release 2013.06.23

(YouTube Subtitles are currently flaky in Germany, especially via IPv6)

.gitignore

@@ -1,3 +1,20 @@
 *.pyc
 *.pyo
 *~
+*.DS_Store
+wine-py2exe/
+py2exe.log
+*.kate-swp
+build/
+dist/
+MANIFEST
+README.txt
+youtube-dl.1
+youtube-dl.bash-completion
+youtube-dl
+youtube-dl.exe
+youtube-dl.tar.gz
+.coverage
+cover/
+updates_key.pem
+*.egg-info

.travis.yml

@@ -0,0 +1,15 @@
+language: python
+python:
+  - "2.6"
+  - "2.7"
+  - "3.3"
+script: nosetests test --verbose
+notifications:
+  email:
+    - filippo.valsorda@gmail.com
+    - phihag@phihag.de
+    - jaime.marquinez.ferrandiz+travis@gmail.com
+#  irc:
+#    channels:
+#      - "irc.freenode.org#youtube-dl"
+#    skip_join: true

CHANGELOG

@@ -0,0 +1,14 @@
+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

LATEST_VERSION

@@ -1 +1 @@
-2012.02.26
+2012.12.99

LICENSE

@@ -0,0 +1,24 @@
+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/>

MANIFEST.in

@@ -0,0 +1,5 @@
+include README.md
+include test/*.py
+include test/*.json
+include youtube-dl.bash-completion
+include youtube-dl.1

Makefile

@@ -1,23 +1,78 @@
-default: update
+all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
 
-update: compile update-readme update-latest
+clean:
+	rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
 
-update-latest:
-	./youtube-dl.dev --version > LATEST_VERSION
+cleanall: clean
+	rm -f youtube-dl youtube-dl.exe
 
-update-readme:
-	@options=$$(COLUMNS=80 ./youtube-dl.dev --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/### \1/') && \
-		header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \
-		footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \
-		echo "$${header}" > README.md && \
-		echo >> README.md && \
-		echo '## OPTIONS' >> README.md && \
-		echo "$${options}" >> README.md&& \
-		echo >> README.md && \
-		echo '## FAQ' >> README.md && \
-		echo "$${footer}" >> README.md
+PREFIX=/usr/local
+BINDIR=$(PREFIX)/bin
+MANDIR=$(PREFIX)/man
+PYTHON=/usr/bin/env python
 
-compile:
-	cp youtube_dl/__init__.py youtube-dl
+# 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
 
-.PHONY: default compile update update-latest update-readme
+install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
+	install -d $(DESTDIR)$(BINDIR)
+	install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
+	install -d $(DESTDIR)$(MANDIR)/man1
+	install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
+	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
+	install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
+
+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 tar bash-completion pypi-files
+
+pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
+
+youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
+	zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
+	zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
+	echo '#!$(PYTHON)' > youtube-dl
+	cat youtube-dl.zip >> youtube-dl
+	rm youtube-dl.zip
+	chmod a+x youtube-dl
+
+README.md: youtube_dl/*.py youtube_dl/*/*.py
+	COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
+
+README.txt: README.md
+	pandoc -f markdown -t plain README.md -o README.txt
+
+youtube-dl.1: README.md
+	pandoc -s -f markdown -t man README.md -o youtube-dl.1
+
+youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
+	python devscripts/bash-completion.py
+
+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

README.md

@@ -1,96 +1,193 @@
-# youtube-dl
+% YOUTUBE-DL(1)
 
-## USAGE
-youtube-dl [options] url [url...]
+# NAME
+youtube-dl - download videos from youtube.com or other video platforms
 
-## DESCRIPTION
+# 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 5), 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)
-    --dump-user-agent        display the current browser identification
-    --list-extractors        List all supported extractors and the URLs they
-                             would handle
+# 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     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
+## 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
+    --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
-    -l, --literal            use literal title in file name
-    -A, --auto-number        number downloaded files starting from 00000
-    -o, --output TEMPLATE    output filename template. Use %(stitle)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), and
-                             %% for a literal percent. Use - to output to
-                             stdout.
-    -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
+## Filesystem Options:
+    -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
+## 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-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)
+## Video Format Options:
+    -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 FORMAT        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
+## Authentication Options:
+    -u, --username USERNAME    account username
+    -p, --password PASSWORD    account password
+    -n, --netrc                use .netrc authentication data
 
-### Post-processing Options:
-    --extract-audio          convert video files to audio-only files (requires
-                             ffmpeg and ffprobe)
-    --audio-format FORMAT    "best", "aac", "vorbis", "mp3", "m4a", or "wav";
-                             best by default
-    --audio-quality QUALITY  ffmpeg audio bitrate specification, 128k by default
-    -k, --keep-video         keeps the video file on disk after the post-
-                             processing; the video is erased by default
+## 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", "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
 
-## FAQ
+# 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 `~/.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.
+ - `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).
+
+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
+
+# 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?
 
@@ -106,25 +203,49 @@ Once the video is fully downloaded, use any video player, such as [vlc](http://w
 
 ### 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.
+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`.
 
-## COPYRIGHT
+### 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](http://www.microsoft.com/en-us/download/details.aspx?id=29).
+
+# 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
 
 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.
+* 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).
+
+For discussions, join us in the irc channel #youtube-dl on freenode.

bin/youtube-dl

@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+
+import youtube_dl
+
+if __name__ == '__main__':
+    youtube_dl.main()

devscripts/bash-completion.in

@@ -0,0 +1,14 @@
+__youtube-dl()
+{
+    local cur prev opts
+    COMPREPLY=()
+    cur="${COMP_WORDS[COMP_CWORD]}"
+    opts="{{flags}}"
+
+    if [[ ${cur} == * ]] ; then
+        COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
+        return 0
+    fi
+}
+
+complete -F __youtube-dl youtube-dl

devscripts/bash-completion.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python
+import os
+from os.path import dirname as dirn
+import sys
+
+sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
+import youtube_dl
+
+BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
+BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
+
+def build_completion(opt_parser):
+    opts_flag = []
+    for group in opt_parser.option_groups:
+        for option in group.option_list:
+            #for every long flag
+            opts_flag.append(option.get_opt_string())
+    with open(BASH_COMPLETION_TEMPLATE) as f:
+        template = f.read()
+    with open(BASH_COMPLETION_FILE, "w") as f:
+        #just using the special char
+        filled_template = template.replace("{{flags}}", " ".join(opts_flag))
+        f.write(filled_template)
+
+parser = youtube_dl.parseOpts()[0]
+build_completion(parser)

devscripts/gh-pages/add-version.py

@@ -0,0 +1,33 @@
+#!/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)

devscripts/gh-pages/generate-download.py

@@ -0,0 +1,32 @@
+#!/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)

devscripts/gh-pages/sign-versions.py

@@ -0,0 +1,32 @@
+#!/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)

devscripts/gh-pages/update-copyright.py

@@ -0,0 +1,21 @@
+#!/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)

devscripts/gh-pages/update-feed.py

@@ -0,0 +1,57 @@
+#!/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)
+
+

devscripts/make_readme.py

@@ -0,0 +1,20 @@
+import sys
+import re
+
+README_FILE = 'README.md'
+helptext = sys.stdin.read()
+
+with open(README_FILE) as f:
+    oldreadme = f.read()
+
+header = oldreadme[:oldreadme.index('# OPTIONS')]
+footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
+
+options = helptext[helptext.index('  General Options:')+19:]
+options = re.sub(r'^  (\w.+)$', r'## \1', options, flags=re.M)
+options = '# OPTIONS\n' + options + '\n'
+
+with open(README_FILE, 'w') as f:
+    f.write(header)
+    f.write(options)
+    f.write(footer)

devscripts/release.sh

@@ -0,0 +1,100 @@
+#!/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
+
+skip_test=false
+if [ "$2" == '--skip-test' ]; then
+    skip_test=true
+fi
+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 | 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
+if $skip_tests; then
+    echo 'SKIPPING TESTS'
+else
+    nosetests --verbose --with-coverage --cover-package=youtube_dl --cover-html test --stop || exit 1
+fi
+
+/bin/echo -e "\n### Changing version in version.py..."
+sed -i "s/__version__ = '.*'/__version__ = '$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"
+
+/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!"

devscripts/transition_helper.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+
+import sys, os
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+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')
+
+try:
+	raw_input()
+except NameError: # Python 3
+	input()
+
+filename = sys.argv[0]
+
+API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
+BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
+
+if not os.access(filename, os.W_OK):
+    sys.exit('ERROR: no write permissions on %s' % filename)
+
+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')
+
+sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

devscripts/transition_helper_exe/setup.py

@@ -0,0 +1,12 @@
+from distutils.core import setup
+import py2exe
+
+py2exe_options = {
+    "bundle_files": 1,
+    "compressed": 1,
+    "optimize": 2,
+    "dist_dir": '.',
+    "dll_excludes": ['w9xpopen.exe']
+}
+
+setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)

devscripts/transition_helper_exe/youtube-dl.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python
+
+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'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]
+
+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)
+
+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:
+    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(u'ERROR: unable to write the new 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')
+
+sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

devscripts/wine-py2exe.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+# Run with as parameter a setup.py that works in the current directory
+# e.g. no os.chdir()
+# It will run twice, the first time will crash
+
+set -e
+
+SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"
+
+if [ ! -d wine-py2exe ]; then
+
+    sudo apt-get install wine1.3 axel bsdiff
+
+    mkdir wine-py2exe
+    cd wine-py2exe
+    export WINEPREFIX=`pwd`
+
+    axel -a "http://www.python.org/ftp/python/2.7/python-2.7.msi"
+    axel -a "http://downloads.sourceforge.net/project/py2exe/py2exe/0.6.9/py2exe-0.6.9.win32-py2.7.exe"
+    #axel -a "http://winetricks.org/winetricks"
+
+    # http://appdb.winehq.org/objectManager.php?sClass=version&iId=21957
+    echo "Follow python setup on screen"
+    wine msiexec /i python-2.7.msi
+    
+    echo "Follow py2exe setup on screen"
+    wine py2exe-0.6.9.win32-py2.7.exe
+    
+    #echo "Follow Microsoft Visual C++ 2008 Redistributable Package setup on screen"
+    #bash winetricks vcrun2008
+
+    rm py2exe-0.6.9.win32-py2.7.exe
+    rm python-2.7.msi
+    #rm winetricks
+    
+    # http://bugs.winehq.org/show_bug.cgi?id=3591
+    
+    mv drive_c/Python27/Lib/site-packages/py2exe/run.exe drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup
+    bspatch drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run.exe "$SCRIPT_DIR/SizeOfImage.patch"
+    mv drive_c/Python27/Lib/site-packages/py2exe/run_w.exe drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup
+    bspatch drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run_w.exe "$SCRIPT_DIR/SizeOfImage_w.patch"
+
+    cd -
+    
+else
+
+    export WINEPREFIX="$( cd wine-py2exe && pwd )"
+
+fi
+
+wine "C:\\Python27\\python.exe" "$1" py2exe > "py2exe.log" 2>&1 || true
+echo '# Copying python27.dll' >> "py2exe.log"
+cp "$WINEPREFIX/drive_c/windows/system32/python27.dll" build/bdist.win32/winexe/bundle-2.7/
+wine "C:\\Python27\\python.exe" "$1" py2exe >> "py2exe.log" 2>&1
+

setup.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import print_function
+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"""
+except ImportError:
+    if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
+        print("Cannot import py2exe", file=sys.stderr)
+        exit(1)
+
+py2exe_options = {
+    "bundle_files": 1,
+    "compressed": 1,
+    "optimize": 2,
+    "dist_dir": '.',
+    "dll_excludes": ['w9xpopen.exe']
+}
+py2exe_console = [{
+    "script": "./youtube_dl/__main__.py",
+    "dest_base": "youtube-dl",
+}]
+py2exe_params = {
+    'console': py2exe_console,
+    'options': { "py2exe": py2exe_options },
+    'zipfile': None
+}
+
+if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
+    params = py2exe_params
+else:
+    params = {
+        'scripts': ['bin/youtube-dl'],
+        'data_files': [('etc/bash_completion.d', ['youtube-dl.bash-completion']), # Installing system-wide would require sudo...
+                       ('share/doc/youtube_dl', ['README.txt']),
+                       ('share/man/man1/', ['youtube-dl.1'])]
+    }
+
+# Get the version from youtube_dl/version.py without importing the package
+exec(compile(open('youtube_dl/version.py').read(), 'youtube_dl/version.py', 'exec'))
+
+setup(
+    name = 'youtube_dl',
+    version = __version__,
+    description = 'YouTube video downloader',
+    long_description = 'Small command-line program to download videos from YouTube.com and other video sites.',
+    url = 'https://github.com/rg3/youtube-dl',
+    author = 'Ricardo Garcia',
+    maintainer = 'Philipp Hagemeister',
+    maintainer_email = 'phihag@phihag.de',
+    packages = ['youtube_dl'],
+
+    # Provokes warning on most systems (why?!)
+    #test_suite = 'nose.collector',
+    #test_requires = ['nosetest'],
+
+    classifiers = [
+        "Topic :: Multimedia :: Video",
+        "Development Status :: 5 - Production/Stable",
+        "Environment :: Console",
+        "License :: Public Domain",
+        "Programming Language :: Python :: 2.6",
+        "Programming Language :: Python :: 2.7",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.3"
+    ],
+
+    **params
+)

