release 2015.01.08

They seem to reencode quite frequently, so simply remove the md5 sum.

.gitignore

@@ -31,3 +31,5 @@ updates_key.pem
 test/testdata
 .tox
 youtube-dl.zsh
+.idea
+.idea/*

.travis.yml

@@ -9,7 +9,6 @@ notifications:
   email:
     - filippo.valsorda@gmail.com
     - phihag@phihag.de
-    - jaime.marquinez.ferrandiz+travis@gmail.com
     - yasoob.khld@gmail.com
 #  irc:
 #    channels:

AUTHORS

@@ -93,3 +93,11 @@ Zack Fernandes
 cryptonaut
 Adrian Kretz
 Mathias Rav
+Petr Kutalek
+Will Glynn
+Max Reimann
+Cédric Luthi
+Thijs Vermeir
+Joel Leclerc
+Christopher Krooss
+Ondřej Caletka

CONTRIBUTING.md

@@ -44,7 +44,7 @@ In particular, every site support request issue should only pertain to services
 
 ###  Is anyone going to need the feature?
 
-Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
 
 ###  Is your question about youtube-dl?
 

Makefile

@@ -1,4 +1,4 @@
-all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
+all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
 	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp
@@ -46,11 +46,11 @@ test:
 ot: offlinetest
 
 offlinetest: codetest
-	nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations
+	nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists
 
 tar: youtube-dl.tar.gz
 
-.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest
+.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
 
 pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
 
@@ -63,11 +63,14 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	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
+	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
 	python devscripts/make_contributing.py README.md CONTRIBUTING.md
 
+supportedsites:
+	python devscripts/make_supportedsites.py docs/supportedsites.md
+
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 

README.md

@@ -248,14 +248,15 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Video Format Options:
     -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes: -f 22/17/18 .  -f
-                                     mp4 , -f m4a and  -f flv  are also
-                                     supported. You can also use the special
-                                     names "best", "bestvideo", "bestaudio",
-                                     "worst", "worstvideo" and "worstaudio". By
-                                     default, youtube-dl will pick the best
-                                     quality. Use commas to download multiple
-                                     audio formats, such as -f
+                                     preference using slashes, as in -f 22/17/18
+                                     .  Instead of format codes, you can select
+                                     by extension for the extensions aac, m4a,
+                                     mp3, mp4, ogg, wav, webm. You can also use
+                                     the special names "best", "bestvideo",
+                                     "bestaudio", "worst".  By default, youtube-
+                                     dl will pick the best quality. Use commas
+                                     to download multiple audio formats, such as
+                                     -f
                                      136/137/mp4/bestvideo,140/m4a/bestaudio.
                                      You can merge the video and audio of two
                                      formats into a single file using -f <video-
@@ -326,7 +327,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # 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/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -449,6 +450,14 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 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).
 
+### How can I detect whether a given URL is supported by youtube-dl?
+
+For one, have a look at the [list of supported sites](docs/supportedsites). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
+
+It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
+
+If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
+
 # DEVELOPER INSTRUCTIONS
 
 Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.

devscripts/gh-pages/update-sites.py

@@ -16,7 +16,7 @@ def main():
         template = tmplf.read()
 
     ie_htmls = []
-    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
+    for ie in youtube_dl.list_extractors(age_limit=None):
         ie_html = '<b>{}</b>'.format(ie.IE_NAME)
         ie_desc = getattr(ie, 'IE_DESC', None)
         if ie_desc is False:

devscripts/make_supportedsites.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import io
+import optparse
+import os
+import sys
+
+
+# Import youtube_dl
+ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
+sys.path.append(ROOT_DIR)
+import youtube_dl
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
+    options, args = parser.parse_args()
+    if len(args) != 1:
+        parser.error('Expected an output filename')
+
+    outfile, = args
+
+    def gen_ies_md(ies):
+        for ie in ies:
+            ie_md = '**{0}**'.format(ie.IE_NAME)
+            ie_desc = getattr(ie, 'IE_DESC', None)
+            if ie_desc is False:
+                continue
+            if ie_desc is not None:
+                ie_md += ': {0}'.format(ie.IE_DESC)
+            if not ie.working():
+                ie_md += ' (Currently broken)'
+            yield ie_md
+
+    ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower())
+    out = '# Supported sites\n' + ''.join(
+        ' - ' + md + '\n'
+        for md in gen_ies_md(ies))
+
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
+        outf.write(out)
+
+if __name__ == '__main__':
+    main()

docs/supportedsites.md

@@ -0,0 +1,500 @@
+# Supported sites
+ - **1up.com**
+ - **220.ro**
+ - **24video**
+ - **3sat**
+ - **4tube**
+ - **56.com**
+ - **5min**
+ - **8tracks**
+ - **9gag**
+ - **abc.net.au**
+ - **AcademicEarth:Course**
+ - **AddAnime**
+ - **AdobeTV**
+ - **AdultSwim**
+ - **Aftonbladet**
+ - **AlJazeera**
+ - **Allocine**
+ - **anitube.se**
+ - **AnySex**
+ - **Aparat**
+ - **AppleTrailers**
+ - **archive.org**: archive.org videos
+ - **ARD**
+ - **ARD:mediathek**
+ - **arte.tv**
+ - **arte.tv:+7**
+ - **arte.tv:concert**
+ - **arte.tv:creative**
+ - **arte.tv:ddc**
+ - **arte.tv:embed**
+ - **arte.tv:future**
+ - **audiomack**
+ - **AUEngine**
+ - **Azubu**
+ - **bambuser**
+ - **bambuser:channel**
+ - **Bandcamp**
+ - **Bandcamp:album**
+ - **bbc.co.uk**: BBC iPlayer
+ - **Beeg**
+ - **BehindKink**
+ - **Bet**
+ - **Bild**: Bild.de
+ - **BiliBili**
+ - **blinkx**
+ - **blip.tv:user**
+ - **BlipTV**
+ - **Bloomberg**
+ - **Bpb**: Bundeszentrale für politische Bildung
+ - **BR**: Bayerischer Rundfunk Mediathek
+ - **Break**
+ - **Brightcove**
+ - **BuzzFeed**
+ - **BYUtv**
+ - **Canal13cl**
+ - **canalc2.tv**
+ - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
+ - **CBS**
+ - **CBSNews**: CBS News
+ - **CeskaTelevize**
+ - **channel9**: Channel 9
+ - **Chilloutzone**
+ - **Cinchcast**
+ - **Cinemassacre**
+ - **clipfish**
+ - **cliphunter**
+ - **Clipsyndicate**
+ - **Cloudy**
+ - **Clubic**
+ - **cmt.com**
+ - **CNET**
+ - **CNN**
+ - **CNNBlogs**
+ - **CollegeHumor**
+ - **ComCarCoff**
+ - **ComedyCentral**
+ - **ComedyCentralShows**: The Daily Show / The Colbert Report
+ - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
+ - **Cracked**
+ - **Criterion**
+ - **Crunchyroll**
+ - **crunchyroll:playlist**
+ - **CSpan**: C-SPAN
+ - **culturebox.francetvinfo.fr**
+ - **dailymotion**
+ - **dailymotion:playlist**
+ - **dailymotion:user**
+ - **daum.net**
+ - **DBTV**
+ - **DeezerPlaylist**
+ - **defense.gouv.fr**
+ - **Discovery**
+ - **divxstage**: DivxStage
+ - **Dotsub**
+ - **Dropbox**
+ - **DrTuber**
+ - **DRTV**
+ - **Dump**
+ - **dvtv**: http://video.aktualne.cz/
+ - **EbaumsWorld**
+ - **eHow**
+ - **Einthusan**
+ - **eitb.tv**
+ - **EllenTV**
+ - **EllenTV:clips**
+ - **ElPais**: El País
+ - **EMPFlix**
+ - **Engadget**
+ - **Eporner**
+ - **Escapist**
+ - **EveryonesMixtape**
+ - **exfm**: ex.fm
+ - **ExpoTV**
+ - **ExtremeTube**
+ - **facebook**
+ - **faz.net**
+ - **fc2**
+ - **fernsehkritik.tv**
+ - **fernsehkritik.tv:postecke**
+ - **Firedrive**
+ - **Firstpost**
+ - **firsttv**: Видеоархив - Первый канал
+ - **Flickr**
+ - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **Foxgay**
+ - **FoxNews**
+ - **france2.fr:generation-quoi**
+ - **FranceCulture**
+ - **FranceInter**
+ - **francetv**: France 2, 3, 4, 5 and Ô
+ - **francetvinfo.fr**
+ - **Freesound**
+ - **freespeech.org**
+ - **FreeVideo**
+ - **FunnyOrDie**
+ - **Gamekings**
+ - **GameOne**
+ - **gameone:playlist**
+ - **GameSpot**
+ - **GameStar**
+ - **Gametrailers**
+ - **GDCVault**
+ - **generic**: Generic downloader that works on some sites
+ - **GiantBomb**
+ - **Glide**: Glide mobile video messages (glide.me)
+ - **Globo**
+ - **GodTube**
+ - **GoldenMoustache**
+ - **Golem**
+ - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
+ - **Goshgay**
+ - **Grooveshark**
+ - **Groupon**
+ - **Hark**
+ - **Heise**
+ - **Helsinki**: helsinki.fi
+ - **HentaiStigma**
+ - **HornBunny**
+ - **HostingBulk**
+ - **HotNewHipHop**
+ - **Howcast**
+ - **HowStuffWorks**
+ - **HuffPost**: Huffington Post
+ - **Hypem**
+ - **Iconosquare**
+ - **ign.com**
+ - **imdb**: Internet Movie Database trailers
+ - **imdb:list**: Internet Movie Database lists
+ - **Ina**
+ - **InfoQ**
+ - **Instagram**
+ - **instagram:user**: Instagram user profile
+ - **InternetVideoArchive**
+ - **IPrima**
+ - **ivi**: ivi.ru
+ - **ivi:compilation**: ivi.ru compilations
+ - **Izlesene**
+ - **JadoreCettePub**
+ - **JeuxVideo**
+ - **Jove**
+ - **jpopsuki.tv**
+ - **Jukebox**
+ - **Kankan**
+ - **keek**
+ - **KeezMovies**
+ - **KhanAcademy**
+ - **KickStarter**
+ - **kontrtube**: KontrTube.ru - Труба зовёт
+ - **KrasView**: Красвью
+ - **Ku6**
+ - **la7.tv**
+ - **Laola1Tv**
+ - **lifenews**: LIFE | NEWS
+ - **LiveLeak**
+ - **livestream**
+ - **livestream:original**
+ - **lrt.lt**
+ - **lynda**: lynda.com videos
+ - **lynda:course**: lynda.com online courses
+ - **m6**
+ - **macgamestore**: MacGameStore trailers
+ - **mailru**: Видео@Mail.Ru
+ - **Malemotion**
+ - **MDR**
+ - **metacafe**
+ - **Metacritic**
+ - **Mgoon**
+ - **Minhateca**
+ - **MinistryGrid**
+ - **mitele.es**
+ - **mixcloud**
+ - **MLB**
+ - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
+ - **Mofosex**
+ - **Mojvideo**
+ - **Moniker**: allmyvideos.net and vidspot.net
+ - **mooshare**: Mooshare.biz
+ - **Morningstar**: morningstar.com
+ - **Motherless**
+ - **Motorsport**: motorsport.com
+ - **MovieClips**
+ - **Moviezine**
+ - **movshare**: MovShare
+ - **MPORA**
+ - **MTV**
+ - **mtviggy.com**
+ - **mtvservices:embedded**
+ - **MuenchenTV**: münchen.tv
+ - **MusicPlayOn**
+ - **MusicVault**
+ - **muzu.tv**
+ - **MySpace**
+ - **MySpace:album**
+ - **MySpass**
+ - **myvideo**
+ - **MyVidster**
+ - **Naver**
+ - **NBA**
+ - **NBC**
+ - **NBCNews**
+ - **ndr**: NDR.de - Mediathek
+ - **NDTV**
+ - **NerdCubedFeed**
+ - **Newgrounds**
+ - **Newstube**
+ - **nfb**: National Film Board of Canada
+ - **nfl.com**
+ - **nhl.com**
+ - **nhl.com:videocenter**: NHL videocenter category
+ - **niconico**: ニコニコ動画
+ - **NiconicoPlaylist**
+ - **Noco**
+ - **Normalboots**
+ - **NosVideo**
+ - **novamov**: NovaMov
+ - **Nowness**
+ - **nowvideo**: NowVideo
+ - **npo.nl**
+ - **NRK**
+ - **NRKTV**
+ - **NTV**
+ - **Nuvid**
+ - **NYTimes**
+ - **ocw.mit.edu**
+ - **OktoberfestTV**
+ - **on.aol.com**
+ - **Ooyala**
+ - **orf:oe1**: Radio Österreich 1
+ - **orf:tvthek**: ORF TVthek
+ - **ORFFM4**: radio FM4
+ - **parliamentlive.tv**: UK parliament videos
+ - **Patreon**
+ - **PBS**
+ - **Phoenix**
+ - **Photobucket**
+ - **PlanetaPlay**
+ - **play.fm**
+ - **played.to**
+ - **Playvid**
+ - **plus.google**: Google Plus
+ - **pluzz.francetv.fr**
+ - **podomatic**
+ - **PornHd**
+ - **PornHub**
+ - **Pornotube**
+ - **PornoXO**
+ - **PromptFile**
+ - **prosiebensat1**: ProSiebenSat.1 Digital
+ - **Pyvideo**
+ - **QuickVid**
+ - **radio.de**
+ - **radiofrance**
+ - **Rai**
+ - **RBMARadio**
+ - **RedTube**
+ - **Restudy**
+ - **ReverbNation**
+ - **RingTV**
+ - **RottenTomatoes**
+ - **Roxwel**
+ - **RTBF**
+ - **RTLnow**
+ - **rtlxl.nl**
+ - **RTP**
+ - **RTS**: RTS.ch
+ - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:live**: RTVE.es live streams
+ - **RUHD**
+ - **rutube**: Rutube videos
+ - **rutube:channel**: Rutube channels
+ - **rutube:movie**: Rutube movies
+ - **rutube:person**: Rutube person videos
+ - **RUTV**: RUTV.RU
+ - **Sapo**: SAPO Vídeos
+ - **savefrom.net**
+ - **SBS**: sbs.com.au
+ - **SciVee**
+ - **screen.yahoo:search**: Yahoo screen search
+ - **Screencast**
+ - **ScreencastOMatic**
+ - **ScreenwaveMedia**
+ - **ServingSys**
+ - **Sexu**
+ - **SexyKarma**: Sexy Karma and Watch Indian Porn
+ - **Shared**
+ - **ShareSix**
+ - **Sina**
+ - **Slideshare**
+ - **Slutload**
+ - **smotri**: Smotri.com
+ - **smotri:broadcast**: Smotri.com broadcasts
+ - **smotri:community**: Smotri.com community videos
+ - **smotri:user**: Smotri.com user videos
+ - **Snotr**
+ - **Sockshare**
+ - **Sohu**
+ - **soundcloud**
+ - **soundcloud:playlist**
+ - **soundcloud:set**
+ - **soundcloud:user**
+ - **Soundgasm**
+ - **southpark.cc.com**
+ - **southpark.de**
+ - **Space**
+ - **Spankwire**
+ - **Spiegel**
+ - **Spiegel:Article**: Articles on spiegel.de
+ - **Spiegeltv**
+ - **Spike**
+ - **Sport5**
+ - **SportBox**
+ - **SportDeutschland**
+ - **SRMediathek**: Süddeutscher Rundfunk
+ - **stanfordoc**: Stanford Open ClassRoom
+ - **Steam**
+ - **streamcloud.eu**
+ - **StreamCZ**
+ - **SunPorno**
+ - **SWRMediathek**
+ - **Syfy**
+ - **SztvHu**
+ - **Tagesschau**
+ - **Tapely**
+ - **Tass**
+ - **teachertube**: teachertube.com videos
+ - **teachertube:user:collection**: teachertube.com user and collection videos
+ - **TeachingChannel**
+ - **Teamcoco**
+ - **TeamFour**
+ - **TechTalks**
+ - **techtv.mit.edu**
+ - **TED**
+ - **tegenlicht.vpro.nl**
+ - **TeleBruxelles**
+ - **telecinco.es**
+ - **TeleMB**
+ - **TenPlay**
+ - **TF1**
+ - **TheOnion**
+ - **ThePlatform**
+ - **TheSixtyOne**
+ - **ThisAV**
+ - **THVideo**
+ - **THVideoPlaylist**
+ - **tinypic**: tinypic.com videos
+ - **tlc.com**
+ - **tlc.de**
+ - **TMZ**
+ - **TNAFlix**
+ - **tou.tv**
+ - **Toypics**: Toypics user profile
+ - **ToypicsUser**: Toypics user profile
+ - **TrailerAddict** (Currently broken)
+ - **Trilulilu**
+ - **TruTube**
+ - **Tube8**
+ - **Tudou**
+ - **Tumblr**
+ - **TuneIn**
+ - **Turbo**
+ - **Tutv**
+ - **tv.dfb.de**
+ - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **tvp.pl**
+ - **TVPlay**: TV3Play and related services
+ - **Twitch**
+ - **Ubu**
+ - **udemy**
+ - **udemy:course**
+ - **Unistra**
+ - **Urort**: NRK P3 Urørt
+ - **ustream**
+ - **ustream:channel**
+ - **Vbox7**
+ - **VeeHD**
+ - **Veoh**
+ - **Vesti**: Вести.Ru
+ - **Vevo**
+ - **VGTV**
+ - **vh1.com**
+ - **Vice**
+ - **Viddler**
+ - **video.google:search**: Google Video search
+ - **video.mit.edu**
+ - **VideoBam**
+ - **VideoDetective**
+ - **videofy.me**
+ - **videolectures.net**
+ - **VideoMega**
+ - **VideoPremium**
+ - **VideoTt**: video.tt - Your True Tube
+ - **videoweed**: VideoWeed
+ - **Vidme**
+ - **Vidzi**
+ - **viki**
+ - **vimeo**
+ - **vimeo:album**
+ - **vimeo:channel**
+ - **vimeo:group**
+ - **vimeo:likes**: Vimeo user likes
+ - **vimeo:review**: Review pages on vimeo
+ - **vimeo:user**
+ - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
+ - **Vimple**: Vimple.ru
+ - **Vine**
+ - **vine:user**
+ - **vk.com**
+ - **vk.com:user-videos**: vk.com:All of a user's videos
+ - **Vodlocker**
+ - **Vporn**
+ - **VRT**
+ - **vube**: Vube.com
+ - **VuClip**
+ - **vulture.com**
+ - **Walla**
+ - **WashingtonPost**
+ - **wat.tv**
+ - **WayOfTheMaster**
+ - **WDR**
+ - **wdr:mobile**
+ - **WDRMaus**: Sendung mit der Maus
+ - **Weibo**
+ - **Wimp**
+ - **Wistia**
+ - **WorldStarHipHop**
+ - **wrzuta.pl**
+ - **XBef**
+ - **XboxClips**
+ - **XHamster**
+ - **XMinus**
+ - **XNXX**
+ - **XTube**
+ - **XTubeUser**: XTube user profile
+ - **XVideos**
+ - **Yahoo**: Yahoo screen and movies
+ - **YesJapan**
+ - **Ynet**
+ - **YouJizz**
+ - **Youku**
+ - **YouPorn**
+ - **YourUpload**
+ - **youtube**: YouTube.com
+ - **youtube:channel**: YouTube.com channels
+ - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
+ - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
+ - **youtube:playlist**: YouTube.com playlists
+ - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
+ - **youtube:search**: YouTube.com searches
+ - **youtube:search:date**: YouTube.com searches, newest videos first
+ - **youtube:search_url**: YouTube.com search URLs
+ - **youtube:show**: YouTube.com (multi-season) shows
+ - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
+ - **youtube:toplist**: YouTube.com top lists, "yttoplist:{channel}:{list title}" (Example: "yttoplist:music:Top Tracks")
+ - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
+ - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
+ - **ZDF**
+ - **ZDFChannel**
+ - **zingmp3:album**: mp3.zing.vn albums
+ - **zingmp3:song**: mp3.zing.vn songs

