release 2016.09.24

Thanks to @daniel100097 for providing a working version

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.31*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.08.31**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.24**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.08.31
+[debug] youtube-dl version 2016.09.24
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}
@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/ISSUE_TEMPLATE_tmpl.md

@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

AUTHORS

@@ -182,3 +182,6 @@ Rob van Bekkum
 Petr Zvoníček
 Pratyush Singh
 Aleksander Nitecki
+Sebastian Blunt
+Matěj Cepl
+Xie Yanbo

ChangeLog

@@ -1,3 +1,184 @@
+version 2016.09.24
+
+Core
++ Add support for watchTVeverywhere.com authentication provider based MSOs for
+  Adobe Pass authentication (#10709)
+
+Extractors
++ [soundcloud:playlist] Provide video id for early playlist entries (#10733)
++ [prosiebensat1] Add support for kabeleinsdoku (#10732)
+* [cbs] Extract info from thunder videoPlayerService (#10728)
+* [openload] Fix extraction (#10408)
++ [ustream] Support the new HLS streams (#10698)
++ [ooyala] Extract all HLS formats
++ [cartoonnetwork] Add support for Adobe Pass authentication
++ [soundcloud] Extract license metadata
++ [fox] Add support for Adobe Pass authentication (#8584)
++ [tbs] Add support for Adobe Pass authentication (#10642, #10222)
++ [trutv] Add support for Adobe Pass authentication (#10519)
++ [turner] Add support for Adobe Pass authentication
+
+
+version 2016.09.19
+
+Extractors
++ [crunchyroll] Check if already authenticated (#10700)
+- [twitch:stream] Remove fallback to profile extraction when stream is offline
+* [thisav] Improve title extraction (#10682)
+* [vyborymos] Improve station info extraction
+
+
+version 2016.09.18
+
+Core
++ Introduce manifest_url and fragments fields in formats dictionary for
+  fragmented media
++ Provide manifest_url field for DASH segments, HLS and HDS
++ Provide fragments field for DASH segments
+* Rework DASH segments downloader to use fragments field
++ Add helper method for Wowza Streaming Engine formats extraction
+
+Extractors
++ [vyborymos] Add extractor for vybory.mos.ru (#10692)
++ [xfileshare] Add title regular expression for streamin.to (#10646)
++ [globo:article] Add support for multiple videos (#10653)
++ [thisav] Recognize HTML5 videos (#10447)
+* [jwplatform] Improve JWPlayer detection
++ [mangomolo] Add support for Mangomolo embeds
++ [toutv] Add support for authentication (#10669)
+* [franceinter] Fix upload date extraction
+* [tv4] Fix HLS and HDS formats extraction (#10659)
+
+
+version 2016.09.15
+
+Core
+* Improve _hidden_inputs
++ Introduce improved explicit Adobe Pass support
++ Add --ap-mso to provide multiple-system operator identifier
++ Add --ap-username to provide MSO account username
++ Add --ap-password to provide MSO account password
++ Add --ap-list-mso to list all supported MSOs
++ Add support for Rogers Cable multiple-system operator (#10606)
+
+Extractors
+* [crunchyroll] Fix authentication (#10655)
+* [twitch] Fix API calls (#10654, #10660)
++ [bellmedia] Add support for more Bell Media Television sites
+* [franceinter] Fix extraction (#10538, #2105)
+* [kuwo] Improve error detection (#10650)
++ [go] Add support for free full episodes (#10439)
+* [bilibili] Fix extraction for specific videos (#10647)
+* [nhk] Fix extraction (#10633)
+* [kaltura] Improve audio detection
+* [kaltura] Skip chun format
++ [vimeo:ondemand] Pass Referer along with embed URL (#10624)
++ [nbc] Add support for NBC Olympics (#10361)
+
+
+version 2016.09.11.1
+
+Extractors
++ [tube8] Extract categories and tags (#10579)
++ [pornhub] Extract categories and tags (#10499)
+* [openload] Temporary fix (#10408)
++ [foxnews] Add support Fox News articles (#10598)
+* [viafree] Improve video id extraction (#10615)
+* [iwara] Fix extraction after relaunch (#10462, #3215)
++ [tfo] Add extractor for tfo.org
+* [lrt] Fix audio extraction (#10566)
+* [9now] Fix extraction (#10561)
++ [canalplus] Add support for c8.fr (#10577)
+* [newgrounds] Fix uploader extraction (#10584)
++ [polskieradio:category] Add support for category lists (#10576)
++ [ketnet] Add extractor for ketnet.be (#10343)
++ [canvas] Add support for een.be (#10605)
++ [telequebec] Add extractor for telequebec.tv (#1999)
+* [parliamentliveuk] Fix extraction (#9137)
+
+
+version 2016.09.08
+
+Extractors
++ [jwplatform] Extract height from format label
++ [yahoo] Extract Brightcove Legacy Studio embeds (#9345)
+* [videomore] Fix extraction (#10592)
+* [foxgay] Fix extraction (#10480)
++ [rmcdecouverte] Add extractor for rmcdecouverte.bfmtv.com (#9709)
+* [gamestar] Fix metadata extraction (#10479)
+* [puls4] Fix extraction (#10583)
++ [cctv] Add extractor for CCTV and CNTV (#8153)
++ [lci] Add extractor for lci.fr (#10573)
++ [wat] Extract DASH formats
++ [viafree] Improve video id detection (#10569)
++ [trutv] Add extractor for trutv.com (#10519)
++ [nick] Add support for nickelodeon.nl (#10559)
++ [abcotvs:clips] Add support for clips.abcotvs.com
++ [abcotvs] Add support for ABC Owned Television Stations sites (#9551)
++ [miaopai] Add extractor for miaopai.com (#10556)
+* [gamestar] Fix metadata extraction (#10479)
++ [bilibili] Add support for episodes (#10190)
++ [tvnoe] Add extractor for tvnoe.cz (#10524)
+
+
+version 2016.09.04.1
+
+Core
+* In DASH downloader if the first segment fails, abort the whole download
+  process to prevent throttling (#10497)
++ Add support for --skip-unavailable-fragments and --fragment retries in
+  hlsnative downloader (#10165, #10448).
++ Add support for --skip-unavailable-fragments in DASH downloader
++ Introduce --skip-unavailable-fragments option for fragment based downloaders
+  that allows to skip fragments unavailable due to a HTTP error
+* Fix extraction of video/audio entries with src attribute in
+  _parse_html5_media_entries (#10540)
+
+Extractors
+* [theplatform] Relax URL regular expression (#10546)
+* [youtube:playlist] Extend URL regular expression
+* [rottentomatoes] Delegate extraction to internetvideoarchive extractor
+* [internetvideoarchive] Extract all formats
+* [pornvoisines] Fix extraction (#10469)
+* [rottentomatoes] Fix extraction (#10467)
+* [espn] Extend URL regular expression (#10549)
+* [vimple] Extend URL regular expression (#10547)
+* [youtube:watchlater] Fix extraction (#10544)
+* [youjizz] Fix extraction (#10437)
++ [foxnews] Add support for FoxNews Insider (#10445)
++ [fc2] Recognize Flash player URLs (#10512)
+
+
+version 2016.09.03
+
+Core
+* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
+  _extract_m3u8_formats (#10522)
+* Handle semicolon in mimetype2ext
+
+Extractors
++ [youtube] Add support for rental videos' previews (#10532)
+* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
+  no playlist is actually served (#10537)
++ [drtv] Add support for dr.dk/nyheder (#10536)
++ [facebook:plugins:video] Add extractor (#10530)
++ [go] Add extractor for *.go.com sites
+* [adobepass] Check for authz_token expiration (#10527)
+* [nytimes] improve extraction
+* [thestar] Fix extraction (#10465)
+* [glide] Fix extraction (#10478)
+- [exfm] Remove extractor (#10482)
+* [youporn] Fix categories and tags extraction (#10521)
++ [curiositystream] Add extractor for app.curiositystream.com
+- [thvideo] Remove extractor (#10464)
+* [movingimage] Fix for the new site name (#10466)
++ [cbs] Add support for once formats (#10515)
+* [limelight] Skip ism snd duplicate manifests
++ [porncom] Extract categories and tags (#10510)
++ [facebook] Extract timestamp (#10508)
++ [yahoo] Extract more formats
+
+
 version 2016.08.31
 
 Extractors

Makefile

@@ -1,7 +1,7 @@
 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 youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	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 youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

README.md

@@ -89,6 +89,8 @@ which means you can modify it, redistribute it or use it however you like.
     --mark-watched                   Mark videos watched (YouTube only)
     --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
+    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
+                                     available
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -173,7 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
     --fragment-retries RETRIES       Number of retries for a fragment (default
-                                     is 10), or "infinite" (DASH only)
+                                     is 10), or "infinite" (DASH and hlsnative
+                                     only)
+    --skip-unavailable-fragments     Skip unavailable fragments (DASH and
+                                     hlsnative only)
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -353,6 +358,17 @@ which means you can modify it, redistribute it or use it however you like.
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
+## Adobe Pass Options:
+    --ap-mso MSO                     Adobe Pass multiple-system operator (TV
+                                     provider) identifier, use --ap-list-mso for
+                                     a list of available MSOs
+    --ap-username USERNAME           Multiple-system operator account login
+    --ap-password PASSWORD           Multiple-system operator account password.
+                                     If this option is left out, youtube-dl will
+                                     ask interactively.
+    --ap-list-mso                    List all supported multiple-system
+                                     operators
+
 ## Post-processing Options:
     -x, --extract-audio              Convert video files to audio-only files
                                      (requires ffmpeg or avconv and ffprobe or
@@ -846,6 +862,16 @@ will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and cre
 
     youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
 
+### Should I add `--hls-prefer-native` into my config?
+
+When youtube-dl detects an HLS video, it can download it either with the built-in downloader or ffmpeg. Since many HLS streams are slightly invalid and ffmpeg/youtube-dl each handle some invalid cases better than the other, there is an option to switch the downloader if needed.
+
+When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
+
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+
+If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
+
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
 As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.

devscripts/release.sh

@@ -60,6 +60,9 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
 if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
+read -p "Is ChangeLog up to date? (y/n) " -n 1
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
+
 /bin/echo -e "\n### First of all, testing..."
 make clean
 if $skip_tests ; then

docs/supportedsites.md

@@ -19,9 +19,10 @@
  - **9now.com.au**
  - **abc.net.au**
  - **abc.net.au:iview**
- - **Abc7News**
  - **abcnews**
  - **abcnews:video**
+ - **abcotvs**: ABC Owned Television Stations
+ - **abcotvs:clips**
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
@@ -88,6 +89,7 @@
  - **BeatportPro**
  - **Beeg**
  - **BehindKink**
+ - **BellMedia**
  - **Bet**
  - **Bigflix**
  - **Bild**: Bild.de
@@ -128,6 +130,7 @@
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
+ - **CCTV**
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
@@ -167,10 +170,11 @@
  - **CSNNE**
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
- - **CTV**
  - **CTVNews**
  - **culturebox.francetvinfo.fr**
  - **CultureUnplugged**
+ - **curiositystream**
+ - **curiositystream:collection**
  - **CWTV**
  - **DailyMail**
  - **dailymotion**
@@ -223,13 +227,14 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
- - **exfm**: ex.fm
  - **ExpoTV**
  - **ExtremeTube**
  - **EyedoTV**
  - **facebook**
+ - **FacebookPluginsVideo**
  - **faz.net**
  - **fc2**
+ - **fc2:embed**
  - **Fczenit**
  - **features.aol.com**
  - **fernsehkritik.tv**
@@ -242,7 +247,9 @@
  - **Formula1**
  - **FOX**
  - **Foxgay**
- - **FoxNews**: Fox News and Fox Business Video
+ - **foxnews**: Fox News and Fox Business Video
+ - **foxnews:article**
+ - **foxnews:insider**
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
@@ -271,6 +278,7 @@
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
+ - **Go**
  - **GodTube**
  - **GodTV**
  - **Golem**
@@ -319,6 +327,7 @@
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
+ - **Iwara**
  - **Izlesene**
  - **JeuxVideo**
  - **Jove**
@@ -332,6 +341,7 @@
  - **KarriereVideos**
  - **keek**
  - **KeezMovies**
+ - **Ketnet**
  - **KhanAcademy**
  - **KickStarter**
  - **KonserthusetPlay**
@@ -347,6 +357,7 @@
  - **kuwo:song**: 酷我音乐
  - **la7.it**
  - **Laola1Tv**
+ - **LCI**
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
@@ -377,6 +388,8 @@
  - **mailru**: Видео@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
+ - **mangomolo:live**
+ - **mangomolo:video**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -385,6 +398,7 @@
  - **Metacritic**
  - **Mgoon**
  - **MGTV**: 芒果TV
+ - **MiaoPai**
  - **Minhateca**
  - **MinistryGrid**
  - **Minoto**
@@ -406,6 +420,7 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
+ - **MovingImage**
  - **MPORA**
  - **MSN**
  - **mtg**: MTG services
@@ -432,6 +447,7 @@
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCOlympics**
  - **NBCSports**
  - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Norddeutscher Rundfunk
@@ -530,6 +546,7 @@
  - **podomatic**
  - **Pokemon**
  - **PolskieRadio**
+ - **PolskieRadioCategory**
  - **PornCom**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
@@ -570,6 +587,7 @@
  - **revision3:embed**
  - **RICE**
  - **RingTV**
+ - **RMCDecouverte**
  - **RockstarGames**
  - **RoosterTeeth**
  - **RottenTomatoes**
@@ -659,7 +677,6 @@
  - **sr:mediathek**: Saarländischer Rundfunk
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **Stitcher**
@@ -691,9 +708,11 @@
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **TeleMB**
+ - **TeleQuebec**
  - **TeleTask**
  - **Telewebion**
  - **TF1**
+ - **TFO**
  - **TheIntercept**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -702,8 +721,6 @@
  - **TheStar**
  - **ThisAmericanLife**
  - **ThisAV**
- - **THVideo**
- - **THVideoPlaylist**
  - **tinypic**: tinypic.com videos
  - **tlc.de**
  - **TMZ**
@@ -717,7 +734,7 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
- - **trollvids**
+ - **TruTV**
  - **Tube8**
  - **TubiTv**
  - **tudou**
@@ -739,6 +756,7 @@
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
+ - **TVNoe**
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
@@ -833,6 +851,7 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VyboryMos**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**

test/test_utils.py

@@ -39,6 +39,8 @@ from youtube_dl.utils import (
     is_html,
     js_to_json,
     limit_length,
+    mimetype2ext,
+    month_by_name,
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
@@ -625,6 +627,22 @@ class TestUtil(unittest.TestCase):
             limit_length('foo bar baz asd', 12).startswith('foo bar'))
         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 
+    def test_mimetype2ext(self):
+        self.assertEqual(mimetype2ext(None), None)
+        self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
+        self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
+        self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
+        self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
+        self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
+
+    def test_month_by_name(self):
+        self.assertEqual(month_by_name(None), None)
+        self.assertEqual(month_by_name('December', 'en'), 12)
+        self.assertEqual(month_by_name('décembre', 'fr'), 12)
+        self.assertEqual(month_by_name('December'), 12)
+        self.assertEqual(month_by_name('décembre'), None)
+        self.assertEqual(month_by_name('Unknown', 'unknown'), None)
+
     def test_parse_codecs(self):
         self.assertEqual(parse_codecs(''), {})
         self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {

youtube_dl/YoutubeDL.py

@@ -131,6 +131,9 @@ class YoutubeDL(object):
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
     videopassword:     Password for accessing a video.
+    ap_mso:            Adobe Pass multiple-system operator identifier.
+    ap_username:       Multiple-system operator account username.
+    ap_password:       Multiple-system operator account password.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.