test/parameters.json

@@ -0,0 +1,44 @@
+{
+    "consoletitle": false, 
+    "continuedl": true, 
+    "forcedescription": false, 
+    "forcefilename": false, 
+    "forceformat": false, 
+    "forcethumbnail": false, 
+    "forcetitle": false, 
+    "forceurl": false, 
+    "format": null, 
+    "format_limit": null, 
+    "ignoreerrors": false, 
+    "listformats": null, 
+    "logtostderr": false, 
+    "matchtitle": null, 
+    "max_downloads": null, 
+    "nooverwrites": false, 
+    "nopart": false, 
+    "noprogress": false, 
+    "outtmpl": "%(id)s.%(ext)s", 
+    "password": null, 
+    "playlistend": -1, 
+    "playliststart": 1, 
+    "prefer_free_formats": false, 
+    "quiet": false, 
+    "ratelimit": null, 
+    "rejecttitle": null, 
+    "retries": 10, 
+    "simulate": false, 
+    "skip_download": false, 
+    "subtitleslang": null, 
+    "subtitlesformat": "srt",
+    "test": true, 
+    "updatetime": true, 
+    "usenetrc": false, 
+    "username": null, 
+    "verbose": true, 
+    "writedescription": false, 
+    "writeinfojson": true, 
+    "writesubtitles": false,
+    "onlysubtitles": false,
+    "allsubtitles": false,
+    "listssubtitles": false
+}

test/test_all_urls.py

@@ -0,0 +1,54 @@
+#!/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.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE
+
+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_justin_tv_channelid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
+
+    def test_justintv_videoid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
+
+    def test_justin_tv_chapterid_matching(self):
+        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
+
+    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()

test/test_div.py

@@ -1,29 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Various small unit tests
-
-import os,sys
-sys.path.append(os.path.dirname(os.path.dirname(__file__)))
-
-import youtube_dl
-
-def test_simplify_title():
-	assert youtube_dl._simplify_title(u'abc') == u'abc'
-	assert youtube_dl._simplify_title(u'abc_d-e') == u'abc_d-e'
-
-	assert youtube_dl._simplify_title(u'123') == u'123'
-
-	assert u'/' not in youtube_dl._simplify_title(u'abc/de')
-	assert u'abc' in youtube_dl._simplify_title(u'abc/de')
-	assert u'de' in youtube_dl._simplify_title(u'abc/de')
-	assert u'/' not in youtube_dl._simplify_title(u'abc/de///')
-
-	assert u'\\' not in youtube_dl._simplify_title(u'abc\\de')
-	assert u'abc' in youtube_dl._simplify_title(u'abc\\de')
-	assert u'de' in youtube_dl._simplify_title(u'abc\\de')
-
-	assert youtube_dl._simplify_title(u'ä') == u'ä'
-	assert youtube_dl._simplify_title(u'кириллица') == u'кириллица'
-
-	# Strip underlines
-	assert youtube_dl._simplify_title(u'\'a_') == u'a'

test/test_download.py

@@ -0,0 +1,164 @@
+#!/usr/bin/env python
+
+import errno
+import hashlib
+import io
+import os
+import json
+import unittest
+import sys
+import socket
+import binascii
+
+# Allow direct execution
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import youtube_dl.FileDownloader
+import youtube_dl.extractor
+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(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
+
+md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+class FileDownloader(youtube_dl.FileDownloader):
+    def __init__(self, *args, **kwargs):
+        self.to_stderr = self.to_screen
+        self.processed_info_dicts = []
+        return youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
+    def report_warning(self, message):
+        # Don't accept warnings during tests
+        raise ExtractorError(message)
+    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()
+
+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)
+
+
+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.extractor.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', {}))
+
+        fd = FileDownloader(params)
+        for ie in youtube_dl.extractor.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, expected) in tc.get('info_dict', {}).items():
+                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                        self.assertEqual(expected, 'md5:' + md5(info_dict.get(info_field)))
+                    else:
+                        got = info_dict.get(info_field)
+                        self.assertEqual(
+                            expected, got,
+                            u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+
+                # If checkable fields are missing from the test case, print the info_dict
+                test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
+                    for key, value in info_dict.items()
+                    if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
+                if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
+                    sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n')
+
+                # Check for the presence of mandatory fields
+                for key in ('id', 'url', 'title', 'ext'):
+                    self.assertTrue(key in info_dict.keys() and info_dict[key])
+        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__':
+    unittest.main()

test/test_execution.py

@@ -0,0 +1,26 @@
+import unittest
+
+import sys
+import os
+import subprocess
+
+rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+try:
+    _DEV_NULL = subprocess.DEVNULL
+except AttributeError:
+    _DEV_NULL = open(os.devnull, 'wb')
+
+class TestExecution(unittest.TestCase):
+    def test_import(self):
+        subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
+
+    def test_module_exec(self):
+        if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution
+            subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+
+    def test_main_exec(self):
+        subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python
+
+# Various small unit tests
+
+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.utils import htmlentity_transform
+from youtube_dl.utils import timeconvert
+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')
+else:
+    _compat_str = lambda s: s
+
+
+class TestUtil(unittest.TestCase):
+    def test_timeconvert(self):
+        self.assertTrue(timeconvert('') is None)
+        self.assertTrue(timeconvert('bougrg') is None)
+
+    def test_sanitize_filename(self):
+        self.assertEqual(sanitize_filename('abc'), 'abc')
+        self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
+
+        self.assertEqual(sanitize_filename('123'), '123')
+
+        self.assertEqual('abc_de', sanitize_filename('abc/de'))
+        self.assertFalse('/' in sanitize_filename('abc/de///'))
+
+        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
+        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
+        self.assertEqual('yes no', sanitize_filename('yes? no'))
+        self.assertEqual('this - that', sanitize_filename('this: that'))
+
+        self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
+        aumlaut = _compat_str('\xe4')
+        self.assertEqual(sanitize_filename(aumlaut), aumlaut)
+        tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
+        self.assertEqual(sanitize_filename(tests), tests)
+
+        forbidden = '"\0\\/'
+        for fc in forbidden:
+            for fbc in forbidden:
+                self.assertTrue(fbc not in sanitize_filename(fc))
+
+    def test_sanitize_filename_restricted(self):
+        self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
+        self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
+
+        self.assertEqual(sanitize_filename('123', restricted=True), '123')
+
+        self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
+        self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
+
+        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
+        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
+        self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
+        self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
+
+        tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
+        self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
+        self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
+
+        forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
+        for fc in forbidden:
+            for fbc in forbidden:
+                self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
+
+        # Handle a common case more neatly
+        self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
+        self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
+        # .. but make sure the file name is never empty
+        self.assertTrue(sanitize_filename('-', restricted=True) != '')
+        self.assertTrue(sanitize_filename(':', restricted=True) != '')
+
+    def test_sanitize_ids(self):
+        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])
+        self.assertEqual(orderedSet([]), [])
+        self.assertEqual(orderedSet([1]), [1])
+        #keep the list ordered
+        self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
+
+    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()

test/test_write_info_json.py

@@ -0,0 +1,77 @@
+#!/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.extractor
+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.extractor.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()

test/test_youtube_lists.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python
+
+import sys
+import unittest
+import json
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor 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()
+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 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)
+        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.assertTrue(len(result['entries']) > 25)
+
+    def test_youtube_playlist_long(self):
+        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)
+        # TODO find a > 100 (paginating?) videos course
+        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):
+        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 = YoutubeUserIE(dl)
+        result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0]
+        self.assertTrue(len(result['entries']) >= 320)
+
+    def test_youtube_safe_search(self):
+        dl = FakeDownloader()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0]
+        self.assertEqual(len(result['entries']), 2)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_subtitles.py

@@ -0,0 +1,111 @@
+#!/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.extractor 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 = []
+        # Different instances of the downloader can't share the same dictionary
+        # some test set the "sublang" parameter, which would break the md5 checks.
+        self.params = dict(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)
+    def test_youtube_automatic_captions(self):
+        DL = FakeDownloader()
+        DL.params['writesubtitles'] = True
+        DL.params['subtitleslang'] = 'it'
+        IE = YoutubeIE(DL)
+        info_dict = IE.extract('8YoUxe5ncPo')
+        sub = info_dict[0]['subtitles'][0]
+        self.assertTrue(sub[2] is not None)
+
+if __name__ == '__main__':
+    unittest.main()