setup.cfg

@@ -2,5 +2,5 @@
 universal = True
 
 [flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build
 ignore = E501

test/helper.py

@@ -82,24 +82,14 @@ class FakeYDL(YoutubeDL):
 
 def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
-        t = getattr(ie, '_TEST', None)
-        if t:
-            assert not hasattr(ie, '_TESTS'), \
-                '%s has _TEST and _TESTS' % type(ie).__name__
-            tests = [t]
-        else:
-            tests = getattr(ie, '_TESTS', [])
-        for t in tests:
-            if not include_onlymatching and t.get('only_matching', False):
-                continue
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
+        for tc in ie.get_testcases(include_onlymatching):
+            yield tc
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 
-def expect_info_dict(self, expected_dict, got_dict):
+def expect_info_dict(self, got_dict, expected_dict):
     for info_field, expected in expected_dict.items():
         if isinstance(expected, compat_str) and expected.startswith('re:'):
             got = got_dict.get(info_field)

test/test_InfoExtractor.py

@@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
         self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
 
+    def test_html_search_meta(self):
+        ie = self.ie
+        html = '''
+            <meta name="a" content="1" />
+            <meta name='b' content='2'>
+            <meta name="c" content='3'>
+            <meta name=d content='4'>
+            <meta property="e" content='5' >
+            <meta content="6" name="f">
+        '''
+
+        self.assertEqual(ie._html_search_meta('a', html), '1')
+        self.assertEqual(ie._html_search_meta('b', html), '2')
+        self.assertEqual(ie._html_search_meta('c', html), '3')
+        self.assertEqual(ie._html_search_meta('d', html), '4')
+        self.assertEqual(ie._html_search_meta('e', html), '5')
+        self.assertEqual(ie._html_search_meta('f', html), '6')
+
 if __name__ == '__main__':
     unittest.main()

test/test_YoutubeDL.py

@@ -8,6 +8,8 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+import copy
+
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
@@ -192,6 +194,37 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-high')
 
+    def test_format_selection_audio_exts(self):
+        formats = [
+            {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+            {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
+        ]
+
+        info_dict = _make_result(formats)
+        ydl = YDL({'format': 'best'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'aac-64')
+
+        ydl = YDL({'format': 'mp3'})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'mp3-64')
+
+        ydl = YDL({'prefer_free_formats': True})
+        ie = YoutubeIE(ydl)
+        ie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(copy.deepcopy(info_dict))
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'ogg-64')
+
     def test_format_selection_video(self):
         formats = [
             {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
@@ -218,7 +251,7 @@ class TestFormatSelection(unittest.TestCase):
             # 3D
             '85', '84', '102', '83', '101', '82', '100',
             # Dash video
-            '138', '137', '248', '136', '247', '135', '246',
+            '137', '248', '136', '247', '135', '246',
             '245', '244', '134', '243', '133', '242', '160',
             # Dash audio
             '141', '172', '140', '171', '139',

test/test_download.py

@@ -155,7 +155,7 @@ def generator(test_case):
             if is_playlist:
                 self.assertEqual(res_dict['_type'], 'playlist')
                 self.assertTrue('entries' in res_dict)
-                expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
+                expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 
             if 'playlist_mincount' in test_case:
                 assertGreaterEqual(
@@ -204,7 +204,7 @@ def generator(test_case):
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 
-                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
+                expect_info_dict(self, info_dict, tc.get('info_dict', {}))
         finally:
             try_rm_tcs_files()
             if is_playlist and res_dict is not None and res_dict.get('entries'):

test/test_subtitles.py

@@ -17,6 +17,7 @@ from youtube_dl.extractor import (
     TEDIE,
     VimeoIE,
     WallaIE,
+    CeskaTelevizeIE,
 )
 
 
@@ -88,6 +89,14 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         subtitles = self.getSubtitles()
         self.assertTrue(subtitles['it'] is not None)
 
+    def test_youtube_translated_subtitles(self):
+        # This video has a subtitles track, which can be translated
+        self.url = 'Ky9eprVWzlI'
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslangs'] = ['it']
+        subtitles = self.getSubtitles()
+        self.assertTrue(subtitles['it'] is not None)
+
     def test_youtube_nosubtitles(self):
         self.DL.expect_warning('video doesn\'t have subtitles')
         self.url = 'n5BB19UTcdA'
@@ -309,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles):
         self.assertEqual(len(subtitles), 0)
 
 
+class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
+    url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
+    IE = CeskaTelevizeIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning('Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning('Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['cs']))
+        self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4')
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning('video doesn\'t have subtitles')
+        self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -16,6 +16,7 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    age_restricted,
     args_to_str,
     clean_html,
     DateRange,
@@ -402,5 +403,12 @@ Trying to open render node...
 Success at /dev/dri/renderD128.
 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 
+    def test_age_restricted(self):
+        self.assertFalse(age_restricted(None, 10))  # unrestricted content
+        self.assertFalse(age_restricted(1, None))  # unrestricted policy
+        self.assertFalse(age_restricted(8, 10))
+        self.assertTrue(age_restricted(18, 14))
+        self.assertFalse(age_restricted(18, 18))
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -63,6 +63,7 @@ from .utils import (
     YoutubeDLHandler,
     prepend_extension,
     args_to_str,
+    age_restricted,
 )
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
@@ -550,13 +551,8 @@ class YoutubeDL(object):
             max_views = self.params.get('max_views')
             if max_views is not None and view_count > max_views:
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
-        age_limit = self.params.get('age_limit')
-        if age_limit is not None:
-            actual_age_limit = info_dict.get('age_limit')
-            if actual_age_limit is None:
-                actual_age_limit = 0
-            if age_limit < actual_age_limit:
-                return 'Skipping "' + title + '" because it is age restricted'
+        if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
+            return 'Skipping "%s" because it is age restricted' % title
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
         return None
@@ -790,7 +786,7 @@ class YoutubeDL(object):
             if video_formats:
                 return video_formats[0]
         else:
-            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
+            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
             if format_spec in extensions:
                 filter_f = lambda f: f['ext'] == format_spec
             else:
@@ -1016,13 +1012,13 @@ class YoutubeDL(object):
             descfn = filename + '.description'
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
+            elif info_dict.get('description') is None:
+                self.report_warning('There\'s no description to write.')
             else:
                 try:
                     self.to_screen('[info] Writing video description to: ' + descfn)
                     with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
                         descfile.write(info_dict['description'])
-                except (KeyError, TypeError):
-                    self.report_warning('There\'s no description to write.')
                 except (OSError, IOError):
                     self.report_error('Cannot write description file ' + descfn)
                     return
@@ -1149,8 +1145,7 @@ class YoutubeDL(object):
                 except (PostProcessingError) as err:
                     self.report_error('postprocessing: %s' % str(err))
                     return
-
-        self.record_download_archive(info_dict)
+                self.record_download_archive(info_dict)
 
     def download(self, url_list):
         """Download a given list of URLs."""
@@ -1334,7 +1329,9 @@ class YoutubeDL(object):
         formats = info_dict.get('formats', [info_dict])
         idlen = max(len('format code'),
                     max(len(f['format_id']) for f in formats))
-        formats_s = [line(f, idlen) for f in formats]
+        formats_s = [
+            line(f, idlen) for f in formats
+            if f.get('preference') is None or f['preference'] >= -1000]
         if len(formats) > 1:
             formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
             formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'

youtube_dl/__init__.py

@@ -38,7 +38,7 @@ from .update import update_self
 from .downloader import (
     FileDownloader,
 )
-from .extractor import gen_extractors
+from .extractor import gen_extractors, list_extractors
 from .YoutubeDL import YoutubeDL
 
 
@@ -95,24 +95,22 @@ def _real_main(argv=None):
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
-    extractors = gen_extractors()
-
     if opts.list_extractors:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
                 compat_print('  ' + mu)
         sys.exit(0)
     if opts.list_extractor_descriptions:
-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):
             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
-                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
+                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             compat_print(desc)
@@ -365,3 +363,5 @@ def main(argv=None):
         sys.exit('ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
+
+__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

youtube_dl/downloader/hls.py

@@ -11,7 +11,6 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
-    check_executable,
     encodeFilename,
 )
 
@@ -27,16 +26,13 @@ class HlsFD(FileDownloader):
             '-bsf:a', 'aac_adtstoasc',
             encodeFilename(tmpfilename, for_subprocess=True)]
 
-        for program in ['avconv', 'ffmpeg']:
-            if check_executable(program, ['-version']):
-                break
-        else:
+        ffpp = FFmpegPostProcessor(downloader=self)
+        program = ffpp._executable
+        if program is None:
             self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
-        cmd = [program] + args
-
-        ffpp = FFmpegPostProcessor(downloader=self)
         ffpp.check_version()
+        cmd = [program] + args
 
         retval = subprocess.call(cmd)
         if retval == 0:

youtube_dl/downloader/mplayer.py

@@ -4,8 +4,8 @@ import os
 import subprocess
 
 from .common import FileDownloader
-from ..compat import compat_subprocess_get_DEVNULL
 from ..utils import (
+    check_executable,
     encodeFilename,
 )
 
@@ -20,11 +20,7 @@ class MplayerFD(FileDownloader):
             'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
             '-dumpstream', '-dumpfile', tmpfilename, url]
         # Check for mplayer first
-        try:
-            subprocess.call(
-                ['mplayer', '-h'],
-                stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
+        if not check_executable('mplayer', ['-h']):
             self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
             return False
 

youtube_dl/extractor/__init__.py

@@ -3,9 +3,11 @@ from __future__ import unicode_literals
 from .abc import ABCIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
 from .aftonbladet import AftonbladetIE
 from .aljazeera import AlJazeeraIE
+from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
 from .aol import AolIE
@@ -23,6 +25,7 @@ from .arte import (
     ArteTVDDCIE,
     ArteTVEmbedIE,
 )
+from .atresplayer import AtresPlayerIE
 from .audiomack import AudiomackIE
 from .auengine import AUEngineIE
 from .azubu import AzubuIE
@@ -63,10 +66,12 @@ from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
+    CNNArticleIE,
 )
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
+from .commonmistakes import CommonMistakesIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
@@ -88,12 +93,14 @@ from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
+from .dvtv import DVTVIE
 from .dump import DumpIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
+from .echomsk import EchoMskIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
@@ -106,6 +113,7 @@ from .elpais import ElPaisIE
 from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
+from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
@@ -151,6 +159,7 @@ from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .giantbomb import GiantBombIE
+from .giga import GigaIE
 from .glide import GlideIE
 from .globo import GloboIE
 from .godtube import GodTubeIE
@@ -164,8 +173,10 @@ from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .heise import HeiseIE
+from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
@@ -263,6 +274,7 @@ from .nbc import (
 )
 from .ndr import NDRIE
 from .ndtv import NDTVIE
+from .nerdcubed import NerdCubedFeedIE
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nfb import NFBIE
@@ -289,6 +301,7 @@ from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
 from .oktoberfesttv import OktoberfestTVIE
 from .ooyala import OoyalaIE
+from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
@@ -313,6 +326,7 @@ from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .quickvid import QuickVidIE
 from .radiode import RadioDeIE
+from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
@@ -333,6 +347,7 @@ from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
+    RutubeEmbedIE,
     RutubeMovieIE,
     RutubePersonIE,
 )
@@ -403,6 +418,7 @@ from .ted import TEDIE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telemb import TeleMBIE
+from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
@@ -461,6 +477,7 @@ from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
+from .vier import VierIE, VierVideosIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -496,6 +513,7 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
+from .webofstories import WebOfStoriesIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -508,6 +526,7 @@ from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
+from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
@@ -530,7 +549,7 @@ from .youtube import (
     YoutubeSearchURLIE,
     YoutubeShowIE,
     YoutubeSubscriptionsIE,
-    YoutubeTopListIE,
+    YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
     YoutubeWatchLaterIE,
@@ -556,6 +575,17 @@ def gen_extractors():
     return [klass() for klass in _ALL_CLASSES]
 
 
+def list_extractors(age_limit):
+    """
+    Return a list of extractors that are suitable for the given age,
+    sorted by extractor ID.
+    """
+
+    return sorted(
+        filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
+        key=lambda ie: ie.IE_NAME.lower())
+
+
 def get_info_extractor(ie_name):
     """Returns the info extractor class with the given ie_name"""
     return globals()[ie_name + 'IE']

youtube_dl/extractor/adobetv.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    str_to_int,
+)
+
+
+class AdobeTVIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
+        'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
+        'info_dict': {
+            'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
+            'ext': 'mp4',
+            'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
+            'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'upload_date': '20110914',
+            'duration': 60,
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player = self._parse_json(
+            self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
+            video_id)
+
+        title = player.get('title') or self._search_regex(
+            r'data-title="([^"]+)"', webpage, 'title')
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        upload_date = unified_strdate(
+            self._html_search_meta('datepublished', webpage, 'upload date'))
+
+        duration = parse_duration(
+            self._html_search_meta('duration', webpage, 'duration')
+            or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
+
+        view_count = str_to_int(self._search_regex(
+            r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
+            webpage, 'view count'))
+
+        formats = [{
+            'url': source['src'],
+            'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
+            'tbr': source.get('bitrate'),
+        } for source in player['sources']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/alphaporno.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    parse_duration,
+    parse_filesize,
+    int_or_none,
+)
+
+
+class AlphaPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
+        'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
+        'info_dict': {
+            'id': '258807',
+            'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
+            'ext': 'mp4',
+            'title': 'Sensual striptease porn with Samantha Alexandra',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'timestamp': 1418694611,
+            'upload_date': '20141216',
+            'duration': 387,
+            'filesize_approx': 54120000,
+            'tbr': 1145,
+            'categories': list,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
+
+        video_url = self._search_regex(
+            r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
+        ext = self._html_search_meta(
+            'encodingFormat', webpage, 'ext', default='.mp4')[1:]
+
+        title = self._search_regex(
+            [r'<meta content="([^"]+)" itemprop="description">',
+             r'class="title" itemprop="name">([^<]+)<'],
+            webpage, 'title')
+        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage, 'upload date'))
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration'))
+        filesize_approx = parse_filesize(self._html_search_meta(
+            'contentSize', webpage, 'file size'))
+        bitrate = int_or_none(self._html_search_meta(
+            'bitrate', webpage, 'bitrate'))
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'ext': ext,
+            'title': title,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'filesize_approx': filesize_approx,
+            'tbr': bitrate,
+            'categories': categories,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/archiveorg.py

