release 2018.12.03

[ci skip]

.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 *2018.08.04*. 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 Issues with outdated version will be rejected.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 **2018.08.04**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.03*. 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 Issues with outdated version will be rejected.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 **2018.12.03**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2018.08.04
+[debug] youtube-dl version 2018.12.03
 [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: {}

.gitignore

@@ -48,3 +48,6 @@ youtube-dl.zsh
 
 tmp/
 venv/
+
+# VS Code related files
+.vscode

.travis.yml

@@ -15,6 +15,18 @@ env:
   - YTDL_TEST_SET=download
 matrix:
   include:
+    - python: 3.7
+      dist: xenial
+      env: YTDL_TEST_SET=core
+    - python: 3.7
+      dist: xenial
+      env: YTDL_TEST_SET=download
+    - python: 3.8-dev
+      dist: xenial
+      env: YTDL_TEST_SET=core
+    - python: 3.8-dev
+      dist: xenial
+      env: YTDL_TEST_SET=download
     - env: JYTHON=true; YTDL_TEST_SET=core
     - env: JYTHON=true; YTDL_TEST_SET=download
   fast_finish: true

CONTRIBUTING.md

@@ -296,5 +296,26 @@ title = self._search_regex(
 
 ### Use safe conversion functions
 
-Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
+Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
+
+Use `url_or_none` for safe URL processing.
+
+Use `try_get` for safe metadata extraction from parsed JSON.
+
+Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
+
+#### More examples
+
+##### Safely extract optional description from parsed JSON
+```python
+description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str)
+```
+
+##### Safely extract more optional metadata
+```python
+video = try_get(response, lambda x: x['result']['video'][0], dict) or {}
+description = video.get('summary')
+duration = float_or_none(video.get('durationMs'), scale=1000)
+view_count = int_or_none(video.get('views'))
+```
 

ChangeLog

@@ -1,3 +1,242 @@
+version 2018.12.03
+
+Core
+* [utils] Fix random_birthday to generate existing dates only (#18284)
+
+Extractors
++ [tiktok] Add support for tiktok.com (#18108, #18135)
+* [pornhub] Use actual URL host for requests (#18359)
+* [lynda] Fix authentication (#18158, #18217)
+* [gfycat] Update API endpoint (#18333, #18343)
++ [hotstar] Add support for alternative app state layout (#18320)
+* [azmedien] Fix extraction (#18334, #18336)
++ [vimeo] Add support for VHX (Vimeo OTT) (#14835)
+* [joj] Fix extraction (#18280, #18281)
++ [wistia] Add support for fast.wistia.com (#18287)
+
+
+version 2018.11.23
+
+Core
++ [setup.py] Add more relevant classifiers
+
+Extractors
+* [mixcloud] Fallback to hardcoded decryption key (#18016)
+* [nbc:news] Fix article extraction (#16194)
+* [foxsports] Fix extraction (#17543)
+* [loc] Relax regular expression and improve formats extraction
++ [ciscolive] Add support for ciscolive.cisco.com (#17984)
+* [nzz] Relax kaltura regex (#18228)
+* [sixplay] Fix formats extraction
+* [bitchute] Improve title extraction
+* [kaltura] Limit requested MediaEntry fields
++ [americastestkitchen] Add support for zype embeds (#18225)
++ [pornhub] Add pornhub.net alias
+* [nova:embed] Fix extraction (#18222)
+
+
+version 2018.11.18
+
+Extractors
++ [wwe] Extract subtitles
++ [wwe] Add support for playlistst (#14781)
++ [wwe] Add support for wwe.com (#14781, #17450)
+* [vk] Detect geo restriction (#17767)
+* [openload] Use original host during extraction (#18211)
+* [atvat] Fix extraction (#18041)
++ [rte] Add support for new API endpoint (#18206)
+* [tnaflixnetwork:embed] Fix extraction (#18205)
+* [picarto] Use API and add token support (#16518)
++ [zype] Add support for player.zype.com (#18143)
+* [vivo] Fix extraction (#18139)
+* [ruutu] Update API endpoint (#18138)
+
+
+version 2018.11.07
+
+Extractors
++ [youtube] Add another JS signature function name regex (#18091, #18093,
+  #18094)
+* [facebook] Fix tahoe request (#17171)
+* [cliphunter] Fix extraction (#18083)
++ [youtube:playlist] Add support for invidio.us (#18077)
+* [zattoo] Arrange API hosts for derived extractors (#18035)
++ [youtube] Add fallback metadata extraction from videoDetails (#18052)
+
+
+version 2018.11.03
+
+Core
+* [extractor/common] Ensure response handle is not prematurely closed before
+  it can be read if it matches expected_status (#17195, #17846, #17447)
+
+Extractors
+* [laola1tv:embed] Set correct stream access URL scheme (#16341)
++ [ehftv] Add support for ehftv.com (#15408)
+* [azmedien] Adopt to major site redesign (#17745, #17746)
++ [twitcasting] Add support for twitcasting.tv (#17981)
+* [orf:tvthek] Fix extraction (#17737, #17956, #18024)
++ [openload] Add support for oload.fun (#18045)
+* [njpwworld] Fix authentication (#17427)
++ [linkedin:learning] Add support for linkedin.com/learning (#13545)
+* [theplatform] Improve error detection (#13222)
+* [cnbc] Simplify extraction (#14280, #17110)
++ [cbnc] Add support for new URL schema (#14193)
+* [aparat] Improve extraction and extract more metadata (#17445, #18008)
+* [aparat] Fix extraction
+
+
+version 2018.10.29
+
+Core
++ [extractor/common] Add validation for JSON-LD URLs
+
+Extractors
++ [sportbox] Add support for matchtv.ru
+* [sportbox] Fix extraction (#17978)
+* [screencast] Fix extraction (#14590, #14617, #17990)
++ [openload] Add support for oload.icu
++ [ivi] Add support for ivi.tv
+* [crunchyroll] Improve extraction failsafeness (#17991)
+* [dailymail] Fix formats extraction (#17976)
+* [viewster] Reduce format requests
+* [cwtv] Handle API errors (#17905)
++ [rutube] Use geo verification headers (#17897)
++ [brightcove:legacy] Add fallbacks to brightcove:new (#13912)
+- [tv3] Remove extractor (#10461, #15339)
+* [ted] Fix extraction for HTTP and RTMP formats (#5941, #17572, #17894)
++ [openload] Add support for oload.cc (#17823)
++ [patreon] Extract post_file URL (#17792)
+* [patreon] Fix extraction (#14502, #10471)
+
+
+version 2018.10.05
+
+Extractors
+* [pluralsight] Improve authentication (#17762)
+* [dailymotion] Fix extraction (#17699)
+* [crunchyroll] Switch to HTTPS for RpcApi (#17749)
++ [philharmoniedeparis] Add support for pad.philharmoniedeparis.fr (#17705)
+* [philharmoniedeparis] Fix extraction (#17705)
++ [jamendo] Add support for licensing.jamendo.com (#17724)
++ [openload] Add support for oload.cloud (#17710)
+* [pluralsight] Fix subtitles extraction (#17726, #17728)
++ [vimeo] Add another config regular expression (#17690)
+* [spike] Fix Paramount Network extraction (#17677)
+* [hotstar] Fix extraction (#14694, #14931, #17637)
+
+
+version 2018.09.26
+
+Extractors
+* [pluralsight] Fix subtitles extraction (#17671)
+* [mediaset] Improve embed support (#17668)
++ [youtube] Add support for invidio.us (#17613)
++ [zattoo] Add support for more zattoo platform sites
+* [zattoo] Fix extraction (#17175, #17542)
+
+
+version 2018.09.18
+
+Core
++ [extractor/common] Introduce channel meta fields
+
+Extractors
+* [adobepass] Don't pollute default headers dict
+* [udemy] Don't pollute default headers dict
+* [twitch] Don't pollute default headers dict
+* [youtube] Don't pollute default query dict (#17593)
+* [crunchyroll] Prefer hardsubless formats and formats in locale language
+* [vrv] Make format ids deterministic
+* [vimeo] Fix ondemand playlist extraction (#14591)
++ [pornhub] Extract upload date (#17574)
++ [porntube] Extract channel meta fields
++ [vimeo] Extract channel meta fields
++ [youtube] Extract channel meta fields (#9676, #12939)
+* [porntube] Fix extraction (#17541)
+* [asiancrush] Fix extraction (#15630)
++ [twitch:clips] Extend URL regular expression (closes #17559)
++ [vzaar] Add support for HLS
+* [tube8] Fix metadata extraction (#17520)
+* [eporner] Extract JSON-LD (#17519)
+
+
+version 2018.09.10
+
+Core
++ [utils] Properly recognize AV1 codec (#17506)
+
+Extractors
++ [iprima] Add support for prima.iprima.cz (#17514)
++ [tele5] Add support for tele5.de (#7805, #7922, #17331, #17414)
+* [nbc] Fix extraction of percent encoded URLs (#17374)
+
+
+version 2018.09.08
+
+Extractors
+* [youtube] Fix extraction (#17457, #17464)
++ [pornhub:uservideos] Add support for new URLs (#17388)
+* [iprima] Confirm adult check (#17437)
+* [slideslive] Make check for video service name case-insensitive (#17429)
+* [radiojavan] Fix extraction (#17151)
+* [generic] Skip unsuccessful jwplayer extraction (#16735)
+
+
+version 2018.09.01
+
+Core
+* [utils] Skip remote IP addresses non matching to source address' IP version
+  when creating a connection (#13422, #17362)
+
+Extractors
++ [ard] Add support for one.ard.de (#17397)
+* [niconico] Fix extraction on python3 (#17393, #17407)
+* [ard] Extract f4m formats
+* [crunchyroll] Parse vilos media data (#17343)
++ [ard] Add support for Beta ARD Mediathek
++ [bandcamp] Extract more metadata (#13197)
+* [internazionale] Fix extraction of non-available-abroad videos (#17386)
+
+
+version 2018.08.28
+
+Extractors
++ [youtube:playlist] Add support for music album playlists (OLAK5uy_ prefix)
+  (#17361)
+* [bitchute] Fix extraction by pass custom User-Agent (#17360)
+* [webofstories:playlist] Fix extraction (#16914)
++ [tvplayhome] Add support for new tvplay URLs (#17344)
++ [generic] Allow relative src for videojs embeds (#17324)
++ [xfileshare] Add support for vidto.se (#17317)
++ [vidzi] Add support for vidzi.nu (#17316)
++ [nova:embed] Add support for media.cms.nova.cz (#17282)
+
+
+version 2018.08.22
+
+Core
+* [utils] Use pure browser header for User-Agent (#17236)
+
+Extractors
++ [kinopoisk] Add support for kinopoisk.ru (#17283)
++ [yourporn] Add support for yourporn.sexy (#17298)
++ [go] Add support for disneynow.go.com (#16299, #17264)
++ [6play] Add support for play.rtl.hr (#17249)
+* [anvato] Fallback to generic API key for access-key-to-API-key lookup
+  (#16788, #17254)
+* [lci] Fix extraction (#17274)
+* [bbccouk] Extend id URL regular expression (#17270)
+* [cwtv] Fix extraction (#17256)
+* [nova] Fix extraction (#17241)
++ [generic] Add support for expressen embeds
+* [raywenderlich] Adapt to site redesign (#17225)
++ [redbulltv] Add support redbull.com tv URLs (#17218)
++ [bitchute] Add support for bitchute.com (#14052)
++ [clyp] Add support for token protected media (#17184)
+* [imdb] Fix extension extraction (#17167)
+
+
 version 2018.08.04
 
 Extractors

README.md

@@ -511,6 +511,8 @@ The basic usage is not to set any template arguments when downloading a single f
  - `timestamp` (numeric): UNIX timestamp of the moment the video became available
  - `upload_date` (string): Video upload date (YYYYMMDD)
  - `uploader_id` (string): Nickname or id of the video uploader
+ - `channel` (string): Full name of the channel the video is uploaded on
+ - `channel_id` (string): Id of the channel
  - `location` (string): Physical location where the video was filmed
  - `duration` (numeric): Length of the video in seconds
  - `view_count` (numeric): How many users have watched the video on the platform
@@ -1166,7 +1168,28 @@ title = self._search_regex(
 
 ### Use safe conversion functions
 
-Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
+Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
+
+Use `url_or_none` for safe URL processing.
+
+Use `try_get` for safe metadata extraction from parsed JSON.
+
+Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
+
+#### More examples
+
+##### Safely extract optional description from parsed JSON
+```python
+description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str)
+```
+
+##### Safely extract more optional metadata
+```python
+video = try_get(response, lambda x: x['result']['video'][0], dict) or {}
+description = video.get('summary')
+duration = float_or_none(video.get('durationMs'), scale=1000)
+view_count = int_or_none(video.get('views'))
+```
 
 # EMBEDDING YOUTUBE-DL
 

docs/supportedsites.md

@@ -56,6 +56,7 @@
  - **archive.org**: archive.org videos
  - **ARD**
  - **ARD:mediathek**
+ - **ARDBetaMediathek**
  - **Arkena**
  - **arte.tv**
  - **arte.tv:+7**
@@ -83,8 +84,6 @@
  - **awaan:season**
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
- - **AZMedienPlaylist**: AZ Medien playlists
- - **AZMedienShowPlaylist**: AZ Medien show playlists
  - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
@@ -97,6 +96,7 @@
  - **bbc.co.uk:article**: BBC articles
  - **bbc.co.uk:iplayer:playlist**
  - **bbc.co.uk:playlist**
+ - **BBVTV**
  - **Beatport**
  - **Beeg**
  - **BehindKink**
@@ -108,6 +108,8 @@
  - **BiliBili**
  - **BioBioChileTV**
  - **BIQLE**
+ - **BitChute**
+ - **BitChuteChannel**
  - **BleacherReport**
  - **BleacherReportCMS**
  - **blinkx**
@@ -161,6 +163,8 @@
  - **chirbit**
  - **chirbit:profile**
  - **Cinchcast**
+ - **CiscoLiveSearch**
+ - **CiscoLiveSession**
  - **CJSW**
  - **cliphunter**
  - **Clippit**
@@ -174,6 +178,7 @@
  - **Clyp**
  - **cmt.com**
  - **CNBC**
+ - **CNBCVideo**
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
@@ -189,7 +194,7 @@
  - **Crackle**
  - **Criterion**
  - **CrooksAndLiars**
- - **Crunchyroll**
+ - **crunchyroll**
  - **crunchyroll:playlist**
  - **CSNNE**
  - **CSpan**: C-SPAN
@@ -247,7 +252,9 @@
  - **EchoMsk**
  - **egghead:course**: egghead.io course
  - **egghead:lesson**: egghead.io lesson
+ - **ehftv**
  - **eHow**
+ - **EinsUndEinsTV**
  - **Einthusan**
  - **eitb.tv**
  - **EllenTube**
@@ -265,6 +272,7 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
+ - **EWETV**
  - **ExpoTV**
  - **Expressen**
  - **ExtremeTube**
@@ -324,6 +332,7 @@
  - **Gfycat**
  - **GiantBomb**
  - **Giga**
+ - **GlattvisionTV**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
@@ -353,7 +362,7 @@
  - **HitRecord**
  - **HornBunny**
  - **HotNewHipHop**
- - **HotStar**
+ - **hotstar**
  - **hotstar:playlist**
  - **Howcast**
  - **HowStuffWorks**
@@ -405,6 +414,7 @@
  - **Ketnet**
  - **KhanAcademy**
  - **KickStarter**
+ - **KinoPoisk**
  - **KonserthusetPlay**
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
@@ -437,6 +447,8 @@
  - **limelight:channel**
  - **limelight:channel_list**
  - **LineTV**
+ - **linkedin:learning**
+ - **linkedin:learning:course**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -490,6 +502,7 @@
  - **Mixer:vod**
  - **MLB**
  - **Mnet**
+ - **MNetTV**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **Mojvideo**
@@ -521,6 +534,7 @@
  - **Myvi**
  - **MyVidster**
  - **MyviEmbed**
+ - **MyVisionTV**
  - **n-tv.de**
  - **natgeo**
  - **natgeo:episodeguide**
@@ -546,6 +560,7 @@
  - **netease:program**: 网易云音乐 - 电台节目
  - **netease:singer**: 网易云音乐 - 歌手
  - **netease:song**: 网易云音乐
+ - **NetPlus**
  - **Netzkino**
  - **Newgrounds**
  - **NewgroundsPlaylist**
@@ -577,6 +592,7 @@
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
+ - **NovaEmbed**
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**
@@ -621,6 +637,7 @@
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **OsnatelTV**
  - **PacktPub**
  - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
@@ -681,6 +698,7 @@
  - **qqmusic:playlist**: QQ音乐 - 歌单
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
+ - **QuantumTV**
  - **Quickline**
  - **QuicklineLive**
  - **R7**
@@ -696,6 +714,7 @@
  - **RaiPlayLive**
  - **RaiPlayPlaylist**
  - **RayWenderlich**
+ - **RayWenderlichCourse**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedBullTV**
@@ -747,6 +766,7 @@
  - **safari**: safaribooksonline.com online video
  - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
+ - **SAKTV**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -802,7 +822,7 @@
  - **Spiegeltv**
  - **sport.francetvinfo.fr**
  - **Sport5**
- - **SportBoxEmbed**
+ - **SportBox**
  - **SportDeutschland**
  - **SpringboardPlatform**
  - **Sprout**
@@ -841,6 +861,7 @@
  - **techtv.mit.edu**
  - **ted**
  - **Tele13**
+ - **Tele5**
  - **TeleBruxelles**
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
@@ -864,6 +885,8 @@
  - **ThisAmericanLife**
  - **ThisAV**
  - **ThisOldHouse**
+ - **TikTok**
+ - **TikTokUser**
  - **tinypic**: tinypic.com videos
  - **TMZ**
  - **TMZArticle**
@@ -892,7 +915,6 @@
  - **TV2**
  - **tv2.hu**
  - **TV2Article**
- - **TV3**
  - **TV4**: tv4.se and tv4play.se
  - **TV5MondePlus**: TV5MONDE+
  - **TVA**
@@ -912,7 +934,9 @@
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
  - **TVPlayer**
+ - **TVPlayHome**
  - **Tweakers**
+ - **TwitCasting**
  - **twitch:chapter**
  - **twitch:clips**
  - **twitch:profile**
@@ -957,6 +981,7 @@
  - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
+ - **vhx:embed**
  - **Viafree**
  - **vice**
  - **vice:article**
@@ -1027,12 +1052,14 @@
  - **vrv**
  - **vrv:series**
  - **VShare**
+ - **VTXTV**
  - **vube**: Vube.com
  - **VuClip**
  - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
  - **Walla**
+ - **WalyTV**
  - **washingtonpost**
  - **washingtonpost:article**
  - **wat.tv**
@@ -1058,6 +1085,7 @@
  - **wrzuta.pl:playlist**
  - **WSJ**: Wall Street Journal
  - **WSJArticle**
+ - **WWE**
  - **XBef**
  - **XboxClips**
  - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me
@@ -1093,6 +1121,7 @@
  - **YouNowLive**
  - **YouNowMoment**
  - **YouPorn**
+ - **YourPorn**
  - **YourUpload**
  - **youtube**: YouTube.com
  - **youtube:channel**: YouTube.com channels
@@ -1116,3 +1145,4 @@
  - **ZDF**
  - **ZDFChannel**
  - **zingmp3**: mp3.zing.vn
+ - **Zype**