test/tests.json

@@ -0,0 +1,653 @@
+[
+  {
+    "name": "Youtube",
+    "url":  "http://www.youtube.com/watch?v=BaW_jenozKc",
+    "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",
+    "md5":  "392c4b85a60a90dc4792da41ce3144eb",
+    "url":  "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
+    "file":  "x33vw9.mp4",
+    "info_dict": {
+      "uploader": "Alex and Van .",
+      "title": "Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+    }
+  },
+  {
+    "name": "Metacafe",
+    "add_ie": ["Youtube"],
+    "url":  "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
+    "file":  "_aUehQsCQtM.flv",
+    "info_dict": {
+      "upload_date": "20090102",
+      "title": "The Electric Company | \"Short I\" | PBS KIDS GO!",
+      "description": "md5:2439a8ef6d5a70e380c22f5ad323e5a8",
+      "uploader": "PBS",
+      "uploader_id": "PBS"
+    }
+  },
+  {
+    "name": "BlipTV",
+    "md5":  "b2d849efcf7ee18917e4b4d9ff37cafe",
+    "url":  "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
+    "file":  "5779306.m4v",
+    "info_dict": {
+      "upload_date": "20111205",
+      "description": "md5:9bc31f227219cde65e47eeec8d2dc596",
+      "uploader": "Comic Book Resources - CBR TV",
+      "title": "CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
+    }
+  },
+  {
+    "name": "XVideos",
+    "md5":  "1d0c835822f0a71a7bf011855db929d0",
+    "url":  "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
+    "file":  "939581.flv",
+    "info_dict": {
+      "title": "Funny Porns By >>>>S<<<<<< -1"
+    }
+  },
+  {
+    "name": "YouPorn",
+    "md5": "c37ddbaaa39058c76a7e86c6813423c1",
+    "url": "http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/",
+    "file": "505835.mp4",
+    "info_dict": {
+      "upload_date": "20101221",
+      "description": "Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
+      "uploader": "Ask Dan And Jennifer",
+      "title": "Sex Ed: Is It Safe To Masturbate Daily?"
+    }
+  },
+  {
+    "name": "Pornotube",
+    "md5": "374dd6dcedd24234453b295209aa69b6",
+    "url": "http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing",
+    "file": "1689755.flv",
+    "info_dict": {
+      "upload_date": "20090708",
+      "title": "Marilyn-Monroe-Bathing"
+    }
+  },
+  {
+    "name": "YouJizz",
+    "md5": "07e15fa469ba384c7693fd246905547c",
+    "url": "http://www.youjizz.com/videos/zeichentrick-1-2189178.html",
+    "file": "2189178.flv",
+    "info_dict": {
+      "title": "Zeichentrick 1"
+    }
+  },
+  {
+    "name": "Vimeo",
+    "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",
+    "md5":  "ebef0a451b909710ed1d7787dddbf0d7",
+    "url":  "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
+    "file":  "62986583.mp3",
+    "info_dict": {
+      "upload_date": "20121011",
+      "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
+      "uploader": "E.T. ExTerrestrial Music",
+      "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+    }
+  },
+  {
+    "name": "StanfordOpenClassroom",
+    "md5":  "544a9468546059d4e80d76265b0443b8",
+    "url":  "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
+    "file":  "PracticalUnix_intro-environment.mp4",
+    "info_dict": {
+      "title": "Intro Environment"
+    }
+  },
+  {
+    "name": "XNXX",
+    "md5":  "0831677e2b4761795f68d417e0b7b445",
+    "url":  "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
+    "file":  "1135332.flv",
+    "info_dict": {
+      "title": "lida » Naked Funny Actress  (5)"
+    }
+  },
+  {
+    "name": "Youku",
+    "url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
+    "file": "XNDgyMDQ2NTQw_part00.flv",
+    "md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
+    "params": { "test": false },
+    "info_dict": {
+      "title": "youtube-dl test video \"'/\\ä↭𝕐"
+    }
+  },
+  {
+    "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",
+    "info_dict": {
+      "description": "Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
+      "title": "Thunder vs. Nets"
+    }
+  },
+  {
+    "name": "JustinTV",
+    "url": "http://www.twitch.tv/thegamedevhub/b/296128360",
+    "file": "296128360.flv",
+    "md5": "ecaa8a790c22a40770901460af191c9a",
+    "info_dict": {
+      "upload_date": "20110927",
+      "uploader_id": 25114803,
+      "uploader": "thegamedevhub",
+      "title": "Beginner Series - Scripting With Python Pt.1"
+    }
+  },
+  {
+    "name": "MyVideo",
+    "url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
+    "file": "8229274.flv",
+    "md5": "2d2753e8130479ba2cb7e0a37002053e",
+    "info_dict": {
+      "title": "bowling-fail-or-win"
+    }
+  },
+  {
+    "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",
+    "info_dict": {
+      "description": "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+      "uploader": "the-escapist-presents",
+      "title": "Breaking Down Baldur's Gate"
+    }
+  },
+  {
+    "name": "GooglePlus",
+    "url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
+    "file": "ZButuJc6CtH.flv",
+    "info_dict": {
+      "upload_date": "20120613",
+      "uploader": "井上ヨシマサ",
+      "title": "嘆きの天使 降臨"
+    }
+  },
+  {
+    "name": "FunnyOrDie",
+    "url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
+    "file": "0732f586d7.mp4",
+    "md5": "f647e9e90064b53b6e046e75d0241fbd",
+    "info_dict": {
+      "description": "Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.",
+      "title": "Heart-Shaped Box: Literal Video Version"
+    }
+  },
+  {
+    "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",
+        "uploader": "Young Americans for Liberty"
+    }
+  },
+  {
+    "name": "InfoQ",
+    "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
+    "file": "12-jan-pythonthings.mp4",
+    "info_dict": {
+      "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
+      "title": "A Few of My Favorite [Python] Things"
+    },
+    "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": {
+      "upload_date": "20121214",
+      "description": "Kristen Stewart",
+      "uploader": "thedailyshow",
+      "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",
+          "uploader_id": "ytdl"
+        }
+      },
+      {
+        "file": "11885680.m4a",
+        "md5": "4eb0a669317cd725f6bbd336a29f923a",
+        "info_dict": {
+          "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
+          "uploader_id": "ytdl"
+        }
+      },
+      {
+        "file": "11885682.m4a",
+        "md5": "1893e872e263a2705558d1d319ad19e8",
+        "info_dict": {
+          "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
+          "uploader_id": "ytdl"
+        }
+      },
+      {
+        "file": "11885683.m4a",
+        "md5": "b673c46f47a216ab1741ae8836af5899",
+        "info_dict": {
+          "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
+          "uploader_id": "ytdl"
+        }
+      },
+      {
+        "file": "11885684.m4a",
+        "md5": "1d74534e95df54986da7f5abf7d842b7",
+        "info_dict": {
+          "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
+          "uploader_id": "ytdl"
+        }
+      },
+      {
+        "file": "11885685.m4a",
+        "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
+        "info_dict": {
+          "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
+          "uploader_id": "ytdl"
+        }
+      }
+    ]
+  },
+  {
+    "name": "Keek",
+    "url": "http://www.keek.com/ytdl/keeks/NODfbab",
+    "file": "NODfbab.mp4",
+    "md5": "9b0636f8c0f7614afa4ea5e4c6e57e83",
+    "info_dict": {
+      "uploader": "ytdl",
+      "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": "8cd9dfa41ee000ce658fd48fb5d89a61",
+    "info_dict": {
+        "title": "Dan Dennett: The illusion of consciousness",
+        "description": "md5:c6fa72e6eedbd938c9caf6b2702f5922"
+    }
+  },
+  {
+    "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": {
+      "description": "Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
+      "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",
+    "info_dict": {
+      "uploader": "www.hodiho.fr",
+      "title": "Régis plante sa Jeep"
+    }
+  },
+  {
+    "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://resigno.tumblr.com/post/53364321212/e-de-extrema-importancia-que-esse-video-seja",
+    "file": "53364321212.mp4",
+    "md5": "0716d3dd51baf68a28b40fdf1251494e",
+    "info_dict": {
+        "title": "Rafael Lemos | Tumblr"
+    }
+  },
+  {
+    "name": "SoundcloudSet",
+    "url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
+    "playlist":[
+      {
+        "file":"30510138.mp3",
+        "md5":"f9136bf103901728f29e419d2c70f55d",
+        "info_dict": {
+          "upload_date": "20111213",
+          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+          "uploader": "The Royal Concept",
+          "title": "D-D-Dance"
+        }
+      },
+      {
+        "file":"47127625.mp3",
+        "md5":"09b6758a018470570f8fd423c9453dd8",
+        "info_dict": {
+          "upload_date": "20120521",
+          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+          "uploader": "The Royal Concept",
+          "title": "The Royal Concept - Gimme Twice"
+        }
+      },
+      {
+        "file":"47127627.mp3",
+        "md5":"154abd4e418cea19c3b901f1e1306d9c",
+        "info_dict": {
+          "upload_date": "20120521",
+          "uploader": "The Royal Concept",
+          "title": "Goldrushed"
+        }
+      },
+      {
+        "file":"47127629.mp3",
+        "md5":"2f5471edc79ad3f33a683153e96a79c1",
+        "info_dict": {
+          "upload_date": "20120521",
+          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+          "uploader": "The Royal Concept",
+          "title": "In the End"
+        }
+      },
+      {
+        "file":"47127631.mp3",
+        "md5":"f9ba87aa940af7213f98949254f1c6e2",
+        "info_dict": {
+          "upload_date": "20120521",
+          "description": "The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
+          "uploader": "The Royal Concept",
+          "title": "Knocked Up"
+        }
+      },
+      {
+        "file":"75206121.mp3",
+        "md5":"f9d1fe9406717e302980c30de4af9353",
+        "info_dict": {
+          "upload_date": "20130116",
+          "description": "The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central).  \r\nAs a gift to our fans we would like to offer you a free download of the track!  ",
+          "uploader": "The Royal Concept",
+          "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": {
+      "upload_date": "20130504",
+      "uploader": "rachaneronas",
+      "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/julian-smith-travis-legg-watch-214727115.html",
+    "file": "214727115.flv",
+    "md5": "2e717f169c1be93d84d3794a00d4a325",
+    "info_dict": {
+        "title": "Julian Smith & Travis Legg Watch Julian Smith"
+    },
+    "skip": "Requires rtmpdump"
+  },
+  {
+    "name": "Howcast",
+    "url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly",
+    "file": "390161.mp4",
+    "md5": "1d7ba54e2c9d7dc6935ef39e00529138",
+    "info_dict":{
+      "title":"How to Tie a Square Knot Properly",
+      "description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot."
+    }
+  },
+  {
+    "name": "Vine",
+    "url": "https://vine.co/v/b9KOOWX7HUx",
+    "file": "b9KOOWX7HUx.mp4",
+    "md5": "2f36fed6235b16da96ce9b4dc890940d",
+    "info_dict":{
+      "title": "Chicken.",
+      "uploader": "Jack Dorsey"
+    }
+  },
+  {
+    "name": "Flickr",
+    "url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/",
+    "file": "5645318632.mp4",
+    "md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b",
+    "info_dict":{
+      "title": "Dark Hollow Waterfalls",
+      "uploader_id": "forestwander-nature-pictures",
+      "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
+    }
+  },
+  {
+    "name": "Teamcoco",
+    "url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
+    "file": "19705.mp4",
+    "md5": "27b6f7527da5acf534b15f21b032656e",
+    "info_dict":{
+      "title": "Louis C.K. Interview Pt. 1 11/3/11",
+      "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
+    }
+  },
+  {
+    "name": "XHamster",
+    "url": "http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html",
+    "file": "1509445.flv",
+    "md5": "9f48e0e8d58e3076bb236ff412ab62fa",
+    "info_dict": {
+      "upload_date": "20121014",
+      "uploader_id": "Ruseful2011",
+      "title": "FemaleAgent Shy beauty takes the bait"
+    }
+  },
+  {
+    "name": "Hypem",
+    "url": "http://hypem.com/track/1v6ga/BODYWORK+-+TAME",
+    "file": "1v6ga.mp3",
+    "md5": "b9cc91b5af8995e9f0c1cee04c575828",
+    "info_dict":{
+      "title":"Tame"
+    }
+  },
+  {
+    "name": "Vbox7",
+    "url": "http://vbox7.com/play:249bb972c2",
+    "file": "249bb972c2.flv",
+    "md5": "9c70d6d956f888bdc08c124acc120cfe",
+    "info_dict":{
+      "title":"Смях! Чудо - чист за секунди - Скрита камера"
+    }
+  },
+  {
+    "name": "Gametrailers",
+    "url": "http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer",
+    "file": "zbvr8i.flv",
+    "md5": "c3edbc995ab4081976e16779bd96a878",
+    "info_dict": {
+        "title": "E3 2013: Debut Trailer"
+    },
+    "skip": "Requires rtmpdump"
+  },
+  {
+    "name": "Statigram",
+    "url": "http://statigr.am/p/484091715184808010_284179915",
+    "file": "484091715184808010_284179915.mp4",
+    "md5": "deda4ff333abe2e118740321e992605b",
+    "info_dict": {
+        "uploader_id": "videoseconds",
+        "title": "Instagram photo by @videoseconds (Videos)"
+    }
+  },
+  {
+    "name": "Break",
+    "url": "http://www.break.com/video/when-girls-act-like-guys-2468056",
+    "file": "2468056.mp4",
+    "md5": "a3513fb1547fba4fb6cfac1bffc6c46b",
+    "info_dict": {
+        "title": "When Girls Act Like D-Bags"
+    }
+  }
+]

youtube-dl.dev

@@ -1,6 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-import youtube_dl
-
-youtube_dl.main()

youtube_dl/InfoExtractors.py

@@ -0,0 +1,4 @@
+# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
+
+from .extractor.common import InfoExtractor, SearchInfoExtractor
+from .extractor import gen_extractors, get_info_extractor

youtube_dl/PostProcessor.py

@@ -0,0 +1,233 @@
+import os
+import subprocess
+import sys
+import time
+
+from .utils import *
+
+
+class PostProcessor(object):
+    """Post Processor class.
+
+    PostProcessor objects can be added to downloaders with their
+    add_post_processor() method. When the downloader has finished a
+    successful download, it will take its internal chain of PostProcessors
+    and start calling the run() method on each one of them, first with
+    an initial argument and then with the returned value of the previous
+    PostProcessor.
+
+    The chain will be stopped if one of them ever returns None or the end
+    of the chain is reached.
+
+    PostProcessor objects follow a "mutual registration" process similar
+    to InfoExtractor objects.
+    """
+
+    _downloader = None
+
+    def __init__(self, downloader=None):
+        self._downloader = downloader
+
+    def set_downloader(self, downloader):
+        """Sets the downloader for this PP."""
+        self._downloader = downloader
+
+    def run(self, information):
+        """Run the PostProcessor.
+
+        The "information" argument is a dictionary like the ones
+        composed by InfoExtractors. The only difference is that this
+        one has an extra field called "filepath" that points to the
+        downloaded file.
+
+        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 if post processing fails.
+        """
+        return None, information # by default, keep file and do nothing
+
+class FFmpegPostProcessorError(PostProcessingError):
+    pass
+
+class AudioConversionError(PostProcessingError):
+    pass
+
+class FFmpegPostProcessor(PostProcessor):
+    def __init__(self,downloader=None):
+        PostProcessor.__init__(self, downloader)
+        self._exes = self.detect_executables()
+
+    @staticmethod
+    def detect_executables():
+        def executable(exe):
+            try:
+                subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
+            except OSError:
+                return False
+            return exe
+        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(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.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:
+                return audio_codec
+        return 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.')
+        if codec is None:
+            acodec_opts = []
+        else:
+            acodec_opts = ['-acodec', codec]
+        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:
+            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 filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
+                # Lossless, but in another container
+                acodec = 'copy'
+                extension = 'm4a'
+                more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
+            elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:
+                # Lossless if possible
+                acodec = 'copy'
+                extension = filecodec
+                if filecodec == 'aac':
+                    more_opts = ['-f', 'adts']
+                if filecodec == 'vorbis':
+                    extension = 'ogg'
+            else:
+                # MP3 otherwise.
+                acodec = 'libmp3lame'
+                extension = 'mp3'
+                more_opts = []
+                if self._preferredquality is not None:
+                    if int(self._preferredquality) < 10:
+                        more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
+                    else:
+                        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', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+            extension = self._preferredcodec
+            more_opts = []
+            if self._preferredquality is not None:
+                if int(self._preferredquality) < 10:
+                    more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
+                else:
+                    more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
+            if self._preferredcodec == 'aac':
+                more_opts += ['-f', 'adts']
+            if self._preferredcodec == 'm4a':
+                more_opts += [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
+            if self._preferredcodec == 'vorbis':
+                extension = 'ogg'
+            if self._preferredcodec == 'wav':
+                extension = 'wav'
+                more_opts += ['-f', 'wav']
+
+        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
+
+        # 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:
+            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):
+                msg = u'audio conversion failed: ' + e.message
+            else:
+                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:
+            try:
+                os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
+            except:
+                self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+        information['filepath'] = new_path
+        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

youtube_dl/__main__.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python
+
+# Execute with
+# $ python youtube_dl/__main__.py (2.6+)
+# $ python -m youtube_dl          (2.7+)
+
+import sys
+
+if __package__ is None and not hasattr(sys, "frozen"):
+    # direct call of __main__.py
+    import os.path
+    path = os.path.realpath(os.path.abspath(__file__))
+    sys.path.append(os.path.dirname(os.path.dirname(path)))
+
+import youtube_dl
+
+if __name__ == '__main__':
+    youtube_dl.main()