@@ -1,42 +1,48 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
-    _TEST = {
-        "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
-        'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _TESTS = [{
+        'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
         'info_dict': {
-            "title": "1968 Demo - FJCC Conference Presentation Reel #1",
-            "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
-            "upload_date": "19681210",
-            "uploader": "SRI International"
+            'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
+            'ext': 'ogv',
+            'title': '1968 Demo - FJCC Conference Presentation Reel #1',
+            'description': 'md5:1780b464abaca9991d8968c877bb53ed',
+            'upload_date': '19681210',
+            'uploader': 'SRI International'
         }
-    }
+    }, {
+        'url': 'https://archive.org/details/Cops1922',
+        'md5': '18f2a19e6d89af8425671da1cf3d4e04',
+        'info_dict': {
+            'id': 'Cops1922',
+            'ext': 'ogv',
+            'title': 'Buster Keaton\'s "Cops" (1922)',
+            'description': 'md5:70f72ee70882f713d4578725461ffcc3',
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         json_url = url + ('?' if '?' in url else '&') + 'output=json'
-        json_data = self._download_webpage(json_url, video_id)
-        data = json.loads(json_data)
+        data = self._download_json(json_url, video_id)
 
-        title = data['metadata']['title'][0]
-        description = data['metadata']['description'][0]
-        uploader = data['metadata']['creator'][0]
-        upload_date = unified_strdate(data['metadata']['date'][0])
+        def get_optional(data_dict, field):
+            return data_dict['metadata'].get(field, [None])[0]
+
+        title = get_optional(data, 'title')
+        description = get_optional(data, 'description')
+        uploader = get_optional(data, 'creator')
+        upload_date = unified_strdate(get_optional(data, 'date'))
 
         formats = [
             {

youtube_dl/extractor/arte.py

@@ -37,7 +37,7 @@ class ArteTvIE(InfoExtractor):
             config_xml_url, video_id, note='Downloading configuration')
 
         formats = [{
-            'forma_id': q.attrib['quality'],
+            'format_id': q.attrib['quality'],
             # The playpath starts at 'mp4:', if we don't manually
             # split the url, rtmpdump will incorrectly parse them
             'url': q.text.split('mp4:', 1)[0],
@@ -133,7 +133,7 @@ class ArteTVPlus7IE(InfoExtractor):
                 'width': int_or_none(f.get('width')),
                 'height': int_or_none(f.get('height')),
                 'tbr': int_or_none(f.get('bitrate')),
-                'quality': qfunc(f['quality']),
+                'quality': qfunc(f.get('quality')),
                 'source_preference': source_pref,
             }
 

youtube_dl/extractor/atresplayer.py

@@ -0,0 +1,114 @@
+from __future__ import unicode_literals
+
+import time
+import hmac
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_request,
+    int_or_none,
+    float_or_none,
+    xpath_text,
+    ExtractorError,
+)
+
+
+class AtresPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
+            'md5': 'efd56753cda1bb64df52a3074f62e38a',
+            'info_dict': {
+                'id': 'capitulo-10-especial-solidario-nochebuena',
+                'ext': 'mp4',
+                'title': 'Especial Solidario de Nochebuena',
+                'description': 'md5:e2d52ff12214fa937107d21064075bf1',
+                'duration': 5527.6,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
+            'only_matching': True,
+        },
+    ]
+
+    _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
+    _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
+    _TIMESTAMP_SHIFT = 30000
+
+    _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
+    _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
+    _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
+    _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        episode_id = self._search_regex(
+            r'episode="([^"]+)"', webpage, 'episode id')
+
+        timestamp = int_or_none(self._download_webpage(
+            self._TIME_API_URL,
+            video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
+        timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
+        token = hmac.new(
+            self._MAGIC.encode('ascii'),
+            (episode_id + timestamp_shifted).encode('utf-8')
+        ).hexdigest()
+
+        formats = []
+        for fmt in ['windows', 'android_tablet']:
+            request = compat_urllib_request.Request(
+                self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
+            request.add_header('Youtubedl-user-agent', self._USER_AGENT)
+
+            fmt_json = self._download_json(
+                request, video_id, 'Downloading %s video JSON' % fmt)
+
+            result = fmt_json.get('resultDes')
+            if result.lower() != 'ok':
+                raise ExtractorError(
+                    '%s returned error: %s' % (self.IE_NAME, result), expected=True)
+
+            for _, video_url in fmt_json['resultObject'].items():
+                if video_url.endswith('/Manifest'):
+                    formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'android',
+                        'preference': 1,
+                    })
+        self._sort_formats(formats)
+
+        player = self._download_json(
+            self._PLAYER_URL_TEMPLATE % episode_id,
+            episode_id)
+
+        path_data = player.get('pathData')
+
+        episode = self._download_xml(
+            self._EPISODE_URL_TEMPLATE % path_data,
+            video_id, 'Downloading episode XML')
+
+        duration = float_or_none(xpath_text(
+            episode, './media/asset/info/technical/contentDuration', 'duration'))
+
+        art = episode.find('./media/asset/info/art')
+        title = xpath_text(art, './name', 'title')
+        description = xpath_text(art, './description', 'description')
+        thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/auengine.py

@@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse
 from ..utils import (
     determine_ext,
     ExtractorError,
+    remove_end,
 )
 
 
@@ -27,23 +28,18 @@ class AUEngineIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
-        title = title.strip()
-        links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
-        links = map(compat_urllib_parse.unquote, links)
+        title = self._html_search_regex(
+            r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title')
+        video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage)
+        video_url = compat_urllib_parse.unquote(video_urls[0])
+        thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage)
+        thumbnail = compat_urllib_parse.unquote(thumbnails[0])
 
-        thumbnail = None
-        video_url = None
-        for link in links:
-            if link.endswith('.png'):
-                thumbnail = link
-            elif '/videos/' in link:
-                video_url = link
         if not video_url:
             raise ExtractorError('Could not find video URL')
+
         ext = '.' + determine_ext(video_url)
-        if ext == title[-len(ext):]:
-            title = title[:-len(ext)]
+        title = remove_end(title, ext)
 
         return {
             'id': video_id,

youtube_dl/extractor/bbccouk.py

@@ -10,7 +10,7 @@ from ..compat import compat_HTTPError
 class BBCCoUkIE(SubtitlesInfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
 
     _TESTS = [
         {
@@ -18,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope: Leonard Cohen',
-                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'title': 'Kaleidoscope, Leonard Cohen',
+                'description': 'The Canadian poet and songwriter reflects on his musical career.',
                 'duration': 1740,
             },
             'params': {
@@ -71,7 +71,54 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
                 'skip_download': True,
             },
             'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        },
+        }, {
+            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
+            'info_dict': {
+                'id': 'b04v209v',
+                'ext': 'flv',
+                'title': 'Pete Tong, The Essential New Tune Special',
+                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'note': 'Audio',
+            'info_dict': {
+                'id': 'p02frcch',
+                'ext': 'flv',
+                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
+                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
+                'duration': 3507,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
+            'note': 'Video',
+            'info_dict': {
+                'id': 'p025c103',
+                'ext': 'flv',
+                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
+                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
+                'duration': 226,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
+            'only_matching': True,
+        }
     ]
 
     def _extract_asx_playlist(self, connection, programme_id):
@@ -203,6 +250,59 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
 
         return formats, subtitles
 
+    def _download_playlist(self, playlist_id):
+        try:
+            playlist = self._download_json(
+                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
+                playlist_id, 'Downloading playlist JSON')
+
+            version = playlist.get('defaultAvailableVersion')
+            if version:
+                smp_config = version['smpConfig']
+                title = smp_config['title']
+                description = smp_config['summary']
+                for item in smp_config['items']:
+                    kind = item['kind']
+                    if kind != 'programme' and kind != 'radioProgramme':
+                        continue
+                    programme_id = item.get('vpid')
+                    duration = int(item.get('duration'))
+                    formats, subtitles = self._download_media_selector(programme_id)
+                return programme_id, title, description, duration, formats, subtitles
+        except ExtractorError as ee:
+            if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                raise
+
+        # fallback to legacy playlist
+        playlist = self._download_xml(
+            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
+            playlist_id, 'Downloading legacy playlist XML')
+
+        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % playlist_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % playlist_id
+            elif reason == 'noMedia':
+                msg = 'Episode %s is not currently available' % playlist_id
+            else:
+                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+            programme_id = item.get('identifier')
+            duration = int(item.get('duration'))
+            formats, subtitles = self._download_media_selector(programme_id)
+
+        return programme_id, title, description, duration, formats, subtitles
+
     def _real_extract(self, url):
         group_id = self._match_id(url)
 
@@ -219,32 +319,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             duration = player['duration']
             formats, subtitles = self._download_media_selector(programme_id)
         else:
-            playlist = self._download_xml(
-                'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id,
-                group_id, 'Downloading playlist XML')
-
-            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
-            if no_items is not None:
-                reason = no_items.get('reason')
-                if reason == 'preAvailability':
-                    msg = 'Episode %s is not yet available' % group_id
-                elif reason == 'postAvailability':
-                    msg = 'Episode %s is no longer available' % group_id
-                elif reason == 'noMedia':
-                    msg = 'Episode %s is not currently available' % group_id
-                else:
-                    msg = 'Episode %s is not available: %s' % (group_id, reason)
-                raise ExtractorError(msg, expected=True)
-
-            for item in self._extract_items(playlist):
-                kind = item.get('kind')
-                if kind != 'programme' and kind != 'radioProgramme':
-                    continue
-                title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-                description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
-                programme_id = item.get('identifier')
-                duration = int(item.get('duration'))
-                formats, subtitles = self._download_media_selector(programme_id)
+            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(programme_id, subtitles)

youtube_dl/extractor/bet.py

@@ -16,7 +16,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
+                'id': '406429c6-1b8a-463e-83fc-814adb81a9db',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
                 'title': 'BET News Presents: A Conversation With President Obama',

youtube_dl/extractor/bilibili.py

@@ -4,9 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_parse_qs
 from ..utils import (
-    ExtractorError,
     int_or_none,
     unified_strdate,
 )
@@ -54,45 +52,38 @@ class BiliBiliIE(InfoExtractor):
         thumbnail = self._html_search_meta(
             'thumbnailUrl', video_code, 'thumbnail', fatal=False)
 
-        player_params = compat_parse_qs(self._html_search_regex(
-            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
-            webpage, 'player params'))
+        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
-        if 'cid' in player_params:
-            cid = player_params['cid'][0]
+        lq_doc = self._download_xml(
+            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
+            video_id,
+            note='Downloading LQ video info'
+        )
+        lq_durl = lq_doc.find('./durl')
+        formats = [{
+            'format_id': 'lq',
+            'quality': 1,
+            'url': lq_durl.find('./url').text,
+            'filesize': int_or_none(
+                lq_durl.find('./size'), get_attr='text'),
+        }]
 
-            lq_doc = self._download_xml(
-                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
-                video_id,
-                note='Downloading LQ video info'
-            )
-            lq_durl = lq_doc.find('.//durl')
-            formats = [{
-                'format_id': 'lq',
-                'quality': 1,
-                'url': lq_durl.find('./url').text,
+        hq_doc = self._download_xml(
+            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
+            video_id,
+            note='Downloading HQ video info',
+            fatal=False,
+        )
+        if hq_doc is not False:
+            hq_durl = hq_doc.find('./durl')
+            formats.append({
+                'format_id': 'hq',
+                'quality': 2,
+                'ext': 'flv',
+                'url': hq_durl.find('./url').text,
                 'filesize': int_or_none(
-                    lq_durl.find('./size'), get_attr='text'),
-            }]
-
-            hq_doc = self._download_xml(
-                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
-                video_id,
-                note='Downloading HQ video info',
-                fatal=False,
-            )
-            if hq_doc is not False:
-                hq_durl = hq_doc.find('.//durl')
-                formats.append({
-                    'format_id': 'hq',
-                    'quality': 2,
-                    'ext': 'flv',
-                    'url': hq_durl.find('./url').text,
-                    'filesize': int_or_none(
-                        hq_durl.find('./size'), get_attr='text'),
-                })
-        else:
-            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
+                    hq_durl.find('./size'), get_attr='text'),
+            })
 
         self._sort_formats(formats)
         return {

youtube_dl/extractor/canalplus.py

@@ -5,6 +5,8 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
+    HEADRequest,
     unified_strdate,
     url_basename,
     qualities,
@@ -76,6 +78,16 @@ class CanalplusIE(InfoExtractor):
 
         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
 
+        fmt_url = next(iter(media.find('VIDEOS'))).text
+        if '/geo' in fmt_url.lower():
+            response = self._request_webpage(
+                HEADRequest(fmt_url), video_id,
+                'Checking if the video is georestricted')
+            if '/blocage' in response.geturl():
+                raise ExtractorError(
+                    'The video is not available in your country',
+                    expected=True)
+
         formats = []
         for fmt in media.find('VIDEOS'):
             format_url = fmt.text

youtube_dl/extractor/ceskatelevize.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
@@ -11,49 +11,42 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
 )
 
 
-class CeskaTelevizeIE(InfoExtractor):
+class CeskaTelevizeIE(SubtitlesInfoExtractor):
     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
 
     _TESTS = [
         {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
+            'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
             'info_dict': {
-                'id': '213512120230004',
-                'ext': 'flv',
-                'title': 'První republika: Španělská chřipka',
-                'duration': 3107.4,
+                'id': '214411058091220',
+                'ext': 'mp4',
+                'title': 'Hyde Park Civilizace',
+                'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 3350,
             },
             'params': {
-                'skip_download': True,  # requires rtmpdump
+                # m3u8 download
+                'skip_download': True,
             },
-            'skip': 'Works only from Czech Republic.',
-        },
-        {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
-            'info_dict': {
-                'id': '20138143440',
-                'ext': 'flv',
-                'title': 'Tsatsiki, maminka a policajt',
-                'duration': 6754.1,
-            },
-            'params': {
-                'skip_download': True,  # requires rtmpdump
-            },
-            'skip': 'Works only from Czech Republic.',
         },
         {
             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
             'info_dict': {
                 'id': '14716',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
-                'duration': 90,
+                'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 88.4,
             },
             'params': {
-                'skip_download': True,  # requires rtmpdump
+                # m3u8 download
+                'skip_download': True,
             },
         },
     ]
@@ -80,8 +73,9 @@ class CeskaTelevizeIE(InfoExtractor):
             'requestSource': 'iVysilani',
         }
 
-        req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
-                                            data=compat_urllib_parse.urlencode(data))
+        req = compat_urllib_request.Request(
+            'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+            data=compat_urllib_parse.urlencode(data))
 
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         req.add_header('x-addr', '127.0.0.1')
@@ -90,39 +84,72 @@ class CeskaTelevizeIE(InfoExtractor):
 
         playlistpage = self._download_json(req, video_id)
 
-        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
+        playlist_url = playlistpage['url']
+        if playlist_url == 'error_region':
+            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+
+        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
         req.add_header('Referer', url)
 
-        playlist = self._download_xml(req, video_id)
+        playlist = self._download_json(req, video_id)
 
+        item = playlist['playlist'][0]
         formats = []
-        for i in playlist.find('smilRoot/body'):
-            if 'AD' not in i.attrib['id']:
-                base_url = i.attrib['base']
-                parsedurl = compat_urllib_parse_urlparse(base_url)
-                duration = i.attrib['duration']
-
-                for video in i.findall('video'):
-                    if video.attrib['label'] != 'AD':
-                        format_id = video.attrib['label']
-                        play_path = video.attrib['src']
-                        vbr = int(video.attrib['system-bitrate'])
-
-                        formats.append({
-                            'format_id': format_id,
-                            'url': base_url,
-                            'vbr': vbr,
-                            'play_path': play_path,
-                            'app': parsedurl.path[1:] + '?' + parsedurl.query,
-                            'rtmp_live': True,
-                            'ext': 'flv',
-                        })
-
+        for format_id, stream_url in item['streamUrls'].items():
+            formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
         self._sort_formats(formats)
 
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        duration = float_or_none(item.get('duration'))
+        thumbnail = item.get('previewImageUrl')
+
+        subtitles = {}
+        subs = item.get('subtitles')
+        if subs:
+            subtitles['cs'] = subs[0]['url']
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles))
+
         return {
             'id': episode_id,
-            'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
-            'duration': float(duration),
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }
+
+    @staticmethod
+    def _fix_subtitles(subtitles):
+        """ Convert millisecond-based subtitles to SRT """
+        if subtitles is None:
+            return subtitles  # subtitles not requested
+
+        def _msectotimecode(msec):
+            """ Helper utility to convert milliseconds to timecode """
+            components = []
+            for divider in [1000, 60, 60, 100]:
+                components.append(msec % divider)
+                msec //= divider
+            return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
+
+        def _fix_subtitle(subtitle):
+            for line in subtitle.splitlines():
+                m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
+                if m:
+                    yield m.group(1)
+                    start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
+                    yield "{0} --> {1}".format(start, stop)
+                else:
+                    yield line
+
+        fixed_subtitles = {}
+        for k, v in subtitles.items():
+            fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v))
+        return fixed_subtitles

youtube_dl/extractor/cnn.py

@@ -11,14 +11,14 @@ from ..utils import (
 
 
 class CNNIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
+    _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
         'md5': '3e6121ea48df7e2259fe73a0628605c4',
         'info_dict': {
-            'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
+            'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
             'ext': 'mp4',
             'title': 'Nadal wins 8th French Open title',
             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
@@ -35,6 +35,16 @@ class CNNIE(InfoExtractor):
             "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
             "upload_date": "20130821",
         }
+    }, {
+        'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
+        'md5': 'f14d02ebd264df951feb2400e2c25a1b',
+        'info_dict': {
+            'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
+            'ext': 'mp4',
+            'title': 'Nashville Ep. 1: Hand crafted skateboards',
+            'description': 'md5:e7223a503315c9f150acac52e76de086',
+            'upload_date': '20141222',
+        }
     }]
 
     def _real_extract(self, url):
@@ -127,3 +137,28 @@ class CNNBlogsIE(InfoExtractor):
             'url': cnn_url,
             'ie_key': CNNIE.ie_key(),
         }
+
+
+class CNNArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
+    _TEST = {
+        'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
+        'md5': '275b326f85d80dff7592a9820f5dc887',
+        'info_dict': {
+            'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn',
+            'ext': 'mp4',
+            'title': 'Obama: We\'re not going to be intimidated',
+            'description': 'md5:e735586f3dc936075fa654a4d91b21f9',
+            'upload_date': '20141220',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': 'http://cnn.com/video/?/video/' + cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/common.py