youtube_dl/__init__.py

@@ -34,12 +34,14 @@ from .utils import (
     setproctitle,
     std_headers,
     write_string,
+    render_table,
 )
 from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors, list_extractors
+from .extractor.adobepass import MSO_INFO
 from .YoutubeDL import YoutubeDL
 
 
@@ -118,18 +120,26 @@ def _real_main(argv=None):
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             write_string(desc + '\n', out=sys.stdout)
         sys.exit(0)
+    if opts.ap_list_mso:
+        table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
+        write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
+        sys.exit(0)
 
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error('using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
         parser.error('account username missing\n')
+    if opts.ap_password is not None and opts.ap_username is None:
+        parser.error('TV Provider account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
         opts.password = compat_getpass('Type account password and press [Return]: ')
+    if opts.ap_username is not None and opts.ap_password is None:
+        opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -155,6 +165,8 @@ def _real_main(argv=None):
             parser.error('max sleep interval must be greater than or equal to min sleep interval')
     else:
         opts.max_sleep_interval = opts.sleep_interval
+    if opts.ap_mso and opts.ap_mso not in MSO_INFO:
+        parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
@@ -293,6 +305,9 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
+        'ap_mso': opts.ap_mso,
+        'ap_username': opts.ap_username,
+        'ap_password': opts.ap_password,
         'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
@@ -318,6 +333,7 @@ def _real_main(argv=None):
         'nooverwrites': opts.nooverwrites,
         'retries': opts.retries,
         'fragment_retries': opts.fragment_retries,
+        'skip_unavailable_fragments': opts.skip_unavailable_fragments,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,

youtube_dl/downloader/dash.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import os
-import re
 
 from .fragment import FragmentFD
 from ..compat import compat_urllib_error
@@ -19,32 +18,32 @@ class DashSegmentsFD(FragmentFD):
     FD_NAME = 'dashsegments'
 
     def real_download(self, filename, info_dict):
-        base_url = info_dict['url']
-        segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
-        initialization_url = info_dict.get('initialization_url')
+        segments = info_dict['fragments'][:1] if self.params.get(
+            'test', False) else info_dict['fragments']
 
         ctx = {
             'filename': filename,
-            'total_frags': len(segment_urls) + (1 if initialization_url else 0),
+            'total_frags': len(segments),
         }
 
         self._prepare_and_start_frag_download(ctx)
 
-        def combine_url(base_url, target_url):
-            if re.match(r'^https?://', target_url):
-                return target_url
-            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
-
         segments_filenames = []
 
         fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        def append_url_to_file(target_url, tmp_filename, segment_name):
+        def process_segment(segment, tmp_filename, num):
+            segment_url = segment['url']
+            segment_name = 'Frag%d' % num
             target_filename = '%s-%s' % (tmp_filename, segment_name)
+            # In DASH, the first segment contains necessary headers to
+            # generate a valid MP4 file, so always abort for the first segment
+            fatal = num == 0 or not skip_unavailable_fragments
             count = 0
             while count <= fragment_retries:
                 try:
-                    success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
+                    success = ctx['dl'].download(target_filename, {'url': segment_url})
                     if not success:
                         return False
                     down, target_sanitized = sanitize_open(target_filename, 'rb')
@@ -52,26 +51,27 @@ class DashSegmentsFD(FragmentFD):
                     down.close()
                     segments_filenames.append(target_sanitized)
                     break
-                except (compat_urllib_error.HTTPError, ) as err:
+                except compat_urllib_error.HTTPError as err:
                     # YouTube may often return 404 HTTP error for a fragment causing the
                     # whole download to fail. However if the same fragment is immediately
                     # retried with the same request data this usually succeeds (1-2 attemps
                     # is usually enough) thus allowing to download the whole file successfully.
-                    # So, we will retry all fragments that fail with 404 HTTP error for now.
-                    if err.code != 404:
-                        raise
-                    # Retry fragment
+                    # To be future-proof we will retry all fragments that fail with any
+                    # HTTP error.
                     count += 1
                     if count <= fragment_retries:
-                        self.report_retry_fragment(segment_name, count, fragment_retries)
+                        self.report_retry_fragment(err, segment_name, count, fragment_retries)
             if count > fragment_retries:
+                if not fatal:
+                    self.report_skip_fragment(segment_name)
+                    return True
                 self.report_error('giving up after %s fragment retries' % fragment_retries)
                 return False
+            return True
 
-        if initialization_url:
-            append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
-        for i, segment_url in enumerate(segment_urls):
-            append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
+        for i, segment in enumerate(segments):
+            if not process_segment(segment, ctx['tmpfilename'], i):
+                return False
 
         self._finish_frag_download(ctx)
 

youtube_dl/downloader/fragment.py

@@ -6,6 +6,7 @@ import time
 from .common import FileDownloader
 from .http import HttpFD
 from ..utils import (
+    error_to_compat_str,
     encodeFilename,
     sanitize_open,
 )
@@ -22,13 +23,19 @@ class FragmentFD(FileDownloader):
 
     Available options:
 
-    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH only)
+    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH
+                        and hlsnative only)
+    skip_unavailable_fragments:
+                        Skip unavailable fragments (DASH and hlsnative only)
     """
 
-    def report_retry_fragment(self, fragment_name, count, retries):
+    def report_retry_fragment(self, err, fragment_name, count, retries):
         self.to_screen(
-            '[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
-            % (fragment_name, count, self.format_retries(retries)))
+            '[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
+            % (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
+
+    def report_skip_fragment(self, fragment_name):
+        self.to_screen('[download] Skipping fragment %s...' % fragment_name)
 
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -13,6 +13,7 @@ from .fragment import FragmentFD
 from .external import FFmpegFD
 
 from ..compat import (
+    compat_urllib_error,
     compat_urlparse,
     compat_struct_pack,
 )
@@ -83,6 +84,10 @@ class HlsFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
+        fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
+        test = self.params.get('test', False)
+
         extra_query = None
         extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
         if extra_param_to_segment_url:
@@ -99,15 +104,37 @@ class HlsFD(FragmentFD):
                         line
                         if re.match(r'^https?://', line)
                         else compat_urlparse.urljoin(man_url, line))
-                    frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+                    frag_name = 'Frag%d' % i
+                    frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
-                    success = ctx['dl'].download(frag_filename, {'url': frag_url})
-                    if not success:
+                    count = 0
+                    while count <= fragment_retries:
+                        try:
+                            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                            if not success:
+                                return False
+                            down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+                            frag_content = down.read()
+                            down.close()
+                            break
+                        except compat_urllib_error.HTTPError as err:
+                            # Unavailable (possibly temporary) fragments may be served.
+                            # First we try to retry then either skip or abort.
+                            # See https://github.com/rg3/youtube-dl/issues/10165,
+                            # https://github.com/rg3/youtube-dl/issues/10448).
+                            count += 1
+                            if count <= fragment_retries:
+                                self.report_retry_fragment(err, frag_name, count, fragment_retries)
+                    if count > fragment_retries:
+                        if skip_unavailable_fragments:
+                            i += 1
+                            media_sequence += 1
+                            self.report_skip_fragment(frag_name)
+                            continue
+                        self.report_error(
+                            'giving up after %s fragment retries' % fragment_retries)
                         return False
-                    down, frag_sanitized = sanitize_open(frag_filename, 'rb')
-                    frag_content = down.read()
-                    down.close()
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
                         frag_content = AES.new(
@@ -115,7 +142,7 @@ class HlsFD(FragmentFD):
                     ctx['dest_stream'].write(frag_content)
                     frags_filenames.append(frag_sanitized)
                     # We only download the first fragment during the test
-                    if self.params.get('test', False):
+                    if test:
                         break
                     i += 1
                     media_sequence += 1

youtube_dl/extractor/abc.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -100,6 +100,7 @@ class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'
     _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
 
+    # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
         'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
         'md5': '979d10b2939101f0d27a06b79edad536',
@@ -112,6 +113,7 @@ class ABCIViewIE(InfoExtractor):
             'uploader_id': 'abc1',
             'timestamp': 1471719600,
         },
+        'skip': 'Video gone',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/abcnews.py

@@ -12,7 +12,7 @@ from ..compat import compat_urlparse
 
 class AbcNewsVideoIE(AMPIE):
     IE_NAME = 'abcnews:video'
-    _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
@@ -49,7 +49,7 @@ class AbcNewsVideoIE(AMPIE):
 
 class AbcNewsIE(InfoExtractor):
     IE_NAME = 'abcnews'
-    _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',

youtube_dl/extractor/abcotvs.py

@@ -1,13 +1,19 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
-class Abc7NewsIE(InfoExtractor):
-    _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+class ABCOTVSIE(InfoExtractor):
+    IE_NAME = 'abcotvs'
+    IE_DESC = 'ABC Owned Television Stations'
+    _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
@@ -15,7 +21,7 @@ class Abc7NewsIE(InfoExtractor):
                 'id': '472581',
                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
                 'ext': 'mp4',
-                'title': 'East Bay museum celebrates history of synthesized music',
+                'title': 'East Bay museum celebrates vintage synthesizers',
                 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'timestamp': 1421123075,
@@ -41,7 +47,7 @@ class Abc7NewsIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         m3u8 = self._html_search_meta(
-            'contentURL', webpage, 'm3u8 url', fatal=True)
+            'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
 
         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
         self._sort_formats(formats)
@@ -66,3 +72,41 @@ class Abc7NewsIE(InfoExtractor):
             'uploader': uploader,
             'formats': formats,
         }
+
+
+class ABCOTVSClipsIE(InfoExtractor):
+    IE_NAME = 'abcotvs:clips'
+    _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://clips.abcotvs.com/kabc/video/214814',
+        'info_dict': {
+            'id': '214814',
+            'ext': 'mp4',
+            'title': 'SpaceX launch pad explosion destroys rocket, satellite',
+            'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
+            'upload_date': '20160901',
+            'timestamp': 1472756695,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
+        title = video_data['title']
+        formats = self._extract_m3u8_formats(
+            video_data['videoURL'].split('?')[0], video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailURL'),
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('pubDate')),
+            'formats': formats,
+        }

youtube_dl/extractor/aljazeera.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
 
     _TEST = {
         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',

youtube_dl/extractor/ard.py

@@ -238,7 +238,7 @@ class ARDMediathekIE(InfoExtractor):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TEST = {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'md5': 'd216c3a86493f9322545e045ddc3eb35',

youtube_dl/extractor/awaan.py

@@ -50,25 +50,6 @@ class AWAANBaseIE(InfoExtractor):
             'is_live': is_live,
         }
 
-    def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol):
-        formats = []
-        format_url_base = 'http' + self._html_search_regex(
-            [
-                r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
-                r'<a[^>]+href="rtsp(://[^"]+)"'
-            ], webpage, 'format url')
-        formats.extend(self._extract_mpd_formats(
-            format_url_base + '/manifest.mpd',
-            video_id, mpd_id='dash', fatal=False))
-        formats.extend(self._extract_m3u8_formats(
-            format_url_base + '/playlist.m3u8', video_id, 'mp4',
-            m3u8_entry_protocol, m3u8_id='hls', fatal=False))
-        formats.extend(self._extract_f4m_formats(
-            format_url_base + '/manifest.f4m',
-            video_id, f4m_id='hds', fatal=False))
-        self._sort_formats(formats)
-        return formats
-
 
 class AWAANVideoIE(AWAANBaseIE):
     IE_NAME = 'awaan:video'
@@ -99,16 +80,18 @@ class AWAANVideoIE(AWAANBaseIE):
             video_id, headers={'Origin': 'http://awaan.ae'})
         info = self._parse_video_data(video_data, video_id, False)
 
-        webpage = self._download_webpage(
-            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
-            compat_urllib_parse_urlencode({
-                'id': video_data['id'],
-                'user_id': video_data['user_id'],
-                'signature': video_data['signature'],
-                'countries': 'Q0M=',
-                'filter': 'DENY',
-            }), video_id)
-        info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
+            'id': video_data['id'],
+            'user_id': video_data['user_id'],
+            'signature': video_data['signature'],
+            'countries': 'Q0M=',
+            'filter': 'DENY',
+        })
+        info.update({
+            '_type': 'url_transparent',
+            'url': embed_url,
+            'ie_key': 'MangomoloVideo',
+        })
         return info
 
 
@@ -138,16 +121,18 @@ class AWAANLiveIE(AWAANBaseIE):
             channel_id, headers={'Origin': 'http://awaan.ae'})
         info = self._parse_video_data(channel_data, channel_id, True)
 
-        webpage = self._download_webpage(
-            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
-            compat_urllib_parse_urlencode({
-                'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
-                'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
-                'signature': channel_data['signature'],
-                'countries': 'Q0M=',
-                'filter': 'DENY',
-            }), channel_id)
-        info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
+            'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
+            'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
+            'signature': channel_data['signature'],
+            'countries': 'Q0M=',
+            'filter': 'DENY',
+        })
+        info.update({
+            '_type': 'url_transparent',
+            'url': embed_url,
+            'ie_key': 'MangomoloLive',
+        })
         return info
 
 

youtube_dl/extractor/azubu.py

@@ -103,7 +103,7 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
 
     _TEST = {
         'url': 'http://www.azubu.tv/MarsTVMDLen',

youtube_dl/extractor/bbc.py

@@ -1028,7 +1028,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 

youtube_dl/extractor/bellmedia.py

@@ -6,8 +6,25 @@ import re
 from .common import InfoExtractor
 
 
-class CTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>ctv|tsn|bnn|thecomedynetwork)\.ca/.*?(?:\bvid=|-vid|~|%7E)(?P<id>[0-9.]+)'
+class BellMediaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+        (?P<domain>
+            (?:
+                ctv|
+                tsn|
+                bnn|
+                thecomedynetwork|
+                discovery|
+                discoveryvelocity|
+                sciencechannel|
+                investigationdiscovery|
+                animalplanet|
+                bravo|
+                mtv|
+                space
+            )\.ca|
+            much\.com
+        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -32,15 +49,27 @@ class CTVIE(InfoExtractor):
     }, {
         'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
         'only_matching': True,
+    }, {
+        'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
+        'only_matching': True,
     }]
+    _DOMAINS = {
+        'thecomedynetwork': 'comedy',
+        'discoveryvelocity': 'discvel',
+        'sciencechannel': 'discsci',
+        'investigationdiscovery': 'invdisc',
+        'animalplanet': 'aniplan',
+    }
 
     def _real_extract(self, url):
         domain, video_id = re.match(self._VALID_URL, url).groups()
-        if domain == 'thecomedynetwork':
-            domain = 'comedy'
+        domain = domain.split('.')[0]
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': '9c9media:%s_web:%s' % (domain, video_id),
+            'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
             'ie_key': 'NineCNineMedia',
         }

youtube_dl/extractor/bilibili.py

@@ -10,13 +10,14 @@ from ..utils import (
     int_or_none,
     float_or_none,
     unified_timestamp,
+    urlencode_postdata,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
 
