uploader, slug_title))
+ self.report_extraction(full_title)
streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(streams_url)
- try:
- stream_json_bytes = compat_urllib_request.urlopen(request).read()
- stream_json = stream_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ stream_json = self._download_webpage(streams_url, full_title,
+ u'Downloading stream definitions',
+ u'unable to download stream definitions')
streams = json.loads(stream_json)
mediaURL = streams['http_mp3_128_url']
+ upload_date = unified_strdate(info['created_at'])
return [{
'id': info['id'],
'url': mediaURL,
'uploader': info['user']['username'],
- 'upload_date': info['created_at'],
+ 'upload_date': upload_date,
'title': info['title'],
'ext': u'mp3',
'description': info['description'],
}]
+class SoundcloudSetIE(InfoExtractor):
+ """Information extractor for soundcloud.com sets
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
-class InfoQIE(InfoExtractor):
- """Information extractor for infoq.com"""
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
- IE_NAME = u'infoq'
-
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+ IE_NAME = u'soundcloud:set'
- def report_extraction(self, video_id):
+ def report_resolve(self, video_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+ self.to_screen(u'%s: Resolving id' % video_id)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
- self.report_webpage(url)
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1)
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2)
+ simple_title = uploader + u'-' + slug_title
+ full_title = '%s/sets/%s' % (uploader, slug_title)
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ self.report_resolve(full_title)
+
+ url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
+ resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ info_json = self._download_webpage(resolv_url, full_title)
+
+ videos = []
+ info = json.loads(info_json)
+ if 'errors' in info:
+ for err in info['errors']:
+ self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
return
- self.report_extraction(url)
+ self.report_extraction(full_title)
+ for track in info['tracks']:
+ video_id = track['id']
+ streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+ stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
- # Extract video URL
- mobj = re.search(r"jsclassref='([^']*)'", webpage)
+ self.report_extraction(video_id)
+ streams = json.loads(stream_json)
+ mediaURL = streams['http_mp3_128_url']
+
+ videos.append({
+ 'id': video_id,
+ 'url': mediaURL,
+ 'uploader': track['user']['username'],
+ 'upload_date': unified_strdate(track['created_at']),
+ 'title': track['title'],
+ 'ext': u'mp3',
+ 'description': track['description'],
+ })
+ return videos
+
+
+class InfoQIE(InfoExtractor):
+ """Information extractor for infoq.com"""
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
- return
- video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64'))
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ webpage = self._download_webpage(url, video_id=url)
+ self.report_extraction(url)
+ # Extract video URL
+ mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract video url')
+ real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
+ video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
mobj = re.search(r'contentTitle = "(.*?)";', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = mobj.group(1)
# Extract description
video_description = u'No description available.'
mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
if mobj is not None:
- video_description = mobj.group(1).decode('utf-8')
+ video_description = mobj.group(1)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
class MixcloudIE(InfoExtractor):
"""Information extractor for www.mixcloud.com"""
+
+ _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'mixcloud'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_download_json(self, file_id):
"""Report JSON download."""
- self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+ self.to_screen(u'Downloading json')
def get_urls(self, jsonData, fmt, bitrate='best'):
"""Get urls from 'audio_formats' section in json"""
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader & filename from url
uploader = mobj.group(1).decode('utf-8')
file_id = uploader + "-" + mobj.group(2).decode('utf-8')
self.report_download_json(file_url)
jsonData = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
# parse JSON
json_data = json.loads(jsonData)
if file_url is not None:
break # got it!
else:
- if req_format not in formats.keys():
- self._downloader.trouble(u'ERROR: format is not available')
- return
+ if req_format not in formats:
+ raise ExtractorError(u'Format is not available')
url_list = self.get_urls(formats, req_format)
file_url = self.check_urls(url_list)
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
IE_NAME = u'stanfordoc'
- def report_download_webpage(self, objid):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if mobj.group('course') and mobj.group('video'): # A specific video
course = mobj.group('course')
try:
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
info['title'] = mdoc.findall('./title')[0].text
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
- return
+ raise ExtractorError(u'Invalid metadata XML file')
info['ext'] = info['url'].rpartition('.')[2]
return [info]
elif mobj.group('course'): # A course page
'upload_date': None,
}
- self.report_download_webpage(info['id'])
- try:
- coursepage = compat_urllib_request.urlopen(url).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
- return
+ coursepage = self._download_webpage(url, info['id'],
+ note='Downloading course info page',
+ errnote='Unable to download course info page')
m = re.search('<h1>([^<]+)</h1>', coursepage)
if m:
assert entry['type'] == 'reference'
results += self.extract(entry['url'])
return results
-
else: # Root page
info = {
'id': 'Stanford OpenClassroom',
try:
rootpage = compat_urllib_request.urlopen(rootURL).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
- return
+ raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
info['title'] = info['id']
_VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
IE_NAME = u'mtv'
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if not mobj.group('proto'):
url = 'http://' + url
video_id = mobj.group('videoid')
- self.report_webpage(video_id)
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract song name')
- return
+ raise ExtractorError(u'Unable to extract song name')
song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract performer')
- return
+ raise ExtractorError(u'Unable to extract performer')
performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
- video_title = performer + ' - ' + song_name
+ video_title = performer + ' - ' + song_name
mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to mtvn_uri')
- return
+ raise ExtractorError(u'Unable to mtvn_uri')
mtvn_uri = mobj.group(1)
mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract content id')
- return
+ raise ExtractorError(u'Unable to extract content id')
content_id = mobj.group(1)
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
try:
metadataXml = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
renditions = mdoc.findall('.//rendition')
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
video_url = rendition.find('./src').text
except KeyError:
- self._downloader.trouble('Invalid rendition field.')
- return
+ raise ExtractorError('Invalid rendition field.')
info = {
'id': video_id,
class YoukuIE(InfoExtractor):
-
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
- IE_NAME = u'Youku'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, file_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
def _gen_sid(self):
nowTime = int(time.time() * 1000)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('ID')
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
- request = compat_urllib_request.Request(info_url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- jsondata = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ jsondata = self._download_webpage(info_url, video_id)
self.report_extraction(video_id)
try:
seed = config['data'][0]['seed']
format = self._downloader.params.get('format', None)
- supported_format = config['data'][0]['streamfileids'].keys()
+ supported_format = list(config['data'][0]['streamfileids'].keys())
if format is None or format == 'best':
if 'hd2' in supported_format:
fileid = config['data'][0]['streamfileids'][format]
- seg_number = len(config['data'][0]['segs'][format])
-
- keys=[]
- for i in xrange(seg_number):
- keys.append(config['data'][0]['segs'][format][i]['k'])
-
- #TODO check error
- #youku only could be viewed from mainland china
- except:
- self._downloader.trouble(u'ERROR: unable to extract info section')
- return
+ keys = [s['k'] for s in config['data'][0]['segs'][format]]
+ except (UnicodeDecodeError, ValueError, KeyError):
+ raise ExtractorError(u'Unable to extract info section')
files_info=[]
sid = self._gen_sid()
class XNXXIE(InfoExtractor):
"""Information extractor for xnxx.com"""
- _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+ _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
IE_NAME = u'xnxx'
VIDEO_URL_RE = r'flv_url=(.*?)&'
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
- def report_webpage(self, video_id):
- """Report information extraction"""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction"""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(1).decode('utf-8')
-
- self.report_webpage(video_id)
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group(1)
# Get webpage content
- try:
- webpage = compat_urllib_request.urlopen(url).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
- return
+ webpage = self._download_webpage(url, video_id)
result = re.search(self.VIDEO_URL_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
- return
- video_url = compat_urllib_parse.unquote(result.group(1).decode('utf-8'))
+ raise ExtractorError(u'Unable to extract video url')
+ video_url = compat_urllib_parse.unquote(result.group(1))
result = re.search(self.VIDEO_TITLE_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = result.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = result.group(1)
result = re.search(self.VIDEO_THUMB_RE, webpage)
if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = result.group(1).decode('utf-8')
+ raise ExtractorError(u'Unable to extract video thumbnail')
+ video_thumbnail = result.group(1)
return [{
'id': video_id,
class GooglePlusIE(InfoExtractor):
"""Information extractor for plus.google.com."""
- _VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
+ _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_extract_entry(self, url):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
+ self.to_screen(u'Downloading entry: %s' % url)
def report_date(self, upload_date):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
+ self.to_screen(u'Entry date: %s' % upload_date)
def report_uploader(self, uploader):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
+ self.to_screen(u'Uploader: %s' % uploader)
def report_title(self, video_title):
"""Report downloading extry"""
- self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
+ self.to_screen(u'Title: %s' % video_title)
def report_extract_vid_page(self, video_page):
"""Report information extraction."""