@@ -21,6 +21,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    age_restricted,
     clean_html,
     compiled_regex_type,
     ExtractorError,
@@ -40,7 +41,7 @@ class InfoExtractor(object):
     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
+    passed to the YoutubeDL. The YoutubeDL processes this
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
@@ -92,6 +93,8 @@ class InfoExtractor(object):
                                  by this field, regardless of all other values.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
+                                 < -1000 to hide the format (if there is
+                                    another one which is strictly better)
                     * language_preference  Is this in the correct requested
                                  language?
                                  10 if it's what the URL is about,
@@ -589,9 +592,9 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?ix)<meta
+            r'''(?isx)<meta
                     (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -875,6 +878,35 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def get_testcases(self, include_onlymatching=False):
+        t = getattr(self, '_TEST', None)
+        if t:
+            assert not hasattr(self, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(self).__name__
+            tests = [t]
+        else:
+            tests = getattr(self, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
+            t['name'] = type(self).__name__[:-len('IE')]
+            yield t
+
+    def is_suitable(self, age_limit):
+        """ Test whether the extractor is generally suitable for the given
+        age limit (i.e. pornographic sites are not, all others usually are) """
+
+        any_restricted = False
+        for tc in self.get_testcases(include_onlymatching=False):
+            if 'playlist' in tc:
+                tc = tc['playlist'][0]
+            is_restricted = age_restricted(
+                tc.get('info_dict', {}).get('age_limit'), age_limit)
+            if not is_restricted:
+                return True
+            any_restricted = any_restricted or is_restricted
+        return not any_restricted
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonmistakes.py

@@ -0,0 +1,29 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class CommonMistakesIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'''(?x)
+        (?:url|URL)
+    '''
+
+    _TESTS = [{
+        'url': 'url',
+        'only_matching': True,
+    }, {
+        'url': 'URL',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        msg = (
+            'You\'ve asked youtube-dl to download the URL "%s". '
+            'That doesn\'t make any sense. '
+            'Simply remove the parameter in your command or configuration.'
+        ) % url
+        if self._downloader.params.get('verbose'):
+            msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
+        raise ExtractorError(msg, expected=True)

youtube_dl/extractor/crunchyroll.py

@@ -29,8 +29,8 @@ from .common import InfoExtractor
 
 
 class CrunchyrollIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
             'id': '645513',
@@ -46,7 +46,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
+        'only_matching': True,
+    }]
 
     _FORMAT_IDS = {
         '360': ('60', '106'),
@@ -225,7 +228,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
         formats = []
-        for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
+        for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
             streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')

youtube_dl/extractor/daum.py

@@ -38,7 +38,7 @@ class DaumIE(InfoExtractor):
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
-            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
+            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
             webpage, 'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
         info = self._download_xml(

youtube_dl/extractor/dbtv.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     float_or_none,
     int_or_none,
@@ -61,7 +62,7 @@ class DBTVIE(InfoExtractor):
         self._sort_formats(formats)
 
         return {
-            'id': video['id'],
+            'id': compat_str(video['id']),
             'display_id': display_id,
             'title': video['title'],
             'description': clean_html(video['desc']),

youtube_dl/extractor/dvtv.py

@@ -0,0 +1,125 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    unescapeHTML,
+    ExtractorError,
+)
+
+
+class DVTVIE(InfoExtractor):
+    IE_NAME = 'dvtv'
+    IE_DESC = 'http://video.aktualne.cz/'
+
+    _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
+
+    _TESTS = [{
+        'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
+        'md5': '67cb83e4a955d36e1b5d31993134a0c2',
+        'info_dict': {
+            'id': 'dc0768de855511e49e4b0025900fea04',
+            'ext': 'mp4',
+            'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
+        }
+    }, {
+        'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/',
+        'md5': '6388f1941b48537dbd28791f712af8bf',
+        'info_dict': {
+            'id': '72c02230849211e49f60002590604f2e',
+            'ext': 'mp4',
+            'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala',
+        }
+    }, {
+        'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
+        'info_dict': {
+            'title': 'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
+            'id': '973eb3bc854e11e498be002590604f2e',
+        },
+        'playlist': [{
+            'md5': 'da7ca6be4935532241fa9520b3ad91e4',
+            'info_dict': {
+                'id': 'b0b40906854d11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne'
+            }
+        }, {
+            'md5': '5f7652a08b05009c1292317b449ffea2',
+            'info_dict': {
+                'id': '420ad9ec854a11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka'
+            }
+        }, {
+            'md5': '498eb9dfa97169f409126c617e2a3d64',
+            'info_dict': {
+                'id': '95d35580846a11e4b6d20025900fea04',
+                'ext': 'mp4',
+                'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?'
+            }
+        }, {
+            'md5': 'b8dc6b744844032dab6ba3781a7274b9',
+            'info_dict': {
+                'id': '6fe14d66853511e4833a0025900fea04',
+                'ext': 'mp4',
+                'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády'
+            }
+        }],
+    }, {
+        'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
+        'only_matching': True,
+    }]
+
+    def _parse_video_metadata(self, js, video_id):
+        metadata = self._parse_json(js, video_id, transform_source=js_to_json)
+
+        formats = []
+        for video in metadata['sources']:
+            ext = video['type'][6:]
+            formats.append({
+                'url': video['file'],
+                'ext': ext,
+                'format_id': '%s-%s' % (ext, video['label']),
+                'height': int(video['label'].rstrip('p')),
+                'fps': 25,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': metadata['mediaid'],
+            'title': unescapeHTML(metadata['title']),
+            'thumbnail': self._proto_relative_url(metadata['image'], 'http:'),
+            'formats': formats
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        # single video
+        item = self._search_regex(
+            r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});",
+            webpage, 'video', default=None, fatal=False)
+
+        if item:
+            return self._parse_video_metadata(item, video_id)
+
+        # playlist
+        items = re.findall(
+            r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);",
+            webpage)
+
+        if items:
+            return {
+                '_type': 'playlist',
+                'id': video_id,
+                'title': self._og_search_title(webpage),
+                'entries': [self._parse_video_metadata(i, video_id) for i in items]
+            }
+
+        raise ExtractorError('Could not find neither video nor playlist')

youtube_dl/extractor/echomsk.py

@@ -0,0 +1,46 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EchoMskIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.echo.msk.ru/sounds/1464134.html',
+        'md5': '2e44b3b78daff5b458e4dbc37f191f7c',
+        'info_dict': {
+            'id': '1464134',
+            'ext': 'mp3',
+            'title': 'Особое мнение - 29 декабря 2014, 19:08',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        audio_url = self._search_regex(
+            r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL')
+
+        title = self._html_search_regex(
+            r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>',
+            webpage, 'title')
+
+        air_date = self._html_search_regex(
+            r'(?s)<div class="date">(.+?)</div>',
+            webpage, 'date', fatal=False, default=None)
+
+        if air_date:
+            air_date = re.sub(r'(\s)\1+', r'\1', air_date)
+            if air_date:
+                title = '%s - %s' % (title, air_date)
+
+        return {
+            'id': video_id,
+            'url': audio_url,
+            'title': title,
+        }

youtube_dl/extractor/ellentv.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import json
 
 from .common import InfoExtractor
@@ -12,32 +11,49 @@ from ..utils import (
 
 
 class EllenTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
+    _TESTS = [{
         'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
         'md5': 'e4af06f3bf0d5f471921a18db5764642',
         'info_dict': {
             'id': '0-7jqrsr18',
             'ext': 'mp4',
             'title': 'What\'s Wrong with These Photos? A Whole Lot',
+            'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
             'timestamp': 1406876400,
             'upload_date': '20140801',
         }
-    }
+    }, {
+        'url': 'http://ellentube.com/videos/0-dvzmabd5/',
+        'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
+        'info_dict': {
+            'id': '0-dvzmabd5',
+            'ext': 'mp4',
+            'title': '1 year old twin sister makes her brother laugh',
+            'description': '1 year old twin sister makes her brother laugh',
+            'timestamp': 1419542075,
+            'upload_date': '20141225',
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_meta('VideoURL', webpage, 'url')
+        title = self._og_search_title(webpage, default=None) or self._search_regex(
+            r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description') or self._og_search_description(webpage)
         timestamp = parse_iso8601(self._search_regex(
             r'<span class="publish-date"><time datetime="([^"]+)">',
             webpage, 'timestamp'))
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'url': self._html_search_meta('VideoURL', webpage, 'url'),
+            'url': video_url,
+            'title': title,
+            'description': description,
             'timestamp': timestamp,
         }
 
@@ -55,8 +71,7 @@ class EllenTVClipsIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
         playlist = self._extract_playlist(webpage)

youtube_dl/extractor/eroprofile.py

@@ -0,0 +1,45 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class EroProfileIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
+        'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
+        'info_dict': {
+            'id': '3733775',
+            'display_id': 'sexy-babe-softcore',
+            'ext': 'm4v',
+            'title': 'sexy babe softcore',
+            'thumbnail': 're:https?://.*\.jpg',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
+            webpage, 'video id', default=None)
+
+        video_url = self._search_regex(
+            r'<source src="([^"]+)', webpage, 'video url')
+        title = self._html_search_regex(
+            r'Title:</th><td>([^<]+)</td>', webpage, 'title')
+        thumbnail = self._search_regex(
+            r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
+            webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'age_limit': 18,
+        }

youtube_dl/extractor/fktv.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class FKTVIE(InfoExtractor):
     IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
 
     _TEST = {
         'url': 'http://fernsehkritik.tv/folge-1',
@@ -26,29 +26,32 @@ class FKTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        episode = int(mobj.group('ep'))
+        episode = int(self._match_id(url))
 
-        server = random.randint(2, 4)
-        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
-        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
+        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode
+        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode,
                                                episode)
         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
                                       'playlist', flags=re.DOTALL)
         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
-        # TODO: return a single multipart video
+
         videos = []
         for i, _ in enumerate(files, 1):
             video_id = '%04d%d' % (episode, i)
-            video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
+            video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i)
             videos.append({
+                'ext': 'flv',
                 'id': video_id,
                 'url': video_url,
                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
                 'thumbnail': video_thumbnail
             })
-        return videos
+        return {
+            '_type': 'multi_video',
+            'entries': videos,
+            'id': 'folge-%s' % episode,
+        }
 
 
 class FKTVPosteckeIE(InfoExtractor):

youtube_dl/extractor/gameone.py

@@ -6,7 +6,9 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     xpath_with_ns,
-    parse_iso8601
+    parse_iso8601,
+    float_or_none,
+    int_or_none,
 )
 
 NAMESPACE_MAP = {
@@ -21,25 +23,41 @@ RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
 
 class GameOneIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.gameone.de/tv/288',
-        'md5': '136656b7fb4c9cb4a8e2d500651c499b',
-        'info_dict': {
-            'id': '288',
-            'ext': 'mp4',
-            'title': 'Game One - Folge 288',
-            'duration': 1238,
-            'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
-            'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
-            'age_limit': 16,
-            'upload_date': '20140513',
-            'timestamp': 1399980122,
+    _TESTS = [
+        {
+            'url': 'http://www.gameone.de/tv/288',
+            'md5': '136656b7fb4c9cb4a8e2d500651c499b',
+            'info_dict': {
+                'id': '288',
+                'ext': 'mp4',
+                'title': 'Game One - Folge 288',
+                'duration': 1238,
+                'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
+                'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
+                'age_limit': 16,
+                'upload_date': '20140513',
+                'timestamp': 1399980122,
+            }
+        },
+        {
+            'url': 'http://gameone.de/tv/220',
+            'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
+            'info_dict': {
+                'id': '220',
+                'ext': 'mp4',
+                'upload_date': '20120918',
+                'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
+                'timestamp': 1347971451,
+                'title': 'Game One - Folge 220',
+                'duration': 896.62,
+                'age_limit': 16,
+            }
         }
-    }
+
+    ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         og_video = self._og_search_video_url(webpage, secure=False)
@@ -66,13 +84,13 @@ class GameOneIE(InfoExtractor):
             video_id,
             'Downloading media:content')
         rendition_items = content.findall('.//rendition')
-        duration = int(rendition_items[0].get('duration'))
+        duration = float_or_none(rendition_items[0].get('duration'))
         formats = [
             {
                 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
-                'width': int(r.get('width')),
-                'height': int(r.get('height')),
-                'tbr': int(r.get('bitrate')),
+                'width': int_or_none(r.get('width')),
+                'height': int_or_none(r.get('height')),
+                'tbr': int_or_none(r.get('bitrate')),
             }
             for r in rendition_items
         ]
@@ -105,7 +123,8 @@ class GameOnePlaylistIE(InfoExtractor):
         webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
         max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
         entries = [
-            self.url_result('http://www.gameone.de/tv/%d' % video_id, 'GameOne')
+            self.url_result('http://www.gameone.de/tv/%d' %
+                            video_id, 'GameOne')
             for video_id in range(max_id, 0, -1)]
 
         return {

youtube_dl/extractor/generic.py

@@ -23,6 +23,7 @@ from ..utils import (
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
+    UnsupportedError,
     url_basename,
 )
 from .brightcove import BrightcoveIE
@@ -130,12 +131,13 @@ class GenericIE(InfoExtractor):
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
-            'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
+            'md5': '166dd577b433b4d4ebfee10b0824d8ff',
             'info_dict': {
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                 'ext': 'mp4',
                 'title': '2cc213299525360.mov',  # that's what we get
             },
+            'add_ie': ['Ooyala'],
         },
         # google redirect
         {
@@ -145,7 +147,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20130224',
                 'uploader_id': 'TheVerge',
-                'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
+                'description': 're:^Chris Ziegler takes a look at the\.*',
                 'uploader': 'The Verge',
                 'title': 'First Firefox OS phones side-by-side',
             },
@@ -180,6 +182,14 @@ class GenericIE(InfoExtractor):
                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
             },
         },
+        # BBC iPlayer embeds
+        {
+            'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
+            'info_dict': {
+                'title': 'BBC - Blogs -  Adam Curtis - BUGGER',
+            },
+            'playlist_mincount': 18,
+        },
         # RUTV embed
         {
             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
@@ -698,9 +708,9 @@ class GenericIE(InfoExtractor):
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
         # Helper method
-        def _playlist_from_matches(matches, getter, ie=None):
+        def _playlist_from_matches(matches, getter=None, ie=None):
             urlrs = orderedSet(
-                self.url_result(self._proto_relative_url(getter(m)), ie)
+                self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
                 for m in matches)
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
@@ -904,6 +914,11 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 matches, getter=unescapeHTML, ie='FunnyOrDie')
 
+        # Look for BBC iPlayer embed
+        matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
+        if matches:
+            return _playlist_from_matches(matches, ie='BBCCoUk')
+
         # Look for embedded RUTV player
         rutv_url = RUTVIE._extract_url(webpage)
         if rutv_url:
@@ -911,7 +926,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded TED player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'TED')
 
@@ -1057,7 +1072,7 @@ class GenericIE(InfoExtractor):
                     'url': new_url,
                 }
         if not found:
-            raise ExtractorError('Unsupported URL: %s' % url)
+            raise UnsupportedError(url)
 
         entries = []
         for video_url in found:

youtube_dl/extractor/giga.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+    qualities,
+    compat_str,
+    parse_duration,
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class GigaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/',
+        'md5': '6bc5535e945e724640664632055a584f',
+        'info_dict': {
+            'id': '2622086',
+            'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss',
+            'ext': 'mp4',
+            'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss',
+            'description': 'md5:afdf5862241aded4718a30dff6a57baf',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 578,
+            'timestamp': 1414749706,
+            'upload_date': '20141031',
+            'uploader': 'Robin Schweiger',
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            [r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'],
+            webpage, 'video id')
+
+        playlist = self._download_json(
+            'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/'
+            % video_id, video_id)[0]
+
+        quality = qualities(['normal', 'hd720'])
+
+        formats = []
+        for format_id in itertools.count(0):
+            fmt = playlist.get(compat_str(format_id))
+            if not fmt:
+                break
+            formats.append({
+                'url': fmt['src'],
+                'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]),
+                'quality': quality(fmt['quality']),
+            })
+        self._sort_formats(formats)
+
+        title = self._html_search_meta(
+            'title', webpage, 'title', fatal=True)
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        duration = parse_duration(self._search_regex(
+            r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id),
+            webpage, 'duration', fatal=False))
+
+        timestamp = parse_iso8601(self._search_regex(
+            r'datetime="([^"]+)"', webpage, 'upload date', fatal=False))
+        uploader = self._search_regex(
+            r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
+
+        view_count = str_to_int(self._search_regex(
+            r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/hellporno.py