-    _TESTS = [{
+    _TEST = {
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
         'info_dict': {
@@ -31,66 +32,26 @@ class BiliBiliIE(InfoExtractor):
             'uploader': '菊子桑',
             'uploader_id': '156160',
         },
-    }, {
-        'url': 'http://www.bilibili.com/video/av1041170/',
-        'info_dict': {
-            'id': '1041170',
-            'ext': 'mp4',
-            'title': '【BD1080P】刀语【诸神&异域】',
-            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
-            'duration': 3382.259,
-            'timestamp': 1396530060,
-            'upload_date': '20140403',
-            'thumbnail': 're:^https?://.+\.jpg',
-            'uploader': '枫叶逝去',
-            'uploader_id': '520116',
-        },
-    }, {
-        'url': 'http://www.bilibili.com/video/av4808130/',
-        'info_dict': {
-            'id': '4808130',
-            'ext': 'mp4',
-            'title': '【长篇】哆啦A梦443【钉铛】',
-            'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
-            'duration': 1493.995,
-            'timestamp': 1464564180,
-            'upload_date': '20160529',
-            'thumbnail': 're:^https?://.+\.jpg',
-            'uploader': '喜欢拉面',
-            'uploader_id': '151066',
-        },
-    }, {
-        # Missing upload time
-        'url': 'http://www.bilibili.com/video/av1867637/',
-        'info_dict': {
-            'id': '1867637',
-            'ext': 'mp4',
-            'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
-            'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
-            'duration': 5760.0,
-            'uploader': '黑夜为猫',
-            'uploader_id': '610729',
-            'thumbnail': 're:^https?://.+\.jpg',
-        },
-        'params': {
-            # Just to test metadata extraction
-            'skip_download': True,
-        },
-        'expected_warnings': ['upload time'],
-    }]
+    }
 
     _APP_KEY = '6f90a59ac58a4123'
     _BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
 
-        cid = compat_parse_qs(self._search_regex(
-            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
-             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
-            webpage, 'player parameters'))['cid'][0]
+        if 'anime/v' not in url:
+            cid = compat_parse_qs(self._search_regex(
+                [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+                 r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+                webpage, 'player parameters'))['cid'][0]
+        else:
+            js = self._download_json(
+                'http://bangumi.bilibili.com/web_api/get_source', video_id,
+                data=urlencode_postdata({'episode_id': video_id}),
+                headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+            cid = js['result']['cid']
 
         payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
         sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
@@ -106,7 +67,7 @@ class BiliBiliIE(InfoExtractor):
                 'url': durl['url'],
                 'filesize': int_or_none(durl['size']),
             }]
-            for backup_url in durl['backup_url']:
+            for backup_url in durl.get('backup_url', []):
                 formats.append({
                     'url': backup_url,
                     # backup URLs have lower priorities
@@ -125,6 +86,7 @@ class BiliBiliIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
+        thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
@@ -132,7 +94,7 @@ class BiliBiliIE(InfoExtractor):
             'title': title,
             'description': description,
             'timestamp': timestamp,
-            'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
+            'thumbnail': thumbnail,
             'duration': float_or_none(video_info.get('timelength'), scale=1000),
         }
 

youtube_dl/extractor/bpb.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class BpbIE(InfoExtractor):
     IE_DESC = 'Bundeszentrale für politische Bildung'
-    _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',

youtube_dl/extractor/camdemy.py

@@ -112,7 +112,7 @@ class CamdemyIE(InfoExtractor):
 
 
 class CamdemyFolderIE(InfoExtractor):
-    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/folder/(?P<id>\d+)'
     _TESTS = [{
         # links with trailing slash
         'url': 'http://www.camdemy.com/folder/450',

youtube_dl/extractor/canalplus.py

@@ -23,6 +23,7 @@ class CanalplusIE(InfoExtractor):
                                     (?:(?:www|m)\.)?canalplus\.fr|
                                     (?:www\.)?piwiplus\.fr|
                                     (?:www\.)?d8\.tv|
+                                    (?:www\.)?c8\.fr|
                                     (?:www\.)?d17\.tv|
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
@@ -35,6 +36,7 @@ class CanalplusIE(InfoExtractor):
         'canalplus': 'cplus',
         'piwiplus': 'teletoon',
         'd8': 'd8',
+        'c8': 'd8',
         'd17': 'd17',
         'itele': 'itele',
     }

youtube_dl/extractor/canvas.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import float_or_none
 
 
 class CanvasIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
         'md5': 'ea838375a547ac787d4064d8c7860a6c',
@@ -38,22 +40,42 @@ class CanvasIE(InfoExtractor):
         'params': {
             'skip_download': True,
         }
+    }, {
+        'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
+        'info_dict': {
+            'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
+            'display_id': 'herbekijk-sorry-voor-alles',
+            'ext': 'mp4',
+            'title': 'Herbekijk Sorry voor alles',
+            'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 3788.06,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        site_id, display_id = mobj.group('site_id'), mobj.group('id')
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._search_regex(
+        title = (self._search_regex(
             r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
-            webpage, 'title', default=None) or self._og_search_title(webpage)
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage)).strip()
 
         video_id = self._html_search_regex(
-            r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
+            r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', group='id')
 
         data = self._download_json(
-            'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+            'https://mediazone.vrt.be/api/v1/%s/assets/%s'
+            % (site_id, video_id), display_id)
 
         formats = []
         for target in data['targetUrls']:

youtube_dl/extractor/cartoonnetwork.py

@@ -30,7 +30,13 @@ class CartoonNetworkIE(TurnerBaseIE):
         return self._extract_cvp_info(
             'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
                 'secure': {
-                    'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
+                    'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
                     'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
                 },
+            }, {
+                'url': url,
+                'site_name': 'CartoonNetwork',
+                'auth_required': self._search_regex(
+                    r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
+                    webpage, 'auth required', default='false') == 'true',
             })

youtube_dl/extractor/cbs.py

@@ -4,7 +4,9 @@ from .theplatform import ThePlatformFeedIE
 from ..utils import (
     int_or_none,
     find_xpath_attr,
-    ExtractorError,
+    xpath_element,
+    xpath_text,
+    update_url_query,
 )
 
 
@@ -47,27 +49,49 @@ class CBSIE(CBSBaseIE):
         'only_matching': True,
     }]
 
-    def _extract_video_info(self, guid):
-        path = 'dJ5BDC/media/guid/2198311517/' + guid
-        smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
-        formats, subtitles = self._extract_theplatform_smil(smil_url + '&manifest=m3u', guid)
-        for r in ('HLS&formats=M3U', 'RTMP', 'WIFI', '3G'):
-            try:
-                tp_formats, _ = self._extract_theplatform_smil(smil_url + '&assetTypes=' + r, guid, 'Downloading %s SMIL data' % r.split('&')[0])
-                formats.extend(tp_formats)
-            except ExtractorError:
+    def _extract_video_info(self, content_id):
+        items_data = self._download_xml(
+            'http://can.cbs.com/thunder/player/videoPlayerService.php',
+            content_id, query={'partner': 'cbs', 'contentId': content_id})
+        video_data = xpath_element(items_data, './/item')
+        title = xpath_text(video_data, 'videoTitle', 'title', True)
+        tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
+        tp_release_url = 'http://link.theplatform.com/s/' + tp_path
+
+        asset_types = []
+        subtitles = {}
+        formats = []
+        for item in items_data.findall('.//item'):
+            asset_type = xpath_text(item, 'assetType')
+            if not asset_type or asset_type in asset_types:
                 continue
+            asset_types.append(asset_type)
+            query = {
+                'mbr': 'true',
+                'assetTypes': asset_type,
+            }
+            if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
+                query['formats'] = 'MPEG4,M3U'
+            elif asset_type in ('RTMP', 'WIFI', '3G'):
+                query['formats'] = 'MPEG4,FLV'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                update_url_query(tp_release_url, query), content_id,
+                'Downloading %s SMIL data' % asset_type)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
         self._sort_formats(formats)
-        metadata = self._download_theplatform_metadata(path, guid)
-        info = self._parse_theplatform_metadata(metadata)
+
+        info = self._extract_theplatform_metadata(tp_path, content_id)
         info.update({
-            'id': guid,
+            'id': content_id,
+            'title': title,
+            'series': xpath_text(video_data, 'seriesTitle'),
+            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
+            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
+            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
+            'thumbnail': xpath_text(video_data, 'previewImageURL'),
             'formats': formats,
             'subtitles': subtitles,
-            'series': metadata.get('cbs$SeriesTitle'),
-            'season_number': int_or_none(metadata.get('cbs$SeasonNumber')),
-            'episode': metadata.get('cbs$EpisodeTitle'),
-            'episode_number': int_or_none(metadata.get('cbs$EpisodeNumber')),
         })
         return info
 

youtube_dl/extractor/cbssports.py

@@ -4,7 +4,7 @@ from .cbs import CBSBaseIE
 
 
 class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',

youtube_dl/extractor/cctv.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CCTVIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:.+?\.)?
+        (?:
+            cctv\.(?:com|cn)|
+            cntv\.cn
+        )/
+        (?:
+            video/[^/]+/(?P<id>[0-9a-f]{32})|
+            \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
+        )'''
+    _TESTS = [{
+        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+        'md5': '819c7b49fc3927d529fb4cd555621823',
+        'info_dict': {
+            'id': '454368eb19ad44a1925bf1eb96140a61',
+            'ext': 'mp4',
+            'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
+        }
+    }, {
+        'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(
+                r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
+                webpage, 'video_id')
+        api_data = self._download_json(
+            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
+        m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+
+        return {
+            'id': video_id,
+            'title': api_data['title'],
+            'formats': self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
+            'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+        }

youtube_dl/extractor/ceskatelevize.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {

youtube_dl/extractor/chirbit.py

@@ -65,7 +65,7 @@ class ChirbitIE(InfoExtractor):
 
 class ChirbitProfileIE(InfoExtractor):
     IE_NAME = 'chirbit:profile'
-    _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {

youtube_dl/extractor/cmt.py

@@ -6,7 +6,7 @@ from ..utils import ExtractorError
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{

youtube_dl/extractor/common.py

@@ -87,6 +87,9 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
+                    * manifest_url
+                                 The URL of the manifest file in case of
+                                 fragmented media (DASH, hls, hds)
                     * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
@@ -115,6 +118,11 @@ class InfoExtractor(object):
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                                  "m3u8", "m3u8_native" or "http_dash_segments".
+                    * fragments  A list of fragments of the fragmented media,
+                                 with the following entries:
+                                 * "url" (mandatory) - fragment's URL
+                                 * "duration" (optional, int or float)
+                                 * "filesize" (optional, int)
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -674,33 +682,36 @@ class InfoExtractor(object):
                     username = info[0]
                     password = info[2]
                 else:
-                    raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
+                    raise netrc.NetrcParseError(
+                        'No authenticators for %s' % netrc_machine)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+                self._downloader.report_warning(
+                    'parsing .netrc: %s' % error_to_compat_str(err))
 
-        return (username, password)
+        return username, password
 
-    def _get_login_info(self):
+    def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None):
         """
         Get the login info as (username, password)
-        It will look in the netrc file using the _NETRC_MACHINE value
+        First look for the manually specified credentials using username_option
+        and password_option as keys in params dictionary. If no such credentials
+        available look in the netrc file using the netrc_machine or _NETRC_MACHINE
+        value.
         If there's no info available, return (None, None)
         """
         if self._downloader is None:
             return (None, None)
 
-        username = None
-        password = None
         downloader_params = self._downloader.params
 
         # Attempt to use provided username and password or .netrc data
-        if downloader_params.get('username') is not None:
-            username = downloader_params['username']
-            password = downloader_params['password']
+        if downloader_params.get(username_option) is not None:
+            username = downloader_params[username_option]
+            password = downloader_params[password_option]
         else:
-            username, password = self._get_netrc_login_info()
+            username, password = self._get_netrc_login_info(netrc_machine)
 
-        return (username, password)
+        return username, password
 
     def _get_tfa_info(self, note='two-factor verification code'):
         """
@@ -888,16 +899,16 @@ class InfoExtractor(object):
     def _hidden_inputs(html):
         html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
         hidden_inputs = {}
-        for input in re.findall(r'(?i)<input([^>]+)>', html):
-            if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
+        for input in re.findall(r'(?i)(<input[^>]+>)', html):
+            attrs = extract_attributes(input)
+            if not input:
                 continue
-            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)
-            if not name:
+            if attrs.get('type') not in ('hidden', 'submit'):
                 continue
-            value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
-            if not value:
-                continue
-            hidden_inputs[name.group('value')] = value.group('value')
+            name = attrs.get('name') or attrs.get('id')
+            value = attrs.get('value')
+            if name and value is not None:
+                hidden_inputs[name] = value
         return hidden_inputs
 
     def _form_hidden_inputs(self, form_id, html):
@@ -1139,6 +1150,7 @@ class InfoExtractor(object):
             formats.append({
                 'format_id': format_id,
                 'url': manifest_url,
+                'manifest_url': manifest_url,
                 'ext': 'flv' if bootstrap_info is not None else None,
                 'tbr': tbr,
                 'width': width,
@@ -1163,13 +1175,6 @@ class InfoExtractor(object):
                               m3u8_id=None, note=None, errnote=None,
                               fatal=True, live=False):
 
-        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
-
-        format_url = lambda u: (
-            u
-            if re.match(r'^https?://', u)
-            else compat_urlparse.urljoin(m3u8_url, u))
-
         res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
@@ -1180,6 +1185,13 @@ class InfoExtractor(object):
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
 
+        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
+
+        format_url = lambda u: (
+            u
+            if re.match(r'^https?://', u)
+            else compat_urlparse.urljoin(m3u8_url, u))
+
         # We should try extracting formats only from master playlists [1], i.e.
         # playlists that describe available qualities. On the other hand media
         # playlists [2] should be returned as is since they contain just the media
@@ -1201,7 +1213,8 @@ class InfoExtractor(object):
                 'protocol': entry_protocol,
                 'preference': preference,
             }]
-        last_info = None
+        last_info = {}
+        last_media = {}
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
                 last_info = parse_m3u8_attributes(line)
@@ -1224,27 +1237,30 @@ class InfoExtractor(object):
                             'protocol': entry_protocol,
                             'preference': preference,
                         })
+                    else:
+                        # When there is no URI in EXT-X-MEDIA let this tag's
+                        # data be used by regular URI lines below
+                        last_media = media
             elif line.startswith('#') or not line.strip():
                 continue
             else:
-                if last_info is None:
-                    formats.append({'url': format_url(line)})
-                    continue
                 tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
                 format_id = []
                 if m3u8_id:
                     format_id.append(m3u8_id)
+                # Despite specification does not mention NAME attribute for
+                # EXT-X-STREAM-INF it still sometimes may be present
+                stream_name = last_info.get('NAME') or last_media.get('NAME')
                 # Bandwidth of live streams may differ over time thus making
                 # format_id unpredictable. So it's better to keep provided
                 # format_id intact.
                 if not live:
-                    # Despite specification does not mention NAME attribute for
-                    # EXT-X-STREAM-INF it still sometimes may be present
-                    stream_name = last_info.get('NAME')
                     format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats)))
+                manifest_url = format_url(line.strip())
                 f = {
                     'format_id': '-'.join(format_id),
-                    'url': format_url(line.strip()),
+                    'url': manifest_url,
+                    'manifest_url': manifest_url,
                     'tbr': tbr,
                     'ext': ext,
                     'fps': float_or_none(last_info.get('FRAME-RATE')),
@@ -1269,6 +1285,7 @@ class InfoExtractor(object):
                 f.update(parse_codecs(last_info.get('CODECS')))
                 formats.append(f)
                 last_info = {}
+                last_media = {}
         return formats
 