youtube_dl/extractor/__init__.py

@@ -0,0 +1,133 @@
+
+from .ard import ARDIE
+from .arte import ArteTvIE
+from .bandcamp import BandcampIE
+from .bliptv import BlipTVIE, BlipTVUserIE
+from .breakcom import BreakIE
+from .comedycentral import ComedyCentralIE
+from .collegehumor import CollegeHumorIE
+from .dailymotion import DailymotionIE
+from .depositfiles import DepositFilesIE
+from .eighttracks import EightTracksIE
+from .escapist import EscapistIE
+from .facebook import FacebookIE
+from .flickr import FlickrIE
+from .funnyordie import FunnyOrDieIE
+from .gametrailers import GametrailersIE
+from .generic import GenericIE
+from .googleplus import GooglePlusIE
+from .googlesearch import GoogleSearchIE
+from .howcast import HowcastIE
+from .hypem import HypemIE
+from .ina import InaIE
+from .infoq import InfoQIE
+from .justintv import JustinTVIE
+from .keek import KeekIE
+from .liveleak import LiveLeakIE
+from .metacafe import MetacafeIE
+from .mixcloud import MixcloudIE
+from .mtv import MTVIE
+from .myspass import MySpassIE
+from .myvideo import MyVideoIE
+from .nba import NBAIE
+from .statigram import StatigramIE
+from .photobucket import PhotobucketIE
+from .pornotube import PornotubeIE
+from .rbmaradio import RBMARadioIE
+from .redtube import RedTubeIE
+from .soundcloud import SoundcloudIE, SoundcloudSetIE
+from .spiegel import SpiegelIE
+from .stanfordoc import StanfordOpenClassroomIE
+from .steam import SteamIE
+from .teamcoco import TeamcocoIE
+from .ted import TEDIE
+from .tumblr import TumblrIE
+from .ustream import UstreamIE
+from .vbox7 import Vbox7IE
+from .vimeo import VimeoIE
+from .vine import VineIE
+from .worldstarhiphop import WorldStarHipHopIE
+from .xnxx import XNXXIE
+from .xhamster import XHamsterIE
+from .xvideos import XVideosIE
+from .yahoo import YahooIE, YahooSearchIE
+from .youjizz import YouJizzIE
+from .youku import YoukuIE
+from .youporn import YouPornIE
+from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
+from .zdf import ZDFIE
+
+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(),
+        BlipTVIE(),
+        BlipTVUserIE(),
+        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(),
+        ZDFIE(),
+        TumblrIE(),
+        BandcampIE(),
+        RedTubeIE(),
+        InaIE(),
+        HowcastIE(),
+        VineIE(),
+        FlickrIE(),
+        TeamcocoIE(),
+        XHamsterIE(),
+        HypemIE(),
+        Vbox7IE(),
+        GametrailersIE(),
+        StatigramIE(),
+        BreakIE(),
+        GenericIE()
+    ]
+
+def get_info_extractor(ie_name):
+    """Returns the info extractor class with the given ie_name"""
+    return globals()[ie_name+'IE']

youtube_dl/extractor/ard.py

@@ -0,0 +1,45 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+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]

youtube_dl/extractor/arte.py

@@ -0,0 +1,136 @@
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+    unified_strdate,
+)
+
+class ArteTvIE(InfoExtractor):
+    """arte.tv information extractor."""
+
+    _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+    _LIVE_URL = r'index-[0-9]+\.html$'
+
+    IE_NAME = u'arte.tv'
+
+    def fetch_webpage(self, url):
+        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:
+            raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
+        except ValueError as err:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        return webpage
+
+    def grep_webpage(self, url, regex, regexFlags, matchTuples):
+        page = self.fetch_webpage(url)
+        mobj = re.search(regex, page, regexFlags)
+        info = {}
+
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        for (i, key, err) in matchTuples:
+            if mobj.group(i) is None:
+                raise ExtractorError(err)
+            else:
+                info[key] = mobj.group(i)
+
+        return info
+
+    # TODO implement Live Stream
+    # def extractLiveStream(self, url):
+    #     video_lang = url.split('/')[-4]
+    #     info = self.grep_webpage(
+    #         url,
+    #         r'src="(.*?/videothek_js.*?\.js)',
+    #         0,
+    #         [
+    #             (1, 'url', u'Invalid URL: %s' % url)
+    #         ]
+    #     )
+    #     http_host = url.split('/')[2]
+    #     next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
+    #     info = self.grep_webpage(
+    #         next_url,
+    #         r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+    #             '(http://.*?\.swf).*?' +
+    #             '(rtmp://.*?)\'',
+    #         re.DOTALL,
+    #         [
+    #             (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'))
+
+    def extractPlus7Stream(self, url):
+        video_lang = url.split('/')[-3]
+        info = self.grep_webpage(
+            url,
+            r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
+            0,
+            [
+                (1, 'url', u'Invalid URL: %s' % url)
+            ]
+        )
+        next_url = compat_urllib_parse.unquote(info.get('url'))
+        info = self.grep_webpage(
+            next_url,
+            r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
+            0,
+            [
+                (1, 'url', u'Could not find <video> tag: %s' % url)
+            ]
+        )
+        next_url = compat_urllib_parse.unquote(info.get('url'))
+
+        info = self.grep_webpage(
+            next_url,
+            r'<video id="(.*?)".*?>.*?' +
+                '<name>(.*?)</name>.*?' +
+                '<dateVideo>(.*?)</dateVideo>.*?' +
+                '<url quality="hd">(.*?)</url>',
+            re.DOTALL,
+            [
+                (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)
+            ]
+        )
+
+        return {
+            'id':           info.get('id'),
+            'url':          compat_urllib_parse.unquote(info.get('url')),
+            'uploader':     u'arte.tv',
+            'upload_date':  unified_strdate(info.get('date')),
+            'title':        info.get('title').decode('utf-8'),
+            'ext':          u'mp4',
+            'format':       u'NA',
+            'player_url':   None,
+        }
+
+    def _real_extract(self, url):
+        video_id = url.split('/')[-1]
+        self.report_extraction(video_id)
+
+        if re.search(self._LIVE_URL, video_id) is not None:
+            raise ExtractorError(u'Arte live streams are not yet supported, sorry')
+            # self.extractLiveStream(url)
+            # return
+        else:
+            info = self.extractPlus7Stream(url)
+
+        return [info]

youtube_dl/extractor/bandcamp.py

@@ -0,0 +1,54 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+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 found')
+
+        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]

youtube_dl/extractor/bliptv.py

@@ -0,0 +1,177 @@
+import datetime
+import json
+import os
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse_urlparse,
+    compat_urllib_request,
+
+    ExtractorError,
+    unescapeHTML,
+)
+
+
+class BlipTVIE(InfoExtractor):
+    """Information extractor for blip.tv"""
+
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
+    _URL_EXT = r'^.*\.([a-z0-9]+)$'
+    IE_NAME = u'blip.tv'
+
+    def report_direct_download(self, title):
+        """Report information extraction."""
+        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:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        # See https://github.com/rg3/youtube-dl/issues/857
+        api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url)
+        if api_mobj is not None:
+            url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id')
+        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)
+        request.add_header('User-Agent', 'iTunes/10.6.1')
+        self.report_extraction(mobj.group(1))
+        info = None
+        try:
+            urlh = compat_urllib_request.urlopen(request)
+            if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+                basename = url.split('/')[-1]
+                title,ext = os.path.splitext(basename)
+                title = title.decode('UTF-8')
+                ext = ext.replace('.', '')
+                self.report_direct_download(title)
+                info = {
+                    'id': title,
+                    'url': url,
+                    'uploader': None,
+                    'upload_date': None,
+                    'title': title,
+                    'ext': ext,
+                    'urlhandle': urlh
+                }
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
+        if info is None: # Regular URL
+            try:
+                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:
+                raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
+
+            try:
+                json_data = json.loads(json_code)
+                if 'Post' in json_data:
+                    data = json_data['Post']
+                else:
+                    data = json_data
+
+                upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+                video_url = data['media']['url']
+                umobj = re.match(self._URL_EXT, video_url)
+                if umobj is None:
+                    raise ValueError('Can not determine filename extension')
+                ext = umobj.group(1)
+
+                info = {
+                    'id': data['item_id'],
+                    'url': video_url,
+                    'uploader': data['display_name'],
+                    'upload_date': upload_date,
+                    'title': data['title'],
+                    'ext': ext,
+                    'format': data['media']['mimeType'],
+                    'thumbnail': data['thumbnailUrl'],
+                    'description': data['description'],
+                    'player_url': data['embedUrl'],
+                    'user_agent': 'iTunes/10.6.1',
+                }
+            except (ValueError,KeyError) as err:
+                raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
+
+        return [info]
+
+
+class BlipTVUserIE(InfoExtractor):
+    """Information Extractor for blip.tv users."""
+
+    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
+    _PAGE_SIZE = 12
+    IE_NAME = u'blip.tv:user'
+
+    def _real_extract(self, url):
+        # Extract username
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            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'
+
+        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
+        # query is limited (currently to 12 videos) so we need to query
+        # page by page until there are no video ids - it means we got
+        # all of them.
+
+        video_ids = []
+        pagenum = 1
+
+        while True:
+            url = page_base + "&page=" + str(pagenum)
+            page = self._download_webpage(url, username,
+                                          u'Downloading video ids from page %d' % pagenum)
+
+            # Extract video identifiers
+            ids_in_page = []
+
+            for mobj in re.finditer(r'href="/([^"]+)"', page):
+                if mobj.group(1) not in ids_in_page:
+                    ids_in_page.append(unescapeHTML(mobj.group(1)))
+
+            video_ids.extend(ids_in_page)
+
+            # A little optimization - if current page is not
+            # "full", ie. does not contain PAGE_SIZE video ids then
+            # we can assume that this page is the last one - there
+            # are no more ids on further pages - no need to query
+            # again.
+
+            if len(ids_in_page) < self._PAGE_SIZE:
+                break
+
+            pagenum += 1
+
+        urls = [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)]

youtube_dl/extractor/breakcom.py

@@ -0,0 +1,25 @@
+import re
+
+from .common import InfoExtractor
+
+
+class BreakIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1).split("-")[-1]
+        webpage = self._download_webpage(url, video_id)
+        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
+        key = re.search(r"icon: '(.+?)',",webpage).group(1)
+        final_url = str(video_url)+"?"+str(key)
+        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
+        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
+        ext = video_url.split('.')[-1]
+        return [{
+            'id':        video_id,
+            'url':       final_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+        }]

youtube_dl/extractor/collegehumor.py

@@ -0,0 +1,74 @@
+import re
+import socket
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse_urlparse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class CollegeHumorIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+
+    def report_manifest(self, video_id):
+        """Report information extraction."""
+        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:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group('videoid')
+
+        info = {
+            'id': video_id,
+            'uploader': None,
+            'upload_date': None,
+        }
+
+        self.report_extraction(video_id)
+        xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
+        try:
+            metaXml = compat_urllib_request.urlopen(xmlUrl).read()
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+
+        mdoc = xml.etree.ElementTree.fromstring(metaXml)
+        try:
+            videoNode = mdoc.findall('./video')[0]
+            info['description'] = videoNode.findall('./description')[0].text
+            info['title'] = videoNode.findall('./caption')[0].text
+            info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+            manifest_url = videoNode.findall('./file')[0].text
+        except IndexError:
+            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:
+            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+
+        adoc = xml.etree.ElementTree.fromstring(manifestXml)
+        try:
+            media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
+            node_id = media_node.attrib['url']
+            video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
+        except IndexError as err:
+            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'
+
+        info['url'] = url
+        info['ext'] = 'f4f'
+        return [info]

youtube_dl/extractor/comedycentral.py

@@ -0,0 +1,179 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_parse,
+
+    ExtractorError,
+    unified_strdate,
+)
+
+
+class ComedyCentralIE(InfoExtractor):
+    """Information extractor for The Daily Show and Colbert Report """
+
+    # 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']
+
+    _video_extensions = {
+        '3500': 'mp4',
+        '2200': 'mp4',
+        '1700': 'mp4',
+        '1200': 'mp4',
+        '750': 'mp4',
+        '400': 'mp4',
+    }
+    _video_dimensions = {
+        '3500': '1280x720',
+        '2200': '960x540',
+        '1700': '768x432',
+        '1200': '640x360',
+        '750': '512x288',
+        '400': '384x216',
+    }
+
+    @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:')
+        for x in formats:
+            print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
+
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+        if mobj is None:
+            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, re.VERBOSE)
+            assert mobj is not None
+
+        if mobj.group('clip'):
+            if mobj.group('showname') == 'thedailyshow':
+                epTitle = mobj.group('tdstitle')
+            else:
+                epTitle = mobj.group('cntitle')
+            dlNewest = False
+        else:
+            dlNewest = not mobj.group('episode')
+            if dlNewest:
+                epTitle = mobj.group('showname')
+            else:
+                epTitle = mobj.group('episode')
+
+        self.report_extraction(epTitle)
+        webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
+        if dlNewest:
+            url = htmlHandle.geturl()
+            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+            if mobj is None:
+                raise ExtractorError(u'Invalid redirected URL: ' + url)
+            if mobj.group('episode') == '':
+                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|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|video).*?:.*?)"', webpage)
+            if len(altMovieParams) == 0:
+                raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
+            else:
+                mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+
+        uri = mMovieParams[0][1]
+        indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
+        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 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 = unified_strdate(itemEl.findall('./pubDate')[0].text)
+
+            configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+                        compat_urllib_parse.urlencode({'uri': mediaId}))
+            configXml = self._download_webpage(configUrl, epTitle,
+                                               u'Downloading configuration for %s' % shortMediaId)
+
+            cdoc = xml.etree.ElementTree.fromstring(configXml)
+            turls = []
+            for rendition in cdoc.findall('.//rendition'):
+                finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+                turls.append(finfo)
+
+            if len(turls) == 0:
+                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,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, rtmp_video_url = f, v
+                    break
+
+            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 + u' part ' + compat_str(partNum+1)
+            info = {
+                'id': shortMediaId,
+                'url': video_url,
+                'uploader': showId,
+                'upload_date': officialDate,
+                'title': effTitle,
+                'ext': 'mp4',
+                'format': format,
+                'thumbnail': None,
+                'description': officialTitle,
+            }
+            results.append(info)
+
+        return results