@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    remove_end,
+)
+
+
+class HellPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
+        'md5': '1fee339c610d2049699ef2aa699439f1',
+        'info_dict': {
+            'id': '149116',
+            'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
+            'ext': 'mp4',
+            'title': 'Dixie is posing with naked ass very erotic',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
+
+        flashvars = self._parse_json(self._search_regex(
+            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+            display_id, transform_source=js_to_json)
+
+        video_id = flashvars.get('video_id')
+        thumbnail = flashvars.get('preview_url')
+        ext = flashvars.get('postfix', '.mp4')[1:]
+
+        formats = []
+        for video_url_key in ['video_url', 'video_alt_url']:
+            video_url = flashvars.get(video_url_key)
+            if not video_url:
+                continue
+            video_text = flashvars.get('%s_text' % video_url_key)
+            fmt = {
+                'url': video_url,
+                'ext': ext,
+                'format_id': video_text,
+            }
+            m = re.search(r'^(?P<height>\d+)[pP]', video_text)
+            if m:
+                fmt['height'] = int(m.group('height'))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'age_limit': 18,
+            'formats': formats,
+        }

youtube_dl/extractor/hitbox.py

@@ -0,0 +1,166 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    parse_iso8601,
+    float_or_none,
+    int_or_none,
+    compat_str,
+)
+
+
+class HitboxIE(InfoExtractor):
+    IE_NAME = 'hitbox'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/video/203213',
+        'info_dict': {
+            'id': '203213',
+            'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy',
+            'alt_title': 'hitboxlive - Aug 9th #6',
+            'description': '',
+            'ext': 'mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 215.1666,
+            'resolution': 'HD 720p',
+            'uploader': 'hitboxlive',
+            'view_count': int,
+            'timestamp': 1407576133,
+            'upload_date': '20140809',
+            'categories': ['Live Show'],
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _extract_metadata(self, url, video_id):
+        thumb_base = 'https://edge.sf.hitbox.tv'
+        metadata = self._download_json(
+            '%s/%s' % (url, video_id), video_id)
+
+        date = 'media_live_since'
+        media_type = 'livestream'
+        if metadata.get('media_type') == 'video':
+            media_type = 'video'
+            date = 'media_date_added'
+
+        video_meta = metadata.get(media_type, [])[0]
+        title = video_meta.get('media_status')
+        alt_title = video_meta.get('media_title')
+        description = clean_html(
+            video_meta.get('media_description') or
+            video_meta.get('media_description_md'))
+        duration = float_or_none(video_meta.get('media_duration'))
+        uploader = video_meta.get('media_user_name')
+        views = int_or_none(video_meta.get('media_views'))
+        timestamp = parse_iso8601(video_meta.get(date), ' ')
+        categories = [video_meta.get('category_name')]
+        thumbs = [
+            {'url': thumb_base + video_meta.get('media_thumbnail'),
+             'width': 320,
+             'height': 180},
+            {'url': thumb_base + video_meta.get('media_thumbnail_large'),
+             'width': 768,
+             'height': 432},
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'alt_title': alt_title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnails': thumbs,
+            'duration': duration,
+            'uploader': uploader,
+            'view_count': views,
+            'timestamp': timestamp,
+            'categories': categories,
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/video',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
+            video_id)
+
+        clip = player_config.get('clip')
+        video_url = clip.get('url')
+        res = clip.get('bitrates', [])[0].get('label')
+
+        metadata['resolution'] = res
+        metadata['url'] = video_url
+        metadata['protocol'] = 'm3u8'
+
+        return metadata
+
+
+class HitboxLiveIE(HitboxIE):
+    IE_NAME = 'hitbox:live'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/dimak',
+        'info_dict': {
+            'id': 'dimak',
+            'ext': 'mp4',
+            'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e',
+            'timestamp': int,
+            'upload_date': compat_str,
+            'title': compat_str,
+            'uploader': 'Dimak',
+        },
+        'params': {
+            # live
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/live',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
+            video_id)
+
+        formats = []
+        cdns = player_config.get('cdns')
+        servers = []
+        for cdn in cdns:
+            base_url = cdn.get('netConnectionUrl')
+            host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
+            if base_url not in servers:
+                servers.append(base_url)
+                for stream in cdn.get('bitrates'):
+                    label = stream.get('label')
+                    if label != 'Auto':
+                        formats.append({
+                            'url': '%s/%s' % (base_url, stream.get('url')),
+                            'ext': 'mp4',
+                            'vbr': stream.get('bitrate'),
+                            'resolution': label,
+                            'rtmp_live': True,
+                            'format_note': host,
+                            'page_url': url,
+                            'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
+                        })
+
+        self._sort_formats(formats)
+        metadata['formats'] = formats
+        metadata['is_live'] = True
+        metadata['title'] = self._live_title(metadata.get('title'))
+        return metadata

youtube_dl/extractor/huffpost.py

@@ -39,8 +39,9 @@ class HuffPostIE(InfoExtractor):
         data = self._download_json(api_url, video_id)['data']
 
         video_title = data['title']
-        duration = parse_duration(data['running_time'])
-        upload_date = unified_strdate(data['schedule']['starts_at'])
+        duration = parse_duration(data.get('running_time'))
+        upload_date = unified_strdate(
+            data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time'))
         description = data.get('description')
 
         thumbnails = []
@@ -59,16 +60,11 @@ class HuffPostIE(InfoExtractor):
             'ext': 'mp4',
             'url': url,
             'vcodec': 'none' if key.startswith('audio/') else None,
-        } for key, url in data['sources']['live'].items()]
-        if data.get('fivemin_id'):
-            fid = data['fivemin_id']
-            fcat = str(int(fid) // 100 + 1)
-            furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
-            formats.append({
-                'format': 'fivemin',
-                'url': furl,
-                'preference': 1,
-            })
+        } for key, url in data.get('sources', {}).get('live', {}).items()]
+
+        if not formats and data.get('fivemin_id'):
+            return self.url_result('5min:%s' % data['fivemin_id'])
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/imdb.py

@@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
-        'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',

youtube_dl/extractor/internetvideoarchive.py

@@ -22,7 +22,7 @@ class InternetVideoArchiveIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'SKYFALL',
             'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.',
-            'duration': 149,
+            'duration': 152,
         },
     }
 

youtube_dl/extractor/khanacademy.py

@@ -22,8 +22,10 @@ class KhanAcademyIE(InfoExtractor):
             'description': 'The perfect cipher',
             'duration': 176,
             'uploader': 'Brit Cruise',
+            'uploader_id': 'khanacademy',
             'upload_date': '20120411',
-        }
+        },
+        'add_ie': ['Youtube'],
     }, {
         'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
         'info_dict': {

youtube_dl/extractor/kontrtube.py

@@ -10,13 +10,14 @@ from ..utils import int_or_none
 class KontrTubeIE(InfoExtractor):
     IE_NAME = 'kontrtube'
     IE_DESC = 'KontrTube.ru - Труба зовёт'
-    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
 
     _TEST = {
         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
         'md5': '975a991a4926c9a85f383a736a2e6b80',
         'info_dict': {
             'id': '2678',
+            'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
             'ext': 'mp4',
             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
@@ -28,21 +29,28 @@ class KontrTubeIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, video_id, 'Downloading page')
+        webpage = self._download_webpage(
+            url, display_id, 'Downloading page')
 
-        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
-        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
+        video_url = self._html_search_regex(
+            r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False)
         title = self._html_search_regex(
             r'<title>(.+?)</title>', webpage, 'video title')
-        description = self._html_search_meta('description', webpage, 'video description')
+        description = self._html_search_meta(
+            'description', webpage, 'video description')
 
         mobj = re.search(
-            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
+            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
+            webpage)
         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
 
         view_count = self._html_search_regex(
-            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
+            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>',
+            webpage, 'view count', fatal=False)
 
         comment_count = None
         comment_str = self._html_search_regex(
@@ -56,6 +64,7 @@ class KontrTubeIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'url': video_url,
             'thumbnail': thumbnail,
             'title': title,

youtube_dl/extractor/lrt.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..utils import (
@@ -28,7 +27,6 @@ class LRTIE(InfoExtractor):
         'params': {
             'skip_download': True,  # HLS download
         },
-
     }
 
     def _real_extract(self, url):
@@ -44,7 +42,9 @@ class LRTIE(InfoExtractor):
 
         formats = []
         for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage):
-            data = json.loads(js_to_json(js))
+            data = self._parse_json(js, video_id, transform_source=js_to_json)
+            if 'provider' not in data:
+                continue
             if data['provider'] == 'rtmp':
                 formats.append({
                     'format_id': 'rtmp',

youtube_dl/extractor/mit.py

@@ -105,6 +105,9 @@ class OCWMITIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
+                'upload_date': '20121109',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
                 # 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
             }
         },
@@ -114,6 +117,9 @@ class OCWMITIE(InfoExtractor):
                 'id': '7K1sB05pE0A',
                 'ext': 'mp4',
                 'title': 'Session 1: Introduction to Derivatives',
+                'upload_date': '20090818',
+                'uploader_id': 'MIT',
+                'uploader': 'MIT OpenCourseWare',
                 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
                 # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
             }

youtube_dl/extractor/moevideo.py

@@ -52,7 +52,8 @@ class MoeVideoIE(InfoExtractor):
                 'height': 296,
                 'duration': 6027,
                 'filesize': 588257923,
-            }
+            },
+            'skip': 'Video has been removed',
         },
     ]
 

youtube_dl/extractor/motorsport.py

@@ -1,63 +1,49 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import hashlib
-import json
-import time
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_parse_qs,
-    compat_str,
-)
-from ..utils import (
-    int_or_none,
+    compat_urlparse,
 )
 
 
 class MotorsportIE(InfoExtractor):
     IE_DESC = 'motorsport.com'
-    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
+    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
     _TEST = {
         'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
-        'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
         'info_dict': {
-            'id': '7063',
+            'id': '2-T3WuR-KMM',
             'ext': 'mp4',
             'title': 'Red Bull Racing: 2014 Rules Explained',
-            'duration': 207,
+            'duration': 208,
             'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
-            'uploader': 'rainiere',
-            'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
-        }
+            'uploader': 'mcomstaff',
+            'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ',
+            'upload_date': '20140903',
+            'thumbnail': r're:^https?://.+\.jpg$'
+        },
+        'add_ie': ['Youtube'],
+        'params': {
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
-        flashvars_code = self._html_search_regex(
-            r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
-        flashvars = compat_parse_qs(flashvars_code)
-        params = json.loads(flashvars['parameters'][0])
-
-        e = compat_str(int(time.time()) + 24 * 60 * 60)
-        base_video_url = params['location'] + '?e=' + e
-        s = 'h3hg713fh32'
-        h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest()
-        video_url = base_video_url + '&h=' + h
-
-        uploader = self._html_search_regex(
-            r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
-            'uploader', fatal=False)
+        iframe_path = self._html_search_regex(
+            r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage,
+            'iframe path')
+        iframe = self._download_webpage(
+            compat_urlparse.urljoin(url, iframe_path), display_id,
+            'Downloading iframe')
+        youtube_id = self._search_regex(
+            r'www.youtube.com/embed/(.{11})', iframe, 'youtube id')
 
         return {
-            'id': params['video_id'],
+            '_type': 'url_transparent',
             'display_id': display_id,
-            'title': params['title'],
-            'url': video_url,
-            'description': params.get('description'),
-            'thumbnail': params.get('main_thumb'),
-            'duration': int_or_none(params.get('duration')),
-            'uploader': uploader,
+            'url': 'https://youtube.com/watch?v=%s' % youtube_id,
         }

youtube_dl/extractor/nerdcubed.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+
+from .common import InfoExtractor
+
+
+class NerdCubedFeedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nerdcubed\.co\.uk/feed\.json'
+    _TEST = {
+        'url': 'http://www.nerdcubed.co.uk/feed.json',
+        'info_dict': {
+            'title': 'nerdcubed.co.uk feed',
+        },
+        'playlist_mincount': 1300,
+    }
+
+    def _real_extract(self, url):
+        feed = self._download_json(url, url, "Downloading NerdCubed JSON feed")
+
+        entries = [{
+            '_type': 'url',
+            'title': feed_entry['title'],
+            'uploader': feed_entry['source']['name'] if feed_entry['source'] else None,
+            'upload_date': datetime.datetime.strptime(feed_entry['date'], '%Y-%m-%d').strftime('%Y%m%d'),
+            'url': "http://www.youtube.com/watch?v=" + feed_entry['youtube_id'],
+        } for feed_entry in feed]
+
+        return {
+            '_type': 'playlist',
+            'title': 'nerdcubed.co.uk feed',
+            'id': 'nerdcubed-feed',
+            'entries': entries,
+        }

youtube_dl/extractor/normalboots.py

@@ -22,7 +22,11 @@ class NormalbootsIE(InfoExtractor):
             'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/',
             'uploader': 'JonTron',
             'upload_date': '20140125',
-        }
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/npo.py

@@ -9,6 +9,7 @@ from ..utils import (
     qualities,
     strip_jsonp,
     url_basename,
+    fix_xml_ampersands,
 )
 
 
@@ -51,7 +52,21 @@ class NPOIE(InfoExtractor):
                 'upload_date': '20130225',
                 'duration': 3000,
             },
-        }
+        },
+        {
+            'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
+            'info_dict': {
+                'id': 'WO_VPRO_043706',
+                'ext': 'wmv',
+                'title': 'De nieuwe mens - Deel 1',
+                'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
+                'duration': 4680,
+            },
+            'params': {
+                # mplayer mms download
+                'skip_download': True,
+            }
+        },
     ]
 
     def _real_extract(self, url):
@@ -74,31 +89,58 @@ class NPOIE(InfoExtractor):
         token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
 
         formats = []
-        quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
-        for format_id in metadata['pubopties']:
-            format_info = self._download_json(
-                'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token),
-                video_id, 'Downloading %s JSON' % format_id)
-            if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
-                continue
-            streams = format_info.get('streams')
-            if streams:
-                video_info = self._download_json(
-                    streams[0] + '&type=json',
-                    video_id, 'Downloading %s stream JSON' % format_id)
-            else:
-                video_info = format_info
-            video_url = video_info.get('url')
-            if not video_url:
-                continue
-            if format_id == 'adaptive':
-                formats.extend(self._extract_m3u8_formats(video_url, video_id))
-            else:
+
+        pubopties = metadata.get('pubopties')
+        if pubopties:
+            quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
+            for format_id in pubopties:
+                format_info = self._download_json(
+                    'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
+                    % (video_id, format_id, token),
+                    video_id, 'Downloading %s JSON' % format_id)
+                if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
+                    continue
+                streams = format_info.get('streams')
+                if streams:
+                    video_info = self._download_json(
+                        streams[0] + '&type=json',
+                        video_id, 'Downloading %s stream JSON' % format_id)
+                else:
+                    video_info = format_info
+                video_url = video_info.get('url')
+                if not video_url:
+                    continue
+                if format_id == 'adaptive':
+                    formats.extend(self._extract_m3u8_formats(video_url, video_id))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': format_id,
+                        'quality': quality(format_id),
+                    })
+
+        streams = metadata.get('streams')
+        if streams:
+            for i, stream in enumerate(streams):
+                stream_url = stream.get('url')
+                if not stream_url:
+                    continue
+                asx = self._download_xml(
+                    stream_url, video_id,
+                    'Downloading stream %d ASX playlist' % i,
+                    transform_source=fix_xml_ampersands)
+                ref = asx.find('./ENTRY/Ref')
+                if ref is None:
+                    continue
+                video_url = ref.get('href')
+                if not video_url:
+                    continue
                 formats.append({
                     'url': video_url,
-                    'format_id': format_id,
-                    'quality': quality(format_id),
+                    'ext': stream.get('formaat', 'asf'),
+                    'quality': stream.get('kwaliteit'),
                 })
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/nrk.py

@@ -72,12 +72,12 @@ class NRKIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
+    _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
     _TESTS = [
         {
             'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
-            'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
+            'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
                 'ext': 'flv',
@@ -85,11 +85,11 @@ class NRKTVIE(InfoExtractor):
                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
                 'upload_date': '20140523',
                 'duration': 1741.52,
-            }
+            },
         },
         {
             'url': 'http://tv.nrk.no/program/mdfp15000514',
-            'md5': 'af01795a31f1cf7265c8657534d8077b',
+            'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
                 'ext': 'flv',
@@ -97,39 +97,119 @@ class NRKTVIE(InfoExtractor):
                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
                 'upload_date': '20140524',
                 'duration': 4605.0,
-            }
+            },
         },
+        {
+            # single playlist video
+            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+            'md5': 'adbd1dbd813edaf532b0a253780719c2',
+            'info_dict': {
+                'id': 'MSPO40010515-part2',
+                'ext': 'flv',
+                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'upload_date': '20150106',
+            },
+            'skip': 'Only works from Norway',
+        },
+        {
+            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+            'playlist': [
+                {
+                    'md5': '9480285eff92d64f06e02a5367970a7a',
+                    'info_dict': {
+                        'id': 'MSPO40010515-part1',
+                        'ext': 'flv',
+                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
+                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                        'upload_date': '20150106',
+                    },
+                },
+                {
+                    'md5': 'adbd1dbd813edaf532b0a253780719c2',
+                    'info_dict': {
+                        'id': 'MSPO40010515-part2',
+                        'ext': 'flv',
+                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                        'upload_date': '20150106',
+                    },
+                },
+            ],
+            'info_dict': {
+                'id': 'MSPO40010515',
+                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
+                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'upload_date': '20150106',
+                'duration': 6947.5199999999995,
+            },
+            'skip': 'Only works from Norway',
+        }
     ]
 