setup.py

@@ -124,6 +124,8 @@ setup(
         'Development Status :: 5 - Production/Stable',
         'Environment :: Console',
         'License :: Public Domain',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2',
         'Programming Language :: Python :: 2.6',
         'Programming Language :: Python :: 2.7',
         'Programming Language :: Python :: 3',
@@ -132,6 +134,13 @@ setup(
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: Implementation',
+        'Programming Language :: Python :: Implementation :: CPython',
+        'Programming Language :: Python :: Implementation :: IronPython',
+        'Programming Language :: Python :: Implementation :: Jython',
+        'Programming Language :: Python :: Implementation :: PyPy',
     ],
 
     cmdclass={'build_lazy_extractors': build_lazy_extractors},

test/helper.py

@@ -7,6 +7,7 @@ import json
 import os.path
 import re
 import types
+import ssl
 import sys
 
 import youtube_dl.extractor
@@ -244,3 +245,12 @@ def expect_warnings(ydl, warnings_re):
             real_warning(w)
 
     ydl.report_warning = _report_warning
+
+
+def http_server_port(httpd):
+    if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
+        # In Jython SSLSocket is not a subclass of socket.socket
+        sock = httpd.socket.sock
+    else:
+        sock = httpd.socket
+    return sock.getsockname()[1]

test/test_InfoExtractor.py

@@ -9,11 +9,30 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL, expect_dict, expect_value
-from youtube_dl.compat import compat_etree_fromstring
+from test.helper import FakeYDL, expect_dict, expect_value, http_server_port
+from youtube_dl.compat import compat_etree_fromstring, compat_http_server
 from youtube_dl.extractor.common import InfoExtractor
 from youtube_dl.extractor import YoutubeIE, get_info_extractor
 from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
+import threading
+
+
+TEAPOT_RESPONSE_STATUS = 418
+TEAPOT_RESPONSE_BODY = "<h1>418 I'm a teapot</h1>"
+
+
+class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+    def log_message(self, format, *args):
+        pass
+
+    def do_GET(self):
+        if self.path == '/teapot':
+            self.send_response(TEAPOT_RESPONSE_STATUS)
+            self.send_header('Content-Type', 'text/html; charset=utf-8')
+            self.end_headers()
+            self.wfile.write(TEAPOT_RESPONSE_BODY.encode())
+        else:
+            assert False
 
 
 class TestIE(InfoExtractor):
@@ -743,6 +762,25 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 for i in range(len(entries)):
                     expect_dict(self, entries[i], expected_entries[i])
 
+    def test_response_with_expected_status_returns_content(self):
+        # Checks for mitigations against the effects of
+        # <https://bugs.python.org/issue15002> that affect Python 3.4.1+, which
+        # manifest as `_download_webpage`, `_download_xml`, `_download_json`,
+        # or the underlying `_download_webpage_handle` returning no content
+        # when a response matches `expected_status`.
+
+        httpd = compat_http_server.HTTPServer(
+            ('127.0.0.1', 0), InfoExtractorTestRequestHandler)
+        port = http_server_port(httpd)
+        server_thread = threading.Thread(target=httpd.serve_forever)
+        server_thread.daemon = True
+        server_thread.start()
+
+        (content, urlh) = self.ie._download_webpage_handle(
+            'http://127.0.0.1:%d/teapot' % port, None,
+            expected_status=TEAPOT_RESPONSE_STATUS)
+        self.assertEqual(content, TEAPOT_RESPONSE_BODY)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_compat.py

@@ -39,7 +39,7 @@ class TestCompat(unittest.TestCase):
 
     def test_compat_expanduser(self):
         old_home = os.environ.get('HOME')
-        test_str = 'C:\Documents and Settings\тест\Application Data'
+        test_str = r'C:\Documents and Settings\тест\Application Data'
         compat_setenv('HOME', test_str)
         self.assertEqual(compat_expanduser('~'), test_str)
         compat_setenv('HOME', old_home or '')

test/test_downloader_http.py

@@ -9,26 +9,16 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import try_rm
+from test.helper import http_server_port, try_rm
 from youtube_dl import YoutubeDL
 from youtube_dl.compat import compat_http_server
 from youtube_dl.downloader.http import HttpFD
 from youtube_dl.utils import encodeFilename
-import ssl
 import threading
 
 TEST_DIR = os.path.dirname(os.path.abspath(__file__))
 
 
-def http_server_port(httpd):
-    if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
-        # In Jython SSLSocket is not a subclass of socket.socket
-        sock = httpd.socket.sock
-    else:
-        sock = httpd.socket
-    return sock.getsockname()[1]
-
-
 TEST_SIZE = 10 * 1024
 
 

test/test_http.py

@@ -8,6 +8,7 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+from test.helper import http_server_port
 from youtube_dl import YoutubeDL
 from youtube_dl.compat import compat_http_server, compat_urllib_request
 import ssl
@@ -16,15 +17,6 @@ import threading
 TEST_DIR = os.path.dirname(os.path.abspath(__file__))
 
 
-def http_server_port(httpd):
-    if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
-        # In Jython SSLSocket is not a subclass of socket.socket
-        sock = httpd.socket.sock
-    else:
-        sock = httpd.socket
-    return sock.getsockname()[1]
-
-
 class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
     def log_message(self, format, *args):
         pass

test/test_postprocessors.py

@@ -14,4 +14,4 @@ from youtube_dl.postprocessor import MetadataFromTitlePP
 class TestMetadataFromTitle(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
-        self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')
+        self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_utils.py

@@ -785,6 +785,10 @@ class TestUtil(unittest.TestCase):
             'vcodec': 'h264',
             'acodec': 'aac',
         })
+        self.assertEqual(parse_codecs('av01.0.05M.08'), {
+            'vcodec': 'av01.0.05M.08',
+            'acodec': 'none',
+        })
 
     def test_escape_rfc3986(self):
         reserved = "!*'();:@&=+$,/?#[]"

youtube_dl/extractor/adobepass.py

@@ -1325,8 +1325,8 @@ class AdobePassIE(InfoExtractor):
     _DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
 
     def _download_webpage_handle(self, *args, **kwargs):
-        headers = kwargs.get('headers', {})
-        headers.update(self.geo_verification_headers())
+        headers = self.geo_verification_headers()
+        headers.update(kwargs.get('headers', {}))
         kwargs['headers'] = headers
         return super(AdobePassIE, self)._download_webpage_handle(
             *args, **compat_kwargs(kwargs))

youtube_dl/extractor/americastestkitchen.py

@@ -43,10 +43,6 @@ class AmericasTestKitchenIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        partner_id = self._search_regex(
-            r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
-            webpage, 'kaltura partner id')
-
         video_data = self._parse_json(
             self._search_regex(
                 r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
@@ -58,7 +54,18 @@ class AmericasTestKitchenIE(InfoExtractor):
             (lambda x: x['episodeDetail']['content']['data'],
              lambda x: x['videoDetail']['content']['data']), dict)
         ep_meta = ep_data.get('full_video', {})
-        external_id = ep_data.get('external_id') or ep_meta['external_id']
+
+        zype_id = ep_meta.get('zype_id')
+        if zype_id:
+            embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id
+            ie_key = 'Zype'
+        else:
+            partner_id = self._search_regex(
+                r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
+                webpage, 'kaltura partner id')
+            external_id = ep_data.get('external_id') or ep_meta['external_id']
+            embed_url = 'kaltura:%s:%s' % (partner_id, external_id)
+            ie_key = 'Kaltura'
 
         title = ep_data.get('title') or ep_meta.get('title')
         description = clean_html(ep_meta.get('episode_description') or ep_data.get(
@@ -72,8 +79,8 @@ class AmericasTestKitchenIE(InfoExtractor):
 
         return {
             '_type': 'url_transparent',
-            'url': 'kaltura:%s:%s' % (partner_id, external_id),
-            'ie_key': 'Kaltura',
+            'url': embed_url,
+            'ie_key': ie_key,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

youtube_dl/extractor/anvato.py

@@ -134,9 +134,33 @@ class AnvatoIE(InfoExtractor):
         'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
     }
 
+    _API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA'
+
     _ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
     _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
 
+    _TESTS = [{
+        # from https://www.boston25news.com/news/watch-humpback-whale-breaches-right-next-to-fishing-boat-near-nh/817484874
+        'url': 'anvato:8v9BEynrwx8EFLYpgfOWcG1qJqyXKlRM:4465496',
+        'info_dict': {
+            'id': '4465496',
+            'ext': 'mp4',
+            'title': 'VIDEO: Humpback whale breaches right next to NH boat',
+            'description': 'VIDEO: Humpback whale breaches right next to NH boat. Footage courtesy: Zach Fahey.',
+            'duration': 22,
+            'timestamp': 1534855680,
+            'upload_date': '20180821',
+            'uploader': 'ANV',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # from https://sanfrancisco.cbslocal.com/2016/06/17/source-oakland-cop-on-leave-for-having-girlfriend-help-with-police-reports/
+        'url': 'anvato:DVzl9QRzox3ZZsP9bNu5Li3X7obQOnqP:3417601',
+        'only_matching': True,
+    }]
+
     def __init__(self, *args, **kwargs):
         super(AnvatoIE, self).__init__(*args, **kwargs)
         self.__server_time = None
@@ -169,7 +193,8 @@ class AnvatoIE(InfoExtractor):
             'api': {
                 'anvrid': anvrid,
                 'anvstk': md5_text('%s|%s|%d|%s' % (
-                    access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])),
+                    access_key, anvrid, server_time,
+                    self._ANVACK_TABLE.get(access_key, self._API_KEY))),
                 'anvts': server_time,
             },
         }
@@ -284,5 +309,6 @@ class AnvatoIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         access_key, video_id = mobj.group('access_key_or_mcp', 'id')
         if access_key not in self._ANVACK_TABLE:
-            access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key]
+            access_key = self._MCP_TO_ACCESS_KEY_TABLE.get(
+                access_key) or access_key
         return self._get_anvato_videos(access_key, video_id)

youtube_dl/extractor/aparat.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    merge_dicts,
     mimetype2ext,
     url_or_none,
 )
@@ -12,59 +13,83 @@ from ..utils import (
 class AparatIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.aparat.com/v/wP8On',
         'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
         'info_dict': {
             'id': 'wP8On',
             'ext': 'mp4',
             'title': 'تیم گلکسی 11 - زومیت',
-            'age_limit': 0,
+            'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028',
+            'duration': 231,
+            'timestamp': 1387394859,
+            'upload_date': '20131218',
+            'view_count': int,
         },
-        # 'skip': 'Extremely unreliable',
-    }
+    }, {
+        # multiple formats
+        'url': 'https://www.aparat.com/v/8dflw/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        # Note: There is an easier-to-parse configuration at
-        # http://www.aparat.com/video/video/config/videohash/%video_id
-        # but the URL in there does not work
-        webpage = self._download_webpage(
-            'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
-            video_id)
+        # Provides more metadata
+        webpage = self._download_webpage(url, video_id, fatal=False)
 
-        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
+        if not webpage:
+            # Note: There is an easier-to-parse configuration at
+            # http://www.aparat.com/video/video/config/videohash/%video_id
+            # but the URL in there does not work
+            webpage = self._download_webpage(
+                'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
+                video_id)
 
-        file_list = self._parse_json(
+        options = self._parse_json(
             self._search_regex(
-                r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage,
-                'file list'),
+                r'options\s*=\s*JSON\.parse\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1\s*\)',
+                webpage, 'options', group='value'),
             video_id)
 
+        player = options['plugins']['sabaPlayerPlugin']
+
         formats = []
-        for item in file_list[0]:
-            file_url = url_or_none(item.get('file'))
-            if not file_url:
-                continue
-            ext = mimetype2ext(item.get('type'))
-            label = item.get('label')
-            formats.append({
-                'url': file_url,
-                'ext': ext,
-                'format_id': label or ext,
-                'height': int_or_none(self._search_regex(
-                    r'(\d+)[pP]', label or '', 'height', default=None)),
-            })
-        self._sort_formats(formats)
+        for sources in player['multiSRC']:
+            for item in sources:
+                if not isinstance(item, dict):
+                    continue
+                file_url = url_or_none(item.get('src'))
+                if not file_url:
+                    continue
+                item_type = item.get('type')
+                if item_type == 'application/vnd.apple.mpegurl':
+                    formats.extend(self._extract_m3u8_formats(
+                        file_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        fatal=False))
+                else:
+                    ext = mimetype2ext(item.get('type'))
+                    label = item.get('label')
+                    formats.append({
+                        'url': file_url,
+                        'ext': ext,
+                        'format_id': 'http-%s' % (label or ext),
+                        'height': int_or_none(self._search_regex(
+                            r'(\d+)[pP]', label or '', 'height',
+                            default=None)),
+                    })
+        self._sort_formats(
+            formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 
-        thumbnail = self._search_regex(
-            r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
+        info = self._search_json_ld(webpage, video_id, default={})
 
-        return {
+        if not info.get('title'):
+            info['title'] = player['title']
+
+        return merge_dicts(info, {
             'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'age_limit': self._family_friendly_search(webpage),
+            'thumbnail': url_or_none(options.get('poster')),
+            'duration': int_or_none(player.get('duration')),
             'formats': formats,
-        }
+        })

youtube_dl/extractor/ard.py

@@ -21,7 +21,7 @@ from ..compat import compat_etree_fromstring
 
 class ARDMediathekIE(InfoExtractor):
     IE_NAME = 'ARD:mediathek'
-    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
         # available till 26.07.2022
@@ -37,6 +37,9 @@ class ARDMediathekIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
+        'only_matching': True,
     }, {
         # audio
         'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
@@ -282,3 +285,76 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
+
+
+class ARDBetaMediathekIE(InfoExtractor):
+    _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
+        'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
+        'info_dict': {
+            'display_id': 'die-robuste-roswita',
+            'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
+            'title': 'Tatort: Die robuste Roswita',
+            'description': r're:^Der Mord.*trüber ist als die Ilm.',
+            'duration': 5316,
+            'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard',
+            'upload_date': '20180826',
+            'ext': 'mp4',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')
+        data = self._parse_json(data_json, display_id)
+
+        res = {
+            'id': video_id,
+            'display_id': display_id,
+        }
+        formats = []
+        for widget in data.values():
+            if widget.get('_geoblocked'):
+                raise ExtractorError('This video is not available due to geoblocking', expected=True)
+
+            if '_duration' in widget:
+                res['duration'] = widget['_duration']
+            if 'clipTitle' in widget:
+                res['title'] = widget['clipTitle']
+            if '_previewImage' in widget:
+                res['thumbnail'] = widget['_previewImage']
+            if 'broadcastedOn' in widget:
+                res['upload_date'] = unified_strdate(widget['broadcastedOn'])
+            if 'synopsis' in widget:
+                res['description'] = widget['synopsis']
+            if '_subtitleUrl' in widget:
+                res['subtitles'] = {'de': [{
+                    'ext': 'ttml',
+                    'url': widget['_subtitleUrl'],
+                }]}
+            if '_quality' in widget:
+                format_url = widget['_stream']['json'][0]
+
+                if format_url.endswith('.f4m'):
+                    formats.extend(self._extract_f4m_formats(
+                        format_url + '?hdcore=3.11.0',
+                        video_id, f4m_id='hds', fatal=False))
+                elif format_url.endswith('m3u8'):
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                else:
+                    formats.append({
+                        'format_id': 'http-' + widget['_quality'],
+                        'url': format_url,
+                        'preference': 10,  # Plain HTTP, that's nice
+                    })
+
+        self._sort_formats(formats)
+        res['formats'] = formats
+
+        return res

youtube_dl/extractor/asiancrush.py

@@ -8,7 +8,6 @@ from .kaltura import KalturaIE
 from ..utils import (
     extract_attributes,
     remove_end,
-    urlencode_postdata,
 )
 