youtube_dl/extractor/common.py

@@ -0,0 +1,264 @@
+import base64
+import os
+import re
+import socket
+import sys
+
+from ..utils import (
+    compat_http_client,
+    compat_urllib_error,
+    compat_urllib_request,
+    compat_str,
+
+    clean_html,
+    compiled_regex_type,
+    ExtractorError,
+)
+
+class InfoExtractor(object):
+    """Information Extractor class.
+
+    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
+    passed to the FileDownloader. The FileDownloader processes this
+    information possibly downloading the video to the file system, among
+    other possible outcomes.
+
+    The dictionaries must include the following fields:
+
+    id:             Video identifier.
+    url:            Final video URL.
+    title:          Video title, unescaped.
+    ext:            Video filename extension.
+
+    The following fields are optional:
+
+    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 subtitle file contents.
+    urlhandle:      [internal] The urlHandle to be used to download the file,
+                    like returned by urllib.request.urlopen
+
+    The fields should all be Unicode strings.
+
+    Subclasses of this one should re-define the _real_initialize() and
+    _real_extract() methods and define a _VALID_URL regexp.
+    Probably, they should also be added to the list of extractors.
+
+    _real_extract() must return a *list* of information dictionaries as
+    described above.
+
+    Finally, the _WORKING attribute should be set to False for broken IEs
+    in order to warn the users and skip the tests.
+    """
+
+    _ready = False
+    _downloader = None
+    _WORKING = True
+
+    def __init__(self, downloader=None):
+        """Constructor. Receives an optional downloader."""
+        self._ready = False
+        self.set_downloader(downloader)
+
+    @classmethod
+    def suitable(cls, url):
+        """Receives a URL and returns True if suitable for this IE."""
+        return re.match(cls._VALID_URL, url) is not None
+
+    @classmethod
+    def working(cls):
+        """Getter method for _WORKING."""
+        return cls._WORKING
+
+    def initialize(self):
+        """Initializes an instance (authentication, etc)."""
+        if not self._ready:
+            self._real_initialize()
+            self._ready = True
+
+    def extract(self, url):
+        """Extracts URL information and returns it in list of dicts."""
+        self.initialize()
+        return self._real_extract(url)
+
+    def set_downloader(self, downloader):
+        """Sets the downloader for this IE."""
+        self._downloader = downloader
+
+    def _real_initialize(self):
+        """Real initialization process. Redefine in subclasses."""
+        pass
+
+    def _real_extract(self, url):
+        """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
+
+    def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+        """
+        Perform a regex search on the given string, using a single or a list of
+        patterns returning the first matching group.
+        In case of failure return a default value or raise a WARNING or a
+        ExtractorError, depending on fatal, specifying the field name.
+        """
+        if isinstance(pattern, (str, compat_str, compiled_regex_type)):
+            mobj = re.search(pattern, string, flags)
+        else:
+            for p in pattern:
+                mobj = re.search(p, string, flags)
+                if mobj: break
+
+        if sys.stderr.isatty() and os.name != 'nt':
+            _name = u'\033[0;34m%s\033[0m' % name
+        else:
+            _name = name
+
+        if mobj:
+            # return the first matching group
+            return next(g for g in mobj.groups() if g is not None)
+        elif default is not None:
+            return default
+        elif fatal:
+            raise ExtractorError(u'Unable to extract %s' % _name)
+        else:
+            self._downloader.report_warning(u'unable to extract %s; '
+                u'please report this issue on GitHub.' % _name)
+            return None
+
+    def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+        """
+        Like _search_regex, but strips HTML tags and unescapes entities.
+        """
+        res = self._search_regex(pattern, string, name, default, fatal, flags)
+        if res:
+            return clean_html(res).strip()
+        else:
+            return res
+
+class SearchInfoExtractor(InfoExtractor):
+    """
+    Base class for paged search queries extractors.
+    They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
+    Instances should define _SEARCH_KEY and _MAX_RESULTS.
+    """
+
+    @classmethod
+    def _make_valid_url(cls):
+        return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
+
+    @classmethod
+    def suitable(cls, url):
+        return re.match(cls._make_valid_url(), url) is not None
+
+    def _real_extract(self, query):
+        mobj = re.match(self._make_valid_url(), query)
+        if mobj is None:
+            raise ExtractorError(u'Invalid search query "%s"' % query)
+
+        prefix = mobj.group('prefix')
+        query = mobj.group('query')
+        if prefix == '':
+            return self._get_n_results(query, 1)
+        elif prefix == 'all':
+            return self._get_n_results(query, self._MAX_RESULTS)
+        else:
+            n = int(prefix)
+            if n <= 0:
+                raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+            elif n > self._MAX_RESULTS:
+                self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+                n = self._MAX_RESULTS
+            return self._get_n_results(query, n)
+
+    def _get_n_results(self, query, n):
+        """Get a specified number of results for a query"""
+        raise NotImplementedError("This method must be implemented by sublclasses")

youtube_dl/extractor/dailymotion.py

@@ -0,0 +1,77 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+
+    ExtractorError,
+    unescapeHTML,
+)
+
+class DailymotionIE(InfoExtractor):
+    """Information Extractor for Dailymotion"""
+
+    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
+    IE_NAME = u'dailymotion'
+
+    def _real_extract(self, url):
+        # Extract id and simplified title from URL
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group(1).split('_')[0].split('?')[0]
+
+        video_extension = 'mp4'
+
+        # Retrieve video webpage to extract further information
+        request = compat_urllib_request.Request(url)
+        request.add_header('Cookie', 'family_filter=off')
+        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:
+            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.to_screen(u'Using %s' % key)
+                break
+        else:
+            raise ExtractorError(u'Unable to extract video URL')
+
+        mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract video URL')
+
+        video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
+
+        # TODO: support choosing qualities
+
+        mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract title')
+        video_title = unescapeHTML(mobj.group('title'))
+
+        video_uploader = None
+        video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
+                                             # Looking for official user
+                                             r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
+                                            webpage, 'video uploader')
+
+        video_upload_date = None
+        mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+        if mobj is not None:
+            video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'uploader': video_uploader,
+            'upload_date':  video_upload_date,
+            'title':    video_title,
+            'ext':      video_extension,
+        }]

youtube_dl/extractor/depositfiles.py

@@ -0,0 +1,60 @@
+import re
+import os
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class DepositFilesIE(InfoExtractor):
+    """Information extractor for depositfiles.com"""
+
+    _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
+
+    def _real_extract(self, url):
+        file_id = url.split('/')[-1]
+        # Rebuild url in english locale
+        url = 'http://depositfiles.com/en/files/' + file_id
+
+        # Retrieve file webpage with 'Free download' button pressed
+        free_download_indication = { 'gateway_result' : '1' }
+        request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
+        try:
+            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:
+            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)
+        if (mobj is None) or (mobj.group(1) is None):
+            # Try to figure out reason of the error.
+            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()
+                raise ExtractorError(u'%s' % restriction_message)
+            else:
+                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
+        file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
+
+        return [{
+            'id':       file_id.decode('utf-8'),
+            'url':      file_url.decode('utf-8'),
+            'uploader': None,
+            'upload_date':  None,
+            'title':    file_title,
+            'ext':      file_extension.decode('utf-8'),
+        }]

youtube_dl/extractor/eighttracks.py

@@ -0,0 +1,51 @@
+import itertools
+import json
+import random
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+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)
+
+        json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
+        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

youtube_dl/extractor/escapist.py

@@ -0,0 +1,68 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+
+class EscapistIE(InfoExtractor):
+    _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        showName = mobj.group('showname')
+        videoId = mobj.group('episode')
+
+        self.report_extraction(videoId)
+        webpage = self._download_webpage(url, videoId)
+
+        videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
+            webpage, u'description', fatal=False)
+
+        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
+            webpage, u'thumbnail', fatal=False)
+
+        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
+            webpage, u'player url')
+
+        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
+            webpage, u'player url').split(' : ')[-1]
+
+        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+        configUrl = compat_urllib_parse.unquote(configUrl)
+
+        configJSON = self._download_webpage(configUrl, videoId,
+                                            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:
+            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+
+        playlist = config['playlist']
+        videoUrl = playlist[1]['url']
+
+        info = {
+            'id': videoId,
+            'url': videoUrl,
+            'uploader': showName,
+            'upload_date': None,
+            'title': title,
+            'ext': 'mp4',
+            'thumbnail': imgUrl,
+            'description': videoDesc,
+            'player_url': playerUrl,
+        }
+
+        return [info]

youtube_dl/extractor/facebook.py

@@ -0,0 +1,111 @@
+import json
+import netrc
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class FacebookIE(InfoExtractor):
+    """Information Extractor for Facebook"""
+
+    _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'
+    IE_NAME = u'facebook'
+
+    def report_login(self):
+        """Report attempt to log in."""
+        self.to_screen(u'Logging in')
+
+    def _real_initialize(self):
+        if self._downloader is None:
+            return
+
+        useremail = None
+        password = None
+        downloader_params = self._downloader.params
+
+        # Attempt to use provided username and password or .netrc data
+        if downloader_params.get('username', None) is not None:
+            useremail = downloader_params['username']
+            password = downloader_params['password']
+        elif downloader_params.get('usenetrc', False):
+            try:
+                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+                if info is not None:
+                    useremail = info[0]
+                    password = info[2]
+                else:
+                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+            except (IOError, netrc.NetrcParseError) as err:
+                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+                return
+
+        if useremail is None:
+            return
+
+        # Log in
+        login_form = {
+            'email': useremail,
+            'pass': password,
+            'login': 'Log+In'
+            }
+        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        try:
+            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.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.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:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group('ID')
+
+        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']
+
+        video_title = self._html_search_regex('<h2 class="uiHeaderTitle">([^<]+)</h2>',
+            webpage, u'title')
+
+        info = {
+            'id': video_id,
+            'title': video_title,
+            'url': video_url,
+            'ext': 'mp4',
+            'duration': video_duration,
+            'thumbnail': thumbnail,
+        }
+        return [info]

youtube_dl/extractor/flickr.py

@@ -0,0 +1,57 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unescapeHTML,
+)
+
+
+class FlickrIE(InfoExtractor):
+    """Information Extractor for Flickr videos"""
+    _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        video_uploader_id = mobj.group('uploader_id')
+        webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
+
+        first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
+        first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
+
+        node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
+            first_xml, u'node_id')
+
+        second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
+        second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
+
+        self.report_extraction(video_id)
+
+        mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract video url')
+        video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
+
+        video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
+            webpage, u'video title')
+
+        video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
+            webpage, u'description', fatal=False)
+
+        thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
+            webpage, u'thumbnail', fatal=False)
+
+        return [{
+            'id':          video_id,
+            'url':         video_url,
+            'ext':         'mp4',
+            'title':       video_title,
+            'description': video_description,
+            'thumbnail':   thumbnail,
+            'uploader_id': video_uploader_id,
+        }]

youtube_dl/extractor/funnyordie.py

@@ -0,0 +1,31 @@
+import re
+
+from .common import InfoExtractor
+
+
+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)
+
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
+            webpage, u'video URL', flags=re.DOTALL)
+
+        title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
+            r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
+
+        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+            webpage, u'description', fatal=False, flags=re.DOTALL)
+
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': video_description,
+        }
+        return [info]

youtube_dl/extractor/gametrailers.py

@@ -0,0 +1,59 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+class GametrailersIE(InfoExtractor):
+    _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?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('id')
+        video_type = mobj.group('type')
+        webpage = self._download_webpage(url, video_id)
+        if video_type == 'full-episodes':
+            mgid_re = r'data-video="(?P<mgid>mgid:.*?)"'
+        else:
+            mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\''
+        mgid = self._search_regex(mgid_re, webpage, u'mgid')
+        data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
+
+        info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
+                                           video_id, u'Downloading video info')
+        links_webpage = self._download_webpage('http://www.gametrailers.com/feeds/mediagen/?' + data,
+                                               video_id, u'Downloading video urls info')
+
+        self.report_extraction(video_id)
+        info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
+                      <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
+                      <image>.*
+                        <url>(?P<thumb>.*?)</url>.*
+                      </image>'''
+
+        m_info = re.search(info_re, info_page, 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')
+
+        m_urls = list(re.finditer(r'<src>(?P<url>.*)</src>', links_webpage))
+        if m_urls is None or len(m_urls) == 0:
+            raise ExtractorError(u'Unable to extract video url')
+        # They are sorted from worst to best quality
+        video_url = m_urls[-1].group('url')
+
+        return {'url':         video_url,
+                'id':          video_id,
+                'title':       video_title,
+                # Videos are actually flv not mp4
+                'ext':         'flv',
+                'thumbnail':   video_thumb,
+                'description': video_description,
+                }

youtube_dl/extractor/generic.py

@@ -0,0 +1,151 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+class GenericIE(InfoExtractor):
+    """Generic last-resort information extractor."""
+
+    _VALID_URL = r'.*'
+    IE_NAME = u'generic'
+
+    def report_download_webpage(self, video_id):
+        """Report webpage download."""
+        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 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
+            HeadRequest also on the redirected URL
+            """
+            def redirect_request(self, req, fp, code, msg, headers, newurl):
+                if code in (301, 302, 303, 307):
+                    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,
+                                       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)
+
+        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):
+                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(),
+                                                 unverifiable=True))
+
+        # Build our opener
+        opener = compat_urllib_request.OpenerDirector()
+        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
+                        HTTPMethodFallback, HEADRedirectHandler,
+                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
+            opener.add_handler(handler())
+
+        response = opener.open(HeadRequest(url))
+        if response is None:
+            raise ExtractorError(u'Invalid URL protocol')
+        new_url = response.geturl()
+
+        if url == new_url:
+            return False
+
+        self.report_following_redirect(new_url)
+        return new_url
+
+    def _real_extract(self, url):
+        new_url = self._test_redirect(url)
+        if new_url: return [self.url_result(new_url)]
+
+        video_id = url.split('/')[-1]
+        try:
+            webpage = self._download_webpage(url, video_id)
+        except ValueError:
+            # since this is the last-resort InfoExtractor, if
+            # this error is thrown, it'll be thrown here
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        self.report_extraction(video_id)
+        # Start with something easy: JW Player in SWFObject
+        mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+        if mobj is None:
+            # Broaden the search a little bit
+            mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+        if mobj is None:
+            # 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:
+            # Try to find twitter cards info
+            mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+        if mobj is None:
+            # We look for Open Graph info:
+            # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
+            m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+            # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
+            if m_video_type is not None:
+                mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', 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:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        video_url = compat_urllib_parse.unquote(mobj.group(1))
+        video_id = os.path.basename(video_url)
+
+        # here's a fun little line of code for you:
+        video_extension = os.path.splitext(video_id)[1][1:]
+        video_id = os.path.splitext(video_id)[0]
+
+        # it's tempting to parse this further, but you would
+        # have to take into account all the variations like
+        #   Video Title - Site Name
+        #   Site Name | Video Title
+        #   Video Title - Tagline | Site Name
+        # and so on and so forth; it's just not practical
+        video_title = self._html_search_regex(r'<title>(.*)</title>',
+            webpage, u'video title')
+
+        # video uploader is domain name
+        video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
+            url, u'video uploader')
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'uploader': video_uploader,
+            'upload_date':  None,
+            'title':    video_title,
+            'ext':      video_extension,
+        }]