+    def _extract_f4m(self, manifest_url, video_id):
+        return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        part_id = mobj.group('part_id')
 
-        page = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_meta('title', page, 'title')
-        description = self._html_search_meta('description', page, 'description')
-        thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
-        upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
-        duration = float_or_none(
-            self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
+        title = self._html_search_meta(
+            'title', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+
+        thumbnail = self._html_search_regex(
+            r'data-posterimage="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+        upload_date = unified_strdate(self._html_search_meta(
+            'rightsfrom', webpage, 'upload date', fatal=False))
+        duration = float_or_none(self._html_search_regex(
+            r'data-duration="([^"]+)"',
+            webpage, 'duration', fatal=False))
+
+        # playlist
+        parts = re.findall(
+            r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
+        if parts:
+            entries = []
+            for current_part_id, stream_url, part_title in parts:
+                if part_id and current_part_id != part_id:
+                    continue
+                video_part_id = '%s-part%s' % (video_id, current_part_id)
+                formats = self._extract_f4m(stream_url, video_part_id)
+                entries.append({
+                    'id': video_part_id,
+                    'title': part_title,
+                    'description': description,
+                    'thumbnail': thumbnail,
+                    'upload_date': upload_date,
+                    'formats': formats,
+                })
+            if part_id:
+                if entries:
+                    return entries[0]
+            else:
+                playlist = self.playlist_result(entries, video_id, title, description)
+                playlist.update({
+                    'thumbnail': thumbnail,
+                    'upload_date': upload_date,
+                    'duration': duration,
+                })
+                return playlist
 
         formats = []
 
-        f4m_url = re.search(r'data-media="([^"]+)"', page)
+        f4m_url = re.search(r'data-media="([^"]+)"', webpage)
         if f4m_url:
-            formats.append({
-                'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                'format_id': 'f4m',
-                'ext': 'flv',
-            })
+            formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 
-        m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
+        m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:
-            formats.append({
-                'url': m3u8_url.group(1),
-                'format_id': 'm3u8',
-            })
+            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
 
         self._sort_formats(formats)
 

youtube_dl/extractor/openfilm.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    compat_urllib_parse,
+    parse_age_limit,
+    int_or_none,
+)
+
+
+class OpenFilmIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.openfilm.com/videos/human-resources-remastered',
+        'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37',
+        'info_dict': {
+            'id': '32736',
+            'display_id': 'human-resources-remastered',
+            'ext': 'mp4',
+            'title': 'Human Resources (Remastered)',
+            'description': 'Social Engineering in the 20th Century.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 7164,
+            'timestamp': 1334756988,
+            'upload_date': '20120418',
+            'uploader_id': '41117',
+            'view_count': int,
+            'age_limit': 0,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        player = compat_urllib_parse.unquote_plus(
+            self._og_search_video_url(webpage))
+
+        video = json.loads(self._search_regex(
+            r'\bp=({.+?})(?:&|$)', player, 'video JSON'))
+
+        video_url = '%s1.mp4' % video['location']
+        video_id = video.get('video_id')
+        display_id = video.get('alias') or display_id
+        title = video.get('title')
+        description = video.get('description')
+        thumbnail = video.get('main_thumb')
+        duration = int_or_none(video.get('duration'))
+        timestamp = parse_iso8601(video.get('dt_published'), ' ')
+        uploader_id = video.get('user_id')
+        view_count = int_or_none(video.get('views_count'))
+        age_limit = parse_age_limit(video.get('age_limit'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/pbs.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     unified_strdate,
     US_RATINGS,
 )
@@ -151,6 +152,19 @@ class PBSIE(InfoExtractor):
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
         info = self._download_json(info_url, display_id)
 
+        redirect_url = info['alternate_encoding']['url']
+        redirect_info = self._download_json(
+            redirect_url + '?format=json', display_id,
+            'Downloading video url info')
+        if redirect_info['status'] == 'error':
+            if redirect_info['http_code'] == 403:
+                message = (
+                    'The video is not available in your region due to '
+                    'right restrictions')
+            else:
+                message = redirect_info['message']
+            raise ExtractorError(message, expected=True)
+
         rating_str = info.get('rating')
         if rating_str is not None:
             rating_str = rating_str.rpartition('-')[2]
@@ -160,7 +174,7 @@ class PBSIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': info['title'],
-            'url': info['alternate_encoding']['url'],
+            'url': redirect_info['url'],
             'ext': 'mp4',
             'description': info['program'].get('description'),
             'thumbnail': info.get('image_url'),

youtube_dl/extractor/played.py

@@ -26,6 +26,7 @@ class PlayedIE(InfoExtractor):
             'ext': 'flv',
             'title': 'youtube-dl_test_video.mp4',
         },
+        'skip': 'Removed for copyright infringement.',  # oh wow
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/radiobremen.py

@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class RadioBremenIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)'
+    IE_NAME = 'radiobremen'
+
+    _TEST = {
+        'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720',
+        'info_dict': {
+            'id': '114720',
+            'ext': 'mp4',
+            'duration': 1685,
+            'width': 512,
+            'title': 'buten un binnen vom 22. Dezember',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % video_id
+        meta_doc = self._download_webpage(
+            meta_url, video_id, 'Downloading metadata')
+        title = self._html_search_regex(
+            r"<h1.*>(?P<title>.+)</h1>", meta_doc, "title")
+        description = self._html_search_regex(
+            r"<p>(?P<description>.*)</p>", meta_doc, "description", fatal=False)
+        duration = parse_duration(self._html_search_regex(
+            r"L&auml;nge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>",
+            meta_doc, "duration", fatal=False))
+
+        page_doc = self._download_webpage(
+            url, video_id, 'Downloading video information')
+        mobj = re.search(
+            r"ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)",
+            page_doc)
+        video_url = (
+            "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" %
+            (video_id, video_id, mobj.group("secret"), mobj.group('width')))
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'width': int(mobj.group("width")),
+        }]
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+            'thumbnail': mobj.group('thumbnail'),
+        }

youtube_dl/extractor/rtlnl.py

@@ -8,7 +8,7 @@ from ..utils import parse_duration
 
 class RtlXlIE(InfoExtractor):
     IE_NAME = 'rtlxl.nl'
-    _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)'
+    _VALID_URL = r'https?://(www\.)?rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)'
 
     _TEST = {
         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',

youtube_dl/extractor/rtp.py

@@ -12,7 +12,7 @@ class RTPIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
         'info_dict': {
-            'id': '174042',
+            'id': 'e174042',
             'ext': 'mp3',
             'title': 'Paixões Cruzadas',
             'description': 'As paixões musicais de António Cartaxo e António Macedo',

youtube_dl/extractor/rutube.py

@@ -70,6 +70,37 @@ class RutubeIE(InfoExtractor):
         }
 
 
+class RutubeEmbedIE(InfoExtractor):
+    IE_NAME = 'rutube:embed'
+    IE_DESC = 'Rutube embedded videos'
+    _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
+        'info_dict': {
+            'id': 'a10e53b86e8f349080f718582ce4c661',
+            'ext': 'mp4',
+            'upload_date': '20131223',
+            'uploader_id': '297833',
+            'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
+            'uploader': 'subziro89 ILya',
+            'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
+        },
+        'params': {
+            'skip_download': 'Requires ffmpeg',
+        },
+    }
+
+    def _real_extract(self, url):
+        embed_id = self._match_id(url)
+        webpage = self._download_webpage(url, embed_id)
+
+        canonical_url = self._html_search_regex(
+            r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
+            'Canonical URL')
+        return self.url_result(canonical_url, 'Rutube')
+
+
 class RutubeChannelIE(InfoExtractor):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'

youtube_dl/extractor/screencastomatic.py

@@ -31,7 +31,6 @@ class ScreencastOMaticIE(InfoExtractor):
             r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);",
             webpage, 'setup code')
         data = self._parse_json(setup_js, video_id, transform_source=js_to_json)
-        modes = data['modes']
         try:
             video_data = next(
                 m for m in data['modes'] if m.get('type') == 'html5')

youtube_dl/extractor/sexykarma.py

@@ -24,7 +24,7 @@ class SexyKarmaIE(InfoExtractor):
             'title': 'Taking a quick pee.',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'wildginger7',
-            'upload_date': '20141007',
+            'upload_date': '20141008',
             'duration': 22,
             'view_count': int,
             'comment_count': int,
@@ -45,6 +45,7 @@ class SexyKarmaIE(InfoExtractor):
             'view_count': int,
             'comment_count': int,
             'categories': list,
+            'age_limit': 18,
         }
     }, {
         'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
@@ -61,6 +62,7 @@ class SexyKarmaIE(InfoExtractor):
             'view_count': int,
             'comment_count': int,
             'categories': list,
+            'age_limit': 18,
         }
     }]
 
@@ -114,4 +116,5 @@ class SexyKarmaIE(InfoExtractor):
             'view_count': view_count,
             'comment_count': comment_count,
             'categories': categories,
+            'age_limit': 18,
         }

youtube_dl/extractor/slideshare.py

@@ -30,7 +30,7 @@ class SlideshareIE(InfoExtractor):
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
-            r'var slideshare_object =  ({.*?}); var user_info =',
+            r'var\s+slideshare_object\s*=\s*({.*?});\s*var\s+user_info\s*=',
             webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
         if info['slideshow']['type'] != 'video':
@@ -41,7 +41,7 @@ class SlideshareIE(InfoExtractor):
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
         description = self._html_search_regex(
-            r'<p\s+(?:style="[^"]*"\s+)?class=".*?description.*?"[^>]*>(.*?)</p>', webpage,
+            r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
             'description', fatal=False)
 
         return {

youtube_dl/extractor/smotri.py

@@ -69,6 +69,7 @@ class SmotriIE(InfoExtractor):
             'params': {
                 'videopassword': 'qwerty',
             },
+            'skip': 'Video is not approved by moderator',
         },
         # age limit + video-password
         {
@@ -86,7 +87,8 @@ class SmotriIE(InfoExtractor):
             },
             'params': {
                 'videopassword': '333'
-            }
+            },
+            'skip': 'Video is not approved by moderator',
         },
         # swf player
         {

youtube_dl/extractor/sohu.py

@@ -1,11 +1,10 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from .common import compat_str
 
 
 class SohuIE(InfoExtractor):
@@ -29,60 +28,73 @@ class SohuIE(InfoExtractor):
                 base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
             else:
                 base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
-            data_url = base_data_url + str(vid_id)
-            data_json = self._download_webpage(
-                data_url, video_id,
-                note='Downloading JSON data for ' + str(vid_id))
-            return json.loads(data_json)
+
+            return self._download_json(
+                base_data_url + vid_id, video_id,
+                'Downloading JSON data for %s' % vid_id)
 
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         mytv = mobj.group('mytv') is not None
 
         webpage = self._download_webpage(url, video_id)
-        raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
-                                            webpage, 'video title')
+        raw_title = self._html_search_regex(
+            r'(?s)<title>(.+?)</title>',
+            webpage, 'video title')
         title = raw_title.partition('-')[0].strip()
 
-        vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
-                                      'video path')
-        data = _fetch_data(vid, mytv)
+        vid = self._html_search_regex(
+            r'var vid ?= ?["\'](\d+)["\']',
+            webpage, 'video path')
+        vid_data = _fetch_data(vid, mytv)
 
-        QUALITIES = ('ori', 'super', 'high', 'nor')
-        vid_ids = [data['data'][q + 'Vid']
-                   for q in QUALITIES
-                   if data['data'][q + 'Vid'] != 0]
-        if not vid_ids:
-            raise ExtractorError('No formats available for this video')
+        formats_json = {}
+        for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
+            vid_id = vid_data['data'].get('%sVid' % format_id)
+            if not vid_id:
+                continue
+            vid_id = compat_str(vid_id)
+            formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv)
 
-        # For now, we just pick the highest available quality
-        vid_id = vid_ids[-1]
-
-        format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
-        part_count = format_data['data']['totalBlocks']
-        allot = format_data['allot']
-        prot = format_data['prot']
-        clipsURL = format_data['data']['clipsURL']
-        su = format_data['data']['su']
+        part_count = vid_data['data']['totalBlocks']
 
         playlist = []
         for i in range(part_count):
-            part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
-                        (allot, prot, clipsURL[i], su[i]))
-            part_str = self._download_webpage(
-                part_url, video_id,
-                note='Downloading part %d of %d' % (i + 1, part_count))
+            formats = []
+            for format_id, format_data in formats_json.items():
+                allot = format_data['allot']
+                prot = format_data['prot']
 
-            part_info = part_str.split('|')
-            video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+                data = format_data['data']
+                clips_url = data['clipsURL']
+                su = data['su']
 
-            video_info = {
-                'id': '%s_part%02d' % (video_id, i + 1),
+                part_str = self._download_webpage(
+                    'http://%s/?prot=%s&file=%s&new=%s' %
+                    (allot, prot, clips_url[i], su[i]),
+                    video_id,
+                    'Downloading %s video URL part %d of %d'
+                    % (format_id, i + 1, part_count))
+
+                part_info = part_str.split('|')
+                video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'filesize': data['clipsBytes'][i],
+                    'width': data['width'],
+                    'height': data['height'],
+                    'fps': data['fps'],
+                })
+            self._sort_formats(formats)
+
+            playlist.append({
+                'id': '%s_part%d' % (video_id, i + 1),
                 'title': title,
-                'url': video_url,
-                'ext': 'mp4',
-            }
-            playlist.append(video_info)
+                'duration': vid_data['data']['clipsDuration'][i],
+                'formats': formats,
+            })
 
         if len(playlist) == 1:
             info = playlist[0]

youtube_dl/extractor/soulanime.py

@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    HEADRequest,
+    urlhandle_detect_ext,
+)
+
+
+class SoulAnimeWatchingIE(InfoExtractor):
+    IE_NAME = "soulanime:watching"
+    IE_DESC = "SoulAnime video"
+    _TEST = {
+        'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/',
+        'md5': '05fae04abf72298098b528e98abf4298',
+        'info_dict': {
+            'id': 'seirei-tsukai-no-blade-dance-episode-9',
+            'ext': 'mp4',
+            'title': 'seirei-tsukai-no-blade-dance-episode-9',
+            'description': 'seirei-tsukai-no-blade-dance-episode-9'
+        }
+    }
+    _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        domain = mobj.group('domain')
+
+        page = self._download_webpage(url, video_id)
+
+        video_url_encoded = self._html_search_regex(
+            r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url')
+        video_url = "http://www.soul-anime." + domain + video_url_encoded
+
+        ext_req = HEADRequest(video_url)
+        ext_handle = self._request_webpage(
+            ext_req, video_id, note='Determining extension')
+        ext = urlhandle_detect_ext(ext_handle)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': ext,
+            'title': video_id,
+            'description': video_id
+        }
+
+
+class SoulAnimeSeriesIE(InfoExtractor):
+    IE_NAME = "soulanime:series"
+    IE_DESC = "SoulAnime Series"
+
+    _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)'
+
+    _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>'
+
+    _TEST = {
+        'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/',
+        'info_dict': {
+            'id': 'black-rock-shooter-tv'
+        },
+        'playlist_count': 8
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        series_id = mobj.group('id')
+        domain = mobj.group('domain')
+
+        pattern = re.compile(self._EPISODE_REGEX)
+
+        page = self._download_webpage(url, series_id, "Downloading series page")
+        mobj = pattern.findall(page)
+
+        entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj]
+
+        return self.playlist_result(entries, series_id)

youtube_dl/extractor/sportdeutschland.py

@@ -60,9 +60,10 @@ class SportDeutschlandIE(InfoExtractor):
 
         categories = list(data.get('section', {}).get('tags', {}).values())
         asset = data['asset']
+        assets_info = self._download_json(asset['url'], video_id)
 
         formats = []
-        smil_url = asset['video']
+        smil_url = assets_info['video']
         if '.smil' in smil_url:
             m3u8_url = smil_url.replace('.smil', '.m3u8')
             formats.extend(

youtube_dl/extractor/sunporno.py

@@ -28,23 +28,27 @@ class SunPornoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
-        description = self._html_search_meta('description', webpage, 'description')
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description')
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         duration = parse_duration(self._search_regex(
-            r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False))
+            r'itemprop="duration">\s*(\d+:\d+)\s*<',
+            webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(
-            r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False))
+            r'class="views">\s*(\d+)\s*<',
+            webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
-            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
+            r'(\d+)</b> Comments?',
+            webpage, 'comment count', fatal=False))
 
         formats = []
         quality = qualities(['mp4', 'flv'])

youtube_dl/extractor/teachertube.py

@@ -57,9 +57,7 @@ class TeacherTubeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_meta('title', webpage, 'title', fatal=True)

youtube_dl/extractor/ted.py

@@ -13,7 +13,7 @@ from ..compat import (
 class TEDIE(SubtitlesInfoExtractor):
     _VALID_URL = r'''(?x)
         (?P<proto>https?://)
-        (?P<type>www|embed)(?P<urlmain>\.ted\.com/
+        (?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/
         (
             (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist
             |
@@ -98,7 +98,7 @@ class TEDIE(SubtitlesInfoExtractor):
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url, re.VERBOSE)
-        if m.group('type') == 'embed':
+        if m.group('type').startswith('embed'):
             desktop_url = m.group('proto') + 'www' + m.group('urlmain')
             return self.url_result(desktop_url, 'TED')
         name = m.group('name')

youtube_dl/extractor/telecinco.py

@@ -6,7 +6,7 @@ from .mitele import MiTeleIE
 
 class TelecincoIE(MiTeleIE):
     IE_NAME = 'telecinco.es'
-    _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html'
+    _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<id>.*?)\.html'
 