- self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
+ self.to_screen(u'Extracting video page: %s' % video_page)
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
post_url = mobj.group(0)
- video_id = mobj.group(2)
+ video_id = mobj.group(1)
video_extension = 'flv'
# Step 1, Retrieve post webpage to extract further information
self.report_extract_entry(post_url)
- request = compat_urllib_request.Request(post_url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
# Extract update date
upload_date = None
pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
mobj = re.search(pattern, webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video page URL')
+ raise ExtractorError(u'Unable to extract video page URL')
video_page = mobj.group(1)
- request = compat_urllib_request.Request(video_page)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
self.report_extract_vid_page(video_page)
pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
mobj = re.findall(pattern, webpage)
if len(mobj) == 0:
- self._downloader.trouble(u'ERROR: unable to extract video links')
+ raise ExtractorError(u'Unable to extract video links')
# Sort in resolution
links = sorted(mobj)
# Only get the url. The resolution part in the tuple has no use anymore
video_url = video_url[-1]
# Treat escaped \u0026 style hex
- video_url = unicode(video_url, "unicode_escape")
+ try:
+ video_url = video_url.decode("unicode_escape")
+ except AttributeError: # Python 3
+ video_url = bytes(video_url, 'ascii').decode('unicode-escape')
return [{
- 'id': video_id.decode('utf-8'),
+ 'id': video_id,
'url': video_url,
- 'uploader': uploader.decode('utf-8'),
- 'upload_date': upload_date.decode('utf-8'),
- 'title': video_title.decode('utf-8'),
- 'ext': video_extension.decode('utf-8'),
+ 'uploader': uploader,
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'ext': video_extension,
}]
+
+class NBAIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
+ IE_NAME = u'nba'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group(1)
+ if video_id.endswith('/index.html'):
+ video_id = video_id[:-len('/index.html')]
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+ def _findProp(rexp, default=None):
+ m = re.search(rexp, webpage)
+ if m:
+ return unescapeHTML(m.group(1))
+ else:
+ return default
+
+ shortened_video_id = video_id.rpartition('/')[2]
+ title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
+ info = {
+ 'id': shortened_video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
+ 'description': _findProp(r'<div class="description">(.*?)</h1>'),
+ }
+ return [info]
+
+class JustinTVIE(InfoExtractor):
+ """Information extractor for justin.tv and twitch.tv"""
+ # TODO: One broadcast may be split into multiple videos. The key
+ # 'broadcast_id' is the same for all parts, and 'broadcast_part'
+ # starts at 1 and increases. Can we treat all parts as one video?
+
+ _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
+ (?:
+ (?P<channelid>[^/]+)|
+ (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
+ (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
+ )
+ /?(?:\#.*)?$
+ """
+ _JUSTIN_PAGE_LIMIT = 100
+ IE_NAME = u'justin.tv'
+
+ def report_download_page(self, channel, offset):
+ """Report attempt to download a single page of videos."""
+ self.to_screen(u'%s: Downloading video information from %d to %d' %
+ (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
+
+ # Return count of items, list of *valid* items
+ def _parse_page(self, url, video_id):
+ webpage = self._download_webpage(url, video_id,
+ u'Downloading video info JSON',
+ u'unable to download video info JSON')
+
+ response = json.loads(webpage)
+ if type(response) != list:
+ error_text = response.get('error', 'unknown error')
+ raise ExtractorError(u'Justin.tv API: %s' % error_text)
+ info = []
+ for clip in response:
+ video_url = clip['video_file_url']
+ if video_url:
+ video_extension = os.path.splitext(video_url)[1][1:]
+ video_date = re.sub('-', '', clip['start_time'][:10])
+ video_uploader_id = clip.get('user_id', clip.get('channel_id'))
+ video_id = clip['id']
+ video_title = clip.get('title', video_id)
+ info.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'uploader': clip.get('channel_name', video_uploader_id),
+ 'uploader_id': video_uploader_id,
+ 'upload_date': video_date,
+ 'ext': video_extension,
+ })
+ return (len(response), info)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'invalid URL: %s' % url)
+
+ api_base = 'http://api.justin.tv'
+ paged = False
+ if mobj.group('channelid'):
+ paged = True
+ video_id = mobj.group('channelid')
+ api = api_base + '/channel/archives/%s.json' % video_id
+ elif mobj.group('chapterid'):
+ chapter_id = mobj.group('chapterid')
+
+ webpage = self._download_webpage(url, chapter_id)
+ m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find archive of a chapter')
+ archive_id = m.group(1)
+
+ api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
+ chapter_info_xml = self._download_webpage(api, chapter_id,
+ note=u'Downloading chapter information',
+ errnote=u'Chapter information download failed')
+ doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
+ for a in doc.findall('.//archive'):
+ if archive_id == a.find('./id').text:
+ break
+ else:
+ raise ExtractorError(u'Could not find chapter in chapter information')
+
+ video_url = a.find('./video_file_url').text
+ video_ext = video_url.rpartition('.')[2] or u'flv'
+
+ chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
+ chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
+ note='Downloading chapter metadata',
+ errnote='Download of chapter metadata failed')
+ chapter_info = json.loads(chapter_info_json)
+
+ bracket_start = int(doc.find('.//bracket_start').text)
+ bracket_end = int(doc.find('.//bracket_end').text)
+
+ # TODO determine start (and probably fix up file)
+ # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
+ #video_url += u'?start=' + TODO:start_timestamp
+ # bracket_start is 13290, but we want 51670615
+ self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
+ u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
+
+ info = {
+ 'id': u'c' + chapter_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': chapter_info['title'],
+ 'thumbnail': chapter_info['preview'],
+ 'description': chapter_info['description'],
+ 'uploader': chapter_info['channel']['display_name'],
+ 'uploader_id': chapter_info['channel']['name'],
+ }
+ return [info]
+ else:
+ video_id = mobj.group('videoid')
+ api = api_base + '/broadcast/by_archive/%s.json' % video_id
+
+ self.report_extraction(video_id)
+
+ info = []
+ offset = 0
+ limit = self._JUSTIN_PAGE_LIMIT
+ while True:
+ if paged:
+ self.report_download_page(video_id, offset)
+ page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
+ page_count, page_info = self._parse_page(page_url, video_id)
+ info.extend(page_info)
+ if not paged or page_count != limit:
+ break
+ offset += limit
+ return info
+
+class FunnyOrDieIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
+ if not m:
+ raise ExtractorError(u'Unable to find video information')
+ video_url = unescapeHTML(m.group('url'))
+
+ m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
+ if not m:
+ m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find video title')
+ title = clean_html(m.group('title'))
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ }
+ return [info]
+
+class SteamIE(InfoExtractor):
+ _VALID_URL = r"""http://store\.steampowered\.com/
+ (agecheck/)?
+ (?P<urltype>video|app)/ #If the page is only for videos or for a game
+ (?P<gameID>\d+)/?