youtube_dl/extractor/googleplus.py

@@ -0,0 +1,82 @@
+import datetime
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class GooglePlusIE(InfoExtractor):
+    """Information extractor for plus.google.com."""
+
+    _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
+    IE_NAME = u'plus.google'
+
+    def _real_extract(self, url):
+        # Extract id from URL
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        post_url = mobj.group(0)
+        video_id = mobj.group(1)
+
+        video_extension = 'flv'
+
+        # Step 1, Retrieve post webpage to extract further information
+        webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+
+        self.report_extraction(video_id)
+
+        # Extract update date
+        upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>',
+            webpage, u'upload date', fatal=False)
+        if upload_date:
+            # Convert timestring to a format suitable for filename
+            upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
+            upload_date = upload_date.strftime('%Y%m%d')
+
+        # Extract uploader
+        uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
+            webpage, u'uploader', fatal=False)
+
+        # Extract title
+        # Get the first line for title
+        video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
+            webpage, 'title', default=u'NA')
+
+        # Step 2, Stimulate clicking the image box to launch video
+        video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]',
+            webpage, u'video page URL')
+        webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
+
+        # Extract video links on video page
+        """Extract video links of all sizes"""
+        pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
+        mobj = re.findall(pattern, webpage)
+        if len(mobj) == 0:
+            raise ExtractorError(u'Unable to extract video links')
+
+        # Sort in resolution
+        links = sorted(mobj)
+
+        # Choose the lowest of the sort, i.e. highest resolution
+        video_url = links[-1]
+        # Only get the url. The resolution part in the tuple has no use anymore
+        video_url = video_url[-1]
+        # Treat escaped \u0026 style hex
+        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,
+            'url':      video_url,
+            'uploader': uploader,
+            'upload_date':  upload_date,
+            'title':    video_title,
+            'ext':      video_extension,
+        }]

youtube_dl/extractor/googlesearch.py

@@ -0,0 +1,39 @@
+import itertools
+import re
+
+from .common import SearchInfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+)
+
+
+class GoogleSearchIE(SearchInfoExtractor):
+    """Information Extractor for Google Video search queries."""
+    _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
+    _MAX_RESULTS = 1000
+    IE_NAME = u'video.google:search'
+    _SEARCH_KEY = 'gvsearch'
+
+    def _get_n_results(self, query, n):
+        """Get a specified number of results for a query"""
+
+        res = {
+            '_type': 'playlist',
+            'id': query,
+            'entries': []
+        }
+
+        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))
+
+            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

youtube_dl/extractor/howcast.py

@@ -0,0 +1,37 @@
+import re
+
+from .common import InfoExtractor
+
+
+class HowcastIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'http://www.howcast.com/videos/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        self.report_extraction(video_id)
+
+        video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
+            webpage, u'video URL')
+
+        video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
+            webpage, u'title')
+
+        video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
+            webpage, u'description', fatal=False)
+
+        thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
+            webpage, u'thumbnail', fatal=False)
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      'mp4',
+            'title':    video_title,
+            'description': video_description,
+            'thumbnail': thumbnail,
+        }]

youtube_dl/extractor/hypem.py

@@ -0,0 +1,63 @@
+import json
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class HypemIE(InfoExtractor):
+    """Information Extractor for hypem"""
+    _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        track_id = mobj.group(1)
+
+        data = { 'ax': 1, 'ts': time.time() }
+        data_encoded = compat_urllib_parse.urlencode(data)
+        complete_url = url + "?" + data_encoded
+        request = compat_urllib_request.Request(complete_url)
+        response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
+        cookie = urlh.headers.get('Set-Cookie', '')
+
+        self.report_extraction(track_id)
+
+        html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
+            response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
+        try:
+            track_list = json.loads(html_tracks)
+            track = track_list[u'tracks'][0]
+        except ValueError:
+            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+
+        key = track[u"key"]
+        track_id = track[u"id"]
+        artist = track[u"artist"]
+        title = track[u"song"]
+
+        serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
+        request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+        request.add_header('cookie', cookie)
+        song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
+        try:
+            song_data = json.loads(song_data_json)
+        except ValueError:
+            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+        final_url = song_data[u"url"]
+
+        return [{
+            'id':       track_id,
+            'url':      final_url,
+            'ext':      "mp3",
+            'title':    title,
+            'artist':   artist,
+        }]

youtube_dl/extractor/ina.py

@@ -0,0 +1,31 @@
+import re
+
+from .common import InfoExtractor
+
+
+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)
+
+        self.report_extraction(video_id)
+
+        video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
+            webpage, u'video URL')
+
+        video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
+            webpage, u'title')
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      video_extension,
+            'title':    video_title,
+        }]

youtube_dl/extractor/infoq.py

@@ -0,0 +1,50 @@
+import base64
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+
+class InfoQIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, 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
+        video_title = self._search_regex(r'contentTitle = "(.*?)";',
+            webpage, u'title')
+
+        # Extract description
+        video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
+            webpage, u'description', fatal=False)
+
+        video_filename = video_url.split('/')[-1]
+        video_id, extension = video_filename.split('.')
+
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'uploader': None,
+            'upload_date': None,
+            'title': video_title,
+            'ext': extension, # Extension is always(?) mp4, but seems to be flv
+            'thumbnail': None,
+            'description': video_description,
+        }
+
+        return [info]

youtube_dl/extractor/justintv.py

@@ -0,0 +1,144 @@
+import json
+import os
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    formatSeconds,
+)
+
+
+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):
+        info_json = self._download_webpage(url, video_id,
+                                           u'Downloading video info JSON',
+                                           u'unable to download video info JSON')
+
+        response = json.loads(info_json)
+        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

youtube_dl/extractor/keek.py

@@ -0,0 +1,32 @@
+import re
+
+from .common import InfoExtractor
+
+
+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)
+
+        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+            webpage, u'title')
+
+        uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
+            webpage, u'uploader', fatal=False)
+
+        info = {
+                'id': video_id,
+                'url': video_url,
+                'ext': 'mp4',
+                'title': video_title,
+                'thumbnail': thumbnail,
+                'uploader': uploader
+        }
+        return [info]

youtube_dl/extractor/liveleak.py

@@ -0,0 +1,44 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+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)
+
+        video_url = self._search_regex(r'file: "(.*?)",',
+            webpage, u'video URL')
+
+        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+            webpage, u'title').replace('LiveLeak.com -', '').strip()
+
+        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+            webpage, u'description', fatal=False)
+
+        video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
+            webpage, u'uploader', fatal=False)
+
+        info = {
+            'id':  video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': video_title,
+            'description': video_description,
+            'uploader': video_uploader
+        }
+
+        return [info]

youtube_dl/extractor/metacafe.py

@@ -0,0 +1,110 @@
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_parse_qs,
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_str,
+
+    ExtractorError,
+)
+
+class MetacafeIE(InfoExtractor):
+    """Information Extractor for metacafe.com."""
+
+    _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+    _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+    _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
+    IE_NAME = u'metacafe'
+
+    def report_disclaimer(self):
+        """Report disclaimer retrieval."""
+        self.to_screen(u'Retrieving disclaimer')
+
+    def _real_initialize(self):
+        # Retrieve disclaimer
+        request = compat_urllib_request.Request(self._DISCLAIMER)
+        try:
+            self.report_disclaimer()
+            compat_urllib_request.urlopen(request).read()
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
+
+        # Confirm age
+        disclaimer_form = {
+            'filters': '0',
+            'submit': "Continue - I'm over 18",
+            }
+        request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
+        try:
+            self.report_age_confirmation()
+            compat_urllib_request.urlopen(request).read()
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            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:
+            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:
+            return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
+
+        # Retrieve video webpage to extract further information
+        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)
+        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        if mobj is not None:
+            mediaURL = compat_urllib_parse.unquote(mobj.group(1))
+            video_extension = mediaURL[-3:]
+
+            # Extract gdaKey if available
+            mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+            if mobj is None:
+                video_url = mediaURL
+            else:
+                gdaKey = mobj.group(1)
+                video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+        else:
+            mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+            if mobj is None:
+                raise ExtractorError(u'Unable to extract media URL')
+            vardict = compat_parse_qs(mobj.group(1))
+            if 'mediaData' not in vardict:
+                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:
+                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('key'))
+
+        mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
+        if mobj is None:
+            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:
+            raise ExtractorError(u'Unable to extract uploader nickname')
+        video_uploader = mobj.group(1)
+
+        return [{
+            'id':       video_id.decode('utf-8'),
+            'url':      video_url.decode('utf-8'),
+            'uploader': video_uploader.decode('utf-8'),
+            'upload_date':  None,
+            'title':    video_title,
+            'ext':      video_extension.decode('utf-8'),
+        }]

youtube_dl/extractor/mixcloud.py

@@ -0,0 +1,115 @@
+import json
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class MixcloudIE(InfoExtractor):
+    _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 report_download_json(self, file_id):
+        """Report JSON download."""
+        self.to_screen(u'Downloading json')
+
+    def get_urls(self, jsonData, fmt, bitrate='best'):
+        """Get urls from 'audio_formats' section in json"""
+        try:
+            bitrate_list = jsonData[fmt]
+            if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+                bitrate = max(bitrate_list) # select highest
+
+            url_list = jsonData[fmt][bitrate]
+        except TypeError: # we have no bitrate info.
+            url_list = jsonData[fmt]
+        return url_list
+
+    def check_urls(self, url_list):
+        """Returns 1st active url from list"""
+        for url in url_list:
+            try:
+                compat_urllib_request.urlopen(url)
+                return url
+            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error):
+                url = None
+
+        return None
+
+    def _print_formats(self, formats):
+        print('Available formats:')
+        for fmt in formats.keys():
+            for b in formats[fmt]:
+                try:
+                    ext = formats[fmt][b][0]
+                    print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
+                except TypeError: # we have no bitrate info
+                    ext = formats[fmt][0]
+                    print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
+                    break
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            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')
+
+        # construct API request
+        file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+        # retrieve .json file with links to files
+        request = compat_urllib_request.Request(file_url)
+        try:
+            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:
+            raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
+
+        # parse JSON
+        json_data = json.loads(jsonData)
+        player_url = json_data['player_swf_url']
+        formats = dict(json_data['audio_formats'])
+
+        req_format = self._downloader.params.get('format', None)
+
+        if self._downloader.params.get('listformats', None):
+            self._print_formats(formats)
+            return
+
+        if req_format is None or req_format == 'best':
+            for format_param in formats.keys():
+                url_list = self.get_urls(formats, format_param)
+                # check urls
+                file_url = self.check_urls(url_list)
+                if file_url is not None:
+                    break # got it!
+        else:
+            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)
+            format_param = req_format
+
+        return [{
+            'id': file_id.decode('utf-8'),
+            'url': file_url.decode('utf-8'),
+            'uploader': uploader.decode('utf-8'),
+            'upload_date': None,
+            'title': json_data['name'],
+            'ext': file_url.split('.')[-1].decode('utf-8'),
+            'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+            'thumbnail': json_data['thumbnail_url'],
+            'description': json_data['description'],
+            'player_url': player_url.decode('utf-8'),
+        }]

youtube_dl/extractor/mtv.py

@@ -0,0 +1,72 @@
+import re
+import socket
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class MTVIE(InfoExtractor):
+    _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
+    _WORKING = False
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        if not mobj.group('proto'):
+            url = 'http://' + url
+        video_id = mobj.group('videoid')
+
+        webpage = self._download_webpage(url, video_id)
+
+        #song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
+        #    webpage, u'song name', fatal=False)
+
+        video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
+            webpage, u'title')
+
+        mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
+            webpage, u'mtvn_uri', fatal=False)
+
+        content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
+            webpage, u'content id', fatal=False)
+
+        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
+        self.report_extraction(video_id)
+        request = compat_urllib_request.Request(videogen_url)
+        try:
+            metadataXml = compat_urllib_request.urlopen(request).read()
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
+
+        mdoc = xml.etree.ElementTree.fromstring(metadataXml)
+        renditions = mdoc.findall('.//rendition')
+
+        # For now, always pick the highest quality.
+        rendition = renditions[-1]
+
+        try:
+            _,_,ext = rendition.attrib['type'].partition('/')
+            format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
+            video_url = rendition.find('./src').text
+        except KeyError:
+            raise ExtractorError('Invalid rendition field.')
+
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'upload_date': None,
+            'title': video_title,
+            'ext': ext,
+            'format': format,
+        }
+
+        return [info]