     _TEST = {
         'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',

youtube_dl/extractor/teletask.py

@@ -0,0 +1,53 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class TeleTaskIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.tele-task.de/archive/video/html5/26168/',
+        'info_dict': {
+            'title': 'Duplicate Detection',
+        },
+        'playlist': [{
+            'md5': '290ef69fb2792e481169c3958dbfbd57',
+            'info_dict': {
+                'id': '26168-speaker',
+                'ext': 'mp4',
+                'title': 'Duplicate Detection',
+                'upload_date': '20141218',
+            }
+        }, {
+            'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
+            'info_dict': {
+                'id': '26168-slides',
+                'ext': 'mp4',
+                'title': 'Duplicate Detection',
+                'upload_date': '20141218',
+            }
+        }]
+    }
+
+    def _real_extract(self, url):
+        lecture_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, lecture_id)
+
+        title = self._html_search_regex(
+            r'itemprop="name">([^<]+)</a>', webpage, 'title')
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False))
+
+        entries = [{
+            'id': '%s-%s' % (lecture_id, format_id),
+            'url': video_url,
+            'title': title,
+            'upload_date': upload_date,
+        } for format_id, video_url in re.findall(
+            r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)]
+
+        return self.playlist_result(entries, lecture_id, title)

youtube_dl/extractor/tf1.py

@@ -1,15 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html'
-    _TEST = {
+    _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
+    _TESTS = {
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {
             'id': '10635995',
@@ -21,14 +19,26 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
+        'info_dict': {
+            'id': '12043945',
+            'ext': 'mp4',
+            'title': 'Le grand Mystérioso - Chuggington',
+            'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
+            'upload_date': '20150103',
+        },
+        'params': {
+            # Sometimes wat serves the whole file with the --test option
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         embed_url = self._html_search_regex(
-            r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url')
+            r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
         embed_page = self._download_webpage(embed_url, video_id,
                                             'Downloading embed player page')
         wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')

youtube_dl/extractor/theplatform.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 import json
 
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..compat import (
     compat_str,
 )
@@ -16,7 +16,7 @@ from ..utils import (
 _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
 
 
-class ThePlatformIE(InfoExtractor):
+class ThePlatformIE(SubtitlesInfoExtractor):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/
            (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
@@ -66,6 +66,20 @@ class ThePlatformIE(InfoExtractor):
         info_json = self._download_webpage(info_url, video_id)
         info = json.loads(info_json)
 
+        subtitles = {}
+        captions = info.get('captions')
+        if isinstance(captions, list):
+            for caption in captions:
+                lang, src = caption.get('lang'), caption.get('src')
+                if lang and src:
+                    subtitles[lang] = src
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
+        subtitles = self.extract_subtitles(video_id, subtitles)
+
         head = meta.find(_x('smil:head'))
         body = meta.find(_x('smil:body'))
 
@@ -117,6 +131,7 @@ class ThePlatformIE(InfoExtractor):
         return {
             'id': video_id,
             'title': info['title'],
+            'subtitles': subtitles,
             'formats': formats,
             'description': info['description'],
             'thumbnail': info['defaultThumbnailUrl'],

youtube_dl/extractor/tmz.py

@@ -15,7 +15,7 @@ class TMZIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
             'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie???  Or is she just showing off her amazing boobs?',
-            'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640',
+            'thumbnail': r're:http://cdnbakmi\.kaltura\.com/.*thumbnail.*',
         }
     }
 

youtube_dl/extractor/tnaflix.py

@@ -12,7 +12,7 @@ from ..utils import (
 class TNAFlixIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)'
 
-    _TITLE_REGEX = None
+    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
     _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
     _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
 
@@ -49,8 +49,8 @@ class TNAFlixIE(InfoExtractor):
         if duration:
             duration = parse_duration(duration[1:])
 
-        cfg_url = self._html_search_regex(
-            self._CONFIG_REGEX, webpage, 'flashvars.config')
+        cfg_url = self._proto_relative_url(self._html_search_regex(
+            self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
 
         cfg_xml = self._download_xml(
             cfg_url, display_id, note='Downloading metadata',

youtube_dl/extractor/tunein.py

@@ -24,7 +24,7 @@ class TuneInIE(InfoExtractor):
     _INFO_DICT = {
         'id': '34682',
         'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
-        'ext': 'AAC',
+        'ext': 'aac',
         'thumbnail': 're:^https?://.*\.png$',
         'location': 'Tacoma, WA',
     }
@@ -78,14 +78,21 @@ class TuneInIE(InfoExtractor):
         for stream in streams:
             if stream.get('Type') == 'Live':
                 is_live = True
+            reliability = stream.get('Reliability')
+            format_note = (
+                'Reliability: %d%%' % reliability
+                if reliability is not None else None)
             formats.append({
+                'preference': (
+                    0 if reliability is None or reliability > 90
+                    else 1),
                 'abr': stream.get('Bandwidth'),
-                'ext': stream.get('MediaType'),
+                'ext': stream.get('MediaType').lower(),
                 'acodec': stream.get('MediaType'),
                 'vcodec': 'none',
                 'url': stream.get('Url'),
-                # Sometimes streams with the highest quality do not exist
-                'preference': stream.get('Reliability'),
+                'source_preference': reliability,
+                'format_note': format_note,
             })
         self._sort_formats(formats)
 

youtube_dl/extractor/twitch.py

@@ -22,6 +22,7 @@ class TwitchIE(InfoExtractor):
     _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?twitch\.tv/
         (?:
             (?P<channelid>[^/]+)|
+            (?:(?:[^/]+)/v/(?P<vodid>[^/]+))|
             (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
             (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
         )
@@ -70,11 +71,24 @@ class TwitchIE(InfoExtractor):
     def _extract_media(self, item, item_id):
         ITEMS = {
             'a': 'video',
+            'v': 'vod',
             'c': 'chapter',
         }
         info = self._extract_info(self._download_json(
             '%s/kraken/videos/%s%s' % (self._API_BASE, item, item_id), item_id,
             'Downloading %s info JSON' % ITEMS[item]))
+
+        if item == 'v':
+            access_token = self._download_json(
+                '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
+                'Downloading %s access token' % ITEMS[item])
+            formats = self._extract_m3u8_formats(
+                'http://usher.twitch.tv/vod/%s?nauth=%s&nauthsig=%s'
+                % (item_id, access_token['token'], access_token['sig']),
+                item_id, 'mp4')
+            info['formats'] = formats
+            return info
+
         response = self._download_json(
             '%s/api/videos/%s%s' % (self._API_BASE, item, item_id), item_id,
             'Downloading %s playlist JSON' % ITEMS[item])
@@ -209,6 +223,8 @@ class TwitchIE(InfoExtractor):
             """
         elif mobj.group('videoid'):
             return self._extract_media('a', mobj.group('videoid'))
+        elif mobj.group('vodid'):
+            return self._extract_media('v', mobj.group('vodid'))
         elif mobj.group('channelid'):
             channel_id = mobj.group('channelid')
             info = self._download_json(

youtube_dl/extractor/vier.py

@@ -0,0 +1,118 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class VierIE(InfoExtractor):
+    IE_NAME = 'vier'
+    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
+    _TESTS = [{
+        'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
+        'info_dict': {
+            'id': '16129',
+            'display_id': 'het-wordt-warm-de-moestuin',
+            'ext': 'mp4',
+            'title': 'Het wordt warm in De Moestuin',
+            'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.vier.be/video/v3/embed/16129',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        embed_id = mobj.group('embed_id')
+        display_id = mobj.group('display_id') or embed_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'"nid"\s*:\s*"(\d+)"', webpage, 'video id')
+        application = self._search_regex(
+            r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod')
+        filename = self._search_regex(
+            r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename')
+
+        playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
+        formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')
+
+        title = self._og_search_title(webpage, default=display_id)
+        description = self._og_search_description(webpage, default=None)
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
+
+
+class VierVideosIE(InfoExtractor):
+    IE_NAME = 'vier:videos'
+    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
+    _TESTS = [{
+        'url': 'http://www.vier.be/demoestuin/videos',
+        'info_dict': {
+            'id': 'demoestuin',
+        },
+        'playlist_mincount': 153,
+    }, {
+        'url': 'http://www.vier.be/demoestuin/videos?page=6',
+        'info_dict': {
+            'id': 'demoestuin-page6',
+        },
+        'playlist_mincount': 20,
+    }, {
+        'url': 'http://www.vier.be/demoestuin/videos?page=7',
+        'info_dict': {
+            'id': 'demoestuin-page7',
+        },
+        'playlist_mincount': 13,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        program = mobj.group('program')
+
+        webpage = self._download_webpage(url, program)
+
+        page_id = mobj.group('page')
+        if page_id:
+            page_id = int(page_id)
+            start_page = page_id
+            last_page = start_page + 1
+            playlist_id = '%s-page%d' % (program, page_id)
+        else:
+            start_page = 0
+            last_page = int(self._search_regex(
+                r'videos\?page=(\d+)">laatste</a>',
+                webpage, 'last page', default=0)) + 1
+            playlist_id = program
+
+        entries = []
+        for current_page_id in range(start_page, last_page):
+            current_page = self._download_webpage(
+                'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
+                program,
+                'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage
+            page_entries = [
+                self.url_result('http://www.vier.be' + video_url, 'Vier')
+                for video_url in re.findall(
+                    r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
+            entries.extend(page_entries)
+
+        return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/viki.py

@@ -17,7 +17,6 @@ class VikiIE(SubtitlesInfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
     _TEST = {
         'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
-        'md5': 'a21454021c2646f5433514177e2caa5f',
         'info_dict': {
             'id': '1023585v',
             'ext': 'mp4',
@@ -31,8 +30,7 @@ class VikiIE(SubtitlesInfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         title = self._og_search_title(webpage)

youtube_dl/extractor/vimple.py

@@ -14,28 +14,17 @@ class VimpleIE(InfoExtractor):
     IE_DESC = 'Vimple.ru'
     _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})'
     _TESTS = [
-        # Quality: Large, from iframe
         {
-            'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c',
+            'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
+            'md5': '2e750a330ed211d3fd41821c6ad9a279',
             'info_dict': {
-                'id': 'b132bdfd71b546d3972f9ab9a25f201c',
-                'title': 'great-escape-minecraft.flv',
+                'id': 'c0f6b1687dcd4000a97ebe70068039cf',
                 'ext': 'mp4',
-                'duration': 352,
-                'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c',
+                'title': 'Sunset',
+                'duration': 20,
+                'thumbnail': 're:https?://.*?\.jpg',
             },
         },
-        # Quality: Medium, from mainpage
-        {
-            'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
-            'info_dict': {
-                'id': 'a15950562888453b8e6f9572dc8600cd',
-                'title': 'DB 01',
-                'ext': 'flv',
-                'duration': 1484,
-                'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
-            }
-        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/vk.py

@@ -164,6 +164,15 @@ class VKIE(InfoExtractor):
             self.to_screen('Youtube video detected')
             return self.url_result(m_yt.group(1), 'Youtube')
 
+        m_rutube = re.search(
+            r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
+        assert m_rutube
+        if m_rutube is not None:
+            self.to_screen('rutube video detected')
+            rutube_url = self._proto_relative_url(
+                m_rutube.group(1).replace('\\', ''))
+            return self.url_result(rutube_url)
+
         m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
         if m_opts:
             m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))

youtube_dl/extractor/washingtonpost.py

@@ -10,14 +10,14 @@ from ..utils import (
 
 
 class WashingtonPostIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])'
     _TEST = {
         'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
         'info_dict': {
             'title': 'Sinkhole of bureaucracy',
         },
         'playlist': [{
-            'md5': 'c3f4b4922ffa259243f68e928db2db8c',
+            'md5': '79132cc09ec5309fa590ae46e4cc31bc',
             'info_dict': {
                 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f',
                 'ext': 'mp4',
@@ -29,7 +29,7 @@ class WashingtonPostIE(InfoExtractor):
                 'upload_date': '20140322',
             },
         }, {
-            'md5': 'f645a07652c2950cd9134bb852c5f5eb',
+            'md5': 'e1d5734c06865cc504ad99dc2de0d443',
             'info_dict': {
                 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f',
                 'ext': 'mp4',
@@ -44,10 +44,9 @@ class WashingtonPostIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = mobj.group('id')
-
+        page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
+
         title = self._og_search_title(webpage)
         uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage)
         entries = []

youtube_dl/extractor/webofstories.py

@@ -0,0 +1,102 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class WebOfStoriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)'
+    _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/'
+    _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
+    _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/'
+    _TESTS = [
+        {
+            'url': 'http://www.webofstories.com/play/hans.bethe/71',
+            'md5': '373e4dd915f60cfe3116322642ddf364',
+            'info_dict': {
+                'id': '4536',
+                'ext': 'mp4',
+                'title': 'The temperature of the sun',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'Hans Bethe talks about calculating the temperature of the sun',
+                'duration': 238,
+            }
+        },
+        {
+            'url': 'http://www.webofstories.com/play/55908',
+            'md5': '2985a698e1fe3211022422c4b5ed962c',
+            'info_dict': {
+                'id': '55908',
+                'ext': 'mp4',
+                'title': 'The story of Gemmata obscuriglobus',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
+                'duration': 169,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._og_search_title(webpage)
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        story_filename = self._search_regex(
+            r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename')
+        speaker_id = self._search_regex(
+            r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID')
+        story_id = self._search_regex(
+            r'\.storyId\((\d+)\)', webpage, 'story ID')
+        speaker_type = self._search_regex(
+            r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type')
+        great_life = self._search_regex(
+            r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story')
+        is_great_life_series = great_life == 'true'
+        duration = int_or_none(self._search_regex(
+            r'\.duration\((\d+)\)', webpage, 'duration', fatal=False))
+
+        # URL building, see: http://www.webofstories.com/scripts/player.js
+        ms_prefix = ''
+        if speaker_type.lower() == 'ms':
+            ms_prefix = 'mini_sites/'
+
+        if is_great_life_series:
+            mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format(
+                self._VIDEO_DOMAIN, speaker_id, story_filename)
+            rtmp_ext = 'flv'
+            streamer = self._GREAT_LIFE_STREAMER
+            play_path = 'stories/{0:}/{1:}'.format(
+                speaker_id, story_filename)
+        else:
+            mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format(
+                self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename)
+            rtmp_ext = 'mp4'
+            streamer = self._USER_STREAMER
+            play_path = 'mp4:{0:}{1:}/{2}.mp4'.format(
+                ms_prefix, speaker_id, story_filename)
+
+        formats = [{
+            'format_id': 'mp4_sd',
+            'url': mp4_url,
+        }, {
+            'format_id': 'rtmp_sd',
+            'page_url': url,
+            'url': streamer,
+            'ext': rtmp_ext,
+            'play_path': play_path,
+        }]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': story_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+        }

youtube_dl/extractor/xboxclips.py

@@ -1,46 +1,42 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    parse_iso8601,
-    float_or_none,
     int_or_none,
+    parse_filesize,
+    unified_strdate,
 )
 
 
 class XboxClipsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})'
+    _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})'
     _TEST = {
         'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
         'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
         'info_dict': {
             'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
             'ext': 'mp4',
-            'title': 'Iabdulelah playing Upload Studio',
-            'filesize_approx': 28101836.8,
-            'timestamp': 1407388500,
+            'title': 'Iabdulelah playing Titanfall',
+            'filesize_approx': 26800000,
             'upload_date': '20140807',
             'duration': 56,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
-            r'>Link: <a href="([^"]+)">', webpage, 'video URL')
+            r'>(?:Link|Download): <a href="([^"]+)">', webpage, 'video URL')
         title = self._html_search_regex(
             r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title')
-        timestamp = parse_iso8601(self._html_search_regex(
+        upload_date = unified_strdate(self._html_search_regex(
             r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False))
-        filesize = float_or_none(self._html_search_regex(
-            r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024)
+        filesize = parse_filesize(self._html_search_regex(
+            r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
         duration = int_or_none(self._html_search_regex(
             r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False))
         view_count = int_or_none(self._html_search_regex(
@@ -50,7 +46,7 @@ class XboxClipsIE(InfoExtractor):
             'id': video_id,
             'url': video_url,
             'title': title,
-            'timestamp': timestamp,
+            'upload_date': upload_date,
             'filesize_approx': filesize,
             'duration': duration,
             'view_count': view_count,

youtube_dl/extractor/xhamster.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [
         {
             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
@@ -39,7 +39,11 @@ class XHamsterIE(InfoExtractor):
                 'duration': 200,
                 'age_limit': 18,
             }
-        }
+        },
+        {
+            'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -57,7 +61,8 @@ class XHamsterIE(InfoExtractor):
 
         video_id = mobj.group('id')
         seo = mobj.group('seo')
-        mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
+        proto = mobj.group('proto')
+        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
         title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')

youtube_dl/extractor/xtube.py

@@ -1,11 +1,11 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
+    compat_urllib_parse,
 )
 from ..utils import (
     parse_duration,
@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class XTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&]+))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))'
     _TEST = {
         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
@@ -30,41 +30,49 @@ class XTubeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title')
+        video_title = self._html_search_regex(
+            r'<p class="title">([^<]+)', webpage, 'title')
         video_uploader = self._html_search_regex(
-            r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
+            [r"var\s+contentOwnerId\s*=\s*'([^']+)",
+             r'By:\s*<a href="/community/profile\.php\?user=([^"]+)'],
+            webpage, 'uploader', fatal=False)
         video_description = self._html_search_regex(
-            r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False)
+            r'<p class="fieldsDesc">([^<]+)',
+            webpage, 'description', fatal=False)
         duration = parse_duration(self._html_search_regex(
-            r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False))
-        view_count = self._html_search_regex(
-            r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False)
-        if view_count:
-            view_count = str_to_int(view_count)
-        comment_count = self._html_search_regex(
-            r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False)
-        if comment_count:
-            comment_count = str_to_int(comment_count)
+            r'<span class="bold">Runtime:</span> ([^<]+)</p>',
+            webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._html_search_regex(
+            r'<span class="bold">Views:</span> ([\d,\.]+)</p>',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<div id="commentBar">([\d,\.]+) Comments</div>',
+            webpage, 'comment count', fatal=False))
 