 
@@ -34,19 +33,40 @@ class AsianCrushIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        data = self._download_json(
-            'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id,
-            data=urlencode_postdata({
-                'postid': video_id,
-                'action': 'get_channel_kaltura_vars',
-            }))
+        webpage = self._download_webpage(url, video_id)
 
-        entry_id = data['entry_id']
+        entry_id, partner_id, title = [None] * 3
+
+        vars = self._parse_json(
+            self._search_regex(
+                r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
+                default='{}'), video_id, fatal=False)
+        if vars:
+            entry_id = vars.get('entry_id')
+            partner_id = vars.get('partner_id')
+            title = vars.get('vid_label')
+
+        if not entry_id:
+            entry_id = self._search_regex(
+                r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
+
+        player = self._download_webpage(
+            'https://api.asiancrush.com/embeddedVideoPlayer', video_id,
+            query={'id': entry_id})
+
+        kaltura_id = self._search_regex(
+            r'entry_id["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', player,
+            'kaltura id', group='id')
+
+        if not partner_id:
+            partner_id = self._search_regex(
+                r'/p(?:artner_id)?/(\d+)', player, 'partner id',
+                default='513551')
 
         return self.url_result(
-            'kaltura:%s:%s' % (data['partner_id'], entry_id),
-            ie=KalturaIE.ie_key(), video_id=entry_id,
-            video_title=data.get('vid_label'))
+            'kaltura:%s:%s' % (partner_id, kaltura_id),
+            ie=KalturaIE.ie_key(), video_id=kaltura_id,
+            video_title=title)
 
 
 class AsianCrushPlaylistIE(InfoExtractor):

youtube_dl/extractor/atvat.py

@@ -28,8 +28,10 @@ class ATVAtIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
         video_data = self._parse_json(unescapeHTML(self._search_regex(
-            r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="([^"]+)"',
-            webpage, 'player data')), display_id)['config']['initial_video']
+            [r'flashPlayerOptions\s*=\s*(["\'])(?P<json>(?:(?!\1).)+)\1',
+             r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="(?P<json>[^"]+)"'],
+            webpage, 'player data', group='json')),
+            display_id)['config']['initial_video']
 
         video_id = video_data['id']
         video_title = video_data['title']

youtube_dl/extractor/azmedien.py

@@ -1,213 +1,86 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from .kaltura import KalturaIE
-from ..utils import (
-    get_element_by_class,
-    get_element_by_id,
-    strip_or_none,
-    urljoin,
-)
 
 
-class AZMedienBaseIE(InfoExtractor):
-    def _kaltura_video(self, partner_id, entry_id):
-        return self.url_result(
-            'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
-            video_id=entry_id)
-
-
-class AZMedienIE(AZMedienBaseIE):
+class AZMedienIE(InfoExtractor):
     IE_DESC = 'AZ Medien videos'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?
-                        (?:
+                        (?P<host>
                             telezueri\.ch|
                             telebaern\.tv|
                             telem1\.ch
                         )/
-                        [0-9]+-show-[^/\#]+
-                        (?:
-                            /[0-9]+-episode-[^/\#]+
-                            (?:
-                                /[0-9]+-segment-(?:[^/\#]+\#)?|
-                                \#
-                            )|
-                            \#
+                        [^/]+/
+                        (?P<id>
+                            [^/]+-(?P<article_id>\d+)
                         )
-                        (?P<id>[^\#]+)
+                        (?:
+                            \#video=
+                            (?P<kaltura_id>
+                                [_0-9a-z]+
+                            )
+                        )?
                     '''
 
     _TESTS = [{
-        # URL with 'segment'
-        'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
+        'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
         'info_dict': {
-            'id': '1_2444peh4',
+            'id': '1_anruz3wy',
             'ext': 'mp4',
-            'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
-            'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
-            'uploader_id': 'TeleZ?ri',
-            'upload_date': '20161218',
-            'timestamp': 1482084490,
+            'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
+            'uploader_id': 'TVOnline',
+            'upload_date': '20180930',
+            'timestamp': 1538328802,
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        # URL with 'segment' and fragment:
-        'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
-        'only_matching': True
-    }, {
-        # URL with 'episode' and fragment:
-        'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
-        'only_matching': True
-    }, {
-        # URL with 'show' and fragment:
-        'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
+        'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
         'only_matching': True
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        partner_id = self._search_regex(
-            r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
-            webpage, 'kaltura partner id')
-        entry_id = self._html_search_regex(
-            r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
-            % re.escape(video_id), webpage, 'kaltura entry id', group='id')
-
-        return self._kaltura_video(partner_id, entry_id)
-
-
-class AZMedienPlaylistIE(AZMedienBaseIE):
-    IE_DESC = 'AZ Medien playlists'
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:www\.)?
-                        (?:
-                            telezueri\.ch|
-                            telebaern\.tv|
-                            telem1\.ch
-                        )/
-                        (?P<id>[0-9]+-
-                            (?:
-                                show|
-                                topic|
-                                themen
-                            )-[^/\#]+
-                            (?:
-                                /[0-9]+-episode-[^/\#]+
-                            )?
-                        )$
-                    '''
-
-    _TESTS = [{
-        # URL with 'episode'
-        'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
-        'info_dict': {
-            'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
-            'title': 'News - Donnerstag, 15. Dezember 2016',
-        },
-        'playlist_count': 9,
-    }, {
-        # URL with 'themen'
-        'url': 'http://www.telem1.ch/258-themen-tele-m1-classics',
-        'info_dict': {
-            'id': '258-themen-tele-m1-classics',
-            'title': 'Tele M1 Classics',
-        },
-        'playlist_mincount': 15,
-    }, {
-        # URL with 'topic', contains nested playlists
-        'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen',
-        'only_matching': True,
-    }, {
-        # URL with 'show' only
-        'url': 'http://www.telezueri.ch/86-show-talktaeglich',
-        'only_matching': True
-    }]
+    _PARTNER_ID = '1719221'
 
     def _real_extract(self, url):
-        show_id = self._match_id(url)
-        webpage = self._download_webpage(url, show_id)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        video_id = mobj.group('id')
+        entry_id = mobj.group('kaltura_id')
 
-        entries = []
+        if not entry_id:
+            api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0])
+            payload = {
+                'query': '''query VideoContext($articleId: ID!) {
+                    article: node(id: $articleId) {
+                      ... on Article {
+                        mainAssetRelation {
+                          asset {
+                            ... on VideoAsset {
+                              kalturaId
+                            }
+                          }
+                        }
+                      }
+                    }
+                  }''',
+                'variables': {'articleId': 'Article:%s' % mobj.group('article_id')},
+            }
+            json_data = self._download_json(
+                api_url, video_id, headers={
+                    'Content-Type': 'application/json',
+                },
+                data=json.dumps(payload).encode())
+            entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId']
 
-        partner_id = self._search_regex(
-            r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
-            webpage, 'kaltura partner id', default=None)
-
-        if partner_id:
-            entries = [
-                self._kaltura_video(partner_id, m.group('id'))
-                for m in re.finditer(
-                    r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
-
-        if not entries:
-            entries = [
-                self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
-                for m in re.finditer(
-                    r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
-
-        if not entries:
-            entries = [
-                # May contain nested playlists (e.g. [1]) thus no explicit
-                # ie_key
-                # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen)
-                self.url_result(urljoin(url, m.group('url')))
-                for m in re.finditer(
-                    r'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
-
-        title = self._search_regex(
-            r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
-            webpage, 'title',
-            default=strip_or_none(get_element_by_id(
-                'video-title', webpage)), group='title')
-
-        return self.playlist_result(entries, show_id, title)
-
-
-class AZMedienShowPlaylistIE(AZMedienBaseIE):
-    IE_DESC = 'AZ Medien show playlists'
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:www\.)?
-                        (?:
-                            telezueri\.ch|
-                            telebaern\.tv|
-                            telem1\.ch
-                        )/
-                        (?:
-                            all-episodes|
-                            alle-episoden
-                        )/
-                        (?P<id>[^/?#&]+)
-                    '''
-
-    _TEST = {
-        'url': 'http://www.telezueri.ch/all-episodes/astrotalk',
-        'info_dict': {
-            'id': 'astrotalk',
-            'title': 'TeleZüri: AstroTalk - alle episoden',
-            'description': 'md5:4c0f7e7d741d906004266e295ceb4a26',
-        },
-        'playlist_mincount': 13,
-    }
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        episodes = get_element_by_class('search-mobile-box', webpage)
-        entries = [self.url_result(
-            urljoin(url, m.group('url'))) for m in re.finditer(
-                r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)]
-        title = self._og_search_title(webpage, fatal=False)
-        description = self._og_search_description(webpage)
-        return self.playlist_result(entries, playlist_id, title, description)
+        return self.url_result(
+            'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
+            ie=KalturaIE.ie_key(), video_id=entry_id)

youtube_dl/extractor/bandcamp.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import random
 import re
 import time
@@ -16,15 +15,18 @@ from ..utils import (
     int_or_none,
     KNOWN_EXTENSIONS,
     parse_filesize,
+    str_or_none,
+    try_get,
     unescapeHTML,
     update_url_query,
     unified_strdate,
+    unified_timestamp,
     url_or_none,
 )
 
 
 class BandcampIE(InfoExtractor):
-    _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
+    _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'md5': 'c557841d5e50261777a6585648adf439',
@@ -36,13 +38,44 @@ class BandcampIE(InfoExtractor):
         },
         '_skip': 'There is a limit of 200 free downloads / month for the test song'
     }, {
+        # free download
         'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
-        'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
+        'md5': '853e35bf34aa1d6fe2615ae612564b36',
         'info_dict': {
             'id': '2650410135',
             'ext': 'aiff',
             'title': 'Ben Prunty - Lanius (Battle)',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Ben Prunty',
+            'timestamp': 1396508491,
+            'upload_date': '20140403',
+            'release_date': '20140403',
+            'duration': 260.877,
+            'track': 'Lanius (Battle)',
+            'track_number': 1,
+            'track_id': '2650410135',
+            'artist': 'Ben Prunty',
+            'album': 'FTL: Advanced Edition Soundtrack',
+        },
+    }, {
+        # no free download, mp3 128
+        'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
+        'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
+        'info_dict': {
+            'id': '2584466013',
+            'ext': 'mp3',
+            'title': 'Mastodon - Hail to Fire',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Mastodon',
+            'timestamp': 1322005399,
+            'upload_date': '20111122',
+            'release_date': '20040207',
+            'duration': 120.79,
+            'track': 'Hail to Fire',
+            'track_number': 5,
+            'track_id': '2584466013',
+            'artist': 'Mastodon',
+            'album': 'Call of the Mastodon',
         },
     }]
 
@@ -51,19 +84,23 @@ class BandcampIE(InfoExtractor):
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
         thumbnail = self._html_search_meta('og:image', webpage, default=None)
-        m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
-        if not m_download:
-            m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
-            if m_trackinfo:
-                json_code = m_trackinfo.group(1)
-                data = json.loads(json_code)[0]
-                track_id = compat_str(data['id'])
 
-                if not data.get('file'):
-                    raise ExtractorError('Not streamable', video_id=track_id, expected=True)
+        track_id = None
+        track = None
+        track_number = None
+        duration = None
 
-                formats = []
-                for format_id, format_url in data['file'].items():
+        formats = []
+        track_info = self._parse_json(
+            self._search_regex(
+                r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n',
+                webpage, 'track info', default='{}'), title)
+        if track_info:
+            file_ = track_info.get('file')
+            if isinstance(file_, dict):
+                for format_id, format_url in file_.items():
+                    if not url_or_none(format_url):
+                        continue
                     ext, abr_str = format_id.split('-', 1)
                     formats.append({
                         'format_id': format_id,
@@ -73,85 +110,110 @@ class BandcampIE(InfoExtractor):
                         'acodec': ext,
                         'abr': int_or_none(abr_str),
                     })
+            track = track_info.get('title')
+            track_id = str_or_none(track_info.get('track_id') or track_info.get('id'))
+            track_number = int_or_none(track_info.get('track_num'))
+            duration = float_or_none(track_info.get('duration'))
 
-                self._sort_formats(formats)
+        def extract(key):
+            return self._search_regex(
+                r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key,
+                webpage, key, default=None, group='value')
 
-                return {
-                    'id': track_id,
-                    'title': data['title'],
-                    'thumbnail': thumbnail,
-                    'formats': formats,
-                    'duration': float_or_none(data.get('duration')),
-                }
-            else:
-                raise ExtractorError('No free songs found')
+        artist = extract('artist')
+        album = extract('album_title')
+        timestamp = unified_timestamp(
+            extract('publish_date') or extract('album_publish_date'))
+        release_date = unified_strdate(extract('album_release_date'))
 
-        download_link = m_download.group(1)
-        video_id = self._search_regex(
-            r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
-            webpage, 'video id')
+        download_link = self._search_regex(
+            r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'download link', default=None, group='url')
+        if download_link:
+            track_id = self._search_regex(
+                r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
+                webpage, 'track id')
 
-        download_webpage = self._download_webpage(
-            download_link, video_id, 'Downloading free downloads page')
+            download_webpage = self._download_webpage(
+                download_link, track_id, 'Downloading free downloads page')
 
-        blob = self._parse_json(
-            self._search_regex(
-                r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
-                'blob', group='blob'),
-            video_id, transform_source=unescapeHTML)
+            blob = self._parse_json(
+                self._search_regex(
+                    r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
+                    'blob', group='blob'),
+                track_id, transform_source=unescapeHTML)
 
-        info = blob['digital_items'][0]
+            info = try_get(
+                blob, (lambda x: x['digital_items'][0],
+                       lambda x: x['download_items'][0]), dict)
+            if info:
+                downloads = info.get('downloads')
+                if isinstance(downloads, dict):
+                    if not track:
+                        track = info.get('title')
+                    if not artist:
+                        artist = info.get('artist')
+                    if not thumbnail:
+                        thumbnail = info.get('thumb_url')
 
-        downloads = info['downloads']
-        track = info['title']
+                    download_formats = {}
+                    download_formats_list = blob.get('download_formats')
+                    if isinstance(download_formats_list, list):
+                        for f in blob['download_formats']:
+                            name, ext = f.get('name'), f.get('file_extension')
+                            if all(isinstance(x, compat_str) for x in (name, ext)):
+                                download_formats[name] = ext.strip('.')
 
-        artist = info.get('artist')
-        title = '%s - %s' % (artist, track) if artist else track
+                    for format_id, f in downloads.items():
+                        format_url = f.get('url')
+                        if not format_url:
+                            continue
+                        # Stat URL generation algorithm is reverse engineered from
+                        # download_*_bundle_*.js
+                        stat_url = update_url_query(
+                            format_url.replace('/download/', '/statdownload/'), {
+                                '.rand': int(time.time() * 1000 * random.random()),
+                            })
+                        format_id = f.get('encoding_name') or format_id
+                        stat = self._download_json(
+                            stat_url, track_id, 'Downloading %s JSON' % format_id,
+                            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
+                            fatal=False)
+                        if not stat:
+                            continue
+                        retry_url = url_or_none(stat.get('retry_url'))
+                        if not retry_url:
+                            continue
+                        formats.append({
+                            'url': self._proto_relative_url(retry_url, 'http:'),
+                            'ext': download_formats.get(format_id),
+                            'format_id': format_id,
+                            'format_note': f.get('description'),
+                            'filesize': parse_filesize(f.get('size_mb')),
+                            'vcodec': 'none',
+                        })
 
-        download_formats = {}
-        for f in blob['download_formats']:
-            name, ext = f.get('name'), f.get('file_extension')
-            if all(isinstance(x, compat_str) for x in (name, ext)):
-                download_formats[name] = ext.strip('.')
-
-        formats = []
-        for format_id, f in downloads.items():
-            format_url = f.get('url')
-            if not format_url:
-                continue
-            # Stat URL generation algorithm is reverse engineered from
-            # download_*_bundle_*.js
-            stat_url = update_url_query(
-                format_url.replace('/download/', '/statdownload/'), {
-                    '.rand': int(time.time() * 1000 * random.random()),
-                })
-            format_id = f.get('encoding_name') or format_id
-            stat = self._download_json(
-                stat_url, video_id, 'Downloading %s JSON' % format_id,
-                transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
-                fatal=False)
-            if not stat:
-                continue
-            retry_url = url_or_none(stat.get('retry_url'))
-            if not retry_url:
-                continue
-            formats.append({
-                'url': self._proto_relative_url(retry_url, 'http:'),
-                'ext': download_formats.get(format_id),
-                'format_id': format_id,
-                'format_note': f.get('description'),
-                'filesize': parse_filesize(f.get('size_mb')),
-                'vcodec': 'none',
-            })
         self._sort_formats(formats)
 
+        title = '%s - %s' % (artist, track) if artist else track
+
+        if not duration:
+            duration = float_or_none(self._html_search_meta(
+                'duration', webpage, default=None))
+
         return {
-            'id': video_id,
+            'id': track_id,
             'title': title,
-            'thumbnail': info.get('thumb_url') or thumbnail,
-            'uploader': info.get('artist'),
-            'artist': artist,
+            'thumbnail': thumbnail,
+            'uploader': artist,
+            'timestamp': timestamp,
+            'release_date': release_date,
+            'duration': duration,
             'track': track,
+            'track_number': track_number,
+            'track_id': track_id,
+            'artist': artist,
+            'album': album,
             'formats': formats,
         }
 

youtube_dl/extractor/bbc.py

@@ -29,7 +29,7 @@ from ..compat import (
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _ID_REGEX = r'[pbw][\da-z]{7}'
+    _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?bbc\.co\.uk/
@@ -236,6 +236,12 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
             'only_matching': True,
+        }, {
+            'url': 'https://www.bbc.co.uk/programmes/m00005xn',
+            'only_matching': True,
+        }, {
+            'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s',
+            'only_matching': True,
         }]
 