youtube_dl/extractor/myspass.py

@@ -0,0 +1,64 @@
+import os.path
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse_urlparse,
+
+    ExtractorError,
+)
+
+
+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 = 'mp4'
+        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]

youtube_dl/extractor/myvideo.py

@@ -0,0 +1,164 @@
+import binascii
+import base64
+import hashlib
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_ord,
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+
+
+class MyVideoIE(InfoExtractor):
+    """Information Extractor for myvideo.de."""
+
+    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+    IE_NAME = u'myvideo'
+
+    # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
+    # Released into the Public Domain by Tristan Fischer on 2013-05-19
+    # https://github.com/rg3/youtube-dl/pull/842
+    def __rc4crypt(self,data, key):
+        x = 0
+        box = list(range(256))
+        for i in list(range(256)):
+            x = (x + box[i] + compat_ord(key[i % len(key)])) % 256
+            box[i], box[x] = box[x], box[i]
+        x = 0
+        y = 0
+        out = ''
+        for char in data:
+            x = (x + 1) % 256
+            y = (y + box[x]) % 256
+            box[x], box[y] = box[y], box[x]
+            out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
+        return out
+
+    def __md5(self,s):
+        return hashlib.md5(s).hexdigest().encode()
+
+    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)
+
+        GK = (
+          b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
+          b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
+          b'TnpsbA0KTVRkbU1tSTRNdz09'
+        )
+
+        # Get video webpage
+        webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        mobj = re.search('source src=\'(.+?)[.]([^.]+)\'', webpage)
+        if mobj is not None:
+            self.report_extraction(video_id)
+            video_url = mobj.group(1) + '.flv'
+
+            video_title = self._html_search_regex('<title>([^<]+)</title>',
+                webpage, u'title')
+
+            video_ext = self._search_regex('[.](.+?)$', video_url, u'extension')
+
+            return [{
+                'id':       video_id,
+                'url':      video_url,
+                'uploader': None,
+                'upload_date':  None,
+                'title':    video_title,
+                'ext':      video_ext,
+            }]
+
+        # try encxml
+        mobj = re.search('var flashvars={(.+?)}', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract video')
+
+        params = {}
+        encxml = ''
+        sec = mobj.group(1)
+        for (a, b) in re.findall('(.+?):\'(.+?)\',?', sec):
+            if not a == '_encxml':
+                params[a] = b
+            else:
+                encxml = compat_urllib_parse.unquote(b)
+        if not params.get('domain'):
+            params['domain'] = 'www.myvideo.de'
+        xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
+        if 'flash_playertype=MTV' in xmldata_url:
+            self._downloader.report_warning(u'avoiding MTV player')
+            xmldata_url = (
+                'http://www.myvideo.de/dynamic/get_player_video_xml.php'
+                '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
+            ) % video_id
+
+        # get enc data
+        enc_data = self._download_webpage(xmldata_url, video_id).split('=')[1]
+        enc_data_b = binascii.unhexlify(enc_data)
+        sk = self.__md5(
+            base64.b64decode(base64.b64decode(GK)) +
+            self.__md5(
+                str(video_id).encode('utf-8')
+            )
+        )
+        dec_data = self.__rc4crypt(enc_data_b, sk)
+
+        # extracting infos
+        self.report_extraction(video_id)
+
+        video_url = None
+        mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
+        if mobj:
+            video_url = compat_urllib_parse.unquote(mobj.group(1))
+            if 'myvideo2flash' in video_url:
+                self._downloader.report_warning(u'forcing RTMPT ...')
+                video_url = video_url.replace('rtmpe://', 'rtmpt://')
+
+        if not video_url:
+            # extract non rtmp videos
+            mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
+            if mobj is None:
+                raise ExtractorError(u'unable to extract url')
+            video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
+
+        video_file = self._search_regex('source=\'(.*?)\'', dec_data, u'video file')
+        video_file = compat_urllib_parse.unquote(video_file)
+
+        if not video_file.endswith('f4m'):
+            ppath, prefix = video_file.split('.')
+            video_playpath = '%s:%s' % (prefix, ppath)
+            video_hls_playlist = ''
+        else:
+            video_playpath = ''
+            video_hls_playlist = (
+                video_file
+            ).replace('.f4m', '.m3u8')
+
+        video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, u'swfobj')
+        video_swfobj = compat_urllib_parse.unquote(video_swfobj)
+
+        video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
+            webpage, u'title')
+
+        return [{
+            'id':                 video_id,
+            'url':                video_url,
+            'tc_url':             video_url,
+            'uploader':           None,
+            'upload_date':        None,
+            'title':              video_title,
+            'ext':                u'flv',
+            'play_path':          video_playpath,
+            'video_file':         video_file,
+            'video_hls_playlist': video_hls_playlist,
+            'player_url':         video_swfobj,
+        }]
+

youtube_dl/extractor/nba.py

@@ -0,0 +1,40 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class NBAIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.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(1)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+
+        shortened_video_id = video_id.rpartition('/')[2]
+        title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
+            webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
+
+        # It isn't there in the HTML it returns to us
+        # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
+
+        description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
+
+        info = {
+            'id': shortened_video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            # 'uploader_date': uploader_date,
+            'description': description,
+        }
+        return [info]

youtube_dl/extractor/photobucket.py

@@ -0,0 +1,66 @@
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    ExtractorError,
+)
+
+class PhotobucketIE(InfoExtractor):
+    """Information extractor for photobucket.com."""
+
+    # 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 _real_extract(self, url):
+        # Extract id from 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 = mobj.group('ext')
+
+        # Retrieve video webpage to extract further information
+        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
+        video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />',
+            webpage, u'video URL')
+
+        mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract title')
+        video_title = mobj.group(1).decode('utf-8')
+        video_uploader = mobj.group(2).decode('utf-8')
+
+        return [{
+            'id':       video_id.decode('utf-8'),
+            'url':      video_url.decode('utf-8'),
+            'uploader': video_uploader,
+            'upload_date':  None,
+            'title':    video_title,
+            'ext':      video_extension.decode('utf-8'),
+        }]

youtube_dl/extractor/pornotube.py

@@ -0,0 +1,41 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    unified_strdate,
+)
+
+
+class PornotubeIE(InfoExtractor):
+    _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)
+
+        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)",'
+        video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+        video_url = compat_urllib_parse.unquote(video_url)
+
+        #Get the uploaded date
+        VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
+        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
+        if upload_date: upload_date = unified_strdate(upload_date)
+
+        info = {'id': video_id,
+                'url': video_url,
+                'uploader': None,
+                'upload_date': upload_date,
+                'title': video_title,
+                'ext': 'flv',
+                'format': 'flv'}
+
+        return [info]

youtube_dl/extractor/rbmaradio.py

@@ -0,0 +1,44 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse_urlparse,
+
+    ExtractorError,
+)
+
+
+class RBMARadioIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('videoID')
+
+        webpage = self._download_webpage(url, video_id)
+
+        json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
+            webpage, u'json data', flags=re.MULTILINE)
+
+        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]

youtube_dl/extractor/redtube.py

@@ -0,0 +1,29 @@
+import re
+
+from .common import InfoExtractor
+
+
+class RedTubeIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        video_extension = 'mp4'        
+        webpage = self._download_webpage(url, video_id)
+
+        self.report_extraction(video_id)
+
+        video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
+            webpage, u'video URL')
+
+        video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+            webpage, u'title')
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      video_extension,
+            'title':    video_title,
+        }]

youtube_dl/extractor/soundcloud.py

@@ -0,0 +1,129 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+
+    ExtractorError,
+    unified_strdate,
+)
+
+
+class SoundcloudIE(InfoExtractor):
+    """Information extractor for soundcloud.com
+       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
+     """
+
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+    IE_NAME = u'soundcloud'
+
+    def report_resolve(self, video_id):
+        """Report information extraction."""
+        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:
+            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)
+        full_title = '%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'
+        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(full_title)
+
+        streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+        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': 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
+     """
+
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+    IE_NAME = u'soundcloud:set'
+
+    def report_resolve(self, video_id):
+        """Report information extraction."""
+        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:
+            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)
+        full_title = '%s/sets/%s' % (uploader, slug_title)
+
+        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(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')
+
+            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

youtube_dl/extractor/spiegel.py

@@ -0,0 +1,37 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+
+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)
+
+        video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
+            webpage, u'title')
+
+        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]

youtube_dl/extractor/stanfordoc.py

@@ -0,0 +1,112 @@
+import re
+import socket
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_http_client,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_request,
+
+    ExtractorError,
+    orderedSet,
+    unescapeHTML,
+)
+
+
+class StanfordOpenClassroomIE(InfoExtractor):
+    """Information extractor for Stanford's Open ClassRoom"""
+
+    _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 _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        if mobj.group('course') and mobj.group('video'): # A specific video
+            course = mobj.group('course')
+            video = mobj.group('video')
+            info = {
+                'id': course + '_' + video,
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            self.report_extraction(info['id'])
+            baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
+            xmlUrl = baseUrl + video + '.xml'
+            try:
+                metaXml = compat_urllib_request.urlopen(xmlUrl).read()
+            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                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:
+                raise ExtractorError(u'Invalid metadata XML file')
+            info['ext'] = info['url'].rpartition('.')[2]
+            return [info]
+        elif mobj.group('course'): # A course page
+            course = mobj.group('course')
+            info = {
+                'id': course,
+                'type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            coursepage = self._download_webpage(url, info['id'],
+                                        note='Downloading course info page',
+                                        errnote='Unable to download course info page')
+
+            info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
+
+            info['description'] = self._html_search_regex('<description>([^<]+)</description>',
+                coursepage, u'description', fatal=False)
+
+            links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
+            info['list'] = [
+                {
+                    'type': 'reference',
+                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
+                }
+                    for vpage in links]
+            results = []
+            for entry in info['list']:
+                assert entry['type'] == 'reference'
+                results += self.extract(entry['url'])
+            return results
+        else: # Root page
+            info = {
+                'id': 'Stanford OpenClassroom',
+                'type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            self.report_download_webpage(info['id'])
+            rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
+            try:
+                rootpage = compat_urllib_request.urlopen(rootURL).read()
+            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
+
+            info['title'] = info['id']
+
+            links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
+            info['list'] = [
+                {
+                    'type': 'reference',
+                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
+                }
+                    for cpage in links]
+
+            results = []
+            for entry in info['list']:
+                assert entry['type'] == 'reference'
+                results += self.extract(entry['url'])
+            return results

youtube_dl/extractor/statigram.py

@@ -0,0 +1,33 @@
+import re
+
+from .common import InfoExtractor
+
+class StatigramIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_regex(
+            r'<meta property="og:video:secure_url" content="(.+?)">',
+            webpage, u'video URL')
+        thumbnail_url = self._html_search_regex(
+            r'<meta property="og:image" content="(.+?)" />',
+            webpage, u'thumbnail URL', fatal=False)
+        html_title = self._html_search_regex(
+            r'<title>(.+?)</title>',
+            webpage, u'title')
+        title = html_title.rpartition(u' | Statigram')[0]
+        uploader_id = self._html_search_regex(
+            r'@([^ ]+)', title, u'uploader name', fatal=False)
+        ext = 'mp4'
+
+        return [{
+            'id':        video_id,
+            'url':       video_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+            'uploader_id' : uploader_id
+        }]

youtube_dl/extractor/steam.py

@@ -0,0 +1,63 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unescapeHTML,
+)
+
+
+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
+                """
+    _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
+    _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
+
+    @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 = self._VIDEO_PAGE_TEMPLATE % gameID
+        webpage = self._download_webpage(videourl, gameID)
+
+        if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
+            videourl = self._AGECHECK_TEMPLATE % gameID
+            self.report_age_confirmation()
+            webpage = self._download_webpage(videourl, gameID)
+
+        self.report_extraction(gameID)
+        game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
+                                             webpage, '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)]

youtube_dl/extractor/teamcoco.py

@@ -0,0 +1,46 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class TeamcocoIE(InfoExtractor):
+    _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        url_title = mobj.group('url_title')
+        webpage = self._download_webpage(url, url_title)
+
+        video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
+            webpage, u'video id')
+
+        self.report_extraction(video_id)
+
+        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+            webpage, u'title')
+
+        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
+            webpage, u'thumbnail', fatal=False)
+
+        video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
+            webpage, u'description', fatal=False)
+
+        data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
+        data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+
+        video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
+            data, u'video URL')
+
+        return [{
+            'id':          video_id,
+            'url':         video_url,
+            'ext':         'mp4',
+            'title':       video_title,
+            'thumbnail':   thumbnail,
+            'description': video_description,
+        }]

youtube_dl/extractor/ted.py

@@ -0,0 +1,79 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+
+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 _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_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
+                                                 webpage, 'playlist title')
+
+        playlist_entries = []
+        for m_video, m_name in zip(m_videos,m_names):
+            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)
+        video_name = m.group('name')
+        webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name)
+        self.report_extraction(video_name)
+        # If the url includes the language we get the title translated
+        title = self._html_search_regex(r'<span id="altHeadline" >(?P<title>.*)</span>',
+                                        webpage, 'title')
+        json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>',
+                                    webpage, 'json data')
+        info = json.loads(json_data)
+        desc = self._html_search_regex(r'<div class="talk-intro">.*?<p.*?>(.*?)</p>',
+                                       webpage, 'description', flags = re.DOTALL)
+        
+        thumbnail = self._search_regex(r'</span>[\s.]*</div>[\s.]*<img src="(.*?)"',
+                                       webpage, 'thumbnail')
+        info = {
+                'id': info['id'],
+                'url': info['htmlStreams'][-1]['file'],
+                'ext': 'mp4',
+                'title': title,
+                'thumbnail': thumbnail,
+                'description': desc,
+                }
+        return info