     @staticmethod
@@ -1515,9 +1532,10 @@ class InfoExtractor(object):
         mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
 
         return self._parse_mpd_formats(
-            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
+            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url,
+            formats_dict=formats_dict, mpd_url=mpd_url)
 
-    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
         """
         Parse formats from MPD manifest.
         References:
@@ -1538,42 +1556,52 @@ class InfoExtractor(object):
 
         def extract_multisegment_info(element, ms_parent_info):
             ms_info = ms_parent_info.copy()
+
+            # As per [1, 5.3.9.2.2] SegmentList and SegmentTemplate share some
+            # common attributes and elements.  We will only extract relevant
+            # for us.
+            def extract_common(source):
+                segment_timeline = source.find(_add_ns('SegmentTimeline'))
+                if segment_timeline is not None:
+                    s_e = segment_timeline.findall(_add_ns('S'))
+                    if s_e:
+                        ms_info['total_number'] = 0
+                        ms_info['s'] = []
+                        for s in s_e:
+                            r = int(s.get('r', 0))
+                            ms_info['total_number'] += 1 + r
+                            ms_info['s'].append({
+                                't': int(s.get('t', 0)),
+                                # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
+                                'd': int(s.attrib['d']),
+                                'r': r,
+                            })
+                start_number = source.get('startNumber')
+                if start_number:
+                    ms_info['start_number'] = int(start_number)
+                timescale = source.get('timescale')
+                if timescale:
+                    ms_info['timescale'] = int(timescale)
+                segment_duration = source.get('duration')
+                if segment_duration:
+                    ms_info['segment_duration'] = int(segment_duration)
+
+            def extract_Initialization(source):
+                initialization = source.find(_add_ns('Initialization'))
+                if initialization is not None:
+                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
+
             segment_list = element.find(_add_ns('SegmentList'))
             if segment_list is not None:
+                extract_common(segment_list)
+                extract_Initialization(segment_list)
                 segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
                 if segment_urls_e:
                     ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
-                initialization = segment_list.find(_add_ns('Initialization'))
-                if initialization is not None:
-                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
             else:
                 segment_template = element.find(_add_ns('SegmentTemplate'))
                 if segment_template is not None:
-                    start_number = segment_template.get('startNumber')
-                    if start_number:
-                        ms_info['start_number'] = int(start_number)
-                    segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
-                    if segment_timeline is not None:
-                        s_e = segment_timeline.findall(_add_ns('S'))
-                        if s_e:
-                            ms_info['total_number'] = 0
-                            ms_info['s'] = []
-                            for s in s_e:
-                                r = int(s.get('r', 0))
-                                ms_info['total_number'] += 1 + r
-                                ms_info['s'].append({
-                                    't': int(s.get('t', 0)),
-                                    # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
-                                    'd': int(s.attrib['d']),
-                                    'r': r,
-                                })
-                    else:
-                        timescale = segment_template.get('timescale')
-                        if timescale:
-                            ms_info['timescale'] = int(timescale)
-                        segment_duration = segment_template.get('duration')
-                        if segment_duration:
-                            ms_info['segment_duration'] = int(segment_duration)
+                    extract_common(segment_template)
                     media_template = segment_template.get('media')
                     if media_template:
                         ms_info['media_template'] = media_template
@@ -1581,11 +1609,14 @@ class InfoExtractor(object):
                     if initialization:
                         ms_info['initialization_url'] = initialization
                     else:
-                        initialization = segment_template.find(_add_ns('Initialization'))
-                        if initialization is not None:
-                            ms_info['initialization_url'] = initialization.attrib['sourceURL']
+                        extract_Initialization(segment_template)
             return ms_info
 
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
+
         mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
         formats = []
         for period in mpd_doc.findall(_add_ns('Period')):
@@ -1628,6 +1659,7 @@ class InfoExtractor(object):
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
+                            'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
@@ -1642,9 +1674,7 @@ class InfoExtractor(object):
                         }
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
                         if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
-                            if 'total_number' not in representation_ms_info and 'segment_duration':
-                                segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale'])
-                                representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
                             media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
@@ -1653,46 +1683,79 @@ class InfoExtractor(object):
 
                             # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
                             # can't be used at the same time
-                            if '%(Number' in media_template:
-                                representation_ms_info['segment_urls'] = [
-                                    media_template % {
+                            if '%(Number' in media_template and 's' not in representation_ms_info:
+                                segment_duration = None
+                                if 'total_number' not in representation_ms_info and 'segment_duration':
+                                    segment_duration = float_or_none(representation_ms_info['segment_duration'], representation_ms_info['timescale'])
+                                    representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+                                representation_ms_info['fragments'] = [{
+                                    'url': media_template % {
                                         'Number': segment_number,
                                         'Bandwidth': representation_attrib.get('bandwidth'),
-                                    }
-                                    for segment_number in range(
-                                        representation_ms_info['start_number'],
-                                        representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                                    },
+                                    'duration': segment_duration,
+                                } for segment_number in range(
+                                    representation_ms_info['start_number'],
+                                    representation_ms_info['total_number'] + representation_ms_info['start_number'])]
                             else:
-                                representation_ms_info['segment_urls'] = []
+                                # $Number*$ or $Time$ in media template with S list available
+                                # Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
+                                # Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
+                                representation_ms_info['fragments'] = []
                                 segment_time = 0
+                                segment_d = None
+                                segment_number = representation_ms_info['start_number']
 
                                 def add_segment_url():
-                                    representation_ms_info['segment_urls'].append(
-                                        media_template % {
-                                            'Time': segment_time,
-                                            'Bandwidth': representation_attrib.get('bandwidth'),
-                                        }
-                                    )
+                                    segment_url = media_template % {
+                                        'Time': segment_time,
+                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Number': segment_number,
+                                    }
+                                    representation_ms_info['fragments'].append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(segment_d, representation_ms_info['timescale']),
+                                    })
 
                                 for num, s in enumerate(representation_ms_info['s']):
                                     segment_time = s.get('t') or segment_time
+                                    segment_d = s['d']
                                     add_segment_url()
+                                    segment_number += 1
                                     for r in range(s.get('r', 0)):
-                                        segment_time += s['d']
+                                        segment_time += segment_d
                                         add_segment_url()
-                                    segment_time += s['d']
-                        if 'segment_urls' in representation_ms_info:
+                                        segment_number += 1
+                                    segment_time += segment_d
+                        elif 'segment_urls' in representation_ms_info and 's' in representation_ms_info:
+                            # No media template
+                            # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
+                            # or any YouTube dashsegments video
+                            fragments = []
+                            s_num = 0
+                            for segment_url in representation_ms_info['segment_urls']:
+                                s = representation_ms_info['s'][s_num]
+                                for r in range(s.get('r', 0) + 1):
+                                    fragments.append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(s['d'], representation_ms_info['timescale']),
+                                    })
+                            representation_ms_info['fragments'] = fragments
+                        # NB: MPD manifest may contain direct URLs to unfragmented media.
+                        # No fragments key is present in this case.
+                        if 'fragments' in representation_ms_info:
                             f.update({
-                                'segment_urls': representation_ms_info['segment_urls'],
+                                'fragments': [],
                                 'protocol': 'http_dash_segments',
                             })
                             if 'initialization_url' in representation_ms_info:
                                 initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
-                                f.update({
-                                    'initialization_url': initialization_url,
-                                })
                                 if not f.get('url'):
                                     f['url'] = initialization_url
+                                f['fragments'].append({'url': initialization_url})
+                            f['fragments'].extend(representation_ms_info['fragments'])
+                            for fragment in f['fragments']:
+                                fragment['url'] = combine_url(base_url, fragment['url'])
                         try:
                             existing_format = next(
                                 fo for fo in formats
@@ -1746,7 +1809,7 @@ class InfoExtractor(object):
             media_attributes = extract_attributes(media_tag)
             src = media_attributes.get('src')
             if src:
-                _, formats = _media_formats(src)
+                _, formats = _media_formats(src, media_type)
                 media_info['formats'].extend(formats)
             media_info['thumbnail'] = media_attributes.get('poster')
             if media_content:
@@ -1789,6 +1852,49 @@ class InfoExtractor(object):
             m3u8_id='hls', fatal=False))
         return formats
 
+    def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
+        url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
+        url_base = self._search_regex(r'(?:https?|rtmp|rtsp)(://[^?]+)', url, 'format url')
+        http_base_url = 'http' + url_base
+        formats = []
+        if 'm3u8' not in skip_protocols:
+            formats.extend(self._extract_m3u8_formats(
+                http_base_url + '/playlist.m3u8', video_id, 'mp4',
+                m3u8_entry_protocol, m3u8_id='hls', fatal=False))
+        if 'f4m' not in skip_protocols:
+            formats.extend(self._extract_f4m_formats(
+                http_base_url + '/manifest.f4m',
+                video_id, f4m_id='hds', fatal=False))
+        if re.search(r'(?:/smil:|\.smil)', url_base):
+            if 'dash' not in skip_protocols:
+                formats.extend(self._extract_mpd_formats(
+                    http_base_url + '/manifest.mpd',
+                    video_id, mpd_id='dash', fatal=False))
+            if 'smil' not in skip_protocols:
+                rtmp_formats = self._extract_smil_formats(
+                    http_base_url + '/jwplayer.smil',
+                    video_id, fatal=False)
+                for rtmp_format in rtmp_formats:
+                    rtsp_format = rtmp_format.copy()
+                    rtsp_format['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
+                    del rtsp_format['play_path']
+                    del rtsp_format['ext']
+                    rtsp_format.update({
+                        'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'),
+                        'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
+                        'protocol': 'rtsp',
+                    })
+                    formats.extend([rtmp_format, rtsp_format])
+        else:
+            for protocol in ('rtmp', 'rtsp'):
+                if protocol not in skip_protocols:
+                    formats.append({
+                        'url': protocol + url_base,
+                        'format_id': protocol,
+                        'protocol': protocol,
+                    })
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()

youtube_dl/extractor/criterion.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
+    _VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
         'url': 'http://www.criterion.com/films/184-le-samourai',
         'md5': 'bc51beba55685509883a9a7830919ec3',

youtube_dl/extractor/crunchyroll.py

@@ -34,22 +34,58 @@ from ..aes import (
 
 
 class CrunchyrollBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.crunchyroll.com/login'
+    _LOGIN_FORM = 'login_form'
     _NETRC_MACHINE = 'crunchyroll'
 
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
             return
-        self.report_login()
-        login_url = 'https://www.crunchyroll.com/?a=formhandler'
-        data = urlencode_postdata({
-            'formname': 'RpcApiUser_Login',
-            'name': username,
-            'password': password,
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        def is_logged(webpage):
+            return '<title>Redirecting' in webpage
+
+        # Already logged in
+        if is_logged(login_page):
+            return
+
+        login_form_str = self._search_regex(
+            r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
+            login_page, 'login form', group='form')
+
+        post_url = extract_attributes(login_form_str).get('action')
+        if not post_url:
+            post_url = self._LOGIN_URL
+        elif not post_url.startswith('http'):
+            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+
+        login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
+
+        login_form.update({
+            'login_form[name]': username,
+            'login_form[password]': password,
         })
-        login_request = sanitized_Request(login_url, data)
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+        response = self._download_webpage(
+            post_url, None, 'Logging in', 'Wrong login info',
+            data=urlencode_postdata(login_form),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})
+
+        # Successful login
+        if is_logged(response):
+            return
+
+        error = self._html_search_regex(
+            '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
+            response, 'error message', default=None)
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+
+        raise ExtractorError('Unable to log in')
 
     def _real_initialize(self):
         self._login()

youtube_dl/extractor/curiositystream.py

@@ -0,0 +1,120 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urlencode_postdata,
+    compat_str,
+    ExtractorError,
+)
+
+
+class CuriosityStreamBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'curiositystream'
+    _auth_token = None
+    _API_BASE_URL = 'https://api.curiositystream.com/v1/'
+
+    def _handle_errors(self, result):
+        error = result.get('error', {}).get('message')
+        if error:
+            if isinstance(error, dict):
+                error = ', '.join(error.values())
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)
+
+    def _call_api(self, path, video_id):
+        headers = {}
+        if self._auth_token:
+            headers['X-Auth-Token'] = self._auth_token
+        result = self._download_json(
+            self._API_BASE_URL + path, video_id, headers=headers)
+        self._handle_errors(result)
+        return result['data']
+
+    def _real_initialize(self):
+        (email, password) = self._get_login_info()
+        if email is None:
+            return
+        result = self._download_json(
+            self._API_BASE_URL + 'login', None, data=urlencode_postdata({
+                'email': email,
+                'password': password,
+            }))
+        self._handle_errors(result)
+        self._auth_token = result['message']['auth_token']
+
+    def _extract_media_info(self, media):
+        video_id = compat_str(media['id'])
+        limelight_media_id = media['limelight_media_id']
+        title = media['title']
+
+        subtitles = {}
+        for closed_caption in media.get('closed_captions', []):
+            sub_url = closed_caption.get('file')
+            if not sub_url:
+                continue
+            lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
+            subtitles.setdefault(lang, []).append({
+                'url': sub_url,
+            })
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'limelight:media:' + limelight_media_id,
+            'title': title,
+            'description': media.get('description'),
+            'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
+            'duration': int_or_none(media.get('duration')),
+            'tags': media.get('tags'),
+            'subtitles': subtitles,
+            'ie_key': 'LimelightMedia',
+        }
+
+
+class CuriosityStreamIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream'
+    _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://app.curiositystream.com/video/2',
+        'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
+        'info_dict': {
+            'id': '2',
+            'ext': 'mp4',
+            'title': 'How Did You Develop The Internet?',
+            'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
+            'timestamp': 1448388615,
+            'upload_date': '20151124',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        media = self._call_api('media/' + video_id, video_id)
+        return self._extract_media_info(media)
+
+
+class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream:collection'
+    _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://app.curiositystream.com/collection/2',
+        'info_dict': {
+            'id': '2',
+            'title': 'Curious Minds: The Internet',
+            'description': 'How is the internet shaping our lives in the 21st Century?',
+        },
+        'playlist_mincount': 17,
+    }
+
+    def _real_extract(self, url):
+        collection_id = self._match_id(url)
+        collection = self._call_api(
+            'collections/' + collection_id, collection_id)
+        entries = []
+        for media in collection.get('media', []):
+            entries.append(self._extract_media_info(media))
+        return self.playlist_result(
+            entries, collection_id,
+            collection.get('title'), collection.get('description'))