     _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'

youtube_dl/extractor/bitchute.py

@@ -0,0 +1,120 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+import re
+
+from .common import InfoExtractor
+from ..utils import urlencode_postdata
+
+
+class BitChuteIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
+        'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
+        'info_dict': {
+            'id': 'szoMrox2JEI',
+            'ext': 'mp4',
+            'title': 'Fuck bitches get money',
+            'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Victoria X Rave',
+        },
+    }, {
+        'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
+                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
+            })
+
+        title = self._html_search_regex(
+            (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
+            webpage, 'title', default=None) or self._html_search_meta(
+            'description', webpage, 'title',
+            default=None) or self._og_search_description(webpage)
+
+        formats = [
+            {'url': mobj.group('url')}
+            for mobj in re.finditer(
+                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
+        self._sort_formats(formats)
+
+        description = self._html_search_regex(
+            r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
+            webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or self._html_search_meta(
+            'twitter:image:src', webpage, 'thumbnail')
+        uploader = self._html_search_regex(
+            r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
+            'uploader', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'formats': formats,
+        }
+
+
+class BitChuteChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.bitchute.com/channel/victoriaxrave/',
+        'playlist_mincount': 185,
+        'info_dict': {
+            'id': 'victoriaxrave',
+        },
+    }
+
+    _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
+
+    def _entries(self, channel_id):
+        channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
+        offset = 0
+        for page_num in itertools.count(1):
+            data = self._download_json(
+                '%sextend/' % channel_url, channel_id,
+                'Downloading channel page %d' % page_num,
+                data=urlencode_postdata({
+                    'csrfmiddlewaretoken': self._TOKEN,
+                    'name': '',
+                    'offset': offset,
+                }), headers={
+                    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                    'Referer': channel_url,
+                    'X-Requested-With': 'XMLHttpRequest',
+                    'Cookie': 'csrftoken=%s' % self._TOKEN,
+                })
+            if data.get('success') is False:
+                break
+            html = data.get('html')
+            if not html:
+                break
+            video_ids = re.findall(
+                r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
+                html)
+            if not video_ids:
+                break
+            offset += len(video_ids)
+            for video_id in video_ids:
+                yield self.url_result(
+                    'https://www.bitchute.com/video/%s' % video_id,
+                    ie=BitChuteIE.ie_key(), video_id=video_id)
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        return self.playlist_result(
+            self._entries(channel_id), playlist_id=channel_id)

youtube_dl/extractor/brightcove.py

@@ -1,8 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import base64
 import json
+import re
+import struct
 
 from .common import InfoExtractor
 from .adobepass import AdobePassIE
@@ -310,6 +312,10 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
                 expected=True)
 
+    def _brightcove_new_url_result(self, publisher_id, video_id):
+        brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
+        return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
+
     def _get_video_info(self, video_id, query, referer=None):
         headers = {}
         linkBase = query.get('linkBaseURL')
@@ -323,6 +329,28 @@ class BrightcoveLegacyIE(InfoExtractor):
             r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
             'error message', default=None)
         if error_msg is not None:
+            publisher_id = query.get('publisherId')
+            if publisher_id and publisher_id[0].isdigit():
+                publisher_id = publisher_id[0]
+            if not publisher_id:
+                player_key = query.get('playerKey')
+                if player_key and ',' in player_key[0]:
+                    player_key = player_key[0]
+                else:
+                    player_id = query.get('playerID')
+                    if player_id and player_id[0].isdigit():
+                        player_page = self._download_webpage(
+                            'http://link.brightcove.com/services/player/bcpid' + player_id[0],
+                            video_id, headers=headers, fatal=False)
+                        if player_page:
+                            player_key = self._search_regex(
+                                r'<param\s+name="playerKey"\s+value="([\w~,-]+)"',
+                                player_page, 'player key', fatal=False)
+                if player_key:
+                    enc_pub_id = player_key.split(',')[1].replace('~', '=')
+                    publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0]
+                if publisher_id:
+                    return self._brightcove_new_url_result(publisher_id, video_id)
             raise ExtractorError(
                 'brightcove said: %s' % error_msg, expected=True)
 
@@ -444,8 +472,12 @@ class BrightcoveLegacyIE(InfoExtractor):
                 else:
                     return ad_info
 
-        if 'url' not in info and not info.get('formats'):
-            raise ExtractorError('Unable to extract video url for %s' % video_id)
+        if not info.get('url') and not info.get('formats'):
+            uploader_id = info.get('uploader_id')
+            if uploader_id:
+                info.update(self._brightcove_new_url_result(uploader_id, video_id))
+            else:
+                raise ExtractorError('Unable to extract video url for %s' % video_id)
         return info
 
 

youtube_dl/extractor/ciscolive.py

@@ -0,0 +1,142 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    clean_html,
+    float_or_none,
+    int_or_none,
+    try_get,
+    urlencode_postdata,
+)
+
+
+class CiscoLiveBaseIE(InfoExtractor):
+    # These appear to be constant across all Cisco Live presentations
+    # and are not tied to any user session or event
+    RAINFOCUS_API_URL = 'https://events.rainfocus.com/api/%s'
+    RAINFOCUS_API_PROFILE_ID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz'
+    RAINFOCUS_WIDGET_ID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5647924234001/SyK2FdqjM_default/index.html?videoId=%s'
+
+    HEADERS = {
+        'Origin': 'https://ciscolive.cisco.com',
+        'rfApiProfileId': RAINFOCUS_API_PROFILE_ID,
+        'rfWidgetId': RAINFOCUS_WIDGET_ID,
+    }
+
+    def _call_api(self, ep, rf_id, query, referrer, note=None):
+        headers = self.HEADERS.copy()
+        headers['Referer'] = referrer
+        return self._download_json(
+            self.RAINFOCUS_API_URL % ep, rf_id, note=note,
+            data=urlencode_postdata(query), headers=headers)
+
+    def _parse_rf_item(self, rf_item):
+        event_name = rf_item.get('eventName')
+        title = rf_item['title']
+        description = clean_html(rf_item.get('abstract'))
+        presenter_name = try_get(rf_item, lambda x: x['participants'][0]['fullName'])
+        bc_id = rf_item['videos'][0]['url']
+        bc_url = self.BRIGHTCOVE_URL_TEMPLATE % bc_id
+        duration = float_or_none(try_get(rf_item, lambda x: x['times'][0]['length']))
+        location = try_get(rf_item, lambda x: x['times'][0]['room'])
+
+        if duration:
+            duration = duration * 60
+
+        return {
+            '_type': 'url_transparent',
+            'url': bc_url,
+            'ie_key': 'BrightcoveNew',
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'creator': presenter_name,
+            'location': location,
+            'series': event_name,
+        }
+
+
+class CiscoLiveSessionIE(CiscoLiveBaseIE):
+    _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/\??[^#]*#/session/(?P<id>[^/?&]+)'
+    _TEST = {
+        'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs',
+        'md5': 'c98acf395ed9c9f766941c70f5352e22',
+        'info_dict': {
+            'id': '5803694304001',
+            'ext': 'mp4',
+            'title': '13 Smart Automations to Monitor Your Cisco IOS Network',
+            'description': 'md5:ec4a436019e09a918dec17714803f7cc',
+            'timestamp': 1530305395,
+            'upload_date': '20180629',
+            'uploader_id': '5647924234001',
+            'location': '16B Mezz.',
+        },
+    }
+
+    def _real_extract(self, url):
+        rf_id = self._match_id(url)
+        rf_result = self._call_api('session', rf_id, {'id': rf_id}, url)
+        return self._parse_rf_item(rf_result['items'][0])
+
+
+class CiscoLiveSearchIE(CiscoLiveBaseIE):
+    _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/'
+    _TESTS = [{
+        'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/',
+        'info_dict': {
+            'title': 'Search query',
+        },
+        'playlist_count': 5,
+    }, {
+        'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if CiscoLiveSessionIE.suitable(url) else super(CiscoLiveSearchIE, cls).suitable(url)
+
+    @staticmethod
+    def _check_bc_id_exists(rf_item):
+        return int_or_none(try_get(rf_item, lambda x: x['videos'][0]['url'])) is not None
+
+    def _entries(self, query, url):
+        query['size'] = 50
+        query['from'] = 0
+        for page_num in itertools.count(1):
+            results = self._call_api(
+                'search', None, query, url,
+                'Downloading search JSON page %d' % page_num)
+            sl = try_get(results, lambda x: x['sectionList'][0], dict)
+            if sl:
+                results = sl
+            items = results.get('items')
+            if not items or not isinstance(items, list):
+                break
+            for item in items:
+                if not isinstance(item, dict):
+                    continue
+                if not self._check_bc_id_exists(item):
+                    continue
+                yield self._parse_rf_item(item)
+            size = int_or_none(results.get('size'))
+            if size is not None:
+                query['size'] = size
+            total = int_or_none(results.get('total'))
+            if total is not None and query['from'] + query['size'] > total:
+                break
+            query['from'] += query['size']
+
+    def _real_extract(self, url):
+        query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        query['type'] = 'session'
+        return self.playlist_result(
+            self._entries(query, url), playlist_title='Search query')

youtube_dl/extractor/cliphunter.py

@@ -1,19 +1,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
-
-
-_translation_table = {
-    'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
-    'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
-    'y': 'l', 'z': 'i',
-    '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
-}
-
-
-def _decode(s):
-    return ''.join(_translation_table.get(c, c) for c in s)
+from ..utils import (
+    int_or_none,
+    url_or_none,
+)
 
 
 class CliphunterIE(InfoExtractor):
@@ -60,14 +51,14 @@ class CliphunterIE(InfoExtractor):
 
         formats = []
         for format_id, f in gexo_files.items():
-            video_url = f.get('url')
+            video_url = url_or_none(f.get('url'))
             if not video_url:
                 continue
             fmt = f.get('fmt')
             height = f.get('h')
             format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
             formats.append({
-                'url': _decode(video_url),
+                'url': video_url,
                 'format_id': format_id,
                 'width': int_or_none(f.get('w')),
                 'height': int_or_none(height),

youtube_dl/extractor/clyp.py

@@ -1,15 +1,19 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     float_or_none,
-    parse_iso8601,
+    unified_timestamp,
 )
 
 
 class ClypIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://clyp.it/ojz2wfah',
         'md5': '1d4961036c41247ecfdcc439c0cddcbb',
         'info_dict': {
@@ -21,13 +25,34 @@ class ClypIE(InfoExtractor):
             'timestamp': 1443515251,
             'upload_date': '20150929',
         },
-    }
+    }, {
+        'url': 'https://clyp.it/b04p1odi?token=b0078e077e15835845c528a44417719d',
+        'info_dict': {
+            'id': 'b04p1odi',
+            'ext': 'mp3',
+            'title': 'GJ! (Reward Edit)',
+            'description': 'Metal Resistance (THE ONE edition)',
+            'duration': 177.789,
+            'timestamp': 1528241278,
+            'upload_date': '20180605',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         audio_id = self._match_id(url)
 
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        token = qs.get('token', [None])[0]
+
+        query = {}
+        if token:
+            query['token'] = token
+
         metadata = self._download_json(
-            'https://api.clyp.it/%s' % audio_id, audio_id)
+            'https://api.clyp.it/%s' % audio_id, audio_id, query=query)
 
         formats = []
         for secure in ('', 'Secure'):
@@ -45,7 +70,7 @@ class ClypIE(InfoExtractor):
         title = metadata['Title']
         description = metadata.get('Description')
         duration = float_or_none(metadata.get('Duration'))
-        timestamp = parse_iso8601(metadata.get('DateCreated'))
+        timestamp = unified_timestamp(metadata.get('DateCreated'))
 
         return {
             'id': audio_id,

youtube_dl/extractor/cnbc.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+
 from .common import InfoExtractor
 from ..utils import smuggle_url
 
@@ -34,3 +35,32 @@ class CNBCIE(InfoExtractor):
                 {'force_smil_url': True}),
             'id': video_id,
         }
+
+
+class CNBCVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cnbc\.com/video/(?:[^/]+/)+(?P<id>[^./?#&]+)'
+    _TEST = {
+        'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
+        'info_dict': {
+            'id': '7000031301',
+            'ext': 'mp4',
+            'title': "Trump: I don't necessarily agree with raising rates",
+            'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
+            'timestamp': 1531958400,
+            'upload_date': '20180719',
+            'uploader': 'NBCU-CNBC',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id,
+            'video id')
+        return self.url_result(
+            'http://video.cnbc.com/gallery/?video=%s' % video_id,
+            CNBCIE.ie_key())

youtube_dl/extractor/common.py

@@ -69,6 +69,7 @@ from ..utils import (
     update_url_query,
     urljoin,
     url_basename,
+    url_or_none,
     xpath_element,
     xpath_text,
     xpath_with_ns,
@@ -211,6 +212,11 @@ class InfoExtractor(object):
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
     uploader_url:   Full URL to a personal webpage of the video uploader.
+    channel:        Full name of the channel the video is uploaded on.
+                    Note that channel fields may or may not repeat uploader
+                    fields. This depends on a particular extractor.
+    channel_id:     Id of the channel.
+    channel_url:    Full URL to a channel webpage.
     location:       Physical location where the video was filmed.
     subtitles:      The available subtitles as a dictionary in the format
                     {tag: subformats}. "tag" is usually a language code, and
@@ -600,6 +606,11 @@ class InfoExtractor(object):
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if isinstance(err, compat_urllib_error.HTTPError):
                 if self.__can_accept_status_code(err, expected_status):
+                    # Retain reference to error to prevent file object from
+                    # being closed before it can be read. Works around the
+                    # effects of <https://bugs.python.org/issue15002>
+                    # introduced in Python 3.4.1.
+                    err.fp._error = err
                     return err.fp
 
             if errnote is False:
@@ -1208,10 +1219,10 @@ class InfoExtractor(object):
         def extract_video_object(e):
             assert e['@type'] == 'VideoObject'
             info.update({
-                'url': e.get('contentUrl'),
+                'url': url_or_none(e.get('contentUrl')),
                 'title': unescapeHTML(e.get('name')),
                 'description': unescapeHTML(e.get('description')),
-                'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
+                'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')),
                 'duration': parse_duration(e.get('duration')),
                 'timestamp': unified_timestamp(e.get('uploadDate')),
                 'filesize': float_or_none(e.get('contentSize')),
@@ -1701,9 +1712,9 @@ class InfoExtractor(object):
                 # However, this is not always respected, for example, [2]
                 # contains EXT-X-STREAM-INF tag which references AUDIO
                 # rendition group but does not have CODECS and despite
-                # referencing audio group an audio group, it represents
-                # a complete (with audio and video) format. So, for such cases
-                # we will ignore references to rendition groups and treat them
+                # referencing an audio group it represents a complete
+                # (with audio and video) format. So, for such cases we will
+                # ignore references to rendition groups and treat them
                 # as complete formats.
                 if audio_group_id and codecs and f.get('vcodec') != 'none':
                     audio_group = groups.get(audio_group_id)

youtube_dl/extractor/crunchyroll.py

@@ -3,11 +3,13 @@ from __future__ import unicode_literals
 
 import re
 import json
+import xml.etree.ElementTree as etree
 import zlib
 
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .common import InfoExtractor
+from .vrv import VRVIE
 from ..compat import (
     compat_b64decode,
     compat_etree_fromstring,
@@ -18,6 +20,8 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     bytes_to_intlist,
+    extract_attributes,
+    float_or_none,
     intlist_to_bytes,
     int_or_none,
     lowercase_escape,
@@ -26,7 +30,6 @@ from ..utils import (
     unified_strdate,
     urlencode_postdata,
     xpath_text,
-    extract_attributes,
 )
 from ..aes import (
     aes_cbc_decrypt,
@@ -43,7 +46,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         data['req'] = 'RpcApi' + method
         data = compat_urllib_parse_urlencode(data).encode('utf-8')
         return self._download_xml(
-            'http://www.crunchyroll.com/xml/',
+            'https://www.crunchyroll.com/xml/',
             video_id, note, fatal=False, data=data, headers={
                 'Content-Type': 'application/x-www-form-urlencoded',
             })
@@ -139,7 +142,8 @@ class CrunchyrollBaseIE(InfoExtractor):
             parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
 
 
-class CrunchyrollIE(CrunchyrollBaseIE):
+class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
+    IE_NAME = 'crunchyroll'
     _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
@@ -148,7 +152,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'ext': 'mp4',
             'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
             'description': 'md5:2d17137920c64f2f49981a7797d275ef',
-            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Yomiuri Telecasting Corporation (YTV)',
             'upload_date': '20131013',
             'url': 're:(?!.*&amp)',
@@ -221,7 +225,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         'info_dict': {
             'id': '535080',
             'ext': 'mp4',
-            'title': '11eyes Episode 1 – Piros éjszaka - Red Night',
+            'title': '11eyes Episode 1 – Red Night ~ Piros éjszaka',
             'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
             'uploader': 'Marvelous AQL Inc.',
             'upload_date': '20091021',
@@ -395,7 +399,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'Downloading subtitles for ' + sub_name, data={
                     'subtitle_script_id': sub_id,
                 })
-            if sub_doc is None:
+            if not isinstance(sub_doc, etree.Element):
                 continue
             sid = sub_doc.get('id')
             iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -437,13 +441,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         if 'To view this, please log in to verify you are 18 or older.' in webpage:
             self.raise_login_required()
 