youtube_dl/extractor/tumblr.py

@@ -0,0 +1,41 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+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:
+           raise ExtractorError(u'Unable to extract video')
+        video_url = video.group('video_url')
+        ext = video.group('ext')
+
+        video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
+            webpage, u'thumbnail', fatal=False)  # We pick the first poster
+        if video_thumbnail: video_thumbnail = video_thumbnail.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
+        video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
+            webpage, u'title', flags=re.DOTALL)
+
+        return [{'id': video_id,
+                 'url': video_url,
+                 'title': video_title,
+                 'thumbnail': video_thumbnail,
+                 'ext': ext
+                 }]

youtube_dl/extractor/ustream.py

@@ -0,0 +1,36 @@
+import re
+
+from .common import InfoExtractor
+
+
+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)
+
+        self.report_extraction(video_id)
+
+        video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
+            webpage, u'title')
+
+        uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
+            webpage, u'uploader', fatal=False, flags=re.DOTALL)
+
+        thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
+            webpage, u'thumbnail', fatal=False)
+
+        info = {
+                'id': video_id,
+                'url': video_url,
+                'ext': 'flv',
+                'title': video_title,
+                'uploader': uploader,
+                'thumbnail': thumbnail,
+               }
+        return info

youtube_dl/extractor/vbox7.py

@@ -0,0 +1,46 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    ExtractorError,
+)
+
+
+class Vbox7IE(InfoExtractor):
+    """Information Extractor for Vbox7"""
+    _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
+
+    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)
+
+        redirect_page, urlh = self._download_webpage_handle(url, video_id)
+        new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
+        redirect_url = urlh.geturl() + new_location
+        webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
+
+        title = self._html_search_regex(r'<title>(.*)</title>',
+            webpage, u'title').split('/')[0].strip()
+
+        ext = "flv"
+        info_url = "http://vbox7.com/play/magare.do"
+        data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
+        info_request = compat_urllib_request.Request(info_url, data)
+        info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
+        if info_response is None:
+            raise ExtractorError(u'Unable to extract the media url')
+        (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
+
+        return [{
+            'id':        video_id,
+            'url':       final_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+        }]

youtube_dl/extractor/vimeo.py

@@ -0,0 +1,138 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+
+    clean_html,
+    get_element_by_attribute,
+    ExtractorError,
+    std_headers,
+)
+
+class VimeoIE(InfoExtractor):
+    """Information extractor for vimeo.com."""
+
+    # _VALID_URL matches Vimeo URLs
+    _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
+    IE_NAME = u'vimeo'
+
+    def _verify_video_password(self, url, video_id, webpage):
+        password = self._downloader.params.get('password', None)
+        if password is None:
+            raise ExtractorError(u'This video is protected by a password, use the --password option')
+        token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
+        data = compat_urllib_parse.urlencode({'password': password,
+                                              'token': token})
+        # I didn't manage to use the password with https
+        if url.startswith('https'):
+            pass_url = url.replace('https','http')
+        else:
+            pass_url = url
+        password_request = compat_urllib_request.Request(pass_url+'/password', data)
+        password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        password_request.add_header('Cookie', 'xsrft=%s' % token)
+        self._download_webpage(password_request, video_id,
+                               u'Verifying the password',
+                               u'Wrong password')
+
+    def _real_extract(self, url, new_video=True):
+        # Extract ID from URL
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+
+        video_id = mobj.group('id')
+        if not mobj.group('proto'):
+            url = 'https://' + url
+        if mobj.group('direct_link') or mobj.group('pro'):
+            url = 'https://vimeo.com/' + video_id
+
+        # Retrieve video webpage to extract further information
+        request = compat_urllib_request.Request(url, None, std_headers)
+        webpage = self._download_webpage(request, video_id)
+
+        # 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
+        try:
+            config = webpage.split(' = {config:')[1].split(',assets:')[0]
+            config = json.loads(config)
+        except:
+            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')
+
+            if re.search('If so please provide the correct password.', webpage):
+                self._verify_video_password(url, video_id, webpage)
+                return self._real_extract(url)
+            else:
+                raise ExtractorError(u'Unable to extract info section')
+
+        # Extract title
+        video_title = config["video"]["title"]
+
+        # Extract uploader and uploader_id
+        video_uploader = config["video"]["owner"]["name"]
+        video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
+
+        # Extract video thumbnail
+        video_thumbnail = config["video"]["thumbnail"]
+
+        # Extract video description
+        video_description = get_element_by_attribute("itemprop", "description", webpage)
+        if video_description: video_description = clean_html(video_description)
+        else: video_description = u''
+
+        # Extract upload date
+        video_upload_date = None
+        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) + mobj.group(2) + mobj.group(3)
+
+        # Vimeo specific: extract request signature and timestamp
+        sig = config['request']['signature']
+        timestamp = config['request']['timestamp']
+
+        # Vimeo specific: extract video codec and quality information
+        # First consider quality, then codecs, then take everything
+        # TODO bind to format param
+        codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
+        files = { 'hd': [], 'sd': [], 'other': []}
+        for codec_name, codec_extension in codecs:
+            if codec_name in config["video"]["files"]:
+                if 'hd' in config["video"]["files"][codec_name]:
+                    files['hd'].append((codec_name, codec_extension, 'hd'))
+                elif 'sd' in config["video"]["files"][codec_name]:
+                    files['sd'].append((codec_name, codec_extension, 'sd'))
+                else:
+                    files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+        for quality in ('hd', 'sd', 'other'):
+            if len(files[quality]) > 0:
+                video_quality = files[quality][0][2]
+                video_codec = files[quality][0][0]
+                video_extension = files[quality][0][1]
+                self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
+                break
+        else:
+            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())
+
+        return [{
+            '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,
+            'thumbnail':    video_thumbnail,
+            'description':  video_description,
+        }]

youtube_dl/extractor/vine.py

@@ -0,0 +1,37 @@
+import re
+
+from .common import InfoExtractor
+
+
+class VineIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'https://vine.co/v/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        self.report_extraction(video_id)
+
+        video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
+            webpage, u'video URL')
+
+        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+            webpage, u'title')
+
+        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
+            webpage, u'thumbnail', fatal=False)
+
+        uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
+            webpage, u'uploader', fatal=False, flags=re.DOTALL)
+
+        return [{
+            'id':        video_id,
+            'url':       video_url,
+            'ext':       'mp4',
+            'title':     video_title,
+            'thumbnail': thumbnail,
+            'uploader':  uploader,
+        }]

youtube_dl/extractor/worldstarhiphop.py

@@ -0,0 +1,44 @@
+import re
+
+from .common import InfoExtractor
+
+
+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):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage_src = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
+            webpage_src, u'video URL')
+
+        if 'mp4' in video_url:
+            ext = 'mp4'
+        else:
+            ext = 'flv'
+
+        video_title = self._html_search_regex(r"<title>(.*)</title>",
+            webpage_src, u'title')
+
+        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+        thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
+            webpage_src, u'thumbnail', fatal=False)
+
+        if not thumbnail:
+            _title = r"""candytitles.*>(.*)</span>"""
+            mobj = re.search(_title, webpage_src)
+            if mobj is not None:
+                video_title = mobj.group(1)
+
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : video_title,
+                    'thumbnail' : thumbnail,
+                    'ext' : ext,
+                    }]
+        return results

youtube_dl/extractor/xhamster.py

@@ -0,0 +1,61 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+
+class XHamsterIE(InfoExtractor):
+    """Information Extractor for xHamster"""
+    _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
+        webpage = self._download_webpage(mrss_url, video_id)
+
+        mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract media URL')
+        if len(mobj.group('server')) == 0:
+            video_url = compat_urllib_parse.unquote(mobj.group('file'))
+        else:
+            video_url = mobj.group('server')+'/key='+mobj.group('file')
+        video_extension = video_url.split('.')[-1]
+
+        video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
+            webpage, u'title')
+
+        # Can't see the description anywhere in the UI
+        # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
+        #     webpage, u'description', fatal=False)
+        # if video_description: video_description = unescapeHTML(video_description)
+
+        mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
+        if mobj:
+            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
+        else:
+            video_upload_date = None
+            self._downloader.report_warning(u'Unable to extract upload date')
+
+        video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+            webpage, u'uploader id', default=u'anonymous')
+
+        video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+            webpage, u'thumbnail', fatal=False)
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      video_extension,
+            'title':    video_title,
+            # 'description': video_description,
+            'upload_date': video_upload_date,
+            'uploader_id': video_uploader_id,
+            'thumbnail': video_thumbnail
+        }]

youtube_dl/extractor/xnxx.py

@@ -0,0 +1,45 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+
+class XNXXIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
+    VIDEO_URL_RE = r'flv_url=(.*?)&'
+    VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
+    VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
+
+    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)
+
+        # Get webpage content
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(self.VIDEO_URL_RE,
+            webpage, u'video URL')
+        video_url = compat_urllib_parse.unquote(video_url)
+
+        video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
+            webpage, u'title')
+
+        video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
+            webpage, u'thumbnail', fatal=False)
+
+        return [{
+            'id': video_id,
+            'url': video_url,
+            'uploader': None,
+            'upload_date': None,
+            'title': video_title,
+            'ext': 'flv',
+            'thumbnail': video_thumbnail,
+            'description': None,
+        }]

youtube_dl/extractor/xvideos.py

@@ -0,0 +1,43 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+)
+
+
+class XVideosIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+
+        webpage = self._download_webpage(url, video_id)
+
+        self.report_extraction(video_id)
+
+        # Extract video URL
+        video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
+            webpage, u'video URL'))
+
+        # Extract title
+        video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
+            webpage, u'title')
+
+        # Extract video thumbnail
+        video_thumbnail = self._search_regex(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, u'thumbnail', fatal=False)
+
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'uploader': None,
+            'upload_date': None,
+            'title': video_title,
+            'ext': 'flv',
+            'thumbnail': video_thumbnail,
+            'description': None,
+        }
+
+        return [info]

youtube_dl/extractor/yahoo.py

@@ -0,0 +1,113 @@
+import datetime
+import itertools
+import json
+import re
+
+from .common import InfoExtractor, SearchInfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+
+    ExtractorError,
+)
+
+class YahooIE(InfoExtractor):
+    """Information extractor for screen.yahoo.com."""
+    _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.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('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
+
+class YahooSearchIE(SearchInfoExtractor):
+    """Information Extractor for Yahoo! Video search queries."""
+
+    _MAX_RESULTS = 1000
+    IE_NAME = u'screen.yahoo:search'
+    _SEARCH_KEY = 'yvsearch'
+
+    def _get_n_results(self, query, n):
+        """Get a specified number of results for a query"""
+
+        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
+
+        return res

youtube_dl/extractor/youjizz.py

@@ -0,0 +1,45 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class YouJizzIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('videoid')
+
+        # Get webpage content
+        webpage = self._download_webpage(url, video_id)
+
+        # Get the video title
+        video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
+            webpage, u'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
+        video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+            webpage, u'video URL')
+
+        info = {'id': video_id,
+                'url': video_url,
+                'title': video_title,
+                'ext': 'flv',
+                'format': 'flv',
+                'player_url': embed_page_url}
+
+        return [info]

youtube_dl/extractor/youku.py

@@ -0,0 +1,104 @@
+import json
+import math
+import random
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class YoukuIE(InfoExtractor):
+    _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
+
+    def _gen_sid(self):
+        nowTime = int(time.time() * 1000)
+        random1 = random.randint(1000,1998)
+        random2 = random.randint(1000,9999)
+
+        return "%d%d%d" %(nowTime,random1,random2)
+
+    def _get_file_ID_mix_string(self, seed):
+        mixed = []
+        source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
+        seed = float(seed)
+        for i in range(len(source)):
+            seed  =  (seed * 211 + 30031 ) % 65536
+            index  =  math.floor(seed / 65536 * len(source) )
+            mixed.append(source[int(index)])
+            source.remove(source[int(index)])
+        #return ''.join(mixed)
+        return mixed
+
+    def _get_file_id(self, fileId, seed):
+        mixed = self._get_file_ID_mix_string(seed)
+        ids = fileId.split('*')
+        realId = []
+        for ch in ids:
+            if ch:
+                realId.append(mixed[int(ch)])
+        return ''.join(realId)
+
+    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')
+
+        info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+
+        jsondata = self._download_webpage(info_url, video_id)
+
+        self.report_extraction(video_id)
+        try:
+            config = json.loads(jsondata)
+
+            video_title =  config['data'][0]['title']
+            seed = config['data'][0]['seed']
+
+            format = self._downloader.params.get('format', None)
+            supported_format = list(config['data'][0]['streamfileids'].keys())
+
+            if format is None or format == 'best':
+                if 'hd2' in supported_format:
+                    format = 'hd2'
+                else:
+                    format = 'flv'
+                ext = u'flv'
+            elif format == 'worst':
+                format = 'mp4'
+                ext = u'mp4'
+            else:
+                format = 'flv'
+                ext = u'flv'
+
+
+            fileid = config['data'][0]['streamfileids'][format]
+            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()
+        fileid = self._get_file_id(fileid, seed)
+
+        #column 8,9 of fileid represent the segment number
+        #fileid[7:9] should be changed
+        for index, key in enumerate(keys):
+
+            temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
+            download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+
+            info = {
+                'id': '%s_part%02d' % (video_id, index),
+                'url': download_url,
+                'uploader': None,
+                'upload_date': None,
+                'title': video_title,
+                'ext': ext,
+            }
+            files_info.append(info)
+
+        return files_info