+ (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
+ """
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url, re.VERBOSE)
+ gameID = m.group('gameID')
+ videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
+ self.report_age_confirmation()
+ webpage = self._download_webpage(videourl, gameID)
+ game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title')
+
+ urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
+ mweb = re.finditer(urlRE, webpage)
+ namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
+ titles = re.finditer(namesRE, webpage)
+ thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
+ thumbs = re.finditer(thumbsRE, webpage)
+ videos = []
+ for vid,vtitle,thumb in zip(mweb,titles,thumbs):
+ video_id = vid.group('videoID')
+ title = vtitle.group('videoName')
+ video_url = vid.group('videoURL')
+ video_thumb = thumb.group('thumbnail')
+ if not video_url:
+ raise ExtractorError(u'Cannot find video url for %s' % video_id)
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': unescapeHTML(title),
+ 'thumbnail': video_thumb
+ }
+ videos.append(info)
+ return [self.playlist_result(videos, gameID, game_title)]
+
+class UstreamIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
+ IE_NAME = u'ustream'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'data-title="(?P<title>.+)"',webpage)
+ title = m.group('title')
+ m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
+ uploader = m.group('uploader')
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': title,
+ 'uploader': uploader
+ }
+ return [info]
+
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ IE_NAME = u'WorldStarHipHop'
+
+ def _real_extract(self, url):
+ _src_url = r'so\.addVariable\("file","(.*?)"\)'
+
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ webpage_src = self._download_webpage(url, video_id)
+
+ mobj = re.search(_src_url, webpage_src)
+
+ if mobj is not None:
+ video_url = mobj.group(1)
+ if 'mp4' in video_url:
+ ext = 'mp4'
+ else:
+ ext = 'flv'
+ else:
+ raise ExtractorError(u'Cannot find video url for %s' % video_id)
+
+ mobj = re.search(r"<title>(.*)</title>", webpage_src)
+
+ if mobj is None:
+ raise ExtractorError(u'Cannot determine title')
+ title = mobj.group(1)
+
+ mobj = re.search(r'rel="image_src" href="(.*)" />', webpage_src)
+ # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+ if mobj is not None:
+ thumbnail = mobj.group(1)
+ else:
+ _title = r"""candytitles.*>(.*)</span>"""
+ mobj = re.search(_title, webpage_src)
+ if mobj is not None:
+ title = mobj.group(1)
+ thumbnail = None
+
+ results = [{
+ 'id': video_id,
+ 'url' : video_url,
+ 'title' : title,
+ 'thumbnail' : thumbnail,
+ 'ext' : ext,
+ }]
+ return results
+
+class RBMARadioIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find metadata')
+ json_data = m.group(1)
+
+ try:
+ data = json.loads(json_data)
+ except ValueError as e:
+ raise ExtractorError(u'Invalid JSON: ' + str(e))
+
+ video_url = data['akamai_url'] + '&cbr=256'
+ url_parts = compat_urllib_parse_urlparse(video_url)
+ video_ext = url_parts.path.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': data['title'],
+ 'description': data.get('teaser_text'),
+ 'location': data.get('country_of_origin'),
+ 'uploader': data.get('host', {}).get('name'),
+ 'uploader_id': data.get('host', {}).get('slug'),
+ 'thumbnail': data.get('image', {}).get('large_url_2x'),
+ 'duration': data.get('duration'),
+ }
+ return [info]
+
+
+class YouPornIE(InfoExtractor):
+ """Information extractor for youporn.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
+
+ def _print_formats(self, formats):
+ """Print all available formats"""
+ print(u'Available formats:')
+ print(u'ext\t\tformat')
+ print(u'---------------------------------')
+ for format in formats:
+ print(u'%s\t\t%s' % (format['ext'], format['format']))
+
+ def _specific(self, req_format, formats):
+ for x in formats:
+ if(x["format"]==req_format):
+ return x
+ return None
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ # Get the video title
+ result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the video date
+ result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract video date')
+ upload_date = None
+ else:
+ upload_date = unified_strdate(result.group('date').strip())
+
+ # Get the video uploader
+ result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract uploader')
+ video_uploader = None
+ else:
+ video_uploader = result.group('uploader').strip()
+ video_uploader = clean_html( video_uploader )
+
+ # Get all of the formats available
+ DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
+ result = re.search(DOWNLOAD_LIST_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract download list')
+ download_list_html = result.group('download_list').strip()
+
+ # Get all of the links from the page
+ LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+ links = re.findall(LINK_RE, download_list_html)
+ if(len(links) == 0):
+ raise ExtractorError(u'ERROR: no known formats available for video')
+
+ self.to_screen(u'Links found: %d' % len(links))
+
+ formats = []
+ for link in links:
+
+ # A link looks like this:
+ # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
+ # A path looks like this:
+ # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
+ video_url = unescapeHTML( link )
+ path = compat_urllib_parse_urlparse( video_url ).path
+ extension = os.path.splitext( path )[1][1:]
+ format = path.split('/')[4].split('_')[:2]
+ size = format[0]
+ bitrate = format[1]
+ format = "-".join( format )
+ title = u'%s-%s-%s' % (video_title, size, bitrate)
+
+ formats.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': upload_date,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': None
+ })
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ req_format = self._downloader.params.get('format', None)
+ self.to_screen(u'Format: %s' % req_format)
+
+ if req_format is None or req_format == 'best':
+ return [formats[0]]
+ elif req_format == 'worst':
+ return [formats[-1]]
+ elif req_format in ('-1', 'all'):
+ return formats
+ else:
+ format = self._specific( req_format, formats )
+ if result is None:
+ raise ExtractorError(u'Requested format not available')
+ return [format]
+
+
+
+class PornotubeIE(InfoExtractor):
+ """Information extractor for pornotube.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+ video_title = mobj.group('title')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video URL
+ VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
+ result = re.search(VIDEO_URL_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video url')
+ video_url = compat_urllib_parse.unquote(result.group('url'))
+
+ #Get the uploaded date
+ VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
+ result = re.search(VIDEO_UPLOADED_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video title')
+ upload_date = unified_strdate(result.group('date'))
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv'}
+
+ return [info]
+
+class YouJizzIE(InfoExtractor):
+ """Information extractor for youjizz.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video title
+ result = re.search(r'<title>(?P<title>.*)</title>', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the embed page
+ result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract embed page')
+
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+
+ webpage = self._download_webpage(embed_page_url, video_id)
+
+ # Get the video URL
+ result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video url')
+ video_url = result.group('source')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'player_url': embed_page_url}
+
+ return [info]
+
+class EightTracksIE(InfoExtractor):
+ IE_NAME = '8tracks'
+ _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ playlist_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
+ if not m:
+ raise ExtractorError(u'Cannot find trax information')
+ json_like = m.group(1)
+ data = json.loads(json_like)
+
+ session = str(random.randint(0, 1000000000))
+ mix_id = data['id']
+ track_count = data['tracks_count']
+ first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
+ next_url = first_url
+ res = []
+ for i in itertools.count():
+ api_json = self._download_webpage(next_url, playlist_id,
+ note=u'Downloading song information %s/%s' % (str(i+1), track_count),
+ errnote=u'Failed to download song information')
+ api_data = json.loads(api_json)
+ track_data = api_data[u'set']['track']
+ info = {
+ 'id': track_data['id'],
+ 'url': track_data['track_file_stream_url'],
+ 'title': track_data['performer'] + u' - ' + track_data['name'],
+ 'raw_title': track_data['name'],
+ 'uploader_id': data['user']['login'],
+ 'ext': 'm4a',
+ }
+ res.append(info)
+ if api_data['set']['at_last_track']:
+ break
+ next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
+ return res
+
+class KeekIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+ IE_NAME = u'keek'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
+ thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ title = unescapeHTML(m.group('title'))
+ m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
+ uploader = clean_html(m.group('uploader'))
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader
+ }
+ return [info]
+
+class TEDIE(InfoExtractor):
+ _VALID_URL=r'''http://www\.ted\.com/
+ (
+ ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
+ |
+ ((?P<type_talk>talks)) # We have a simple talk
+ )
+ (/lang/(.*?))? # The url may contain the language
+ /(?P<name>\w+) # Here goes the name and then ".html"
+ '''
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m=re.match(self._VALID_URL, url, re.VERBOSE)
+ if m.group('type_talk'):
+ return [self._talk_info(url)]
+ else :
+ playlist_id=m.group('playlist_id')
+ name=m.group('name')
+ self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
+ return [self._playlist_videos_info(url,name,playlist_id)]
+
+ def _talk_video_link(self,mediaSlug):
+ '''Returns the video link for that mediaSlug'''
+ return 'http://download.ted.com/talks/%s.mp4' % mediaSlug
+
+ def _playlist_videos_info(self,url,name,playlist_id=0):
+ '''Returns the videos of the playlist'''
+ video_RE=r'''
+ <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
+ ([.\s]*?)data-playlist_item_id="(\d+)"
+ ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
+ '''
+ video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
+ webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
+ m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
+ m_names=re.finditer(video_name_RE,webpage)
+
+ playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>'
+ m_playlist = re.search(playlist_RE, webpage)
+ playlist_title = m_playlist.group('playlist_title')
+
+ playlist_entries = []
+ for m_video, m_name in zip(m_videos,m_names):
+ video_id=m_video.group('video_id')
+ talk_url='http://www.ted.com%s' % m_name.group('talk_url')
+ playlist_entries.append(self.url_result(talk_url, 'TED'))
+ return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
+
+ def _talk_info(self, url, video_id=0):
+ """Return the video for the talk in the url"""
+ m=re.match(self._VALID_URL, url,re.VERBOSE)
+ videoName=m.group('name')
+ webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
+ # If the url includes the language we get the title translated
+ title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
+ title=re.search(title_RE, webpage).group('title')
+ info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
+ "id":(?P<videoID>[\d]+).*?