youtube_dl/extractor/dailymotion.py

@@ -394,7 +394,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
 
 
 class DailymotionCloudIE(DailymotionBaseInfoExtractor):
-    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
     _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
     _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
 

youtube_dl/extractor/dctp.py

@@ -6,7 +6,7 @@ from ..compat import compat_str
 
 
 class DctpTvIE(InfoExtractor):
-    _VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+    _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
     _TEST = {
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
         'info_dict': {

youtube_dl/extractor/democracynow.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class DemocracynowIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    _VALID_URL = r'https?://(?:www\.)?democracynow\.org/(?P<id>[^\?]*)'
     IE_NAME = 'democracynow'
     _TESTS = [{
         'url': 'http://www.democracynow.org/shows/2015/7/3',

youtube_dl/extractor/drtv.py

@@ -4,26 +4,45 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
+    float_or_none,
+    mimetype2ext,
     parse_iso8601,
+    remove_end,
 )
 
 
 class DRTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
-    _TEST = {
-        'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
-        'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
+    _TESTS = [{
+        'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
+        'md5': '25e659cccc9a2ed956110a299fdf5983',
         'info_dict': {
-            'id': 'panisk-paske-5',
+            'id': 'klassen-darlig-taber-10',
             'ext': 'mp4',
-            'title': 'Panisk Påske (5)',
-            'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
-            'timestamp': 1426984612,
-            'upload_date': '20150322',
-            'duration': 1455,
+            'title': 'Klassen - Dårlig taber (10)',
+            'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
+            'timestamp': 1471991907,
+            'upload_date': '20160823',
+            'duration': 606.84,
         },
-    }
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
+        'md5': '2c37175c718155930f939ef59952474a',
+        'info_dict': {
+            'id': 'christiania-pusher-street-ryddes-drdkrjpo',
+            'ext': 'mp4',
+            'title': 'LIVE Christianias rydning af Pusher Street er i gang',
+            'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
+            'timestamp': 1472800279,
+            'upload_date': '20160902',
+            'duration': 131.4,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
                 'Video %s is not available' % video_id, expected=True)
 
         video_id = self._search_regex(
-            r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+            (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+                r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
             webpage, 'video id')
 
         programcard = self._download_json(
@@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
             video_id, 'Downloading video JSON')
         data = programcard['Data'][0]
 
-        title = data['Title']
-        description = data['Description']
-        timestamp = parse_iso8601(data['CreatedTime'])
+        title = remove_end(self._og_search_title(
+            webpage, default=None), ' | TV | DR') or data['Title']
+        description = self._og_search_description(
+            webpage, default=None) or data.get('Description')
+
+        timestamp = parse_iso8601(data.get('CreatedTime'))
 
         thumbnail = None
         duration = None
@@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
         subtitles = {}
 
         for asset in data['Assets']:
-            if asset['Kind'] == 'Image':
-                thumbnail = asset['Uri']
-            elif asset['Kind'] == 'VideoResource':
-                duration = asset['DurationInMilliseconds'] / 1000.0
-                restricted_to_denmark = asset['RestrictedToDenmark']
-                spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
-                for link in asset['Links']:
-                    uri = link['Uri']
-                    target = link['Target']
-                    format_id = target
+            if asset.get('Kind') == 'Image':
+                thumbnail = asset.get('Uri')
+            elif asset.get('Kind') == 'VideoResource':
+                duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
+                restricted_to_denmark = asset.get('RestrictedToDenmark')
+                spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
+                for link in asset.get('Links', []):
+                    uri = link.get('Uri')
+                    if not uri:
+                        continue
+                    target = link.get('Target')
+                    format_id = target or ''
                     preference = None
                     if spoken_subtitles:
                         preference = -1
@@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
                             video_id, preference, f4m_id=format_id))
                     elif target == 'HLS':
                         formats.extend(self._extract_m3u8_formats(
-                            uri, video_id, 'mp4', preference=preference,
-                            m3u8_id=format_id))
+                            uri, video_id, 'mp4', entry_protocol='m3u8_native',
+                            preference=preference, m3u8_id=format_id))
                     else:
                         bitrate = link.get('Bitrate')
                         if bitrate:
@@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
                         formats.append({
                             'url': uri,
                             'format_id': format_id,
-                            'tbr': bitrate,
+                            'tbr': int_or_none(bitrate),
                             'ext': link.get('FileFormat'),
                         })
                 subtitles_list = asset.get('SubtitlesList')
@@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
                         'Danish': 'da',
                     }
                     for subs in subtitles_list:
-                        lang = subs['Language']
-                        subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
+                        if not subs.get('Uri'):
+                            continue
+                        lang = subs.get('Language') or 'da'
+                        subtitles.setdefault(LANGS.get(lang, lang), []).append({
+                            'url': subs['Uri'],
+                            'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
+                        })
 
         if not formats and restricted_to_denmark:
-            raise ExtractorError(
-                'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
+            self.raise_geo_restricted(
+                'Unfortunately, DR is not allowed to show this program outside Denmark.',
+                expected=True)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/engadget.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class EngadgetIE(InfoExtractor):
-    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?engadget\.com/video/(?P<id>[^/?#]+)'
 
     _TESTS = [{
         # video with 5min ID

youtube_dl/extractor/espn.py

@@ -5,7 +5,7 @@ from ..utils import remove_end
 
 
 class ESPNIE(InfoExtractor):
-    _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://espn.go.com/video/clip?id=10365079',
         'md5': '60e5d097a523e767d06479335d1bdc58',
@@ -47,6 +47,9 @@ class ESPNIE(InfoExtractor):
     }, {
         'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
         'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/video/clip?id=10365079',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/exfm.py

@@ -1,58 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class ExfmIE(InfoExtractor):
-    IE_NAME = 'exfm'
-    IE_DESC = 'ex.fm'
-    _VALID_URL = r'https?://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
-    _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
-    _TESTS = [
-        {
-            'url': 'http://ex.fm/song/eh359',
-            'md5': 'e45513df5631e6d760970b14cc0c11e7',
-            'info_dict': {
-                'id': '44216187',
-                'ext': 'mp3',
-                'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
-                'uploader': 'deadjournalist',
-                'upload_date': '20120424',
-                'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
-            },
-            'note': 'Soundcloud song',
-            'skip': 'The site is down too often',
-        },
-        {
-            'url': 'http://ex.fm/song/wddt8',
-            'md5': '966bd70741ac5b8570d8e45bfaed3643',
-            'info_dict': {
-                'id': 'wddt8',
-                'ext': 'mp3',
-                'title': 'Safe and Sound',
-                'uploader': 'Capital Cities',
-            },
-            'skip': 'The site is down too often',
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group('id')
-        info_url = 'http://ex.fm/api/v3/song/%s' % song_id
-        info = self._download_json(info_url, song_id)['song']
-        song_url = info['url']
-        if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
-            self.to_screen('Soundcloud song detected')
-            return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
-        return {
-            'id': song_id,
-            'url': song_url,
-            'ext': 'mp3',
-            'title': info['title'],
-            'thumbnail': info['image']['large'],
-            'uploader': info['artist'],
-            'view_count': info['loved_count'],
-        }

youtube_dl/extractor/expotv.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class ExpoTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
     _TEST = {
         'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
         'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',

youtube_dl/extractor/extractors.py

@@ -5,11 +5,14 @@ from .abc import (
     ABCIE,
     ABCIViewIE,
 )
-from .abc7news import Abc7NewsIE
 from .abcnews import (
     AbcNewsIE,
     AbcNewsVideoIE,
 )
+from .abcotvs import (
+    ABCOTVSIE,
+    ABCOTVSClipsIE,
+)
 from .academicearth import AcademicEarthCourseIE
 from .acast import (
     ACastIE,
@@ -90,6 +93,7 @@ from .bbc import (
 )
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .bellmedia import BellMediaIE
 from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bigflix import BigflixIE
@@ -143,6 +147,7 @@ from .cbsnews import (
 )
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
+from .cctv import CCTVIE
 from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
@@ -191,9 +196,12 @@ from .crunchyroll import (
 )
 from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
-from .ctv import CTVIE
 from .ctvnews import CTVNewsIE
 from .cultureunplugged import CultureUnpluggedIE
+from .curiositystream import (
+    CuriosityStreamIE,
+    CuriosityStreamCollectionIE,
+)
 from .cwtv import CWTVIE
 from .dailymail import DailyMailIE
 from .dailymotion import (
@@ -257,13 +265,18 @@ from .espn import ESPNIE
 from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
-from .exfm import ExfmIE
 from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
 from .eyedotv import EyedoTVIE
-from .facebook import FacebookIE
+from .facebook import (
+    FacebookIE,
+    FacebookPluginsVideoIE,
+)
 from .faz import FazIE
-from .fc2 import FC2IE
+from .fc2 import (
+    FC2IE,
+    FC2EmbedIE,
+)
 from .fczenit import FczenitIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
@@ -278,7 +291,11 @@ from .formula1 import Formula1IE
 from .fourtube import FourTubeIE
 from .fox import FOXIE
 from .foxgay import FoxgayIE
-from .foxnews import FoxNewsIE
+from .foxnews import (
+    FoxNewsIE,
+    FoxNewsArticleIE,
+    FoxNewsInsiderIE,
+)
 from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
@@ -315,6 +332,7 @@ from .globo import (
     GloboIE,
     GloboArticleIE,
 )
+from .go import GoIE
 from .godtube import GodTubeIE
 from .godtv import GodTVIE
 from .golem import GolemIE
@@ -378,6 +396,7 @@ from .ivi import (
     IviCompilationIE
 )
 from .ivideon import IvideonIE
+from .iwara import IwaraIE
 from .izlesene import IzleseneIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
@@ -390,6 +409,7 @@ from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
+from .ketnet import KetnetIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
@@ -408,6 +428,7 @@ from .kuwo import (
 )
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
+from .lci import LCIIE
 from .lcp import (
     LcpPlayIE,
     LcpIE,
@@ -451,6 +472,10 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
+from .mangomolo import (
+    MangomoloVideoIE,
+    MangomoloLiveIE,
+)
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .meta import METAIE
@@ -458,6 +483,7 @@ from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .mgtv import MGTVIE
+from .miaopai import MiaoPaiIE
 from .microsoftvirtualacademy import (
     MicrosoftVirtualAcademyIE,
     MicrosoftVirtualAcademyCourseIE,
@@ -486,6 +512,7 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
+from .movingimage import MovingImageIE
 from .msn import MSNIE
 from .mtv import (
     MTVIE,
@@ -511,6 +538,7 @@ from .nbc import (
     CSNNEIE,
     NBCIE,
     NBCNewsIE,
+    NBCOlympicsIE,
     NBCSportsIE,
     NBCSportsVPlayerIE,
 )
@@ -650,7 +678,10 @@ from .pluralsight import (
 )
 from .podomatic import PodomaticIE
 from .pokemon import PokemonIE
-from .polskieradio import PolskieRadioIE
+from .polskieradio import (
+    PolskieRadioIE,
+    PolskieRadioCategoryIE,
+)
 from .porn91 import Porn91IE
 from .porncom import PornComIE
 from .pornhd import PornHdIE
@@ -704,6 +735,7 @@ from .revision3 import (
 )
 from .rice import RICEIE
 from .ringtv import RingTVIE
+from .rmcdecouverte import RMCDecouverteIE
 from .ro220 import Ro220IE
 from .rockstargames import RockstarGamesIE
 from .roosterteeth import RoosterTeethIE
@@ -806,7 +838,6 @@ from .srgssr import (
     SRGSSRPlayIE,
 )
 from .srmediathek import SRMediathekIE
-from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamable import StreamableIE
@@ -841,10 +872,12 @@ from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
+from .telequebec import TeleQuebecIE
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
+from .tfo import TFOIE
 from .theintercept import TheInterceptIE
 from .theplatform import (
     ThePlatformIE,
@@ -869,15 +902,11 @@ from .tnaflix import (
     MovieFapIE,
 )
 from .toggle import ToggleIE
-from .thvideo import (
-    THVideoIE,
-    THVideoPlaylistIE
-)
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
-from .trollvids import TrollvidsIE
+from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
 from .tudou import (
@@ -907,6 +936,7 @@ from .tvc import (
 )
 from .tvigle import TvigleIE
 from .tvland import TVLandIE
+from .tvnoe import TVNoeIE
 from .tvp import (
     TVPEmbedIE,
     TVPIE,
@@ -1039,6 +1069,7 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vyborymos import VyboryMosIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,

youtube_dl/extractor/facebook.py

@@ -15,6 +15,7 @@ from ..compat import (
 from ..utils import (
     error_to_compat_str,
     ExtractorError,
+    int_or_none,
     limit_length,
     sanitized_Request,
     urlencode_postdata,
@@ -62,6 +63,8 @@ class FacebookIE(InfoExtractor):
             'ext': 'mp4',
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
             'uploader': 'Tennis on Facebook',
+            'upload_date': '20140908',
+            'timestamp': 1410199200,
         }
     }, {
         'note': 'Video without discernible title',
@@ -71,6 +74,8 @@ class FacebookIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
             'uploader': 'Asif Nawab Butt',
+            'upload_date': '20140506',
+            'timestamp': 1399398998,
         },
         'expected_warnings': [
             'title'
@@ -78,12 +83,14 @@ class FacebookIE(InfoExtractor):
     }, {
         'note': 'Video with DASH manifest',
         'url': 'https://www.facebook.com/video.php?v=957955867617029',
-        'md5': '54706e4db4f5ad58fbad82dde1f1213f',
+        'md5': 'b2c28d528273b323abe5c6ab59f0f030',
         'info_dict': {
             'id': '957955867617029',
             'ext': 'mp4',
             'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
             'uploader': 'Demy de Zeeuw',
+            'upload_date': '20160110',
+            'timestamp': 1452431627,
         },
     }, {
         'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
@@ -306,12 +313,16 @@ class FacebookIE(InfoExtractor):
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
         uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+        timestamp = int_or_none(self._search_regex(
+            r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
+            'timestamp', default=None))
 
         info_dict = {
             'id': video_id,
             'title': video_title,
             'formats': formats,
             'uploader': uploader,
+            'timestamp': timestamp,
         }
 
         return webpage, info_dict
@@ -340,3 +351,32 @@ class FacebookIE(InfoExtractor):
                 self._VIDEO_PAGE_TEMPLATE % video_id,
                 video_id, fatal_if_no_video=True)
             return info_dict
+
+
+class FacebookPluginsVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
+
+    _TESTS = [{
+        'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
+        'md5': '5954e92cdfe51fe5782ae9bda7058a07',
+        'info_dict': {
+            'id': '10154383743583686',
+            'ext': 'mp4',
+            'title': 'What to do during the haze?',
+            'uploader': 'Gov.sg',
+            'upload_date': '20160826',
+            'timestamp': 1472184808,
+        },
+        'add_ie': [FacebookIE.ie_key()],
+    }, {
+        'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        return self.url_result(
+            compat_urllib_parse_unquote(self._match_id(url)),
+            FacebookIE.ie_key())

youtube_dl/extractor/fc2.py

@@ -1,10 +1,12 @@
-#! -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import hashlib
+import re
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_parse_qs,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -16,7 +18,7 @@ from ..utils import (
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
+    _VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _NETRC_MACHINE = 'fc2'
     _TESTS = [{
@@ -75,12 +77,17 @@ class FC2IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         self._login()
-        webpage = self._download_webpage(url, video_id)
-        self._downloader.cookiejar.clear_session_cookies()  # must clear
-        self._login()
+        webpage = None
+        if not url.startswith('fc2:'):
+            webpage = self._download_webpage(url, video_id)
+            self._downloader.cookiejar.clear_session_cookies()  # must clear
+            self._login()
 