-        player_quality_option = json.loads(self._html_search_regex(
-            r'playerQualityOption = ({.+?});', webpage, 'player quality option'))
-
-        QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080']
-        formats = [
-            {
-                'url': furl,
+        formats = []
+        for format_id, video_url in re.findall(
+                r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
+            fmt = {
+                'url': compat_urllib_parse.unquote(video_url),
                 'format_id': format_id,
-                'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1,
-            } for format_id, furl in player_quality_option.items()
-        ]
+            }
+            m = re.search(r'^(?P<height>\d+)[pP]', format_id)
+            if m:
+                fmt['height'] = int(m.group('height'))
+            formats.append(fmt)
+
+        if not formats:
+            video_url = compat_urllib_parse.unquote(self._search_regex(
+                r'flashvars\.video_url\s*=\s*"([^"]+)"',
+                webpage, 'video URL'))
+            formats.append({'url': video_url})
+
         self._sort_formats(formats)
 
         return {
@@ -87,6 +95,7 @@ class XTubeUserIE(InfoExtractor):
         'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
         'info_dict': {
             'id': 'greenshowers',
+            'age_limit': 18,
         },
         'playlist_mincount': 155,
     }
@@ -116,6 +125,7 @@ class XTubeUserIE(InfoExtractor):
         return {
             '_type': 'playlist',
             'id': username,
+            'age_limit': 18,
             'entries': [{
                 '_type': 'url',
                 'url': eurl,

youtube_dl/extractor/xxxymovies.py

@@ -0,0 +1,81 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class XXXYMoviesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
+    _TEST = {
+        'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
+        'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
+        'info_dict': {
+            'id': '138669',
+            'display_id': 'ecstatic-orgasm-sofcore',
+            'ext': 'mp4',
+            'title': 'Ecstatic Orgasm Sofcore',
+            'duration': 931,
+            'categories': list,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
+
+        title = self._html_search_regex(
+            [r'<div class="block_header">\s*<h1>([^<]+)</h1>',
+             r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'],
+            webpage, 'title')
+
+        thumbnail = self._search_regex(
+            r"preview_url\s*:\s*'([^']+)'",
+            webpage, 'thumbnail', fatal=False)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration:</span>\s*(\d+:\d+)',
+            webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<div class="video_views">\s*(\d+)',
+            webpage, 'view count', fatal=False))
+        like_count = int_or_none(self._search_regex(
+            r'>\s*Likes? <b>\((\d+)\)',
+            webpage, 'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'>\s*Dislike <b>\((\d+)\)</b>',
+            webpage, 'dislike count', fatal=False))
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/yahoo.py

@@ -12,6 +12,7 @@ from ..compat import (
 )
 from ..utils import (
     clean_html,
+    unescapeHTML,
     ExtractorError,
     int_or_none,
 )
@@ -55,14 +56,14 @@ class YahooIE(InfoExtractor):
             }
         },
         {
-            'url': 'https://tw.screen.yahoo.com/taipei-opinion-poll/選情站報-街頭民調-台北市篇-102823042.html',
-            'md5': '92a7fdd8a08783c68a174d7aa067dde8',
+            'url': 'https://tw.screen.yahoo.com/election-2014-askmayor/敢問市長-黃秀霜批賴清德-非常高傲-033009720.html',
+            'md5': '3a09cf59349cfaddae1797acc3c087fc',
             'info_dict': {
-                'id': '7a23b569-7bea-36cb-85b9-bd5301a0a1fb',
+                'id': 'cac903b3-fcf4-3c14-b632-643ab541712f',
                 'ext': 'mp4',
-                'title': '選情站報 街頭民調 台北市篇',
-                'description': '選情站報 街頭民調 台北市篇',
-                'duration': 429,
+                'title': '敢問市長／黃秀霜批賴清德「非常高傲」',
+                'description': '直言台南沒捷運 交通居五都之末',
+                'duration': 396,
             }
         },
         {
@@ -87,14 +88,14 @@ class YahooIE(InfoExtractor):
                 'duration': 121,
             }
         }, {
-            'url': 'https://ca.finance.yahoo.com/news/20-most-valuable-brands-world-112600775.html',
-            'md5': '3e401e4eed6325aa29d9b96125fd5b4f',
+            'url': 'https://ca.finance.yahoo.com/news/hackers-sony-more-trouble-well-154609075.html',
+            'md5': '226a895aae7e21b0129e2a2006fe9690',
             'info_dict': {
-                'id': 'c1b4c09c-8ed8-3b65-8b05-169c55358a83',
+                'id': 'e624c4bc-3389-34de-9dfc-025f74943409',
                 'ext': 'mp4',
-                'title': "Apple Is The World's Most Valuable Brand",
-                'description': 'md5:73eabc1a11c6f59752593b2ceefa1262',
-                'duration': 21,
+                'title': '\'The Interview\' TV Spot: War',
+                'description': 'The Interview',
+                'duration': 30,
             }
         }, {
             'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
@@ -116,6 +117,16 @@ class YahooIE(InfoExtractor):
                 'description': 'md5:1428185051cfd1949807ad4ff6d3686a',
                 'duration': 201,
             }
+        }, {
+            'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
+            'md5': '989396ae73d20c6f057746fb226aa215',
+            'info_dict': {
+                'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
+                'ext': 'mp4',
+                'title': '\'True Story\' Trailer',
+                'description': 'True Story',
+                'duration': 150,
+            },
         }, {
             'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
             'only_matching': True,
@@ -125,6 +136,7 @@ class YahooIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('display_id')
+        page_id = mobj.group('id')
         url = mobj.group('url')
         host = mobj.group('host')
         webpage = self._download_webpage(url, display_id)
@@ -149,6 +161,7 @@ class YahooIE(InfoExtractor):
                 r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
                 r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
                 r'"first_videoid"\s*:\s*"([^"]+)"',
+                r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
             ]
             video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
         else:
@@ -163,17 +176,15 @@ class YahooIE(InfoExtractor):
         region = self._search_regex(
             r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"',
             webpage, 'region', fatal=False, default='US')
-        query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
-                 ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="%s"'
-                 ' AND protocol="http"' % (video_id, region))
         data = compat_urllib_parse.urlencode({
-            'q': query,
-            'env': 'prod',
-            'format': 'json',
+            'protocol': 'http',
+            'region': region,
         })
+        query_url = (
+            'https://video.media.yql.yahoo.com/v1/video/sapi/streams/'
+            '{id}?{data}'.format(id=video_id, data=data))
         query_result = self._download_json(
-            'http://video.query.yahoo.com/v1/public/yql?' + data,
-            display_id, 'Downloading video info')
+            query_url, display_id, 'Downloading video info')
 
         info = query_result['query']['results']['mediaObj'][0]
         meta = info.get('meta')
@@ -211,7 +222,7 @@ class YahooIE(InfoExtractor):
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': meta['title'],
+            'title': unescapeHTML(meta['title']),
             'formats': formats,
             'description': clean_html(meta['description']),
             'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),

youtube_dl/extractor/youtube.py

@@ -256,7 +256,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
-        '138': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},  # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
         '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'},
@@ -287,7 +287,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
         '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
+        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
         '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
+        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
 
         # Dash webm audio
         '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
@@ -412,12 +414,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'id': 'HtVdAasjOgU',
                 'ext': 'mp4',
                 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
-                'description': 'md5:eca57043abae25130f58f655ad9a7771',
+                'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
                 'uploader': 'The Witcher',
                 'uploader_id': 'WitcherGame',
                 'upload_date': '20140605',
             },
         },
+        # Age-gate video with encrypted signature
+        {
+            'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
+            'info_dict': {
+                'id': '6kLq3WMV1nU',
+                'ext': 'mp4',
+                'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
+                'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
+                'uploader': 'LloydVEVO',
+                'uploader_id': 'LloydVEVO',
+                'upload_date': '20110629',
+            },
+        },
         # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
         {
             'url': '__2ABJjxzNo',
@@ -599,24 +614,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
     def _get_available_subtitles(self, video_id, webpage):
         try:
-            sub_list = self._download_webpage(
+            subs_doc = self._download_xml(
                 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
             self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
             return {}
-        lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
 
         sub_lang_list = {}
-        for l in lang_list:
-            lang = l[1]
+        for track in subs_doc.findall('track'):
+            lang = track.attrib['lang_code']
             if lang in sub_lang_list:
                 continue
             params = compat_urllib_parse.urlencode({
                 'lang': lang,
                 'v': video_id,
                 'fmt': self._downloader.params.get('subtitlesformat', 'srt'),
-                'name': unescapeHTML(l[0]).encode('utf-8'),
+                'name': track.attrib['name'].encode('utf-8'),
             })
             url = 'https://www.youtube.com/api/timedtext?' + params
             sub_lang_list[lang] = url
@@ -649,10 +663,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             list_url = caption_url + '&' + list_params
             caption_list = self._download_xml(list_url, video_id)
             original_lang_node = caption_list.find('track')
-            if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr':
+            if original_lang_node is None:
                 self._downloader.report_warning('Video doesn\'t have automatic captions')
                 return {}
             original_lang = original_lang_node.attrib['lang_code']
+            caption_kind = original_lang_node.attrib.get('kind', '')
 
             sub_lang_list = {}
             for lang_node in caption_list.findall('target'):
@@ -662,7 +677,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     'tlang': sub_lang,
                     'fmt': sub_format,
                     'ts': timestamp,
-                    'kind': 'asr',
+                    'kind': caption_kind,
                 })
                 sub_lang_list[sub_lang] = caption_url + '&' + params
             return sub_lang_list
@@ -723,6 +738,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'format_id': format_id,
                 'url': video_url,
                 'width': int_or_none(r.attrib.get('width')),
+                'height': int_or_none(r.attrib.get('height')),
                 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
                 'asr': int_or_none(r.attrib.get('audioSamplingRate')),
                 'filesize': filesize,
@@ -733,7 +749,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     fo for fo in formats
                     if fo['format_id'] == format_id)
             except StopIteration:
-                f.update(self._formats.get(format_id, {}))
+                f.update(self._formats.get(format_id, {}).items())
                 formats.append(f)
             else:
                 existing_format.update(f)
@@ -766,11 +782,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
             # this can be viewed without login into Youtube
+            url = proto + '://www.youtube.com/embed/%s' % video_id
+            embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
             data = compat_urllib_parse.urlencode({
                 'video_id': video_id,
                 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
                 'sts': self._search_regex(
-                    r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''),
+                    r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
             })
             video_info_url = proto + '://www.youtube.com/get_video_info?' + data
             video_info_webpage = self._download_webpage(
@@ -968,11 +986,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 elif 's' in url_data:
                     encrypted_sig = url_data['s'][0]
 
-                    if not age_gate:
-                        jsplayer_url_json = self._search_regex(
-                            r'"assets":.+?"js":\s*("[^"]+")',
-                            video_webpage, 'JS player URL')
-                        player_url = json.loads(jsplayer_url_json)
+                    jsplayer_url_json = self._search_regex(
+                        r'"assets":.+?"js":\s*("[^"]+")',
+                        embed_webpage if age_gate else video_webpage, 'JS player URL')
+                    player_url = json.loads(jsplayer_url_json)
                     if player_url is None:
                         player_url_json = self._search_regex(
                             r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
@@ -1026,6 +1043,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     self.report_warning(
                         'Skipping DASH manifest: %r' % e, video_id)
                 else:
+                    # Hide the formats we found through non-DASH
+                    dash_keys = set(df['format_id'] for df in dash_formats)
+                    for f in formats:
+                        if f['format_id'] in dash_keys:
+                            f['format_id'] = 'nondash-%s' % f['format_id']
+                            f['preference'] = f.get('preference', 0) - 10000
                     formats.extend(dash_formats)
 
         self._sort_formats(formats)
@@ -1185,9 +1208,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         if playlist_id.startswith('RD'):
             # Mixes require a custom extraction process
             return self._extract_mix(playlist_id)
-        if playlist_id.startswith('TL'):
-            raise ExtractorError('For downloading YouTube.com top lists, use '
-                                 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
 
         url = self._TEMPLATE_URL % playlist_id
         page = self._download_webpage(url, playlist_id)
@@ -1233,49 +1253,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         return self.playlist_result(url_results, playlist_id, playlist_title)
 
 
-class YoutubeTopListIE(YoutubePlaylistIE):
-    IE_NAME = 'youtube:toplist'
-    IE_DESC = ('YouTube.com top lists, "yttoplist:{channel}:{list title}"'
-               ' (Example: "yttoplist:music:Top Tracks")')
-    _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
-    _TESTS = [{
-        'url': 'yttoplist:music:Trending',
-        'playlist_mincount': 5,
-        'skip': 'Only works for logged-in users',
-    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        channel = mobj.group('chann')
-        title = mobj.group('title')
-        query = compat_urllib_parse.urlencode({'title': title})
-        channel_page = self._download_webpage(
-            'https://www.youtube.com/%s' % channel, title)
-        link = self._html_search_regex(
-            r'''(?x)
-                <a\s+href="([^"]+)".*?>\s*
-                <span\s+class="branded-page-module-title-text">\s*
-                <span[^>]*>.*?%s.*?</span>''' % re.escape(query),
-            channel_page, 'list')
-        url = compat_urlparse.urljoin('https://www.youtube.com/', link)
-
-        video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"'
-        ids = []
-        # sometimes the webpage doesn't contain the videos
-        # retry until we get them
-        for i in itertools.count(0):
-            msg = 'Downloading Youtube mix'
-            if i > 0:
-                msg += ', retry #%d' % i
-
-            webpage = self._download_webpage(url, title, msg)
-            ids = orderedSet(re.findall(video_re, webpage))
-            if ids:
-                break
-        url_results = self._ids_to_results(ids)
-        return self.playlist_result(url_results, playlist_title=title)
-
-
 class YoutubeChannelIE(InfoExtractor):
     IE_DESC = 'YouTube.com channels'
     _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
@@ -1687,3 +1664,20 @@ class YoutubeTruncatedURLIE(InfoExtractor):
             '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
             ' or simply  youtube-dl BaW_jenozKc  .',
             expected=True)
+
+
+class YoutubeTruncatedIDIE(InfoExtractor):
+    IE_NAME = 'youtube:truncated_id'
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
+
+    _TESTS = [{
+        'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        raise ExtractorError(
+            'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
+            expected=True)

youtube_dl/extractor/zdf.py

@@ -119,7 +119,7 @@ class ZDFChannelIE(InfoExtractor):
         'info_dict': {
             'id': '1586442',
         },
-        'playlist_count': 4,
+        'playlist_count': 3,
     }
     _PAGE_SIZE = 50
 

youtube_dl/options.py

@@ -109,7 +109,7 @@ def parseOpts(overrideArguments=None):
     kw = {
         'version': __version__,
         'formatter': fmt,
-        'usage': '%prog [options] url [url...]',
+        'usage': '%prog [OPTIONS] URL [URL...]',
         'conflict_handler': 'resolve',
     }
 
@@ -267,10 +267,12 @@ def parseOpts(overrideArguments=None):
         action='store', dest='format', metavar='FORMAT', default=None,
         help=(
             'video format code, specify the order of preference using'
-            ' slashes: -f 22/17/18 .  -f mp4 , -f m4a and  -f flv  are also'
-            ' supported. You can also use the special names "best",'
-            ' "bestvideo", "bestaudio", "worst", "worstvideo" and'
-            ' "worstaudio". By default, youtube-dl will pick the best quality.'
+            ' slashes, as in -f 22/17/18 . '
+            ' Instead of format codes, you can select by extension for the '
+            'extensions aac, m4a, mp3, mp4, ogg, wav, webm. '
+            'You can also use the special names "best",'
+            ' "bestvideo", "bestaudio", "worst". '
+            ' By default, youtube-dl will pick the best quality.'
             ' Use commas to download multiple audio formats, such as'
             ' -f  136/137/mp4/bestvideo,140/m4a/bestaudio.'
             ' You can merge the video and audio of two formats into a single'