+ "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
+ thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
+ thumb_match=re.search(thumb_RE,webpage)
+ info_match=re.search(info_RE,webpage,re.VERBOSE)
+ video_id=info_match.group('videoID')
+ mediaSlug=info_match.group('mediaSlug')
+ video_url=self._talk_video_link(mediaSlug)
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumb_match.group('thumbnail')
+ }
+ return info
+
+class MySpassIE(InfoExtractor):
+ _VALID_URL = r'http://www.myspass.de/.*'
+
+ def _real_extract(self, url):
+ META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+
+ # video id is the last path element of the URL
+ # usually there is a trailing slash, so also try the second but last
+ url_path = compat_urllib_parse_urlparse(url).path
+ url_parent_path, video_id = os.path.split(url_path)
+ if not video_id:
+ _, video_id = os.path.split(url_parent_path)
+
+ # get metadata
+ metadata_url = META_DATA_URL_TEMPLATE % video_id
+ metadata_text = self._download_webpage(metadata_url, video_id)
+ metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+
+ # extract values from metadata
+ url_flv_el = metadata.find('url_flv')
+ if url_flv_el is None:
+ raise ExtractorError(u'Unable to extract download url')
+ video_url = url_flv_el.text
+ extension = os.path.splitext(video_url)[1][1:]
+ title_el = metadata.find('title')
+ if title_el is None:
+ raise ExtractorError(u'Unable to extract title')
+ title = title_el.text
+ format_id_el = metadata.find('format_id')
+ if format_id_el is None:
+ format = ext
+ else:
+ format = format_id_el.text
+ description_el = metadata.find('description')
+ if description_el is not None:
+ description = description_el.text
+ else:
+ description = None
+ imagePreview_el = metadata.find('imagePreview')
+ if imagePreview_el is not None:
+ thumbnail = imagePreview_el.text
+ else:
+ thumbnail = None
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': thumbnail,
+ 'description': description
+ }
+ return [info]
+
+class SpiegelIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title')
+ video_title = unescapeHTML(m.group(1))
+
+ xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+ xml_code = self._download_webpage(xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
+
+ idoc = xml.etree.ElementTree.fromstring(xml_code)
+ last_type = idoc[-1]
+ filename = last_type.findall('./filename')[0].text
+ duration = float(last_type.findall('./duration')[0].text)
+
+ video_url = 'http://video2.spiegel.de/flash/' + filename
+ video_ext = filename.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': video_title,
+ 'duration': duration,
+ }
+ return [info]
+
+class LiveLeakIE(InfoExtractor):
+
+ _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ IE_NAME = u'liveleak'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'file: "(.*?)",', webpage)
+ if not m:
+ raise ExtractorError(u'Unable to find video url')
+ video_url = m.group(1)
+
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find video title')
+ title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ m = re.search(r'By:.*?(\w+)</a>', webpage)
+ if m:
+ uploader = clean_html(m.group(1))
+ else:
+ uploader = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ 'uploader': uploader
+ }
+
+ return [info]
+
+class ARDIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+ _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
+ _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+
+ def _real_extract(self, url):
+ # determine video id from url
+ m = re.match(self._VALID_URL, url)
+
+ numid = re.search(r'documentId=([0-9]+)', url)
+ if numid:
+ video_id = numid.group(1)
+ else:
+ video_id = m.group('video_id')
+
+ # determine title and media streams from webpage
+ html = self._download_webpage(url, video_id)
+ title = re.search(self._TITLE, html).group('title')
+ streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+ if not streams:
+ assert '"fsk"' in html
+ raise ExtractorError(u'This video is only available after 8:00 pm')
+
+ # choose default media type and highest quality for now
+ stream = max([s for s in streams if int(s["media_type"]) == 0],
+ key=lambda s: int(s["quality"]))
+
+ # there's two possibilities: RTMP stream or HTTP download
+ info = {'id': video_id, 'title': title, 'ext': 'mp4'}
+ if stream['rtmp_url']:
+ self.to_screen(u'RTMP download detected')
+ assert stream['video_url'].startswith('mp4:')
+ info["url"] = stream["rtmp_url"]
+ info["play_path"] = stream['video_url']
+ else:
+ assert stream["video_url"].endswith('.mp4')
+ info["url"] = stream["video_url"]
+ return [info]
+
+class TumblrIE(InfoExtractor):
+ _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
+
+ def _real_extract(self, url):
+ m_url = re.match(self._VALID_URL, url)
+ video_id = m_url.group('id')
+ blog = m_url.group('blog_name')
+
+ url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
+ webpage = self._download_webpage(url, video_id)
+
+ re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
+ video = re.search(re_video, webpage)
+ if video is None:
+ self.to_screen("No video founded")
+ return []
+ video_url = video.group('video_url')
+ ext = video.group('ext')
+
+ re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster
+ thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
+
+ # The only place where you can get a title, it's not complete,
+ # but searching in other places doesn't work for all videos
+ re_title = r'<title>(?P<title>.*?)</title>'
+ title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title'))
+
+ return [{'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'thumbnail': thumb,
+ 'ext': ext
+ }]
+
+class BandcampIE(InfoExtractor):
+ _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ # We get the link to the free download page
+ m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
+ if m_download is None:
+ raise ExtractorError(u'No free songs founded')
+
+ download_link = m_download.group(1)
+ id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
+ webpage, re.MULTILINE|re.DOTALL).group('id')
+
+ download_webpage = self._download_webpage(download_link, id,
+ 'Downloading free downloads page')
+ # We get the dictionary of the track from some javascrip code
+ info = re.search(r'items: (.*?),$',
+ download_webpage, re.MULTILINE).group(1)
+ info = json.loads(info)[0]
+ # We pick mp3-320 for now, until format selection can be easily implemented.
+ mp3_info = info[u'downloads'][u'mp3-320']
+ # If we try to use this url it says the link has expired
+ initial_url = mp3_info[u'url']
+ re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
+ m_url = re.match(re_url, initial_url)
+ #We build the url we will use to get the final track url
+ # This url is build in Bandcamp in the script download_bunde_*.js
+ request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
+ final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
+ # If we could correctly generate the .rand field the url would be
+ #in the "download_url" key
+ final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
+
+ track_info = {'id':id,
+ 'title' : info[u'title'],
+ 'ext' : 'mp3',
+ 'url' : final_url,
+ 'thumbnail' : info[u'thumb_url'],
+ 'uploader' : info[u'artist']
+ }
+
+ return [track_info]
+
+class RedTubeIE(InfoExtractor):
+ """Information Extractor for redtube"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ video_extension = 'mp4'
+ webpage = self._download_webpage(url, video_id)
+ self.report_extraction(video_id)
+ mobj = re.search(r'<source src="'+'(.+)'+'" type="video/mp4">',webpage)
+
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+
+ video_url = mobj.group(1)
+ mobj = re.search('<h1 class="videoTitle slidePanelMovable">(.+)</h1>',webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract title')
+ video_title = mobj.group(1)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+class InaIE(InfoExtractor):
+ """Information Extractor for Ina.fr"""
+ _VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
+ video_extension = 'mp4'
+ webpage = self._download_webpage(mrss_url, video_id)
+
+ mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+ video_url = mobj.group(1)
+
+ mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract title')
+ video_title = mobj.group(1)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+def gen_extractors():
+ """ Return a list of an instance of every supported extractor.
+ The order does matter; the first extractor matched is the one handling the URL.
+ """
+ return [
+ YoutubePlaylistIE(),
+ YoutubeChannelIE(),
+ YoutubeUserIE(),
+ YoutubeSearchIE(),
+ YoutubeIE(),
+ MetacafeIE(),
+ DailymotionIE(),
+ GoogleSearchIE(),
+ PhotobucketIE(),
+ YahooIE(),
+ YahooSearchIE(),
+ DepositFilesIE(),
+ FacebookIE(),
+ BlipTVUserIE(),
+ BlipTVIE(),
+ VimeoIE(),
+ MyVideoIE(),
+ ComedyCentralIE(),
+ EscapistIE(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudSetIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+ MixcloudIE(),
+ StanfordOpenClassroomIE(),
+ MTVIE(),
+ YoukuIE(),
+ XNXXIE(),
+ YouJizzIE(),
+ PornotubeIE(),
+ YouPornIE(),
+ GooglePlusIE(),
+ ArteTvIE(),
+ NBAIE(),
+ WorldStarHipHopIE(),
+ JustinTVIE(),
+ FunnyOrDieIE(),
+ SteamIE(),
+ UstreamIE(),
+ RBMARadioIE(),
+ EightTracksIE(),
+ KeekIE(),
+ TEDIE(),
+ MySpassIE(),
+ SpiegelIE(),
+ LiveLeakIE(),
+ ARDIE(),
+ TumblrIE(),
+ BandcampIE(),
+ RedTubeIE(),
+ InaIE(),
+ GenericIE()
+ ]
+
+def get_info_extractor(ie_name):
+ """Returns the info extractor class with the given ie_name"""
+ return globals()[ie_name+'IE']
one has an extra field called "filepath" that points to the
downloaded file.
- When this method returns None, the postprocessing chain is
- stopped. However, this method may return an information
- dictionary that will be passed to the next postprocessing
- object in the chain. It can be the one it received after
- changing some fields.
+ This method returns a tuple, the first element of which describes
+ whether the original file should be kept (i.e. not deleted - None for
+ no preference), and the second of which is the updated information.