+        media = self._parse_json(self._search_regex(
+            r'vilos\.config\.media\s*=\s*({.+?});',
+            webpage, 'vilos media', default='{}'), video_id)
+        media_metadata = media.get('metadata') or {}
+
+        language = self._search_regex(
+            r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1',
+            webpage, 'language', default=None, group='lang')
+
         video_title = self._html_search_regex(
             r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
             webpage, 'video_title')
         video_title = re.sub(r' {2,}', ' ', video_title)
-        video_description = self._parse_json(self._html_search_regex(
+        video_description = (self._parse_json(self._html_search_regex(
             r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
-            webpage, 'description', default='{}'), video_id).get('description')
+            webpage, 'description', default='{}'), video_id) or media_metadata).get('description')
         if video_description:
             video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
         video_upload_date = self._html_search_regex(
@@ -456,92 +469,113 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
             webpage, 'video_uploader', fatal=False)
 
-        available_fmts = []
-        for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
-            attrs = extract_attributes(a)
-            href = attrs.get('href')
-            if href and '/freetrial' in href:
-                continue
-            available_fmts.append(fmt)
-        if not available_fmts:
-            for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
-                available_fmts = re.findall(p, webpage)
-                if available_fmts:
-                    break
-        video_encode_ids = []
         formats = []
-        for fmt in available_fmts:
-            stream_quality, stream_format = self._FORMAT_IDS[fmt]
-            video_format = fmt + 'p'
-            stream_infos = []
-            streamdata = self._call_rpc_api(
-                'VideoPlayer_GetStandardConfig', video_id,
-                'Downloading media info for %s' % video_format, data={
-                    'media_id': video_id,
-                    'video_format': stream_format,
-                    'video_quality': stream_quality,
-                    'current_page': url,
-                })
-            if streamdata is not None:
-                stream_info = streamdata.find('./{default}preload/stream_info')
-                if stream_info is not None:
+        for stream in media.get('streams', []):
+            audio_lang = stream.get('audio_lang')
+            hardsub_lang = stream.get('hardsub_lang')
+            vrv_formats = self._extract_vrv_formats(
+                stream.get('url'), video_id, stream.get('format'),
+                audio_lang, hardsub_lang)
+            for f in vrv_formats:
+                if not hardsub_lang:
+                    f['preference'] = 1
+                language_preference = 0
+                if audio_lang == language:
+                    language_preference += 1
+                if hardsub_lang == language:
+                    language_preference += 1
+                if language_preference:
+                    f['language_preference'] = language_preference
+            formats.extend(vrv_formats)
+        if not formats:
+            available_fmts = []
+            for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
+                attrs = extract_attributes(a)
+                href = attrs.get('href')
+                if href and '/freetrial' in href:
+                    continue
+                available_fmts.append(fmt)
+            if not available_fmts:
+                for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
+                    available_fmts = re.findall(p, webpage)
+                    if available_fmts:
+                        break
+            if not available_fmts:
+                available_fmts = self._FORMAT_IDS.keys()
+            video_encode_ids = []
+
+            for fmt in available_fmts:
+                stream_quality, stream_format = self._FORMAT_IDS[fmt]
+                video_format = fmt + 'p'
+                stream_infos = []
+                streamdata = self._call_rpc_api(
+                    'VideoPlayer_GetStandardConfig', video_id,
+                    'Downloading media info for %s' % video_format, data={
+                        'media_id': video_id,
+                        'video_format': stream_format,
+                        'video_quality': stream_quality,
+                        'current_page': url,
+                    })
+                if isinstance(streamdata, etree.Element):
+                    stream_info = streamdata.find('./{default}preload/stream_info')
+                    if stream_info is not None:
+                        stream_infos.append(stream_info)
+                stream_info = self._call_rpc_api(
+                    'VideoEncode_GetStreamInfo', video_id,
+                    'Downloading stream info for %s' % video_format, data={
+                        'media_id': video_id,
+                        'video_format': stream_format,
+                        'video_encode_quality': stream_quality,
+                    })
+                if isinstance(stream_info, etree.Element):
                     stream_infos.append(stream_info)
-            stream_info = self._call_rpc_api(
-                'VideoEncode_GetStreamInfo', video_id,
-                'Downloading stream info for %s' % video_format, data={
-                    'media_id': video_id,
-                    'video_format': stream_format,
-                    'video_encode_quality': stream_quality,
-                })
-            if stream_info is not None:
-                stream_infos.append(stream_info)
-            for stream_info in stream_infos:
-                video_encode_id = xpath_text(stream_info, './video_encode_id')
-                if video_encode_id in video_encode_ids:
-                    continue
-                video_encode_ids.append(video_encode_id)
+                for stream_info in stream_infos:
+                    video_encode_id = xpath_text(stream_info, './video_encode_id')
+                    if video_encode_id in video_encode_ids:
+                        continue
+                    video_encode_ids.append(video_encode_id)
 
-                video_file = xpath_text(stream_info, './file')
-                if not video_file:
-                    continue
-                if video_file.startswith('http'):
-                    formats.extend(self._extract_m3u8_formats(
-                        video_file, video_id, 'mp4', entry_protocol='m3u8_native',
-                        m3u8_id='hls', fatal=False))
-                    continue
-
-                video_url = xpath_text(stream_info, './host')
-                if not video_url:
-                    continue
-                metadata = stream_info.find('./metadata')
-                format_info = {
-                    'format': video_format,
-                    'height': int_or_none(xpath_text(metadata, './height')),
-                    'width': int_or_none(xpath_text(metadata, './width')),
-                }
-
-                if '.fplive.net/' in video_url:
-                    video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
-                    parsed_video_url = compat_urlparse.urlparse(video_url)
-                    direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
-                        netloc='v.lvlt.crcdn.net',
-                        path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
-                    if self._is_valid_url(direct_video_url, video_id, video_format):
-                        format_info.update({
-                            'format_id': 'http-' + video_format,
-                            'url': direct_video_url,
-                        })
-                        formats.append(format_info)
+                    video_file = xpath_text(stream_info, './file')
+                    if not video_file:
+                        continue
+                    if video_file.startswith('http'):
+                        formats.extend(self._extract_m3u8_formats(
+                            video_file, video_id, 'mp4', entry_protocol='m3u8_native',
+                            m3u8_id='hls', fatal=False))
                         continue
 
-                format_info.update({
-                    'format_id': 'rtmp-' + video_format,
-                    'url': video_url,
-                    'play_path': video_file,
-                    'ext': 'flv',
-                })
-                formats.append(format_info)
-        self._sort_formats(formats, ('height', 'width', 'tbr', 'fps'))
+                    video_url = xpath_text(stream_info, './host')
+                    if not video_url:
+                        continue
+                    metadata = stream_info.find('./metadata')
+                    format_info = {
+                        'format': video_format,
+                        'height': int_or_none(xpath_text(metadata, './height')),
+                        'width': int_or_none(xpath_text(metadata, './width')),
+                    }
+
+                    if '.fplive.net/' in video_url:
+                        video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
+                        parsed_video_url = compat_urlparse.urlparse(video_url)
+                        direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
+                            netloc='v.lvlt.crcdn.net',
+                            path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
+                        if self._is_valid_url(direct_video_url, video_id, video_format):
+                            format_info.update({
+                                'format_id': 'http-' + video_format,
+                                'url': direct_video_url,
+                            })
+                            formats.append(format_info)
+                            continue
+
+                    format_info.update({
+                        'format_id': 'rtmp-' + video_format,
+                        'url': video_url,
+                        'play_path': video_file,
+                        'ext': 'flv',
+                    })
+                    formats.append(format_info)
+        self._sort_formats(formats, ('preference', 'language_preference', 'height', 'width', 'tbr', 'fps'))
 
         metadata = self._call_rpc_api(
             'VideoPlayer_GetMediaMetadata', video_id,
@@ -549,16 +583,38 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'media_id': video_id,
             })
 
-        subtitles = self.extract_subtitles(video_id, webpage)
+        subtitles = {}
+        for subtitle in media.get('subtitles', []):
+            subtitle_url = subtitle.get('url')
+            if not subtitle_url:
+                continue
+            subtitles.setdefault(subtitle.get('language', 'enUS'), []).append({
+                'url': subtitle_url,
+                'ext': subtitle.get('format', 'ass'),
+            })
+        if not subtitles:
+            subtitles = self.extract_subtitles(video_id, webpage)
 
         # webpage provide more accurate data than series_title from XML
         series = self._html_search_regex(
             r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
             webpage, 'series', fatal=False)
-        season = xpath_text(metadata, 'series_title')
 
-        episode = xpath_text(metadata, 'episode_title')
-        episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+        season = episode = episode_number = duration = thumbnail = None
+
+        if isinstance(metadata, etree.Element):
+            season = xpath_text(metadata, 'series_title')
+            episode = xpath_text(metadata, 'episode_title')
+            episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+            duration = float_or_none(media_metadata.get('duration'), 1000)
+            thumbnail = xpath_text(metadata, 'episode_image_url')
+
+        if not episode:
+            episode = media_metadata.get('title')
+        if not episode_number:
+            episode_number = int_or_none(media_metadata.get('episode_number'))
+        if not thumbnail:
+            thumbnail = media_metadata.get('thumbnail', {}).get('url')
 
         season_number = int_or_none(self._search_regex(
             r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
@@ -568,7 +624,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'id': video_id,
             'title': video_title,
             'description': video_description,
-            'thumbnail': xpath_text(metadata, 'episode_image_url'),
+            'duration': duration,
+            'thumbnail': thumbnail,
             'uploader': video_uploader,
             'upload_date': video_upload_date,
             'series': series,

youtube_dl/extractor/cwtv.py

@@ -3,8 +3,12 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
+    parse_age_limit,
     parse_iso8601,
+    smuggle_url,
+    str_or_none,
 )
 
 
@@ -40,10 +44,15 @@ class CWTVIE(InfoExtractor):
             'duration': 1263,
             'series': 'Whose Line Is It Anyway?',
             'season_number': 11,
-            'season': '11',
             'episode_number': 20,
             'upload_date': '20151006',
             'timestamp': 1444107300,
+            'age_limit': 14,
+            'uploader': 'CWTV',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
         },
     }, {
         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
@@ -58,60 +67,31 @@ class CWTVIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = None
-        formats = []
-        for partner in (154, 213):
-            vdata = self._download_json(
-                'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/%d?format=json' % (video_id, partner), video_id, fatal=False)
-            if not vdata:
-                continue
-            video_data = vdata
-            for quality, quality_data in vdata.get('videos', {}).items():
-                quality_url = quality_data.get('uri')
-                if not quality_url:
-                    continue
-                if quality == 'variantplaylist':
-                    formats.extend(self._extract_m3u8_formats(
-                        quality_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
-                else:
-                    tbr = int_or_none(quality_data.get('bitrate'))
-                    format_id = 'http' + ('-%d' % tbr if tbr else '')
-                    if self._is_valid_url(quality_url, video_id, format_id):
-                        formats.append({
-                            'format_id': format_id,
-                            'url': quality_url,
-                            'tbr': tbr,
-                        })
-        video_metadata = video_data['assetFields']
-        ism_url = video_metadata.get('smoothStreamingUrl')
-        if ism_url:
-            formats.extend(self._extract_ism_formats(
-                ism_url, video_id, ism_id='mss', fatal=False))
-        self._sort_formats(formats)
+        data = self._download_json(
+            'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id,
+            video_id)
+        if data.get('result') != 'ok':
+            raise ExtractorError(data['msg'], expected=True)
+        video_data = data['video']
+        title = video_data['title']
+        mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id
 
-        thumbnails = [{
-            'url': image['uri'],
-            'width': image.get('width'),
-            'height': image.get('height'),
-        } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
-
-        subtitles = {
-            'en': [{
-                'url': video_metadata['UnicornCcUrl'],
-            }],
-        } if video_metadata.get('UnicornCcUrl') else None
+        season = str_or_none(video_data.get('season'))
+        episode = str_or_none(video_data.get('episode'))
+        if episode and season:
+            episode = episode.lstrip(season)
 
         return {
+            '_type': 'url_transparent',
             'id': video_id,
-            'title': video_metadata['title'],
-            'description': video_metadata.get('description'),
-            'duration': int_or_none(video_metadata.get('duration')),
-            'series': video_metadata.get('seriesName'),
-            'season_number': int_or_none(video_metadata.get('seasonNumber')),
-            'season': video_metadata.get('seasonName'),
-            'episode_number': int_or_none(video_metadata.get('episodeNumber')),
-            'timestamp': parse_iso8601(video_data.get('startTime')),
-            'thumbnails': thumbnails,
-            'formats': formats,
-            'subtitles': subtitles,
+            'title': title,
+            'url': smuggle_url(mpx_url, {'force_smil_url': True}),
+            'description': video_data.get('description_long'),
+            'duration': int_or_none(video_data.get('duration_secs')),
+            'series': video_data.get('series_name'),
+            'season_number': int_or_none(season),
+            'episode_number': int_or_none(episode),
+            'timestamp': parse_iso8601(video_data.get('start_time')),
+            'age_limit': parse_age_limit(video_data.get('rating')),
+            'ie_key': 'ThePlatform',
         }

youtube_dl/extractor/dailymail.py

@@ -49,6 +49,9 @@ class DailyMailIE(InfoExtractor):
             'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
 
         video_sources = self._download_json(sources_url, video_id)
+        body = video_sources.get('body')
+        if body:
+            video_sources = body
 
         formats = []
         for rendition in video_sources['renditions']:

youtube_dl/extractor/dailymotion.py

@@ -22,7 +22,10 @@ from ..utils import (
     parse_iso8601,
     sanitized_Request,
     str_to_int,
+    try_get,
     unescapeHTML,
+    update_url_query,
+    url_or_none,
     urlencode_postdata,
 )
 
@@ -171,10 +174,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
              r'__PLAYER_CONFIG__\s*=\s*({.+?});'],
             webpage, 'player v5', default=None)
         if player_v5:
-            player = self._parse_json(player_v5, video_id)
-            metadata = player['metadata']
+            player = self._parse_json(player_v5, video_id, fatal=False) or {}
+            metadata = try_get(player, lambda x: x['metadata'], dict)
+            if not metadata:
+                metadata_url = url_or_none(try_get(
+                    player, lambda x: x['context']['metadata_template_url1']))
+                if metadata_url:
+                    metadata_url = metadata_url.replace(':videoId', video_id)
+                else:
+                    metadata_url = update_url_query(
+                        'https://www.dailymotion.com/player/metadata/video/%s'
+                        % video_id, {
+                            'embedder': url,
+                            'integration': 'inline',
+                            'GK_PV5_NEON': '1',
+                        })
+                metadata = self._download_json(
+                    metadata_url, video_id, 'Downloading metadata JSON')
 
-            if metadata.get('error', {}).get('type') == 'password_protected':
+            if try_get(metadata, lambda x: x['error']['type']) == 'password_protected':
                 password = self._downloader.params.get('videopassword')
                 if password:
                     r = int(metadata['id'][1:], 36)

youtube_dl/extractor/dtube.py

@@ -59,7 +59,7 @@ class DTubeIE(InfoExtractor):
             try:
                 self.to_screen('%s: Checking %s video format URL' % (video_id, format_id))
                 self._downloader._opener.open(video_url, timeout=5).close()
-            except timeout as e:
+            except timeout:
                 self.to_screen(
                     '%s: %s URL is invalid, skipping' % (video_id, format_id))
                 continue

youtube_dl/extractor/eporner.py

@@ -9,6 +9,7 @@ from ..utils import (
     encode_base_n,
     ExtractorError,
     int_or_none,
+    merge_dicts,
     parse_duration,
     str_to_int,
     url_or_none,
@@ -25,10 +26,16 @@ class EpornerIE(InfoExtractor):
             'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
             'ext': 'mp4',
             'title': 'Infamous Tiffany Teen Strip Tease Video',
+            'description': 'md5:764f39abf932daafa37485eb46efa152',
+            'timestamp': 1232520922,
+            'upload_date': '20090121',
             'duration': 1838,
             'view_count': int,
             'age_limit': 18,
         },
+        'params': {
+            'proxy': '127.0.0.1:8118'
+        }
     }, {
         # New (May 2016) URL layout
         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
@@ -104,12 +111,15 @@ class EpornerIE(InfoExtractor):
                     })
         self._sort_formats(formats)
 
-        duration = parse_duration(self._html_search_meta('duration', webpage))
+        json_ld = self._search_json_ld(webpage, display_id, default={})
+
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, default=None))
         view_count = str_to_int(self._search_regex(
             r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
             webpage, 'view count', fatal=False))
 