-        title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        title = 'FC2 video %s' % video_id
+        thumbnail = None
+        if webpage is not None:
+            title = self._og_search_title(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
         refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
 
         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
@@ -113,3 +120,41 @@ class FC2IE(InfoExtractor):
             'ext': 'flv',
             'thumbnail': thumbnail,
         }
+
+
+class FC2EmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.fc2\.com/flv2\.swf\?(?P<query>.+)'
+    IE_NAME = 'fc2:embed'
+
+    _TEST = {
+        'url': 'http://video.fc2.com/flv2.swf?t=201404182936758512407645&i=20130316kwishtfitaknmcgd76kjd864hso93htfjcnaogz629mcgfs6rbfk0hsycma7shkf85937cbchfygd74&i=201403223kCqB3Ez&d=2625&sj=11&lang=ja&rel=1&from=11&cmt=1&tk=TlRBM09EQTNNekU9&tl=プリズン･ブレイク%20S1-01%20マイケル%20【吹替】',
+        'md5': 'b8aae5334cb691bdb1193a88a6ab5d5a',
+        'info_dict': {
+            'id': '201403223kCqB3Ez',
+            'ext': 'flv',
+            'title': 'プリズン･ブレイク S1-01 マイケル 【吹替】',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        query = compat_parse_qs(mobj.group('query'))
+
+        video_id = query['i'][-1]
+        title = query.get('tl', ['FC2 video %s' % video_id])[0]
+
+        sj = query.get('sj', [None])[0]
+        thumbnail = None
+        if sj:
+            # See thumbnailImagePath() in ServerConst.as of flv2.swf
+            thumbnail = 'http://video%s-thumbnail.fc2.com/up/pic/%s.jpg' % (
+                sj, '/'.join((video_id[:6], video_id[6:8], video_id[-2], video_id[-1], video_id)))
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': FC2IE.ie_key(),
+            'url': 'fc2:%s' % video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/fox.py

@@ -1,14 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .adobepass import AdobePassIE
 from ..utils import (
     smuggle_url,
     update_url_query,
 )
 
 
-class FOXIE(InfoExtractor):
+class FOXIE(AdobePassIE):
     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.fox.com/watch/255180355939/7684182528',
@@ -30,14 +30,26 @@ class FOXIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        release_url = self._parse_json(self._search_regex(
-            r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
-            video_id)['release_url']
+        settings = self._parse_json(self._search_regex(
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+            webpage, 'drupal settings'), video_id)
+        fox_pdk_player = settings['fox_pdk_player']
+        release_url = fox_pdk_player['release_url']
+        query = {
+            'mbr': 'true',
+            'switch': 'http'
+        }
+        if fox_pdk_player.get('access') == 'locked':
+            ap_p = settings['foxAdobePassProvider']
+            rating = ap_p.get('videoRating')
+            if rating == 'n/a':
+                rating = None
+            resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
 
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': smuggle_url(update_url_query(
-                release_url, {'switch': 'http'}), {'force_smil_url': True}),
+            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
             'id': video_id,
         }

youtube_dl/extractor/foxgay.py

@@ -1,18 +1,24 @@
 from __future__ import unicode_literals
 
+import itertools
+
 from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    remove_end,
+)
 
 
 class FoxgayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
     _TEST = {
         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
-        'md5': '80d72beab5d04e1655a56ad37afe6841',
+        'md5': '344558ccfea74d33b7adbce22e577f54',
         'info_dict': {
             'id': '2582',
             'ext': 'mp4',
-            'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
-            'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
+            'title': 'Fuck Turkish-style',
+            'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
             'age_limit': 18,
             'thumbnail': 're:https?://.*\.jpg$',
         },
@@ -22,27 +28,35 @@ class FoxgayIE(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', fatal=False)
-        description = self._html_search_regex(
-            r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
-            webpage, 'description', fatal=False)
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Foxgay.com')
+        description = get_element_by_id('inf_tit', webpage)
 
+        # The default user-agent with foxgay cookies leads to pages without videos
+        self._downloader.cookiejar.clear('.foxgay.com')
         # Find the URL for the iFrame which contains the actual video.
+        iframe_url = self._html_search_regex(
+            r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
+            'video frame', group='url')
         iframe = self._download_webpage(
-            self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
-            video_id)
-        video_url = self._html_search_regex(
-            r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
-        thumb_url = self._html_search_regex(
-            r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
+            iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
+            note='Downloading video frame')
+        video_data = self._parse_json(self._search_regex(
+            r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
+
+        formats = [{
+            'url': source,
+            'height': resolution,
+        } for source, resolution in zip(
+            video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'url': video_url,
+            'formats': formats,
             'description': description,
-            'thumbnail': thumb_url,
+            'thumbnail': video_data.get('act_vid', {}).get('thumb'),
             'age_limit': 18,
         }

youtube_dl/extractor/foxnews.py

@@ -3,11 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .amp import AMPIE
+from .common import InfoExtractor
 
 
 class FoxNewsIE(AMPIE):
+    IE_NAME = 'foxnews'
     IE_DESC = 'Fox News and Fox Business Video'
-    _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
@@ -49,6 +51,11 @@ class FoxNewsIE(AMPIE):
             'url': 'http://video.foxbusiness.com/v/4442309889001',
             'only_matching': True,
         },
+        {
+            # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
+            'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -58,3 +65,76 @@ class FoxNewsIE(AMPIE):
             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
         info['id'] = video_id
         return info
+
+
+class FoxNewsArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
+    IE_NAME = 'foxnews:article'
+
+    _TEST = {
+        'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
+        'md5': '62aa5a781b308fdee212ebb6f33ae7ef',
+        'info_dict': {
+            'id': '5116295019001',
+            'ext': 'mp4',
+            'title': 'Trump and Clinton asked to defend positions on Iraq War',
+            'description': 'Veterans react on \'The Kelly File\'',
+            'timestamp': 1473299755,
+            'upload_date': '20160908',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._html_search_regex(
+            r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
+            webpage, 'video ID', group='id')
+        return self.url_result(
+            'http://video.foxnews.com/v/' + video_id,
+            FoxNewsIE.ie_key())
+
+
+class FoxNewsInsiderIE(InfoExtractor):
+    _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
+    IE_NAME = 'foxnews:insider'
+
+    _TEST = {
+        'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
+        'md5': 'a10c755e582d28120c62749b4feb4c0c',
+        'info_dict': {
+            'id': '5099377331001',
+            'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
+            'ext': 'mp4',
+            'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
+            'description': 'Is campus censorship getting out of control?',
+            'timestamp': 1472168725,
+            'upload_date': '20160825',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': [FoxNewsIE.ie_key()],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': FoxNewsIE.ie_key(),
+            'url': embed_url,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/franceinter.py

@@ -2,21 +2,21 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import month_by_name
 
 
 class FranceInterIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
+
     _TEST = {
-        'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
-        'md5': '4764932e466e6f6c79c317d2e74f6884',
+        'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
+        'md5': '9e54d7bdb6fdc02a841007f8a975c094',
         'info_dict': {
-            'id': '793962',
+            'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
             'ext': 'mp3',
-            'title': 'L’Histoire dans les jeux vidéo',
-            'description': 'md5:7e93ddb4451e7530022792240a3049c7',
-            'timestamp': 1387369800,
-            'upload_date': '20131218',
+            'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
+            'description': 'md5:401969c5d318c061f86bda1fa359292b',
+            'upload_date': '20160907',
         },
     }
 
@@ -25,23 +25,30 @@ class FranceInterIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        path = self._search_regex(
-            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
-        video_url = 'http://www.franceinter.fr/' + path
+        video_url = self._search_regex(
+            r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'video url', group='url')
 
-        title = self._html_search_regex(
-            r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
-        description = self._html_search_regex(
-            r'<span class="description">(.*?)</span>',
-            webpage, 'description', fatal=False)
-        timestamp = int_or_none(self._search_regex(
-            r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        upload_date_str = self._search_regex(
+            r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
+            webpage, 'upload date', fatal=False)
+        if upload_date_str:
+            upload_date_list = upload_date_str.split()
+            upload_date_list.reverse()
+            upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
+            upload_date_list[2] = '%02d' % int(upload_date_list[2])
+            upload_date = ''.join(upload_date_list)
+        else:
+            upload_date = None
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'timestamp': timestamp,
+            'upload_date': upload_date,
             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',

youtube_dl/extractor/freespeech.py

@@ -8,7 +8,7 @@ from .common import InfoExtractor
 
 class FreespeechIE(InfoExtractor):
     IE_NAME = 'freespeech.org'
-    _VALID_URL = r'https://www\.freespeech\.org/video/(?P<title>.+)'
+    _VALID_URL = r'https?://(?:www\.)?freespeech\.org/video/(?P<title>.+)'
     _TEST = {
         'add_ie': ['Youtube'],
         'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',

youtube_dl/extractor/gamestar.py

@@ -1,19 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_duration,
-    str_to_int,
-    unified_strdate,
+    remove_end,
 )
 
 
 class GameStarIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
     _TEST = {
         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
         'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
@@ -21,8 +17,9 @@ class GameStarIE(InfoExtractor):
             'id': '76110',
             'ext': 'mp4',
             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
-            'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.',
-            'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
+            'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1406542020,
             'upload_date': '20140728',
             'duration': 17
         }
@@ -32,41 +29,27 @@ class GameStarIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        og_title = self._og_search_title(webpage)
-        title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
-
         url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
 
-        description = self._og_search_description(webpage).strip()
-
-        thumbnail = self._proto_relative_url(
-            self._og_search_thumbnail(webpage), scheme='http:')
-
-        upload_date = unified_strdate(self._html_search_regex(
-            r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+)&nbsp;&nbsp;',
-            webpage, 'upload_date', fatal=False))
-
-        duration = parse_duration(self._html_search_regex(
-            r'&nbsp;&nbsp;Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
-            fatal=False))
-
-        view_count = str_to_int(self._html_search_regex(
-            r'&nbsp;&nbsp;Zuschauer: ([0-9\.]+)&nbsp;&nbsp;', webpage,
-            'view_count', fatal=False))
+        # TODO: there are multiple ld+json objects in the webpage,
+        # while _search_json_ld finds only the first one
+        json_ld = self._parse_json(self._search_regex(
+            r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
+            webpage, 'JSON-LD', group='json_ld'), video_id)
+        info_dict = self._json_ld(json_ld, video_id)
+        info_dict['title'] = remove_end(info_dict['title'], ' - GameStar')
 
+        view_count = json_ld.get('interactionCount')
         comment_count = int_or_none(self._html_search_regex(
-            r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
+            r'([0-9]+) Kommentare</span>', webpage, 'comment_count',
             fatal=False))
 
-        return {
+        info_dict.update({
             'id': video_id,
-            'title': title,
             'url': url,
             'ext': 'mp4',
-            'thumbnail': thumbnail,
-            'description': description,
-            'upload_date': upload_date,
-            'duration': duration,
             'view_count': view_count,
             'comment_count': comment_count
-        }
+        })
+
+        return info_dict

youtube_dl/extractor/generic.py

@@ -1369,6 +1369,11 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Vimeo'],
         },
+        {
+            # generic vimeo embed that requires original URL passed as Referer
+            'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
+            'only_matching': True,
+        },
         {
             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
@@ -1652,7 +1657,9 @@ class GenericIE(InfoExtractor):
                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
                 info_dict['formats'] = self._parse_mpd_formats(
-                    doc, video_id, mpd_base_url=url.rpartition('/')[0])
+                    doc, video_id,
+                    mpd_base_url=full_response.geturl().rpartition('/')[0],
+                    mpd_url=url)
                 self._sort_formats(info_dict['formats'])
                 return info_dict
             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
@@ -2249,6 +2256,35 @@ class GenericIE(InfoExtractor):
             return self.url_result(
                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
 
+        # Look for Mangomolo embeds
+        mobj = re.search(
+            r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
+                (?:
+                    video\?.*?\bid=(?P<video_id>\d+)|
+                    index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
+                ).+?)\1''', webpage)
+        if mobj is not None:
+            info = {
+                '_type': 'url_transparent',
+                'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
+                'title': video_title,
+                'description': video_description,
+                'thumbnail': video_thumbnail,
+                'uploader': video_uploader,
+            }
+            video_id = mobj.group('video_id')
+            if video_id:
+                info.update({
+                    'ie_key': 'MangomoloVideo',
+                    'id': video_id,
+                })
+            else:
+                info.update({
+                    'ie_key': 'MangomoloLive',
+                    'id': mobj.group('channel_id'),
+                })
+            return info
+
         # Look for Instagram embeds
         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
         if instagram_embed_url is not None:

youtube_dl/extractor/glide.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
 
 
 class GlideIE(InfoExtractor):
@@ -14,10 +13,8 @@ class GlideIE(InfoExtractor):
         'info_dict': {
             'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
             'ext': 'mp4',
-            'title': 'Damon Timm\'s Glide message',
+            'title': "Damon's Glide message",
             'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
-            'uploader': 'Damon Timm',
-            'upload_date': '20140919',
         }
     }
 
@@ -27,7 +24,8 @@ class GlideIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<title>(.+?)</title>', webpage, 'title')
+            r'<title>(.+?)</title>', webpage,
+            'title', default=None) or self._og_search_title(webpage)
         video_url = self._proto_relative_url(self._search_regex(
             r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
             webpage, 'video URL', default=None,
@@ -36,18 +34,10 @@ class GlideIE(InfoExtractor):
             r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1',
             webpage, 'thumbnail url', default=None,
             group='url')) or self._og_search_thumbnail(webpage)
-        uploader = self._search_regex(
-            r'<div[^>]+class=["\']info-name["\'][^>]*>([^<]+)',
-            webpage, 'uploader', fatal=False)
-        upload_date = unified_strdate(self._search_regex(
-            r'<div[^>]+class="info-date"[^>]*>([^<]+)',
-            webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
             'thumbnail': thumbnail,
-            'uploader': uploader,
-            'upload_date': upload_date,
         }

youtube_dl/extractor/globo.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import random
+import re
 import math
 
 from .common import InfoExtractor
@@ -14,12 +15,13 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    orderedSet,
     str_or_none,
 )
 
 
 class GloboIE(InfoExtractor):
-    _VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
+    _VALID_URL = r'(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
 