In addition, this method may raise a PostProcessingError
- exception that will be taken into account by the downloader
- it was called from.
+ exception if post processing fails.
"""
- return information # by default, do nothing
+ return None, information # by default, keep file and do nothing
-class AudioConversionError(BaseException):
- def __init__(self, message):
- self.message = message
+class FFmpegPostProcessorError(PostProcessingError):
+ pass
-class FFmpegExtractAudioPP(PostProcessor):
- def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
+class AudioConversionError(PostProcessingError):
+ pass
+
+class FFmpegPostProcessor(PostProcessor):
+ def __init__(self,downloader=None):
PostProcessor.__init__(self, downloader)
- if preferredcodec is None:
- preferredcodec = 'best'
- self._preferredcodec = preferredcodec
- self._preferredquality = preferredquality
- self._keepvideo = keepvideo
self._exes = self.detect_executables()
@staticmethod
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
return dict((program, executable(program)) for program in programs)
+ def run_ffmpeg(self, path, out_path, opts):
+ if not self._exes['ffmpeg'] and not self._exes['avconv']:
+ raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
+ cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path)]
+ + opts +
+ [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+ p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ stdout,stderr = p.communicate()
+ if p.returncode != 0:
+ stderr = stderr.decode('utf-8', 'replace')
+ msg = stderr.strip().split('\n')[-1]
+ raise FFmpegPostProcessorError(msg)
+
+ def _ffmpeg_filename_argument(self, fn):
+ # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
+ if fn.startswith(u'-'):
+ return u'./' + fn
+ return fn
+
+class FFmpegExtractAudioPP(FFmpegPostProcessor):
+ def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, nopostoverwrites=False):
+ FFmpegPostProcessor.__init__(self, downloader)
+ if preferredcodec is None:
+ preferredcodec = 'best'
+ self._preferredcodec = preferredcodec
+ self._preferredquality = preferredquality
+ self._nopostoverwrites = nopostoverwrites
+
def get_audio_codec(self, path):
if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
try:
- cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)]
- handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
+ cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
+ handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
output = handle.communicate()[0]
if handle.wait() != 0:
return None
except (IOError, OSError):
return None
audio_codec = None
- for line in output.split('\n'):
+ for line in output.decode('ascii', 'ignore').split('\n'):
if line.startswith('codec_name='):
audio_codec = line.split('=')[1].strip()
elif line.strip() == 'codec_type=audio' and audio_codec is not None:
def run_ffmpeg(self, path, out_path, codec, more_opts):
if not self._exes['ffmpeg'] and not self._exes['avconv']:
- raise AudioConversionError('ffmpeg or avconv not found. Please install one.')
+ raise AudioConversionError('ffmpeg or avconv not found. Please install one.')
if codec is None:
acodec_opts = []
else:
acodec_opts = ['-acodec', codec]
- cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path), '-vn']
- + acodec_opts + more_opts +
- ['--', encodeFilename(out_path)])
- p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
- stdout,stderr = p.communicate()
- if p.returncode != 0:
- msg = stderr.strip().split('\n')[-1]
- raise AudioConversionError(msg)
+ opts = ['-vn'] + acodec_opts + more_opts
+ try:
+ FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
+ except FFmpegPostProcessorError as err:
+ raise AudioConversionError(err.message)
def run(self, information):
path = information['filepath']
filecodec = self.get_audio_codec(path)
if filecodec is None:
- self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
- return None
+ raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe')
more_opts = []
if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
- if self._preferredcodec == 'm4a' and filecodec == 'aac':
+ if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
# Lossless, but in another container
acodec = 'copy'
- extension = self._preferredcodec
+ extension = 'm4a'
more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
- elif filecodec in ['aac', 'mp3', 'vorbis']:
+ elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
# Lossless if possible
acodec = 'copy'
extension = filecodec
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
else:
# We convert the audio (lossy)
- acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+ acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
extension = self._preferredcodec
more_opts = []
if self._preferredquality is not None:
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
new_path = prefix + sep + extension
- self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+
+ # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
+ if new_path == path:
+ self._nopostoverwrites = True
+
try:
- self.run_ffmpeg(path, new_path, acodec, more_opts)
+ if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
+ self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
+ else:
+ self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+ self.run_ffmpeg(path, new_path, acodec, more_opts)
except:
etype,e,tb = sys.exc_info()
if isinstance(e, AudioConversionError):
- self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
+ msg = u'audio conversion failed: ' + e.message
else:
- self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg'))
- return None
+ msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
+ raise PostProcessingError(msg)
# Try to update the date time for extracted audio file.
if information.get('filetime') is not None:
except:
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
- if not self._keepvideo:
- try:
- os.remove(encodeFilename(path))
- except (IOError, OSError):
- self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
- return None
-
information['filepath'] = new_path
- return information
+ return self._nopostoverwrites,information
+
+class FFmpegVideoConvertor(FFmpegPostProcessor):
+ def __init__(self, downloader=None,preferedformat=None):
+ super(FFmpegVideoConvertor, self).__init__(downloader)
+ self._preferedformat=preferedformat
+
+ def run(self, information):
+ path = information['filepath']
+ prefix, sep, ext = path.rpartition(u'.')
+ outpath = prefix + sep + self._preferedformat
+ if information['ext'] == self._preferedformat:
+ self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
+ return True,information
+ self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath)
+ self.run_ffmpeg(path, outpath, [])
+ information['filepath'] = outpath
+ information['format'] = self._preferedformat
+ information['ext'] = self._preferedformat
+ return False,information
'shizeeg',
'Filippo Valsorda',
'Christian Albrecht',
+ 'Dave Vasilevsky',
+ 'Jaime Marquínez Ferrándiz',
+ 'Jeff Crouse',
+ 'Osama Khalid',
+ 'Michael Walter',
+ 'M. Yasoob Ullah Khalid',
+ 'Julien Fraichard',
+ 'Johny Mo Swag',
)
__license__ = 'Public Domain'
+import codecs
import getpass
import optparse
import os
import subprocess
import sys
import warnings
+import platform
from .utils import *
+from .update import update_self
from .version import __version__
from .FileDownloader import *
-from .InfoExtractors import *
+from .InfoExtractors import gen_extractors
from .PostProcessor import *
-def updateSelf(downloader, filename):
- """Update the program file with the latest version from the repository"""
-
- # TODO: at least, check https certificates
-
- from zipimport import zipimporter
-
- API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
- BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
- EXE_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl.exe"
-
- if hasattr(sys, "frozen"): # PY2EXE
- if not os.access(filename, os.W_OK):
- sys.exit('ERROR: no write permissions on %s' % filename)
-
- downloader.to_screen(u'Updating to latest version...')
-
- urla = compat_urllib_request.urlopen(API_URL)
- download = filter(lambda x: x["name"] == "youtube-dl.exe", json.loads(urla.read()))
- if not download:
- downloader.to_screen(u'ERROR: can\'t find the current version. Please try again later.')
- return
- newversion = download[0]["description"].strip()
- if newversion == __version__:
- downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
- return
- urla.close()
-
- exe = os.path.abspath(filename)
- directory = os.path.dirname(exe)
- if not os.access(directory, os.W_OK):
- sys.exit('ERROR: no write permissions on %s' % directory)
-
- try:
- urlh = compat_urllib_request.urlopen(EXE_URL)
- newcontent = urlh.read()
- urlh.close()
- with open(exe + '.new', 'wb') as outf:
- outf.write(newcontent)
- except (IOError, OSError) as err:
- sys.exit('ERROR: unable to download latest version')
-
- try:
- bat = os.path.join(directory, 'youtube-dl-updater.bat')
- b = open(bat, 'w')
- b.write("""
-echo Updating youtube-dl...
-ping 127.0.0.1 -n 5 -w 1000 > NUL
-move /Y "%s.new" "%s"
-del "%s"
- \n""" %(exe, exe, bat))
- b.close()
-
- os.startfile(bat)
- except (IOError, OSError) as err:
- sys.exit('ERROR: unable to overwrite current version')
-
- elif isinstance(globals().get('__loader__'), zipimporter): # UNIX ZIP
- if not os.access(filename, os.W_OK):
- sys.exit('ERROR: no write permissions on %s' % filename)
-
- downloader.to_screen(u'Updating to latest version...')
-
- urla = compat_urllib_request.urlopen(API_URL)
- download = [x for x in json.loads(urla.read().decode('utf8')) if x["name"] == "youtube-dl"]
- if not download:
- downloader.to_screen(u'ERROR: can\'t find the current version. Please try again later.')