-        return {
+        return merge_dicts(json_ld, {
             'id': video_id,
             'display_id': display_id,
             'title': title,
@@ -117,4 +127,4 @@ class EpornerIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
             'age_limit': 18,
-        }
+        })

youtube_dl/extractor/expressen.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -11,7 +13,13 @@ from ..utils import (
 
 
 class ExpressenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?expressen\.se/
+                        (?:(?:tvspelare/video|videoplayer/embed)/)?
+                        tv/(?:[^/]+/)*
+                        (?P<id>[^/?#&]+)
+                    '''
     _TESTS = [{
         'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
         'md5': '2fbbe3ca14392a6b1b36941858d33a45',
@@ -28,8 +36,21 @@ class ExpressenIE(InfoExtractor):
     }, {
         'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.expressen.se/tvspelare/video/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url') for mobj in re.finditer(
+                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1',
+                webpage)]
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
 

youtube_dl/extractor/extractors.py

@@ -54,6 +54,7 @@ from .appletrailers import (
 from .archiveorg import ArchiveOrgIE
 from .arkena import ArkenaIE
 from .ard import (
+    ARDBetaMediathekIE,
     ARDIE,
     ARDMediathekIE,
 )
@@ -87,11 +88,7 @@ from .awaan import (
     AWAANLiveIE,
     AWAANSeasonIE,
 )
-from .azmedien import (
-    AZMedienIE,
-    AZMedienPlaylistIE,
-    AZMedienShowPlaylistIE,
-)
+from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
@@ -118,6 +115,10 @@ from .bilibili import (
     BiliBiliBangumiIE,
 )
 from .biobiochiletv import BioBioChileTVIE
+from .bitchute import (
+    BitChuteIE,
+    BitChuteChannelIE,
+)
 from .biqle import BIQLEIE
 from .bleacherreport import (
     BleacherReportIE,
@@ -193,6 +194,10 @@ from .chirbit import (
     ChirbitProfileIE,
 )
 from .cinchcast import CinchcastIE
+from .ciscolive import (
+    CiscoLiveSessionIE,
+    CiscoLiveSearchIE,
+)
 from .cjsw import CJSWIE
 from .cliphunter import CliphunterIE
 from .clippit import ClippitIE
@@ -204,7 +209,10 @@ from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .clyp import ClypIE
 from .cmt import CMTIE
-from .cnbc import CNBCIE
+from .cnbc import (
+    CNBCIE,
+    CNBCVideoIE,
+)
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
@@ -516,6 +524,7 @@ from .keezmovies import KeezMoviesIE
 from .ketnet import KetnetIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
+from .kinopoisk import KinoPoiskIE
 from .keek import KeekIE
 from .konserthusetplay import KonserthusetPlayIE
 from .kontrtube import KontrTubeIE
@@ -534,6 +543,7 @@ from .la7 import LA7IE
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
+    EHFTVIE,
     ITTFIE,
 )
 from .lci import LCIIE
@@ -563,6 +573,10 @@ from .limelight import (
     LimelightChannelListIE,
 )
 from .line import LineTVIE
+from .linkedin import (
+    LinkedInLearningIE,
+    LinkedInLearningCourseIE,
+)
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -736,7 +750,10 @@ from .nonktube import NonkTubeIE
 from .noovo import NoovoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
-from .nova import NovaIE
+from .nova import (
+    NovaEmbedIE,
+    NovaIE,
+)
 from .novamov import (
     AuroraVidIE,
     CloudTimeIE,
@@ -895,7 +912,10 @@ from .rai import (
     RaiPlayPlaylistIE,
     RaiIE,
 )
-from .raywenderlich import RayWenderlichIE
+from .raywenderlich import (
+    RayWenderlichIE,
+    RayWenderlichCourseIE,
+)
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
 from .redbulltv import RedBullTVIE
@@ -1031,7 +1051,7 @@ from .spike import (
 )
 from .stitcher import StitcherIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxEmbedIE
+from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
 from .springboardplatform import SpringboardPlatformIE
 from .sprout import SproutIE
@@ -1074,6 +1094,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .tele5 import Tele5IE
 from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
@@ -1103,6 +1124,10 @@ from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
 from .threeqsdn import ThreeQSDNIE
+from .tiktok import (
+    TikTokIE,
+    TikTokUserIE,
+)
 from .tinypic import TinyPicIE
 from .tmz import (
     TMZIE,
@@ -1140,7 +1165,6 @@ from .tv2 import (
     TV2ArticleIE,
 )
 from .tv2hu import TV2HuIE
-from .tv3 import TV3IE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
 from .tva import TVAIE
@@ -1170,12 +1194,14 @@ from .tvp import (
 from .tvplay import (
     TVPlayIE,
     ViafreeIE,
+    TVPlayHomeIE,
 )
 from .tvplayer import TVPlayerIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
 from .twentythreevideo import TwentyThreeVideoIE
+from .twitcasting import TwitCastingIE
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -1281,6 +1307,7 @@ from .vimeo import (
     VimeoReviewIE,
     VimeoUserIE,
     VimeoWatchLaterIE,
+    VHXEmbedIE,
 )
 from .vimple import VimpleIE
 from .vine import (
@@ -1368,6 +1395,7 @@ from .wsj import (
     WSJIE,
     WSJArticleIE,
 )
+from .wwe import WWEIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xfileshare import XFileShareIE
@@ -1417,6 +1445,7 @@ from .younow import (
     YouNowMomentIE,
 )
 from .youporn import YouPornIE
+from .yourporn import YourPornIE
 from .yourupload import YourUploadIE
 from .youtube import (
     YoutubeIE,
@@ -1440,10 +1469,23 @@ from .youtube import (
 from .zapiks import ZapiksIE
 from .zaq1 import Zaq1IE
 from .zattoo import (
+    BBVTVIE,
+    EinsUndEinsTVIE,
+    EWETVIE,
+    GlattvisionTVIE,
+    MNetTVIE,
+    MyVisionTVIE,
+    NetPlusIE,
+    OsnatelTVIE,
+    QuantumTVIE,
     QuicklineIE,
     QuicklineLiveIE,
+    SAKTVIE,
+    VTXTVIE,
+    WalyTVIE,
     ZattooIE,
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
 from .zingmp3 import ZingMp3IE
+from .zype import ZypeIE

youtube_dl/extractor/facebook.py

@@ -57,7 +57,7 @@ class FacebookIE(InfoExtractor):
     _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
 
     _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
-    _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true'
+    _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary'
 
     _TESTS = [{
         'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',

youtube_dl/extractor/fourtube.py

@@ -3,15 +3,45 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_b64decode,
+    compat_str,
+    compat_urllib_parse_unquote,
+    compat_urlparse,
+)
 from ..utils import (
+    int_or_none,
     parse_duration,
     parse_iso8601,
+    str_or_none,
     str_to_int,
+    try_get,
+    unified_timestamp,
+    url_or_none,
 )
 
 
 class FourTubeBaseIE(InfoExtractor):
+    _TKN_HOST = 'tkn.kodicdn.com'
+
+    def _extract_formats(self, url, video_id, media_id, sources):
+        token_url = 'https://%s/%s/desktop/%s' % (
+            self._TKN_HOST, media_id, '+'.join(sources))
+
+        parsed_url = compat_urlparse.urlparse(url)
+        tokens = self._download_json(token_url, video_id, data=b'', headers={
+            'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
+            'Referer': url,
+        })
+        formats = [{
+            'url': tokens[format]['token'],
+            'format_id': format + 'p',
+            'resolution': format + 'p',
+            'quality': int(format),
+        } for format in sources]
+        self._sort_formats(formats)
+        return formats
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         kind, video_id, display_id = mobj.group('kind', 'id', 'display_id')
@@ -68,21 +98,7 @@ class FourTubeBaseIE(InfoExtractor):
             media_id = params[0]
             sources = ['%s' % p for p in params[2]]
 
-        token_url = 'https://tkn.kodicdn.com/{0}/desktop/{1}'.format(
-            media_id, '+'.join(sources))
-
-        parsed_url = compat_urlparse.urlparse(url)
-        tokens = self._download_json(token_url, video_id, data=b'', headers={
-            'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
-            'Referer': url,
-        })
-        formats = [{
-            'url': tokens[format]['token'],
-            'format_id': format + 'p',
-            'resolution': format + 'p',
-            'quality': int(format),
-        } for format in sources]
-        self._sort_formats(formats)
+        formats = self._extract_formats(url, video_id, media_id, sources)
 
         return {
             'id': video_id,
@@ -164,6 +180,7 @@ class FuxIE(FourTubeBaseIE):
 class PornTubeIE(FourTubeBaseIE):
     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?porntube\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
     _URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s'
+    _TKN_HOST = 'tkn.porntube.com'
     _TESTS = [{
         'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759',
         'info_dict': {
@@ -171,13 +188,32 @@ class PornTubeIE(FourTubeBaseIE):
             'ext': 'mp4',
             'title': 'Teen couple doing anal',
             'uploader': 'Alexy',
-            'uploader_id': 'Alexy',
+            'uploader_id': '91488',
             'upload_date': '20150606',
             'timestamp': 1433595647,
             'duration': 5052,
             'view_count': int,
             'like_count': int,
-            'categories': list,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.porntube.com/videos/squirting-teen-ballerina-ecg_1331406',
+        'info_dict': {
+            'id': '1331406',
+            'ext': 'mp4',
+            'title': 'Squirting Teen Ballerina on ECG',
+            'uploader': 'Exploited College Girls',
+            'uploader_id': '665',
+            'channel': 'Exploited College Girls',
+            'channel_id': '665',
+            'upload_date': '20130920',
+            'timestamp': 1379685485,
+            'duration': 851,
+            'view_count': int,
+            'like_count': int,
             'age_limit': 18,
         },
         'params': {
@@ -191,6 +227,55 @@ class PornTubeIE(FourTubeBaseIE):
         'only_matching': True,
     }]
 
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id, display_id = mobj.group('id', 'display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video = self._parse_json(
+            self._search_regex(
+                r'INITIALSTATE\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'data', group='value'), video_id,
+            transform_source=lambda x: compat_urllib_parse_unquote(
+                compat_b64decode(x).decode('utf-8')))['page']['video']
+
+        title = video['title']
+        media_id = video['mediaId']
+        sources = [compat_str(e['height'])
+                   for e in video['encodings'] if e.get('height')]
+        formats = self._extract_formats(url, video_id, media_id, sources)
+
+        thumbnail = url_or_none(video.get('masterThumb'))
+        uploader = try_get(video, lambda x: x['user']['username'], compat_str)
+        uploader_id = str_or_none(try_get(
+            video, lambda x: x['user']['id'], int))
+        channel = try_get(video, lambda x: x['channel']['name'], compat_str)
+        channel_id = str_or_none(try_get(
+            video, lambda x: x['channel']['id'], int))
+        like_count = int_or_none(video.get('likes'))
+        dislike_count = int_or_none(video.get('dislikes'))
+        view_count = int_or_none(video.get('playsQty'))
+        duration = int_or_none(video.get('durationInSeconds'))
+        timestamp = unified_timestamp(video.get('publishedAt'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'uploader': uploader or channel,
+            'uploader_id': uploader_id or channel_id,
+            'channel': channel,
+            'channel_id': channel_id,
+            'timestamp': timestamp,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'view_count': view_count,
+            'duration': duration,
+            'age_limit': 18,
+        }
+
 
 class PornerBrosIE(FourTubeBaseIE):
     _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'

youtube_dl/extractor/foxsports.py

@@ -1,43 +1,33 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    smuggle_url,
-    update_url_query,
-)
 
 
 class FoxSportsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*video/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.foxsports.com/tennessee/video/432609859715',
         'md5': 'b49050e955bebe32c301972e4012ac17',
         'info_dict': {
-            'id': 'bwduI3X_TgUB',
+            'id': '432609859715',
             'ext': 'mp4',
             'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
             'description': 'Courtney Lee talks about Memphis being focused.',
-            'upload_date': '20150423',
-            'timestamp': 1429761109,
+            # TODO: fix timestamp
+            'upload_date': '19700101',  # '20150423',
+            # 'timestamp': 1429761109,
             'uploader': 'NEWA-FNG-FOXSPORTS',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
         'add_ie': ['ThePlatform'],
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        config = self._parse_json(
-            self._html_search_regex(
-                r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""",
-                webpage, 'data player config'),
-            video_id)
-
-        return self.url_result(smuggle_url(update_url_query(
-            config['releaseURL'], {
-                'mbr': 'true',
-                'switch': 'http',
-            }), {'force_smil_url': True}))
+        return self.url_result(
+            'https://feed.theplatform.com/f/BKQ29B/foxsports-all?byId=' + video_id, 'ThePlatformFeed')

youtube_dl/extractor/generic.py

@@ -32,7 +32,6 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     UnsupportedError,
-    url_or_none,
     xpath_text,
 )
 from .commonprotocols import RtmpIE
@@ -48,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .tvc import TVCIE
-from .sportbox import SportBoxEmbedIE
+from .sportbox import SportBoxIE
 from .smotri import SmotriIE
 from .myvi import MyviIE
 from .condenast import CondeNastIE
@@ -114,6 +113,8 @@ from .indavideo import IndavideoEmbedIE
 from .apa import APAIE
 from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
+from .expressen import ExpressenIE
+from .zype import ZypeIE
 
 
 class GenericIE(InfoExtractor):
@@ -2070,6 +2071,35 @@ class GenericIE(InfoExtractor):
             },
             'playlist_count': 6,
         },
+        {
+            # Zype embed
+            'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
+            'info_dict': {
+                'id': '5b400b834b32992a310622b9',
+                'ext': 'mp4',
+                'title': 'Smoky Barbecue Favorites',
+                'thumbnail': r're:^https?://.*\.jpe?g',
+            },
+            'add_ie': [ZypeIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # videojs embed
+            'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
+            'info_dict': {
+                'id': 'shell',
+                'ext': 'mp4',
+                'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
+                'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['Failed to download MPD manifest'],
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2621,9 +2651,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(tvc_url, 'TVC')
 
         # Look for embedded SportBox player
-        sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+        sportbox_urls = SportBoxIE._extract_urls(webpage)
         if sportbox_urls:
-            return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
+            return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
 
         # Look for embedded XHamster player
         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
@@ -3008,7 +3038,7 @@ class GenericIE(InfoExtractor):
                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
 
         # Look for Mediaset embeds
-        mediaset_urls = MediasetIE._extract_urls(webpage)
+        mediaset_urls = MediasetIE._extract_urls(self, webpage)
         if mediaset_urls:
             return self.playlist_from_matches(
                 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
@@ -3097,7 +3127,7 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
 
-        sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
+        sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
             r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
             webpage)]
         if sharevideos_urls:
@@ -3109,6 +3139,16 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
 
+        expressen_urls = ExpressenIE._extract_urls(webpage)
+        if expressen_urls:
+            return self.playlist_from_matches(
+                expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
+
+        zype_urls = ZypeIE._extract_urls(webpage)
+        if zype_urls:
+            return self.playlist_from_matches(
+                zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
+
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:
@@ -3130,9 +3170,13 @@ class GenericIE(InfoExtractor):
         jwplayer_data = self._find_jwplayer_data(
             webpage, video_id, transform_source=js_to_json)
         if jwplayer_data:
-            info = self._parse_jwplayer_data(
-                jwplayer_data, video_id, require_title=False, base_url=url)
-            return merge_dicts(info, info_dict)
+            try:
+                info = self._parse_jwplayer_data(
+                    jwplayer_data, video_id, require_title=False, base_url=url)
+                return merge_dicts(info, info_dict)
+            except ExtractorError:
+                # See https://github.com/rg3/youtube-dl/pull/16735
+                pass
 
         # Video.js embed
         mobj = re.search(
@@ -3146,8 +3190,8 @@ class GenericIE(InfoExtractor):
                 sources = [sources]
             formats = []
             for source in sources:
-                src = url_or_none(source.get('src'))
-                if not src:
+                src = source.get('src')
+                if not src or not isinstance(src, compat_str):
                     continue
                 src = compat_urlparse.urljoin(url, src)
                 src_type = source.get('type')

youtube_dl/extractor/gfycat.py

@@ -53,7 +53,7 @@ class GfycatIE(InfoExtractor):
         video_id = self._match_id(url)
 
         gfy = self._download_json(
-            'http://gfycat.com/cajax/get/%s' % video_id,
+            'https://api.gfycat.com/v1/gfycats/%s' % video_id,
             video_id, 'Downloading video info')
         if 'error' in gfy:
             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)

youtube_dl/extractor/go.py

@@ -36,7 +36,8 @@ class GoIE(AdobePassIE):
             'requestor_id': 'DisneyXD',
         }
     }
-    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
+                 % '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
     _TESTS = [{
         'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
         'info_dict': {
@@ -62,6 +63,14 @@ class GoIE(AdobePassIE):
     }, {
         'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
         'only_matching': True,
+    }, {
+        # brand 004
+        'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
+        'only_matching': True,
+    }, {
+        # brand 008
+        'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
+        'only_matching': True,
     }]
 
     def _extract_videos(self, brand, video_id='-1', show_id='-1'):
@@ -72,14 +81,23 @@ class GoIE(AdobePassIE):
 
     def _real_extract(self, url):
         sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
-        site_info = self._SITE_INFO[sub_domain]
-        brand = site_info['brand']
-        if not video_id:
-            webpage = self._download_webpage(url, display_id)
+        site_info = self._SITE_INFO.get(sub_domain, {})
+        brand = site_info.get('brand')
+        if not video_id or not site_info:
+            webpage = self._download_webpage(url, display_id or video_id)
             video_id = self._search_regex(
                 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
                 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
-                r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None)
+                r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id',
+                default=None)
+            if not site_info:
+                brand = self._search_regex(
+                    (r'data-brand=\s*["\']\s*(\d+)',
+                     r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
+                    default='004')
+                site_info = next(
+                    si for _, si in self._SITE_INFO.items()
+                    if si.get('brand') == brand)
             if not video_id:
                 # show extraction works for Disney, DisneyJunior and DisneyXD
                 # ABC and Freeform has different layout

youtube_dl/extractor/hotstar.py

@@ -1,49 +1,56 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import hashlib
+import hmac
+import time
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
+    try_get,
 )
 
 
 class HotStarBaseIE(InfoExtractor):
-    _GEO_COUNTRIES = ['IN']
+    _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
 