     _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
     _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
@@ -63,6 +65,9 @@ class GloboIE(InfoExtractor):
     }, {
         'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
         'only_matching': True,
+    }, {
+        'url': 'globo:3607726',
+        'only_matching': True,
     }]
 
     class MD5(object):
@@ -396,7 +401,7 @@ class GloboIE(InfoExtractor):
 
 
 class GloboArticleIE(InfoExtractor):
-    _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
+    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id=["\'](\d{7,})',
@@ -408,15 +413,20 @@ class GloboArticleIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
-        'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
         'info_dict': {
-            'id': '3652183',
-            'ext': 'mp4',
-            'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
-            'duration': 110.711,
-            'uploader': 'Rede Globo',
-            'uploader_id': '196',
-        }
+            'id': 'novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes',
+            'title': 'Novidade na fiscalização de bagagem pela Receita provoca discussões',
+            'description': 'md5:c3c4b4d4c30c32fce460040b1ac46b12',
+        },
+        'playlist_count': 1,
+    }, {
+        'url': 'http://g1.globo.com/pr/parana/noticia/2016/09/mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato.html',
+        'info_dict': {
+            'id': 'mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato',
+            'title': "Lula era o 'comandante máximo' do esquema da Lava Jato, diz MPF",
+            'description': 'md5:8aa7cc8beda4dc71cc8553e00b77c54c',
+        },
+        'playlist_count': 6,
     }, {
         'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
         'only_matching': True,
@@ -435,5 +445,12 @@ class GloboArticleIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
-        return self.url_result('globo:%s' % video_id, 'Globo')
+        video_ids = []
+        for video_regex in self._VIDEOID_REGEXES:
+            video_ids.extend(re.findall(video_regex, webpage))
+        entries = [
+            self.url_result('globo:%s' % video_id, GloboIE.ie_key())
+            for video_id in orderedSet(video_ids)]
+        title = self._og_search_title(webpage, fatal=False)
+        description = self._html_search_meta('description', webpage)
+        return self.playlist_result(entries, display_id, title, description)

youtube_dl/extractor/go.py

@@ -0,0 +1,122 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    determine_ext,
+    parse_age_limit,
+    urlencode_postdata,
+    ExtractorError,
+)
+
+
+class GoIE(InfoExtractor):
+    _BRANDS = {
+        'abc': '001',
+        'freeform': '002',
+        'watchdisneychannel': '004',
+        'watchdisneyjunior': '008',
+        'watchdisneyxd': '009',
+    }
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
+    _TESTS = [{
+        'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
+        'info_dict': {
+            'id': '0_g86w5onx',
+            'ext': 'mp4',
+            'title': 'Sneak Peek: Language Arts',
+            'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
+        brand = self._BRANDS[sub_domain]
+        video_data = self._download_json(
+            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
+            video_id)['video'][0]
+        title = video_data['title']
+
+        formats = []
+        for asset in video_data.get('assets', {}).get('asset', []):
+            asset_url = asset.get('value')
+            if not asset_url:
+                continue
+            format_id = asset.get('format')
+            ext = determine_ext(asset_url)
+            if ext == 'm3u8':
+                video_type = video_data.get('type')
+                if video_type == 'lf':
+                    entitlement = self._download_json(
+                        'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
+                        video_id, data=urlencode_postdata({
+                            'video_id': video_data['id'],
+                            'video_type': video_type,
+                            'brand': brand,
+                            'device': '001',
+                        }))
+                    errors = entitlement.get('errors', {}).get('errors', [])
+                    if errors:
+                        error_message = ', '.join([error['message'] for error in errors])
+                        raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
+                    asset_url += '?' + entitlement['uplynkData']['sessionKey']
+                formats.extend(self._extract_m3u8_formats(
+                    asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_id,
+                    'url': asset_url,
+                    'ext': ext,
+                })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for cc in video_data.get('closedcaption', {}).get('src', []):
+            cc_url = cc.get('value')
+            if not cc_url:
+                continue
+            ext = determine_ext(cc_url)
+            if ext == 'xml':
+                ext = 'ttml'
+            subtitles.setdefault(cc.get('lang'), []).append({
+                'url': cc_url,
+                'ext': ext,
+            })
+
+        thumbnails = []
+        for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
+            thumbnail_url = thumbnail.get('value')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(thumbnail.get('width')),
+                'height': int_or_none(thumbnail.get('height')),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('longdescription') or video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
+            'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
+            'episode_number': int_or_none(video_data.get('episodenumber')),
+            'series': video_data.get('show', {}).get('title'),
+            'season_number': int_or_none(video_data.get('season', {}).get('num')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/googleplus.py

@@ -10,7 +10,7 @@ from ..utils import unified_strdate
 
 class GooglePlusIE(InfoExtractor):
     IE_DESC = 'Google Plus'
-    _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
+    _VALID_URL = r'https?://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
     IE_NAME = 'plus.google'
     _TEST = {
         'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',

youtube_dl/extractor/goshgay.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class GoshgayIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
+    _VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
     _TEST = {
         'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
         'md5': '4b6db9a0a333142eb9f15913142b0ed1',

youtube_dl/extractor/hark.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class HarkIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+'
+    _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
     _TEST = {
         'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
         'md5': '6783a58491b47b92c7c1af5a77d4cbee',

youtube_dl/extractor/hotnewhiphop.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
+    _VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',

youtube_dl/extractor/imdb.py

@@ -94,7 +94,7 @@ class ImdbIE(InfoExtractor):
 class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
-    _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {

youtube_dl/extractor/internetvideoarchive.py

@@ -48,13 +48,23 @@ class InternetVideoArchiveIE(InfoExtractor):
             # There are multiple videos in the playlist whlie only the first one
             # matches the video played in browsers
             video_info = configuration['playlist'][0]
+            title = video_info['title']
 
             formats = []
             for source in video_info['sources']:
                 file_url = source['file']
                 if determine_ext(file_url) == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        file_url, video_id, ext='mp4', m3u8_id='hls'))
+                    m3u8_formats = self._extract_m3u8_formats(
+                        file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+                    if m3u8_formats:
+                        formats.extend(m3u8_formats)
+                        file_url = m3u8_formats[0]['url']
+                        formats.extend(self._extract_f4m_formats(
+                            file_url.replace('.m3u8', '.f4m'),
+                            video_id, f4m_id='hds', fatal=False))
+                        formats.extend(self._extract_mpd_formats(
+                            file_url.replace('.m3u8', '.mpd'),
+                            video_id, mpd_id='dash', fatal=False))
                 else:
                     a_format = {
                         'url': file_url,
@@ -70,7 +80,6 @@ class InternetVideoArchiveIE(InfoExtractor):
 
             self._sort_formats(formats)
 
-            title = video_info['title']
             description = video_info.get('description')
             thumbnail = video_info.get('image')
         else:

youtube_dl/extractor/iwara.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import remove_end
+
+
+class IwaraIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
+        'md5': '1d53866b2c514b23ed69e4352fdc9839',
+        'info_dict': {
+            'id': 'amVwUl1EHpAD9RD',
+            'ext': 'mp4',
+            'title': '【MMD R-18】ガールフレンド carry_me_off',
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
+        'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
+        'info_dict': {
+            'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
+            'ext': 'mp4',
+            'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
+            'age_limit': 18,
+        },
+        'add_ie': ['GoogleDrive'],
+    }, {
+        'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
+        'md5': '1d85f1e5217d2791626cff5ec83bb189',
+        'info_dict': {
+            'id': '6liAP9s2Ojc',
+            'ext': 'mp4',
+            'age_limit': 0,
+            'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
+            'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
+            'upload_date': '20160910',
+            'uploader': 'aMMDsork',
+            'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
+        },
+        'add_ie': ['Youtube'],
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
+        # ecchi is 'sexy' in Japanese
+        age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
+
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+
+        if not entries:
+            iframe_url = self._html_search_regex(
+                r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
+                webpage, 'iframe URL', group='url')
+            return {
+                '_type': 'url_transparent',
+                'url': iframe_url,
+                'age_limit': age_limit,
+            }
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
+
+        info_dict = entries[0]
+        info_dict.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': age_limit,
+        })
+
+        return info_dict

youtube_dl/extractor/jwplatform.py

@@ -9,6 +9,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    js_to_json,
     mimetype2ext,
 )
 
@@ -19,14 +20,15 @@ class JWPlatformBaseIE(InfoExtractor):
         # TODO: Merge this with JWPlayer-related codes in generic.py
 
         mobj = re.search(
-            'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\((?P<options>[^)]+)\)',
+            r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
             webpage)
         if mobj:
             return mobj.group('options')
 
     def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
         jwplayer_data = self._parse_json(
-            self._find_jwplayer_data(webpage), video_id)
+            self._find_jwplayer_data(webpage), video_id,
+            transform_source=js_to_json)
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 
@@ -63,10 +65,17 @@ class JWPlatformBaseIE(InfoExtractor):
                         'ext': ext,
                     })
                 else:
+                    height = int_or_none(source.get('height'))
+                    if height is None:
+                        # Often no height is provided but there is a label in
+                        # format like 1080p.
+                        height = int_or_none(self._search_regex(
+                            r'^(\d{3,})[pP]$', source.get('label') or '',
+                            'height', default=None))
                     a_format = {
                         'url': source_url,
                         'width': int_or_none(source.get('width')),
-                        'height': int_or_none(source.get('height')),
+                        'height': height,
                         'ext': ext,
                     }
                     if source_url.startswith('rtmp'):

youtube_dl/extractor/kaltura.py

@@ -262,8 +262,16 @@ class KalturaIE(InfoExtractor):
             # Continue if asset is not ready
             if f.get('status') != 2:
                 continue
+            # Original format that's not available (e.g. kaltura:1926081:0_c03e1b5g)
+            # skip for now.
+            if f.get('fileExt') == 'chun':
+                continue
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
+            # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
+            # -f mp4-56)
+            vcodec = 'none' if 'videoCodecId' not in f and f.get(
+                'frameRate') == 0 else f.get('videoCodecId')
             formats.append({
                 'format_id': '%(fileExt)s-%(bitrate)s' % f,
                 'ext': f.get('fileExt'),
@@ -271,7 +279,7 @@ class KalturaIE(InfoExtractor):
                 'fps': int_or_none(f.get('frameRate')),
                 'filesize_approx': int_or_none(f.get('size'), invscale=1024),
                 'container': f.get('containerFormat'),
-                'vcodec': f.get('videoCodecId'),
+                'vcodec': vcodec,
                 'height': int_or_none(f.get('height')),
                 'width': int_or_none(f.get('width')),
                 'url': video_url,

youtube_dl/extractor/karaoketv.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class KaraoketvIE(InfoExtractor):
-    _VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?karaoketv\.co\.il/[^/]+/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
         'info_dict': {

youtube_dl/extractor/ketnet.py

@@ -0,0 +1,52 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class KetnetIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes',
+        'md5': 'd907f7b1814ef0fa285c0475d9994ed7',
+        'info_dict': {
+            'id': 'zomerse-filmpjes',
+            'ext': 'mp4',
+            'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
+            'description': 'Gluur mee met Ghost Rockers op de filmset',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        config = self._parse_json(
+            self._search_regex(
+                r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage,
+                'player config'),
+            video_id)
+
+        title = config['title']
+
+        formats = self._extract_m3u8_formats(
+            config['source']['hls'], video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': config.get('description'),
+            'thumbnail': config.get('image'),
+            'series': config.get('program'),
+            'episode': config.get('episode'),
+            'formats': formats,
+        }

youtube_dl/extractor/kickstarter.py

@@ -6,7 +6,7 @@ from ..utils import smuggle_url
 
 
 class KickStarterIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
+    _VALID_URL = r'https?://(?:www\.)?kickstarter\.com/projects/(?P<id>[^/]*)/.*'
     _TESTS = [{
         'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant/description',
         'md5': 'c81addca81327ffa66c642b5d8b08cab',

youtube_dl/extractor/kuwo.py

@@ -59,7 +59,7 @@ class KuwoBaseIE(InfoExtractor):
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
     IE_DESC = '酷我音乐'
-    _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
         'info_dict': {
@@ -82,7 +82,7 @@ class KuwoIE(KuwoBaseIE):
             'upload_date': '20150518',
         },
         'params': {
-            'format': 'mp3-320'
+            'format': 'mp3-320',
         },
     }, {
         'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
@@ -91,10 +91,10 @@ class KuwoIE(KuwoBaseIE):
 
     def _real_extract(self, url):
         song_id = self._match_id(url)
-        webpage = self._download_webpage(
+        webpage, urlh = self._download_webpage_handle(
             url, song_id, note='Download song detail info',
             errnote='Unable to get song detail info')
-        if '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
+        if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
 
         song_name = self._html_search_regex(
@@ -139,7 +139,7 @@ class KuwoIE(KuwoBaseIE):
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
     IE_DESC = '酷我音乐 - 专辑'
-    _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
@@ -181,7 +181,7 @@ class KuwoChartIE(InfoExtractor):
         'info_dict': {
             'id': '香港中文龙虎榜',
         },
-        'playlist_mincount': 10,
+        'playlist_mincount': 7,
     }
 
     def _real_extract(self, url):
@@ -200,7 +200,7 @@ class KuwoChartIE(InfoExtractor):
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
     IE_DESC = '酷我音乐 - 歌手'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
@@ -296,14 +296,14 @@ class KuwoCategoryIE(InfoExtractor):
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
     IE_DESC = '酷我音乐 - MV'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',
         'info_dict': {
             'id': '6480076',
             'ext': 'mp4',
             'title': 'My HouseMV',
-            'creator': 'PM02:00',
+            'creator': '2PM',
         },
         # In this video, music URLs (anti.s) are blocked outside China and
         # USA, while the MV URL (mvurl) is available globally, so force the MV

youtube_dl/extractor/lci.py

@@ -0,0 +1,24 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class LCIIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
+        'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
+        'info_dict': {
+            'id': '13244802',
+            'ext': 'mp4',
+            'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
+            'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        wat_id = self._search_regex(r'data-watid=[\'"](\d+)', webpage, 'wat id')
+        return self.url_result('wat:' + wat_id, 'Wat', wat_id)

youtube_dl/extractor/limelight.py

@@ -34,11 +34,12 @@ class LimelightBaseIE(InfoExtractor):
     def _extract_info(self, streams, mobile_urls, properties):
         video_id = properties['media_id']
         formats = []
-
+        urls = []
         for stream in streams:
             stream_url = stream.get('url')
-            if not stream_url or stream.get('drmProtected'):
+            if not stream_url or stream.get('drmProtected') or stream_url in urls:
                 continue
+            urls.append(stream_url)
             ext = determine_ext(stream_url)
             if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
@@ -58,9 +59,11 @@ class LimelightBaseIE(InfoExtractor):
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
+                    http_url = 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:])
+                    urls.append(http_url)
                     http_fmt = fmt.copy()
                     http_fmt.update({
-                        'url': 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:]),
+                        'url': http_url,
                         'format_id': format_id.replace('rtmp', 'http'),
                     })
                     formats.append(http_fmt)
@@ -76,8 +79,9 @@ class LimelightBaseIE(InfoExtractor):
         for mobile_url in mobile_urls:
             media_url = mobile_url.get('mobileUrl')
             format_id = mobile_url.get('targetMediaPlatform')
-            if not media_url or format_id == 'Widevine':
+            if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
                 continue
+            urls.append(media_url)
             ext = determine_ext(media_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(

youtube_dl/extractor/litv.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class LiTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
+    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
 