- return
- newversion = download[0]["description"].strip()
- if newversion == __version__:
- downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
- return
- urla.close()
-
- try:
- urlh = compat_urllib_request.urlopen(BIN_URL)
- newcontent = urlh.read()
- urlh.close()
- except (IOError, OSError) as err:
- sys.exit('ERROR: unable to download latest version')
-
- try:
- with open(filename, 'wb') as outf:
- outf.write(newcontent)
- except (IOError, OSError) as err:
- sys.exit('ERROR: unable to overwrite current version')
-
- else:
- downloader.to_screen(u'It looks like you installed youtube-dl with pip or setup.py. Please use that to update.')
- return
-
- downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
-
-def parseOpts():
+def parseOpts(overrideArguments=None):
def _readOptions(filename_bytes):
try:
optionf = open(filename_bytes)
general.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
general.add_option('-r', '--rate-limit',
- dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+ dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
general.add_option('-R', '--retries',
dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
general.add_option('--buffer-size',
help='display the current browser identification', default=False)
general.add_option('--user-agent',
dest='user_agent', help='specify a custom user agent', metavar='UA')
+ general.add_option('--referer',
+ dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
+ metavar='REF', default=None)
general.add_option('--list-extractors',
action='store_true', dest='list_extractors',
help='List all supported extractors and the URLs they would handle', default=False)
+ general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+ general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
selection.add_option('--playlist-start',
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
+ selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
+ selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
+ selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
+ selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
+ selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
+
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
video_format.add_option('-f', '--format',
- action='store', dest='format', metavar='FORMAT', help='video format code')
+ action='store', dest='format', metavar='FORMAT',
+ help='video format code, specifiy the order of preference using slashes: "-f 22/17/18"')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='all')
video_format.add_option('--prefer-free-formats',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-F', '--list-formats',
action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
- video_format.add_option('--write-srt',
+ video_format.add_option('--write-sub', '--write-srt',
action='store_true', dest='writesubtitles',
- help='write video closed captions to a .srt file (currently youtube only)', default=False)
- video_format.add_option('--srt-lang',
+ help='write subtitle file (currently youtube only)', default=False)
+ video_format.add_option('--only-sub',
+ action='store_true', dest='skip_download',
+ help='[deprecated] alias of --skip-download', default=False)
+ video_format.add_option('--all-subs',
+ action='store_true', dest='allsubtitles',
+ help='downloads all the available subtitles of the video (currently youtube only)', default=False)
+ video_format.add_option('--list-subs',
+ action='store_true', dest='listsubtitles',
+ help='lists all available subtitles for the video (currently youtube only)', default=False)
+ video_format.add_option('--sub-format',
+ action='store', dest='subtitlesformat', metavar='LANG',
+ help='subtitle format [srt/sbv] (default=srt) (currently youtube only)', default='srt')
+ video_format.add_option('--sub-lang', '--srt-lang',
action='store', dest='subtitleslang', metavar='LANG',
- help='language of the closed captions to download (optional) use IETF language tags like \'en\'')
-
+ help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+ verbosity.add_option('--get-id',
+ action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
verbosity.add_option('--get-thumbnail',
action='store_true', dest='getthumbnail',
help='simulate, quiet but print thumbnail URL', default=False)
verbosity.add_option('--get-format',
action='store_true', dest='getformat',
help='simulate, quiet but print output format', default=False)
+ verbosity.add_option('--newline',
+ action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title',
help='display progress in console titlebar', default=False)
verbosity.add_option('-v', '--verbose',
action='store_true', dest='verbose', help='print various debugging information', default=False)
-
+ verbosity.add_option('--dump-intermediate-pages',
+ action='store_true', dest='dump_intermediate_pages', default=False,
+ help='print downloaded pages to debug problems(very verbose)')
filesystem.add_option('-t', '--title',
- action='store_true', dest='usetitle', help='use title in file name', default=False)
+ action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
filesystem.add_option('--id',
- action='store_true', dest='useid', help='use video ID in file name', default=False)
+ action='store_true', dest='useid', help='use only video ID in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
filesystem.add_option('-A', '--auto-number',
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')
+ dest='outtmpl', metavar='TEMPLATE',
+ help=('output filename template. Use %(title)s to get the title, '
+ '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
+ '%(autonumber)s to get an automatically incremented number, '
+ '%(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), '
+ '%(extractor)s for the provider (youtube, metacafe, etc), '
+ '%(id)s for the video id , %(playlist)s for the playlist the video is in, '
+ '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+ 'Use - to output to stdout. Can also be used to download to a different directory, '
+ 'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
+ filesystem.add_option('--autonumber-size',
+ dest='autonumber_size', metavar='NUMBER',
+ help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
filesystem.add_option('--write-info-json',
action='store_true', dest='writeinfojson',
help='write video metadata to a .info.json file', default=False)
+ filesystem.add_option('--write-thumbnail',
+ action='store_true', dest='writethumbnail',
+ help='write thumbnail image to disk', default=False)
postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
- help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
+ help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default')
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
+ postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
+ help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm)')
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
help='keeps the video file on disk after the post-processing; the video is erased by default')
+ postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
+ help='do not overwrite post-processed files; the post-processed files are overwritten by default')
parser.add_option_group(general)
parser.add_option_group(authentication)
parser.add_option_group(postproc)
- xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
- if xdg_config_home:
- userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
+ if overrideArguments is not None:
+ opts, args = parser.parse_args(overrideArguments)
+ if opts.verbose:
+ print(u'[debug] Override config: ' + repr(overrideArguments))
else:
- userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
- argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
- opts, args = parser.parse_args(argv)
+ xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+ if xdg_config_home:
+ userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
+ else:
+ userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+ systemConf = _readOptions('/etc/youtube-dl.conf')
+ userConf = _readOptions(userConfFile)
+ commandLineConf = sys.argv[1:]
+ argv = systemConf + userConf + commandLineConf
+ opts, args = parser.parse_args(argv)
+ if opts.verbose:
+ print(u'[debug] System config: ' + repr(systemConf))
+ print(u'[debug] User config: ' + repr(userConf))
+ print(u'[debug] Command-line args: ' + repr(commandLineConf))
return parser, opts, args
-def gen_extractors():
- """ Return a list of an instance of every supported extractor.
- The order does matter; the first extractor matched is the one handling the URL.