-    def _download_json(self, *args, **kwargs):
-        response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
-        if response['resultCode'] != 'OK':
-            if kwargs.get('fatal'):
-                raise ExtractorError(
-                    response['errorDescription'], expected=True)
-            return None
-        return response['resultObj']
-
-    def _download_content_info(self, content_id):
-        return self._download_json(
-            'https://account.hotstar.com/AVS/besc', content_id, query={
-                'action': 'GetAggregatedContentDetails',
-                'appVersion': '5.0.40',
-                'channel': 'PCTV',
-                'contentId': content_id,
-            })['contentInfo'][0]
+    def _call_api(self, path, video_id, query_name='contentId'):
+        st = int(time.time())
+        exp = st + 6000
+        auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
+        auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
+        response = self._download_json(
+            'https://api.hotstar.com/' + path,
+            video_id, headers={
+                'hotstarauth': auth,
+                'x-country-code': 'IN',
+                'x-platform-code': 'JIO',
+            }, query={
+                query_name: video_id,
+                'tas': 10000,
+            })
+        if response['statusCode'] != 'OK':
+            raise ExtractorError(
+                response['body']['message'], expected=True)
+        return response['body']['results']
 
 
 class HotStarIE(HotStarBaseIE):
+    IE_NAME = 'hotstar'
     _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
     _TESTS = [{
-        'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
+        # contentData
+        'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
         'info_dict': {
             'id': '1000076273',
             'ext': 'mp4',
-            'title': 'On Air With AIB',
+            'title': 'Can You Not Spread Rumours?',
             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
-            'timestamp': 1447227000,
+            'timestamp': 1447248600,
             'upload_date': '20151111',
             'duration': 381,
         },
@@ -51,6 +58,10 @@ class HotStarIE(HotStarBaseIE):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # contentDetail
+        'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
+        'only_matching': True,
     }, {
         'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
         'only_matching': True,
@@ -58,47 +69,51 @@ class HotStarIE(HotStarBaseIE):
         'url': 'http://www.hotstar.com/1000000515',
         'only_matching': True,
     }]
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        video_data = self._download_content_info(video_id)
+        webpage = self._download_webpage(url, video_id)
+        app_state = self._parse_json(self._search_regex(
+            r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
+            webpage, 'app state'), video_id)
+        video_data = {}
+        getters = (
+            lambda x, k=k: x['initialState']['content%s' % k]['content']
+            for k in ('Data', 'Detail')
+        )
+        for v in app_state.values():
+            content = try_get(v, getters, dict)
+            if content and content.get('contentId') == video_id:
+                video_data = content
 
-        title = video_data['episodeTitle']
+        title = video_data['title']
 
-        if video_data.get('encrypted') == 'Y':
+        if video_data.get('drmProtected'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = []
-        for f in ('JIO',):
-            format_data = self._download_json(
-                'http://getcdn.hotstar.com/AVS/besc',
-                video_id, 'Downloading %s JSON metadata' % f,
-                fatal=False, query={
-                    'action': 'GetCDN',
-                    'asJson': 'Y',
-                    'channel': f,
-                    'id': video_id,
-                    'type': 'VOD',
-                })
-            if format_data:
-                format_url = format_data.get('src')
-                if not format_url:
-                    continue
-                ext = determine_ext(format_url)
-                if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        format_url, video_id, 'mp4',
-                        m3u8_id='hls', fatal=False))
-                elif ext == 'f4m':
-                    # produce broken files
-                    continue
-                else:
-                    formats.append({
-                        'url': format_url,
-                        'width': int_or_none(format_data.get('width')),
-                        'height': int_or_none(format_data.get('height')),
-                    })
+        format_data = self._call_api('h/v1/play', video_id)['item']
+        format_url = format_data['playbackUrl']
+        ext = determine_ext(format_url)
+        if ext == 'm3u8':
+            try:
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id='hls'))
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                    self.raise_geo_restricted(countries=['IN'])
+                raise
+        elif ext == 'f4m':
+            # produce broken files
+            pass
+        else:
+            formats.append({
+                'url': format_url,
+                'width': int_or_none(format_data.get('width')),
+                'height': int_or_none(format_data.get('height')),
+            })
         self._sort_formats(formats)
 
         return {
@@ -106,57 +121,43 @@ class HotStarIE(HotStarBaseIE):
             'title': title,
             'description': video_data.get('description'),
             'duration': int_or_none(video_data.get('duration')),
-            'timestamp': int_or_none(video_data.get('broadcastDate')),
+            'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
             'formats': formats,
+            'channel': video_data.get('channelName'),
+            'channel_id': video_data.get('channelId'),
+            'series': video_data.get('showName'),
+            'season': video_data.get('seasonName'),
+            'season_number': int_or_none(video_data.get('seasonNo')),
+            'season_id': video_data.get('seasonId'),
             'episode': title,
-            'episode_number': int_or_none(video_data.get('episodeNumber')),
-            'series': video_data.get('contentTitle'),
+            'episode_number': int_or_none(video_data.get('episodeNo')),
         }
 
 
 class HotStarPlaylistIE(HotStarBaseIE):
     IE_NAME = 'hotstar:playlist'
-    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
     _TESTS = [{
-        'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
+        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
         'info_dict': {
-            'id': '14812',
+            'id': '3_2_26',
         },
-        'playlist_mincount': 75,
+        'playlist_mincount': 20,
     }, {
-        'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
+        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
         'only_matching': True,
     }]
-    _ITEM_TYPES = {
-        'episodes': 'EPISODE',
-        'popular-clips': 'CLIPS',
-    }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        base_url = mobj.group('url')
-        content_id = mobj.group('content_id')
-        playlist_type = mobj.group('type')
+        playlist_id = self._match_id(url)
 
-        content_info = self._download_content_info(content_id)
-        playlist_id = compat_str(content_info['categoryId'])
-
-        collection = self._download_json(
-            'https://search.hotstar.com/AVS/besc', playlist_id, query={
-                'action': 'SearchContents',
-                'appVersion': '5.0.40',
-                'channel': 'PCTV',
-                'moreFilters': 'series:%s;' % playlist_id,
-                'query': '*',
-                'searchOrder': 'last_broadcast_date desc,year desc,title asc',
-                'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
-            })
+        collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')
 
         entries = [
             self.url_result(
-                '%s/_/%s' % (base_url, video['contentId']),
+                'https://www.hotstar.com/%s' % video['contentId'],
                 ie=HotStarIE.ie_key(), video_id=video['contentId'])
-            for video in collection['response']['docs']
+            for video in collection['assets']['items']
             if video.get('contentId')]
 
         return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/imdb.py

@@ -64,7 +64,8 @@ class ImdbIE(InfoExtractor):
             video_url = url_or_none(encoding.get('videoUrl'))
             if not video_url:
                 continue
-            ext = determine_ext(video_url, mimetype2ext(encoding.get('mimeType')))
+            ext = mimetype2ext(encoding.get(
+                'mimeType')) or determine_ext(video_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     video_url, video_id, 'mp4', entry_protocol='m3u8_native',

youtube_dl/extractor/internazionale.py

@@ -7,7 +7,7 @@ from ..utils import unified_timestamp
 
 class InternazionaleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
         'md5': '3e39d32b66882c1218e305acbf8348ca',
         'info_dict': {
@@ -23,7 +23,23 @@ class InternazionaleIE(InfoExtractor):
         'params': {
             'format': 'bestvideo',
         },
-    }
+    }, {
+        'url': 'https://www.internazionale.it/video/2018/08/29/telefono-stare-con-noi-stessi',
+        'md5': '9db8663704cab73eb972d1cee0082c79',
+        'info_dict': {
+            'id': '761344',
+            'display_id': 'telefono-stare-con-noi-stessi',
+            'ext': 'mp4',
+            'title': 'Usiamo il telefono per evitare di stare con noi stessi',
+            'description': 'md5:75ccfb0d6bcefc6e7428c68b4aa1fe44',
+            'timestamp': 1535528954,
+            'upload_date': '20180829',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -40,8 +56,13 @@ class InternazionaleIE(InfoExtractor):
             DATA_RE % 'job-id', webpage, 'video id', group='value')
         video_path = self._search_regex(
             DATA_RE % 'video-path', webpage, 'video path', group='value')
+        video_available_abroad = self._search_regex(
+            DATA_RE % 'video-available_abroad', webpage,
+            'video available aboard', default='1', group='value')
+        video_available_abroad = video_available_abroad == '1'
 
-        video_base = 'https://video.internazionale.it/%s/%s.' % (video_path, video_id)
+        video_base = 'https://video%s.internazionale.it/%s/%s.' % \
+            ('' if video_available_abroad else '-ita', video_path, video_id)
 
         formats = self._extract_m3u8_formats(
             video_base + 'm3u8', display_id, 'mp4',

youtube_dl/extractor/iprima.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
     _GEO_BYPASS = False
 
     _TESTS = [{
@@ -33,14 +33,27 @@ class IPrimaIE(InfoExtractor):
         # geo restricted
         'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
         'only_matching': True,
+    }, {
+        # iframe api.play-backend.iprima.cz
+        'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
+        'only_matching': True,
+    }, {
+        # iframe prima.iprima.cz
+        'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')
+
         webpage = self._download_webpage(url, video_id)
 
-        video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
+        video_id = self._search_regex(
+            (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
+             r'data-product="([^"]+)">'),
+            webpage, 'real id')
 
         playerpage = self._download_webpage(
             'http://play.iprima.cz/prehravac/init',

youtube_dl/extractor/ivi.py

@@ -15,7 +15,7 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
     _GEO_BYPASS = False
     _GEO_COUNTRIES = ['RU']
 
@@ -65,7 +65,11 @@ class IviIE(InfoExtractor):
                 'thumbnail': r're:^https?://.*\.jpg$',
             },
             'skip': 'Only works from Russia',
-        }
+        },
+        {
+            'url': 'https://www.ivi.tv/watch/33560/',
+            'only_matching': True,
+        },
     ]
 
     # Sorted by quality

youtube_dl/extractor/jamendo.py

@@ -26,8 +26,15 @@ class JamendoBaseIE(InfoExtractor):
 
 
 class JamendoIE(JamendoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
-    _TEST = {
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            licensing\.jamendo\.com/[^/]+|
+                            (?:www\.)?jamendo\.com
+                        )
+                        /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)
+                    '''
+    _TESTS = [{
         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
         'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
         'info_dict': {
@@ -40,14 +47,19 @@ class JamendoIE(JamendoBaseIE):
             'duration': 210,
             'thumbnail': r're:^https?://.*\.jpg'
         }
-    }
+    }, {
+        'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = self._VALID_URL_RE.match(url)
         track_id = mobj.group('id')
         display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(
+            'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
+            display_id)
 
         title, artist, track = self._extract_meta(webpage)
 

youtube_dl/extractor/joj.py

@@ -61,7 +61,7 @@ class JojIE(InfoExtractor):
 
         bitrates = self._parse_json(
             self._search_regex(
-                r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates',
+                r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',
                 default='{}'),
             video_id, transform_source=js_to_json, fatal=False)
 

youtube_dl/extractor/kaltura.py

@@ -192,6 +192,8 @@ class KalturaIE(InfoExtractor):
                 'entryId': video_id,
                 'service': 'baseentry',
                 'ks': '{1:result:ks}',
+                'responseProfile:fields': 'createdAt,dataUrl,duration,name,plays,thumbnailUrl,userId',
+                'responseProfile:type': 1,
             },
             {
                 'action': 'getbyentryid',

youtube_dl/extractor/kinopoisk.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    dict_get,
+    int_or_none,
+)
+
+
+class KinoPoiskIE(InfoExtractor):
+    _GEO_COUNTRIES = ['RU']
+    _VALID_URL = r'https?://(?:www\.)?kinopoisk\.ru/film/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.kinopoisk.ru/film/81041/watch/',
+        'md5': '4f71c80baea10dfa54a837a46111d326',
+        'info_dict': {
+            'id': '81041',
+            'ext': 'mp4',
+            'title': 'Алеша попович и тугарин змей',
+            'description': 'md5:43787e673d68b805d0aa1df5a5aea701',
+            'thumbnail': r're:^https?://.*',
+            'duration': 4533,
+            'age_limit': 12,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }, {
+        'url': 'https://www.kinopoisk.ru/film/81041',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://ott-widget.kinopoisk.ru/v1/kp/', video_id,
+            query={'kpId': video_id})
+
+        data = self._parse_json(
+            self._search_regex(
+                r'(?s)<script[^>]+\btype=["\']application/json[^>]+>(.+?)<',
+                webpage, 'data'),
+            video_id)['models']
+
+        film = data['filmStatus']
+        title = film.get('title') or film['originalTitle']
+
+        formats = self._extract_m3u8_formats(
+            data['playlistEntity']['uri'], video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        description = dict_get(
+            film, ('descriptscription', 'description',
+                   'shortDescriptscription', 'shortDescription'))
+        thumbnail = film.get('coverUrl') or film.get('posterUrl')
+        duration = int_or_none(film.get('duration'))
+        age_limit = int_or_none(film.get('restrictionAge'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/laola1tv.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import json
+import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -32,7 +33,8 @@ class Laola1TvEmbedIE(InfoExtractor):
 
     def _extract_token_url(self, stream_access_url, video_id, data):
         return self._download_json(
-            stream_access_url, video_id, headers={
+            self._proto_relative_url(stream_access_url, 'https:'), video_id,
+            headers={
                 'Content-Type': 'application/json',
             }, data=json.dumps(data).encode())['data']['stream-access'][0]
 
@@ -119,9 +121,59 @@ class Laola1TvEmbedIE(InfoExtractor):
         }
 
 
-class Laola1TvIE(Laola1TvEmbedIE):
+class Laola1TvBaseIE(Laola1TvEmbedIE):
+    def _extract_video(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        if 'Dieser Livestream ist bereits beendet.' in webpage:
+            raise ExtractorError('This live stream has already finished.', expected=True)
+
+        conf = self._parse_json(self._search_regex(
+            r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
+            display_id,
+            transform_source=lambda s: js_to_json(re.sub(r'shareurl:.+,', '', s)))
+        video_id = conf['videoid']
+
+        config = self._download_json(conf['configUrl'], video_id, query={
+            'videoid': video_id,
+            'partnerid': conf['partnerid'],
+            'language': conf.get('language', ''),
+            'portal': conf.get('portalid', ''),
+        })
+        error = config.get('error')
+        if error:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
+
+        video_data = config['video']
+        title = video_data['title']
+        is_live = video_data.get('isLivestream') and video_data.get('isLive')
+        meta = video_data.get('metaInformation')
+        sports = meta.get('sports')
+        categories = sports.split(',') if sports else []
+
+        token_url = self._extract_token_url(
+            video_data['streamAccess'], video_id,
+            video_data['abo']['required'])
+
+        formats = self._extract_formats(token_url, video_id)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': self._live_title(title) if is_live else title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('image'),
+            'categories': categories,
+            'formats': formats,
+            'is_live': is_live,
+        }
+
+
+class Laola1TvIE(Laola1TvBaseIE):
     IE_NAME = 'laola1tv'
     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
+
     _TESTS = [{
         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
@@ -169,52 +221,30 @@ class Laola1TvIE(Laola1TvEmbedIE):
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        return self._extract_video(url)
 
-        webpage = self._download_webpage(url, display_id)
 
-        if 'Dieser Livestream ist bereits beendet.' in webpage:
-            raise ExtractorError('This live stream has already finished.', expected=True)
+class EHFTVIE(Laola1TvBaseIE):
+    IE_NAME = 'ehftv'
+    _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(?:-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)'
 
-        conf = self._parse_json(self._search_regex(
-            r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
-            display_id, js_to_json)
+    _TESTS = [{
+        'url': 'https://www.ehftv.com/int/video/paris-saint-germain-handball-pge-vive-kielce/1166761',
+        'info_dict': {
+            'id': '1166761',
+            'display_id': 'paris-saint-germain-handball-pge-vive-kielce',
+            'ext': 'mp4',
+            'title': 'Paris Saint-Germain Handball - PGE Vive Kielce',
+            'is_live': False,
+            'categories': ['Handball'],
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
-        video_id = conf['videoid']
-
-        config = self._download_json(conf['configUrl'], video_id, query={
-            'videoid': video_id,
-            'partnerid': conf['partnerid'],
-            'language': conf.get('language', ''),
-            'portal': conf.get('portalid', ''),
-        })
-        error = config.get('error')
-        if error:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
-
-        video_data = config['video']
-        title = video_data['title']
-        is_live = video_data.get('isLivestream') and video_data.get('isLive')
-        meta = video_data.get('metaInformation')
-        sports = meta.get('sports')
-        categories = sports.split(',') if sports else []
-
-        token_url = self._extract_token_url(
-            video_data['streamAccess'], video_id,
-            video_data['abo']['required'])
-
-        formats = self._extract_formats(token_url, video_id)
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': self._live_title(title) if is_live else title,
-            'description': video_data.get('description'),
-            'thumbnail': video_data.get('image'),
-            'categories': categories,
-            'formats': formats,
-            'is_live': is_live,
-        }
+    def _real_extract(self, url):
+        return self._extract_video(url)
 
 
 class ITTFIE(InfoExtractor):

youtube_dl/extractor/lci.py

@@ -20,5 +20,7 @@ class LCIIE(InfoExtractor):
     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')
+        wat_id = self._search_regex(
+            (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
+            webpage, 'wat id')
         return self.url_result('wat:' + wat_id, 'Wat', wat_id)

youtube_dl/extractor/libraryofcongress.py

@@ -16,16 +16,15 @@ from ..utils import (
 class LibraryOfCongressIE(InfoExtractor):
     IE_NAME = 'loc'
     IE_DESC = 'Library of Congress'
-    _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)'
     _TESTS = [{
         # embedded via <div class="media-player"
         'url': 'http://loc.gov/item/90716351/',
-        'md5': '353917ff7f0255aa6d4b80a034833de8',
+        'md5': '6ec0ae8f07f86731b1b2ff70f046210a',
         'info_dict': {
             'id': '90716351',
             'ext': 'mp4',
             'title': "Pa's trip to Mars",
-            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 0,
             'view_count': int,
         },
@@ -57,6 +56,12 @@ class LibraryOfCongressIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.loc.gov/item/ihas.200197114/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -67,12 +72,13 @@ class LibraryOfCongressIE(InfoExtractor):
             (r'id=(["\'])media-player-(?P<id>.+?)\1',
              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
-             r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'),
+             r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
+             r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
             webpage, 'media id', group='id')
 
         data = self._download_json(
             'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
-            video_id)['mediaObject']
+            media_id)['mediaObject']
 
         derivative = data['derivatives'][0]
         media_url = derivative['derivativeUrl']
@@ -89,25 +95,29 @@ class LibraryOfCongressIE(InfoExtractor):
         if ext not in ('mp4', 'mp3'):
             media_url += '.mp4' if is_video else '.mp3'
 