     _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
 

youtube_dl/extractor/lrt.py

@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     int_or_none,
     parse_duration,
     remove_end,
@@ -12,8 +15,10 @@ from ..utils import (
 class LRTIE(InfoExtractor):
     IE_NAME = 'lrt.lt'
     _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
+        # m3u8 download
         'url': 'http://www.lrt.lt/mediateka/irasas/54391/',
+        'md5': 'fe44cf7e4ab3198055f2c598fc175cb0',
         'info_dict': {
             'id': '54391',
             'ext': 'mp4',
@@ -23,20 +28,45 @@ class LRTIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
-        'params': {
-            'skip_download': True,  # m3u8 download
+    }, {
+        # direct mp3 download
+        'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
+        'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
+        'info_dict': {
+            'id': '1013074524',
+            'ext': 'mp3',
+            'title': 'Kita tema 2016-09-05 15:05',
+            'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
+            'duration': 3008,
+            'view_count': int,
+            'like_count': int,
         },
-    }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = remove_end(self._og_search_title(webpage), ' - LRT')
-        m3u8_url = self._search_regex(
-            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
-            webpage, 'm3u8 url', group='url')
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+
+        formats = []
+        for _, file_url in re.findall(
+                r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
+            ext = determine_ext(file_url)
+            if ext not in ('m3u8', 'mp3'):
+                continue
+            # mp3 served as m3u8 produces stuttered media file
+            if ext == 'm3u8' and '.mp3' in file_url:
+                continue
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    file_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    fatal=False))
+            elif ext == 'mp3':
+                formats.append({
+                    'url': file_url,
+                    'vcodec': 'none',
+                })
         self._sort_formats(formats)
 
         thumbnail = self._og_search_thumbnail(webpage)

youtube_dl/extractor/lynda.py

@@ -94,7 +94,7 @@ class LyndaBaseIE(InfoExtractor):
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
-    _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 

youtube_dl/extractor/macgamestore.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 class MacGameStoreIE(InfoExtractor):
     IE_NAME = 'macgamestore'
     IE_DESC = 'MacGameStore trailers'
-    _VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',

youtube_dl/extractor/mangomolo.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+    int_or_none,
+)
+
+
+class MangomoloBaseIE(InfoExtractor):
+    def _get_real_id(self, page_id):
+        return page_id
+
+    def _real_extract(self, url):
+        page_id = self._get_real_id(self._match_id(url))
+        webpage = self._download_webpage(url, page_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
+
+        format_url = self._html_search_regex(
+            [
+                r'file\s*:\s*"(https?://[^"]+?/playlist.m3u8)',
+                r'<a[^>]+href="(rtsp://[^"]+)"'
+            ], webpage, 'format url')
+        formats = self._extract_wowza_formats(
+            format_url, page_id, m3u8_entry_protocol, ['smil'])
+        self._sort_formats(formats)
+
+        return {
+            'id': page_id,
+            'title': self._live_title(page_id) if self._IS_LIVE else page_id,
+            'uploader_id': hidden_inputs.get('userid'),
+            'duration': int_or_none(hidden_inputs.get('duration')),
+            'is_live': self._IS_LIVE,
+            'formats': formats,
+        }
+
+
+class MangomoloVideoIE(MangomoloBaseIE):
+    IE_NAME = 'mangomolo:video'
+    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)'
+    _IS_LIVE = False
+
+
+class MangomoloLiveIE(MangomoloBaseIE):
+    IE_NAME = 'mangomolo:live'
+    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
+    _IS_LIVE = True
+
+    def _get_real_id(self, page_id):
+        return base64.b64decode(compat_urllib_parse_unquote(page_id).encode()).decode()

youtube_dl/extractor/metacritic.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class MetacriticIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?metacritic\.com/.+?/trailers/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',

youtube_dl/extractor/mgtv.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class MGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
     IE_DESC = '芒果TV'
 
     _TESTS = [{

youtube_dl/extractor/miaopai.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MiaoPaiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
+    _TEST = {
+        'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
+        'md5': '095ed3f1cd96b821add957bdc29f845b',
+        'info_dict': {
+            'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
+            'ext': 'mp4',
+            'title': '西游记音乐会的秒拍视频',
+            'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
+        }
+    }
+
+    _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
+            webpage, 'thumbnail', fatal=False, group='url')
+        videos = self._parse_html5_media_entries(url, webpage, video_id)
+        info = videos[0]
+
+        info.update({
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        })
+        return info

youtube_dl/extractor/ministrygrid.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class MinistryGridIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
 
     _TEST = {
         'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',

youtube_dl/extractor/mitele.py

@@ -74,7 +74,7 @@ class MiTeleBaseIE(InfoExtractor):
 
 class MiTeleIE(MiTeleBaseIE):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
 
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',

youtube_dl/extractor/moevideo.py

@@ -35,7 +35,8 @@ class MoeVideoIE(InfoExtractor):
                 'height': 360,
                 'duration': 179,
                 'filesize': 17822500,
-            }
+            },
+            'skip': 'Video has been removed',
         },
         {
             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',

youtube_dl/extractor/motorsport.py

@@ -9,7 +9,7 @@ from ..compat import (
 
 class MotorsportIE(InfoExtractor):
     IE_DESC = 'motorsport.com'
-    _VALID_URL = r'https?://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
     _TEST = {
         'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
         'info_dict': {

youtube_dl/extractor/moviezine.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class MoviezineIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.moviezine\.se/video/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?moviezine\.se/video/(?P<id>[^?#]+)'
 
     _TEST = {
         'url': 'http://www.moviezine.se/video/205866',

youtube_dl/extractor/movingimage.py

@@ -7,22 +7,19 @@ from ..utils import (
 )
 
 
-class SSAIE(InfoExtractor):
-    _VALID_URL = r'https?://ssa\.nls\.uk/film/(?P<id>\d+)'
+class MovingImageIE(InfoExtractor):
+    _VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://ssa.nls.uk/film/3561',
+        'url': 'http://movingimage.nls.uk/film/3561',
+        'md5': '4caa05c2b38453e6f862197571a7be2f',
         'info_dict': {
             'id': '3561',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'SHETLAND WOOL',
             'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
             'duration': 900,
             'thumbnail': 're:^https?://.*\.jpg$',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
     }
 
     def _real_extract(self, url):
@@ -30,10 +27,9 @@ class SSAIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        streamer = self._search_regex(
-            r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
-        play_path = self._search_regex(
-            r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
+        formats = self._extract_m3u8_formats(
+            self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
+            video_id, ext='mp4', entry_protocol='m3u8_native')
 
         def search_field(field_name, fatal=False):
             return self._search_regex(
@@ -44,13 +40,11 @@ class SSAIE(InfoExtractor):
         description = unescapeHTML(search_field('Description'))
         duration = parse_duration(search_field('Running time'))
         thumbnail = self._search_regex(
-            r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
+            r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,
-            'url': streamer,
-            'play_path': play_path,
-            'ext': 'flv',
+            'formats': formats,
             'title': title,
             'description': description,
             'duration': duration,

youtube_dl/extractor/myspass.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class MySpassIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.myspass\.de/.*'
+    _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
     _TEST = {
         'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
         'md5': '0b49f4844a068f8b33f4b7c88405862b',

youtube_dl/extractor/myvidster.py

@@ -13,7 +13,7 @@ class MyVidsterIE(InfoExtractor):
             'id': '3685814',
             'title': 'md5:7d8427d6d02c4fbcef50fe269980c749',
             'upload_date': '20141027',
-            'uploader_id': 'utkualp',
+            'uploader': 'utkualp',
             'ext': 'mp4',
             'age_limit': 18,
         },

youtube_dl/extractor/nbc.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class NBCIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
 
     _TESTS = [
         {
@@ -138,7 +138,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
 
 class NBCSportsIE(InfoExtractor):
     # Does not include https because its certificate is invalid
-    _VALID_URL = r'https?://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 
     _TEST = {
         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
@@ -161,7 +161,7 @@ class NBCSportsIE(InfoExtractor):
 
 
 class CSNNEIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.csnne\.com/video/(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 
     _TEST = {
         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
@@ -335,3 +335,43 @@ class NBCNewsIE(ThePlatformIE):
                 'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
                 'ie_key': 'ThePlatformFeed',
             }
+
+
+class NBCOlympicsIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
+
+    _TEST = {
+        # Geo-restricted to US
+        'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
+        'md5': '54fecf846d05429fbaa18af557ee523a',
+        'info_dict': {
+            'id': 'WjTBzDXx5AUq',
+            'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
+            'ext': 'mp4',
+            'title': 'Rose\'s son Leo was in tears after his dad won gold',
+            'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
+            'timestamp': 1471274964,
+            'upload_date': '20160815',
+            'uploader': 'NBCU-SPORTS',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        drupal_settings = self._parse_json(self._search_regex(
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+            webpage, 'drupal settings'), display_id)
+
+        iframe_url = drupal_settings['vod']['iframe_url']
+        theplatform_url = iframe_url.replace(
+            'vplayer.nbcolympics.com', 'player.theplatform.com')
+
+        return {
+            '_type': 'url_transparent',
+            'url': theplatform_url,
+            'ie_key': ThePlatformIE.ie_key(),
+            'display_id': display_id,
+        }

youtube_dl/extractor/ndr.py

@@ -23,7 +23,7 @@ class NDRBaseIE(InfoExtractor):
 class NDRIE(NDRBaseIE):
     IE_NAME = 'ndr'
     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
+    _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@@ -105,7 +105,7 @@ class NDRIE(NDRBaseIE):
 class NJoyIE(NDRBaseIE):
     IE_NAME = 'njoy'
     IE_DESC = 'N-JOY'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
@@ -238,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor):
 
 class NDREmbedIE(NDREmbedBaseIE):
     IE_NAME = 'ndr:embed'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
+    _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
     _TESTS = [{
         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
@@ -332,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
 
 class NJoyEmbedIE(NDREmbedBaseIE):
     IE_NAME = 'njoy:embed'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
+    _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
     _TESTS = [{
         # httpVideo
         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',

youtube_dl/extractor/newgrounds.py

@@ -1,15 +1,12 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 
 
 class NewgroundsIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://www.newgrounds.com/audio/listen/549479',
+        'url': 'https://www.newgrounds.com/audio/listen/549479',
         'md5': 'fe6033d297591288fa1c1f780386f07a',
         'info_dict': {
             'id': '549479',
@@ -18,7 +15,7 @@ class NewgroundsIE(InfoExtractor):
             'uploader': 'Burn7',
         }
     }, {
-        'url': 'http://www.newgrounds.com/portal/view/673111',
+        'url': 'https://www.newgrounds.com/portal/view/673111',
         'md5': '3394735822aab2478c31b1004fe5e5bc',
         'info_dict': {
             'id': '673111',
@@ -29,24 +26,20 @@ class NewgroundsIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        music_id = mobj.group('id')
-        webpage = self._download_webpage(url, music_id)
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
 
         title = self._html_search_regex(
             r'<title>([^>]+)</title>', webpage, 'title')
 
         uploader = self._html_search_regex(
-            [r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
-            webpage, 'uploader')
+            r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
 
-        music_url_json_string = self._html_search_regex(
-            r'({"url":"[^"]+"),', webpage, 'music url') + '}'
-        music_url_json = json.loads(music_url_json_string)
-        music_url = music_url_json['url']
+        music_url = self._parse_json(self._search_regex(
+            r'"url":("[^"]+"),', webpage, ''), media_id)
 
         return {
-            'id': music_id,
+            'id': media_id,
             'title': title,
             'url': music_url,
             'uploader': uploader,

youtube_dl/extractor/nextmedia.py

@@ -7,7 +7,7 @@ from ..utils import parse_iso8601
 
 class NextMediaIE(InfoExtractor):
     IE_DESC = '蘋果日報'
-    _VALID_URL = r'https?://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
         'md5': 'dff9fad7009311c421176d1ac90bfe4f',
@@ -68,7 +68,7 @@ class NextMediaIE(InfoExtractor):
 
 class NextMediaActionNewsIE(NextMediaIE):
     IE_DESC = '蘋果日報 - 動新聞'
-    _VALID_URL = r'https?://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
+    _VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
     _TESTS = [{
         'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
         'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
@@ -93,7 +93,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',

youtube_dl/extractor/nfl.py

@@ -165,7 +165,7 @@ class NFLIE(InfoExtractor):
             group='config'))
         # For articles, the id in the url is not the video id
         video_id = self._search_regex(
-            r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>.+?)\1',
+            r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'video id', default=video_id, group='id')
         config = self._download_json(config_url, video_id, 'Downloading player config')
         url_template = NFLIE.prepend_host(

youtube_dl/extractor/nhk.py

@@ -1,14 +1,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+?)\.html'
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
     _TEST = {
         # Videos available only for a limited period of time. Visit
         # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
-        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
+        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
         'info_dict': {
             'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
             'ext': 'flv',
@@ -19,25 +20,25 @@ class NhkVodIE(InfoExtractor):
         },
         'skip': 'Videos available only for a limited period of time',
     }
+    _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        data = self._download_json(self._API_URL, video_id)
 
-        embed_code = self._search_regex(
-            r'nw_vod_ooplayer\([^,]+,\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'ooyala embed code', group='id')
+        try:
+            episode = next(
+                e for e in data['data']['episodes']
+                if e.get('url') and video_id in e['url'])
+        except StopIteration:
+            raise ExtractorError('Unable to find episode')
 
-        title = self._search_regex(
-            r'<div[^>]+class=["\']episode-detail["\']>\s*<h\d+>([^<]+)',
-            webpage, 'title', default=None)
-        description = self._html_search_regex(
-            r'(?s)<p[^>]+class=["\']description["\'][^>]*>(.+?)</p>',
-            webpage, 'description', default=None)
-        series = self._search_regex(
-            r'<h2[^>]+class=["\']detail-top-player-title[^>]+><a[^>]+>([^<]+)',
-            webpage, 'series', default=None)
+        embed_code = episode['vod_id']
+
+        title = episode.get('sub_title_clean') or episode['sub_title']
+        description = episode.get('description_clean') or episode.get('description')
+        series = episode.get('title_clean') or episode.get('title')
 
         return {
             '_type': 'url_transparent',

youtube_dl/extractor/nick.py

@@ -69,13 +69,16 @@ class NickIE(MTVServicesInfoExtractor):
 
 class NickDeIE(MTVServicesInfoExtractor):
     IE_NAME = 'nick.de'
-    _VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
         'only_matching': True,
     }, {
         'url': 'http://www.nick.de/shows/342-icarly',
         'only_matching': True,
+    }, {
+        'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/niconico.py

@@ -252,7 +252,7 @@ class NiconicoIE(InfoExtractor):
 
 
 class NiconicoPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/mylist/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.nicovideo.jp/mylist/27411728',