- """
- return [
- YoutubePlaylistIE(),
- YoutubeChannelIE(),
- YoutubeUserIE(),
- YoutubeSearchIE(),
- YoutubeIE(),
- MetacafeIE(),
- DailymotionIE(),
- GoogleIE(),
- GoogleSearchIE(),
- PhotobucketIE(),
- YahooIE(),
- YahooSearchIE(),
- DepositFilesIE(),
- FacebookIE(),
- BlipTVUserIE(),
- BlipTVIE(),
- VimeoIE(),
- MyVideoIE(),
- ComedyCentralIE(),
- EscapistIE(),
- CollegeHumorIE(),
- XVideosIE(),
- SoundcloudIE(),
- InfoQIE(),
- MixcloudIE(),
- StanfordOpenClassroomIE(),
- MTVIE(),
- YoukuIE(),
- XNXXIE(),
- GooglePlusIE(),
- ArteTvIE(),
- GenericIE()
- ]
-
-def _real_main():
- parser, opts, args = parseOpts()
+def _real_main(argv=None):
+ # Compatibility fixes for Windows
+ if sys.platform == 'win32':
+ # https://github.com/rg3/youtube-dl/issues/820
+ codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
+
+ parser, opts, args = parseOpts(argv)
# Open appropriate CookieJar
if opts.cookiefile is None:
else:
try:
jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile)
- if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+ if os.access(opts.cookiefile, os.R_OK):
jar.load()
except (IOError, OSError) as err:
- sys.exit(u'ERROR: unable to open cookie file')
+ if opts.verbose:
+ traceback.print_exc()
+ sys.stderr.write(u'ERROR: unable to open cookie file\n')
+ sys.exit(101)
# Set user agent
if opts.user_agent is not None:
std_headers['User-Agent'] = opts.user_agent
+
+ # Set referer
+ if opts.referer is not None:
+ std_headers['Referer'] = opts.referer
# Dump user agent
if opts.dump_user_agent:
# General configuration
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
- proxy_handler = compat_urllib_request.ProxyHandler()
- opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+ if opts.proxy:
+ proxies = {'http': opts.proxy, 'https': opts.proxy}
+ else:
+ proxies = compat_urllib_request.getproxies()
+ # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
+ if 'http' in proxies and 'https' not in proxies:
+ proxies['https'] = proxies['http']
+ proxy_handler = compat_urllib_request.ProxyHandler(proxies)
+ https_handler = make_HTTPS_handler(opts)
+ opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
if opts.list_extractors:
for ie in extractors:
print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
- matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
- all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+ matchedUrls = [url for url in all_urls if ie.suitable(url)]
+ all_urls = [url for url in all_urls if url not in matchedUrls]
for mu in matchedUrls:
print(u' ' + mu)
sys.exit(0)
if numeric_limit is None:
parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
+ if opts.min_filesize is not None:
+ numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
+ if numeric_limit is None:
+ parser.error(u'invalid min_filesize specified')
+ opts.min_filesize = numeric_limit
+ if opts.max_filesize is not None:
+ numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
+ if numeric_limit is None:
+ parser.error(u'invalid max_filesize specified')
+ opts.max_filesize = numeric_limit
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
except (TypeError, ValueError) as err:
parser.error(u'invalid playlist end number specified')
if opts.extractaudio:
- if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
+ if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error(u'invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit():
parser.error(u'invalid audio quality specified')
+ if opts.recodevideo is not None:
+ if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+ parser.error(u'invalid video recode format specified')
+ if opts.date is not None:
+ date = DateRange.day(opts.date)
+ else:
+ date = DateRange(opts.dateafter, opts.datebefore)
+
+ if sys.version_info < (3,):
+ # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
+ if opts.outtmpl is not None:
+ opts.outtmpl = opts.outtmpl.decode(preferredencoding())
+ outtmpl =((opts.outtmpl is not None and opts.outtmpl)
+ or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+ or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+ or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
+ or (opts.useid and u'%(id)s.%(ext)s')
+ or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
+ or u'%(title)s-%(id)s.%(ext)s')
# File downloader
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
- 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
+ 'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'simulate': opts.simulate,
- 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+ 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
- or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
- or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
- or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
- or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
- or (opts.useid and u'%(id)s.%(ext)s')
- or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
- or u'%(id)s.%(ext)s'),
+ 'outtmpl': outtmpl,
+ 'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
+ 'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'logtostderr': opts.outtmpl == '-',
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson,
+ 'writethumbnail': opts.writethumbnail,
'writesubtitles': opts.writesubtitles,
+ 'allsubtitles': opts.allsubtitles,
+ 'listsubtitles': opts.listsubtitles,
+ 'subtitlesformat': opts.subtitlesformat,
'subtitleslang': opts.subtitleslang,
- 'matchtitle': opts.matchtitle,
- 'rejecttitle': opts.rejecttitle,
+ 'matchtitle': decodeOption(opts.matchtitle),
+ 'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
'prefer_free_formats': opts.prefer_free_formats,
'verbose': opts.verbose,
+ 'dump_intermediate_pages': opts.dump_intermediate_pages,
'test': opts.test,
+ 'keepvideo': opts.keepvideo,
+ 'min_filesize': opts.min_filesize,
+ 'max_filesize': opts.max_filesize,
+ 'daterange': date,
})
if opts.verbose:
+ fd.to_screen(u'[debug] youtube-dl version ' + __version__)
+ try:
+ sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+ cwd=os.path.dirname(os.path.abspath(__file__)))
+ out, err = sp.communicate()
+ out = out.decode().strip()
+ if re.match('[0-9a-f]+', out):
+ fd.to_screen(u'[debug] Git HEAD: ' + out)
+ except:
+ pass
+ fd.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()))
fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
for extractor in extractors:
# PostProcessors
if opts.extractaudio:
- fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
+ fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
+ if opts.recodevideo:
+ fd.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
# Update version
if opts.update_self:
- updateSelf(fd, sys.argv[0])
+ update_self(fd.to_screen, opts.verbose, sys.argv[0])
# Maybe do nothing
if len(all_urls) < 1:
sys.exit(retcode)
-def main():
+def main(argv=None):
try:
- _real_main()
+ _real_main(argv)
except DownloadError:
sys.exit(1)
except SameFileError:
if __package__ is None and not hasattr(sys, "frozen"):
# direct call of __main__.py
import os.path
- sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+ path = os.path.realpath(os.path.abspath(__file__))
+ sys.path.append(os.path.dirname(os.path.dirname(path)))
import youtube_dl
--- /dev/null
+import json
+import traceback
+import hashlib
+from zipimport import zipimporter
+
+from .utils import *
+from .version import __version__
+
+def rsa_verify(message, signature, key):
+ from struct import pack
+ from hashlib import sha256
+ from sys import version_info
+ def b(x):
+ if version_info[0] == 2: return x
+ else: return x.encode('latin1')
+ assert(type(message) == type(b('')))
+ block_size = 0
+ n = key[0]
+ while n:
+ block_size += 1
+ n >>= 8
+ signature = pow(int(signature, 16), key[1], key[0])
+ raw_bytes = []
+ while signature:
+ raw_bytes.insert(0, pack("B", signature & 0xFF))
+ signature >>= 8
+ signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
+ if signature[0:2] != b('\x00\x01'): return False
+ signature = signature[2:]
+ if not b('\x00') in signature: return False
+ signature = signature[signature.index(b('\x00'))+1:]
+ if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
+ signature = signature[19:]
+ if signature != sha256(message).digest(): return False
+ return True
+
+def update_self(to_screen, verbose, filename):
+ """Update the program file with the latest version from the repository"""
+
+ UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
+ VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
+ JSON_URL = UPDATE_URL + 'versions.json'
+ UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
+
+
+ if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"):
+ to_screen(u'It looks like you installed youtube-dl with pip, setup.py or a tarball. Please use that to update.')
+ return
+
+ # Check if there is a new version
+ try:
+ newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip()
+ except:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: can\'t find the current version. Please try again later.')
+ return
+ if newversion == __version__:
+ to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
+ return
+
+ # Download and check versions info
+ try:
+ versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
+ versions_info = json.loads(versions_info)
+ except:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: can\'t obtain versions info. Please try again later.')
+ return
+ if not 'signature' in versions_info:
+ to_screen(u'ERROR: the versions file is not signed or corrupted. Aborting.')
+ return
+ signature = versions_info['signature']
+ del versions_info['signature']
+ if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
+ to_screen(u'ERROR: the versions file signature is invalid. Aborting.')
+ return
+
+ to_screen(u'Updating to version ' + versions_info['latest'] + '...')
+ version = versions_info['versions'][versions_info['latest']]
+
+ print_notes(to_screen, versions_info['versions'])
+
+ if not os.access(filename, os.W_OK):
+ to_screen(u'ERROR: no write permissions on %s' % filename)
+ return
+
+ # Py2EXE
+ if hasattr(sys, "frozen"):
+ exe = os.path.abspath(filename)
+ directory = os.path.dirname(exe)
+ if not os.access(directory, os.W_OK):
+ to_screen(u'ERROR: no write permissions on %s' % directory)
+ return
+
+ try:
+ urlh = compat_urllib_request.urlopen(version['exe'][0])
+ newcontent = urlh.read()
+ urlh.close()
+ except (IOError, OSError) as err:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: unable to download latest version')
+ return
+
+ newcontent_hash = hashlib.sha256(newcontent).hexdigest()
+ if newcontent_hash != version['exe'][1]:
+ to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
+ return
+
+ try:
+ with open(exe + '.new', 'wb') as outf:
+ outf.write(newcontent)
+ except (IOError, OSError) as err:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: unable to write the new version')
+ return
+
+ try:
+ bat = os.path.join(directory, 'youtube-dl-updater.bat')
+ b = open(bat, 'w')
+ b.write("""
+echo Updating youtube-dl...
+ping 127.0.0.1 -n 5 -w 1000 > NUL
+move /Y "%s.new" "%s"
+del "%s"
+ \n""" %(exe, exe, bat))
+ b.close()
+
+ os.startfile(bat)
+ except (IOError, OSError) as err:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: unable to overwrite current version')
+ return
+
+ # Zip unix package
+ elif isinstance(globals().get('__loader__'), zipimporter):
+ try:
+ urlh = compat_urllib_request.urlopen(version['bin'][0])
+ newcontent = urlh.read()
+ urlh.close()
+ except (IOError, OSError) as err:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: unable to download latest version')
+ return
+
+ newcontent_hash = hashlib.sha256(newcontent).hexdigest()
+ if newcontent_hash != version['bin'][1]:
+ to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
+ return
+
+ try:
+ with open(filename, 'wb') as outf:
+ outf.write(newcontent)
+ except (IOError, OSError) as err:
+ if verbose: to_screen(compat_str(traceback.format_exc()))
+ to_screen(u'ERROR: unable to overwrite current version')
+ return
+
+ to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
+
+def get_notes(versions, fromVersion):
+ notes = []
+ for v,vdata in sorted(versions.items()):
+ if v > fromVersion:
+ notes.extend(vdata.get('notes', []))
+ return notes
+
+def print_notes(to_screen, versions, fromVersion=__version__):
+ notes = get_notes(versions, fromVersion)
+ if notes:
+ to_screen(u'PLEASE NOTE:')
+ for note in notes:
+ to_screen(note)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
+import errno
import gzip
import io
+import json
import locale
import os
import re
import sys
+import traceback
import zlib
import email.utils
import json
+import datetime
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
import httplib as compat_http_client
+try:
+ from subprocess import DEVNULL
+ compat_subprocess_get_DEVNULL = lambda: DEVNULL
+except ImportError:
+ compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+
try:
from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
+
def preferredencoding():
"""Get preferred encoding.
assert type(s) == type(u'')
print(s)
+# In Python 2.x, json.dump expects a bytestream.
+# In Python 3.x, it writes to a character stream
+if sys.version_info < (3,0):
+ def write_json_file(obj, fn):
+ with open(fn, 'wb') as f:
+ json.dump(obj, f)
+else:
+ def write_json_file(obj, fn):
+ with open(fn, 'w', encoding='utf-8') as f:
+ json.dump(obj, f)
+
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a character.
return (u'&%s;' % entity)
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class IDParser(compat_html_parser.HTMLParser):
- """Modified HTMLParser that isolates a tag with the specified id"""
- def __init__(self, id):
- self.id = id
+class AttrParser(compat_html_parser.HTMLParser):
+ """Modified HTMLParser that isolates a tag with the specified attribute"""
+ def __init__(self, attribute, value):
+ self.attribute = attribute
+ self.value = value
self.result = None
self.started = False
self.depth = {}
attrs = dict(attrs)
if self.started:
self.find_startpos(None)
- if 'id' in attrs and attrs['id'] == self.id:
+ if self.attribute in attrs and attrs[self.attribute] == self.value:
self.result = [tag]
self.started = True
self.watch_startpos = True
lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
lines[-1] = lines[-1][:self.result[2][1]]
return '\n'.join(lines).strip()
+# Hack for https://github.com/rg3/youtube-dl/issues/662
+if sys.version_info < (2, 7, 3):
+ AttrParser.parse_endtag = (lambda self, i:
+ i + len("</scr'+'ipt>")
+ if self.rawdata[i:].startswith("</scr'+'ipt>")
+ else compat_html_parser.HTMLParser.parse_endtag(self, i))
def get_element_by_id(id, html):
- """Return the content of the tag with the specified id in the passed HTML document"""
- parser = IDParser(id)
+ """Return the content of the tag with the specified ID in the passed HTML document"""
+ return get_element_by_attribute("id", id, html)
+
+def get_element_by_attribute(attribute, value, html):
+ """Return the content of the tag with the specified attribute in the passed HTML document"""
+ parser = AttrParser(attribute, value)
try:
parser.loads(html)
except compat_html_parser.HTMLParseError:
"""Clean an HTML snippet into a readable string"""
# Newline vs <br />
html = html.replace('\n', ' ')
- html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
+ html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
+ html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
html = unescapeHTML(html)
- return html
+ return html.strip()
def sanitize_open(filename, open_mode):
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
- return (sys.stdout, filename)
+ return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError) as err:
- # In case of error, try to remove win32 forbidden chars
- filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
+ if err.errno in (errno.EACCES,):
+ raise
- # An exception here should be caught in the caller
- stream = open(encodeFilename(filename), open_mode)
- return (stream, filename)
+ # In case of error, try to remove win32 forbidden chars
+ alt_filename = os.path.join(
+ re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
+ for path_part in os.path.split(filename)
+ )
+ if alt_filename == filename:
+ raise
+ else:
+ # An exception here should be caught in the caller
+ stream = open(encodeFilename(filename), open_mode)
+ return (stream, alt_filename)
def timeconvert(timestr):
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
return s
else:
- return s.encode(sys.getfilesystemencoding(), 'ignore')
+ encoding = sys.getfilesystemencoding()
+ if encoding is None:
+ encoding = 'utf-8'
+ return s.encode(encoding, 'ignore')
+
+def decodeOption(optval):
+ if optval is None:
+ return optval
+ if isinstance(optval, bytes):
+ optval = optval.decode(preferredencoding())
+
+ assert isinstance(optval, compat_str)
+ return optval
+
+def formatSeconds(secs):
+ if secs > 3600:
+ return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
+ elif secs > 60:
+ return '%d:%02d' % (secs // 60, secs % 60)
+ else:
+ return '%d' % secs
+
+def make_HTTPS_handler(opts):
+ if sys.version_info < (3,2):
+ # Python's 2.x handler is very simplistic
+ return compat_urllib_request.HTTPSHandler()
+ else:
+ import ssl
+ context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
+ context.set_default_verify_paths()
+
+ context.verify_mode = (ssl.CERT_NONE
+ if opts.no_check_certificate
+ else ssl.CERT_REQUIRED)
+ return compat_urllib_request.HTTPSHandler(context=context)
+
+class ExtractorError(Exception):
+ """Error during info extraction."""
+ def __init__(self, msg, tb=None):
+ """ tb, if given, is the original traceback (so that it can be printed out). """
+ super(ExtractorError, self).__init__(msg)
+ self.traceback = tb
+ self.exc_info = sys.exc_info() # preserve original exception
+
+ def format_traceback(self):
+ if self.traceback is None:
+ return None
+ return u''.join(traceback.format_tb(self.traceback))
+
class DownloadError(Exception):
"""Download Error exception.
configured to continue on errors. They will contain the appropriate
error message.
"""
- pass
+ def __init__(self, msg, exc_info=None):
+ """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
+ super(DownloadError, self).__init__(msg)
+ self.exc_info = exc_info
class SameFileError(Exception):
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
- pass
+ def __init__(self, msg):
+ self.msg = msg
class MaxDownloadsReached(Exception):
""" --max-downloads limit has been reached. """
self.downloaded = downloaded
self.expected = expected
-
-class Trouble(Exception):
- """Trouble helper exception
-
- This is an exception to be handled with
- FileDownloader.trouble
- """
-
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
"""Handler for HTTP requests and responses.
return ret
def http_request(self, req):
- for h in std_headers:
+ for h,v in std_headers.items():
if h in req.headers:
del req.headers[h]
- req.add_header(h, std_headers[h])
+ req.add_header(h, v)
if 'Youtubedl-no-compression' in req.headers:
if 'Accept-encoding' in req.headers:
del req.headers['Accept-encoding']
del req.headers['Youtubedl-no-compression']
+ if 'Youtubedl-user-agent' in req.headers:
+ if 'User-agent' in req.headers:
+ del req.headers['User-agent']
+ req.headers['User-agent'] = req.headers['Youtubedl-user-agent']
+ del req.headers['Youtubedl-user-agent']
return req
def http_response(self, req, resp):
https_request = http_request
https_response = http_response
+
+def unified_strdate(date_str):
+ """Return a string with the date in the format YYYYMMDD"""
+ upload_date = None
+ #Replace commas
+ date_str = date_str.replace(',',' ')
+ # %z (UTC offset) is only supported in python>=3.2
+ date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
+ format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S']
+ for expression in format_expressions:
+ try:
+ upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
+ except:
+ pass
+ return upload_date
+
+def date_from_str(date_str):
+ """
+ Return a datetime object from a string in the format YYYYMMDD or
+ (now|today)[+-][0-9](day|week|month|year)(s)?"""
+ today = datetime.date.today()
+ if date_str == 'now'or date_str == 'today':
+ return today
+ match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
+ if match is not None:
+ sign = match.group('sign')
+ time = int(match.group('time'))
+ if sign == '-':
+ time = -time
+ unit = match.group('unit')
+ #A bad aproximation?
+ if unit == 'month':
+ unit = 'day'
+ time *= 30
+ elif unit == 'year':
+ unit = 'day'
+ time *= 365
+ unit += 's'
+ delta = datetime.timedelta(**{unit: time})
+ return today + delta
+ return datetime.datetime.strptime(date_str, "%Y%m%d").date()
+
+class DateRange(object):
+ """Represents a time interval between two dates"""
+ def __init__(self, start=None, end=None):
+ """start and end must be strings in the format accepted by date"""
+ if start is not None:
+ self.start = date_from_str(start)
+ else:
+ self.start = datetime.datetime.min.date()
+ if end is not None:
+ self.end = date_from_str(end)
+ else:
+ self.end = datetime.datetime.max.date()
+ if self.start > self.end:
+ raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
+ @classmethod
+ def day(cls, day):
+ """Returns a range that only contains the given day"""
+ return cls(day,day)
+ def __contains__(self, date):
+ """Check if the date is in the range"""
+ if not isinstance(date, datetime.date):
+ date = date_from_str(date)
+ return self.start <= date <= self.end
+ def __str__(self):
+ return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
-__version__ = '2012.12.11'
+__version__ = '2013.05.14'
Rapsys Git / youtubedl / commitdiff