-        if 'vod/mp4:' in media_url:
-            formats = [{
-                'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8',
+        formats = []
+        if '/vod/mp4:' in media_url:
+            formats.append({
+                'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
                 'format_id': 'hls',
                 'ext': 'mp4',
                 'protocol': 'm3u8_native',
                 'quality': 1,
-            }]
-        elif 'vod/mp3:' in media_url:
-            formats = [{
-                'url': media_url.replace('vod/mp3:', ''),
-                'vcodec': 'none',
-            }]
+            })
+        http_format = {
+            'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
+            'format_id': 'http',
+            'quality': 1,
+        }
+        if not is_video:
+            http_format['vcodec'] = 'none'
+        formats.append(http_format)
 
         download_urls = set()
         for m in re.finditer(
                 r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
             format_id = m.group('id').lower()
-            if format_id == 'gif':
+            if format_id in ('gif', 'jpeg'):
                 continue
             download_url = m.group('url')
             if download_url in download_urls:

youtube_dl/extractor/linkedin.py

@@ -0,0 +1,175 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class LinkedInLearningBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'linkedin'
+
+    def _call_api(self, course_slug, fields, video_slug=None, resolution=None):
+        query = {
+            'courseSlug': course_slug,
+            'fields': fields,
+            'q': 'slugs',
+        }
+        sub = ''
+        if video_slug:
+            query.update({
+                'videoSlug': video_slug,
+                'resolution': '_%s' % resolution,
+            })
+            sub = ' %dp' % resolution
+        api_url = 'https://www.linkedin.com/learning-api/detailedCourses'
+        return self._download_json(
+            api_url, video_slug, 'Downloading%s JSON metadata' % sub, headers={
+                'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value,
+            }, query=query)['elements'][0]
+
+    def _get_video_id(self, urn, course_slug, video_slug):
+        if urn:
+            mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn)
+            if mobj:
+                return mobj.group(1)
+        return '%s/%s' % (course_slug, video_slug)
+
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            return
+
+        login_page = self._download_webpage(
+            'https://www.linkedin.com/uas/login?trk=learning',
+            None, 'Downloading login page')
+        action_url = self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, 'post url',
+            default='https://www.linkedin.com/uas/login-submit', group='url')
+        data = self._hidden_inputs(login_page)
+        data.update({
+            'session_key': email,
+            'session_password': password,
+        })
+        login_submit_page = self._download_webpage(
+            action_url, None, 'Logging in',
+            data=urlencode_postdata(data))
+        error = self._search_regex(
+            r'<span[^>]+class="error"[^>]*>\s*(.+?)\s*</span>',
+            login_submit_page, 'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+
+class LinkedInLearningIE(LinkedInLearningBaseIE):
+    IE_NAME = 'linkedin:learning'
+    _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<course_slug>[^/]+)/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals/welcome?autoplay=true',
+        'md5': 'a1d74422ff0d5e66a792deb996693167',
+        'info_dict': {
+            'id': '90426',
+            'ext': 'mp4',
+            'title': 'Welcome',
+            'timestamp': 1430396150.82,
+            'upload_date': '20150430',
+        },
+    }
+
+    def _real_extract(self, url):
+        course_slug, video_slug = re.match(self._VALID_URL, url).groups()
+
+        video_data = None
+        formats = []
+        for width, height in ((640, 360), (960, 540), (1280, 720)):
+            video_data = self._call_api(
+                course_slug, 'selectedVideo', video_slug, height)['selectedVideo']
+
+            video_url_data = video_data.get('url') or {}
+            progressive_url = video_url_data.get('progressiveUrl')
+            if progressive_url:
+                formats.append({
+                    'format_id': 'progressive-%dp' % height,
+                    'url': progressive_url,
+                    'height': height,
+                    'width': width,
+                    'source_preference': 1,
+                })
+
+        title = video_data['title']
+
+        audio_url = video_data.get('audio', {}).get('progressiveUrl')
+        if audio_url:
+            formats.append({
+                'abr': 64,
+                'ext': 'm4a',
+                'format_id': 'audio',
+                'url': audio_url,
+                'vcodec': 'none',
+            })
+
+        streaming_url = video_url_data.get('streamingUrl')
+        if streaming_url:
+            formats.extend(self._extract_m3u8_formats(
+                streaming_url, video_slug, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+
+        self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr'))
+
+        return {
+            'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug),
+            'title': title,
+            'formats': formats,
+            'thumbnail': video_data.get('defaultThumbnail'),
+            'timestamp': float_or_none(video_data.get('publishedOn'), 1000),
+            'duration': int_or_none(video_data.get('durationInSeconds')),
+        }
+
+
+class LinkedInLearningCourseIE(LinkedInLearningBaseIE):
+    IE_NAME = 'linkedin:learning:course'
+    _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals',
+        'info_dict': {
+            'id': 'programming-foundations-fundamentals',
+            'title': 'Programming Foundations: Fundamentals',
+            'description': 'md5:76e580b017694eb89dc8e8923fff5c86',
+        },
+        'playlist_mincount': 61,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if LinkedInLearningIE.suitable(url) else super(LinkedInLearningCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        course_slug = self._match_id(url)
+        course_data = self._call_api(course_slug, 'chapters,description,title')
+
+        entries = []
+        for chapter in course_data.get('chapters', []):
+            chapter_title = chapter.get('title')
+            for video in chapter.get('videos', []):
+                video_slug = video.get('slug')
+                if not video_slug:
+                    continue
+                entries.append({
+                    '_type': 'url_transparent',
+                    'id': self._get_video_id(video.get('urn'), course_slug, video_slug),
+                    'title': video.get('title'),
+                    'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug),
+                    'chapter': chapter_title,
+                    'ie_key': LinkedInLearningIE.ie_key(),
+                })
+
+        return self.playlist_result(
+            entries, course_slug,
+            course_data.get('title'),
+            course_data.get('description'))

youtube_dl/extractor/lynda.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class LyndaBaseIE(InfoExtractor):
-    _SIGNIN_URL = 'https://www.lynda.com/signin'
+    _SIGNIN_URL = 'https://www.lynda.com/signin/lynda'
     _PASSWORD_URL = 'https://www.lynda.com/signin/password'
     _USER_URL = 'https://www.lynda.com/signin/user'
     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'

youtube_dl/extractor/mediaset.py

@@ -4,6 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .theplatform import ThePlatformBaseIE
+from ..compat import (
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -76,12 +81,33 @@ class MediasetIE(ThePlatformBaseIE):
     }]
 
     @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
-                webpage)]
+    def _extract_urls(ie, webpage):
+        def _qs(url):
+            return compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+
+        def _program_guid(qs):
+            return qs.get('programGuid', [None])[0]
+
+        entries = []
+        for mobj in re.finditer(
+                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
+                webpage):
+            embed_url = mobj.group('url')
+            embed_qs = _qs(embed_url)
+            program_guid = _program_guid(embed_qs)
+            if program_guid:
+                entries.append(embed_url)
+                continue
+            video_id = embed_qs.get('id', [None])[0]
+            if not video_id:
+                continue
+            urlh = ie._request_webpage(
+                embed_url, video_id, note='Following embed URL redirect')
+            embed_url = compat_str(urlh.geturl())
+            program_guid = _program_guid(_qs(embed_url))
+            if program_guid:
+                entries.append(embed_url)
+        return entries
 
     def _real_extract(self, url):
         guid = self._match_id(url)

youtube_dl/extractor/mixcloud.py

@@ -161,11 +161,17 @@ class MixcloudIE(InfoExtractor):
             stream_info = info_json['streamInfo']
             formats = []
 
+            def decrypt_url(f_url):
+                for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'):
+                    decrypted_url = self._decrypt_xor_cipher(k, f_url)
+                    if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url):
+                        return decrypted_url
+
             for url_key in ('url', 'hlsUrl', 'dashUrl'):
                 format_url = stream_info.get(url_key)
                 if not format_url:
                     continue
-                decrypted = self._decrypt_xor_cipher(key, compat_b64decode(format_url))
+                decrypted = decrypt_url(compat_b64decode(format_url))
                 if not decrypted:
                     continue
                 if url_key == 'hlsUrl':

youtube_dl/extractor/motherless.py

@@ -167,9 +167,9 @@ class MotherlessGroupIE(InfoExtractor):
         if not entries:
             entries = [
                 self.url_result(
-                    compat_urlparse.urljoin(base, '/' + video_id),
-                    ie=MotherlessIE.ie_key(), video_id=video_id)
-                for video_id in orderedSet(re.findall(
+                    compat_urlparse.urljoin(base, '/' + entry_id),
+                    ie=MotherlessIE.ie_key(), video_id=entry_id)
+                for entry_id in orderedSet(re.findall(
                     r'data-codename=["\']([A-Z0-9]+)', webpage))]
         return entries
 

youtube_dl/extractor/nbc.py

@@ -7,11 +7,10 @@ import re
 from .common import InfoExtractor
 from .theplatform import ThePlatformIE
 from .adobepass import AdobePassIE
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
-    find_xpath_attr,
     smuggle_url,
     try_get,
-    unescapeHTML,
     update_url_query,
     int_or_none,
 )
@@ -75,11 +74,16 @@ class NBCIE(AdobePassIE):
             'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
             'only_matching': True,
         },
+        {
+            # Percent escaped url
+            'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
         permalink, video_id = re.match(self._VALID_URL, url).groups()
-        permalink = 'http' + permalink
+        permalink = 'http' + compat_urllib_parse_unquote(permalink)
         response = self._download_json(
             'https://api.nbc.com/v3/videos', video_id, query={
                 'filter[permalink]': permalink,
@@ -263,27 +267,14 @@ class CSNNEIE(InfoExtractor):
 
 
 class NBCNewsIE(ThePlatformIE):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
-        (?:video/.+?/(?P<id>\d+)|
-        ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
-        '''
+    _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
 
     _TESTS = [
-        {
-            'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
-            'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
-            'info_dict': {
-                'id': '52753292',
-                'ext': 'flv',
-                'title': 'Crew emerges after four-month Mars food study',
-                'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
-            },
-        },
         {
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
             'md5': 'af1adfa51312291a017720403826bb64',
             'info_dict': {
-                'id': 'p_tweet_snow_140529',
+                'id': '269389891880',
                 'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
@@ -307,7 +298,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
             'info_dict': {
-                'id': 'nn_netcast_150204',
+                'id': '394064451844',
                 'ext': 'mp4',
                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
@@ -320,7 +311,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
             'md5': 'a49e173825e5fcd15c13fc297fced39d',
             'info_dict': {
-                'id': 'x_lon_vwhorn_150922',
+                'id': '529953347624',
                 'ext': 'mp4',
                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
@@ -333,7 +324,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
             'md5': '118d7ca3f0bea6534f119c68ef539f71',
             'info_dict': {
-                'id': 'tdy_al_space_160420',
+                'id': '669831235788',
                 'ext': 'mp4',
                 'title': 'See the aurora borealis from space in stunning new NASA video',
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
@@ -346,7 +337,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
             'info_dict': {
-                'id': 'n_hayes_Aimm_140801_272214',
+                'id': '314487875924',
                 'ext': 'mp4',
                 'title': 'The chaotic GOP immigration vote',
                 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
@@ -368,60 +359,22 @@ class NBCNewsIE(ThePlatformIE):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        if video_id is not None:
-            all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
-            info = all_info.find('video')
-
-            return {
-                'id': video_id,
-                'title': info.find('headline').text,
-                'ext': 'flv',
-                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-                'description': info.find('caption').text,
-                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-            }
-        else:
-            # "feature" and "nightly-news" pages use theplatform.com
-            video_id = mobj.group('mpx_id')
+        video_id = self._match_id(url)
+        if not video_id.isdigit():
             webpage = self._download_webpage(url, video_id)
 
-            filter_param = 'byId'
-            bootstrap_json = self._search_regex(
-                [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
-                 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
-                 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
-                webpage, 'bootstrap json', default=None)
-            if bootstrap_json:
-                bootstrap = self._parse_json(
-                    bootstrap_json, video_id, transform_source=unescapeHTML)
+            data = self._parse_json(self._search_regex(
+                r'window\.__data\s*=\s*({.+});', webpage,
+                'bootstrap json'), video_id)
+            video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
 
-                info = None
-                if 'results' in bootstrap:
-                    info = bootstrap['results'][0]['video']
-                elif 'video' in bootstrap:
-                    info = bootstrap['video']
-                elif 'msnbcVideoInfo' in bootstrap:
-                    info = bootstrap['msnbcVideoInfo']['meta']
-                elif 'msnbcThePlatform' in bootstrap:
-                    info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
-                else:
-                    info = bootstrap
-
-                if 'guid' in info:
-                    video_id = info['guid']
-                    filter_param = 'byGuid'
-                elif 'mpxId' in info:
-                    video_id = info['mpxId']
-
-            return {
-                '_type': 'url_transparent',
-                'id': video_id,
-                # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
-                'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
-                'ie_key': 'ThePlatformFeed',
-            }
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
+            'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
+            'ie_key': 'ThePlatformFeed',
+        }
 
 
 class NBCOlympicsIE(InfoExtractor):

youtube_dl/extractor/niconico.py

@@ -252,7 +252,7 @@ class NiconicoIE(InfoExtractor):
                     },
                     'timing_constraint': 'unlimited'
                 }
-            }))
+            }).encode())
 
         resolution = video_quality.get('resolution', {})
 

youtube_dl/extractor/njpwworld.py

@@ -31,6 +31,8 @@ class NJPWWorldIE(InfoExtractor):
         'skip': 'Requires login',
     }
 
+    _LOGIN_URL = 'https://front.njpwworld.com/auth/login'
+
     def _real_initialize(self):
         self._login()
 
@@ -40,13 +42,17 @@ class NJPWWorldIE(InfoExtractor):
         if not username:
             return True
 
+        # Setup session (will set necessary cookies)
+        self._request_webpage(
+            'https://njpwworld.com/', None, note='Setting up session')
+
         webpage, urlh = self._download_webpage_handle(
-            'https://njpwworld.com/auth/login', None,
+            self._LOGIN_URL, None,
             note='Logging in', errnote='Unable to login',
             data=urlencode_postdata({'login_id': username, 'pw': password}),
-            headers={'Referer': 'https://njpwworld.com/auth'})
+            headers={'Referer': 'https://front.njpwworld.com/auth'})
         # /auth/login will return 302 for successful logins
-        if urlh.geturl() == 'https://njpwworld.com/auth/login':
+        if urlh.geturl() == self._LOGIN_URL:
             self.report_warning('unable to login')
             return False
 

youtube_dl/extractor/nova.py

@@ -6,28 +6,90 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    int_or_none,
+    js_to_json,
+    qualities,
     unified_strdate,
+    url_or_none,
 )
 
 
+class NovaEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
+        'md5': 'b3834f6de5401baabf31ed57456463f7',
+        'info_dict': {
+            'id': '8o0n0r',
+            'ext': 'mp4',
+            'title': '2180. díl',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 2578,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        bitrates = self._parse_json(
+            self._search_regex(
+                r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'),
+            video_id, transform_source=js_to_json)
+
+        QUALITIES = ('lq', 'mq', 'hq', 'hd')
+        quality_key = qualities(QUALITIES)
+
+        formats = []
+        for format_id, format_list in bitrates.items():
+            if not isinstance(format_list, list):
+                continue
+            for format_url in format_list:
+                format_url = url_or_none(format_url)
+                if not format_url:
+                    continue
+                f = {
+                    'url': format_url,
+                }
+                f_id = format_id
+                for quality in QUALITIES:
+                    if '%s.mp4' % quality in format_url:
+                        f_id += '-%s' % quality
+                        f.update({
+                            'quality': quality_key(quality),
+                            'format_note': quality.upper(),
+                        })
+                        break
+                f['format_id'] = f_id
+                formats.append(f)
+        self._sort_formats(formats)
+
+        title = self._og_search_title(
+            webpage, default=None) or self._search_regex(
+            (r'<value>(?P<title>[^<]+)',
+             r'videoTitle\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'title', group='value')
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or self._search_regex(
+            r'poster\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'thumbnail', fatal=False, group='value')
+        duration = int_or_none(self._search_regex(
+            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
 class NovaIE(InfoExtractor):
     IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
     _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
     _TESTS = [{
-        'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus',
-        'info_dict': {
-            'id': '1608920',
-            'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou',
-            'ext': 'flv',
-            'title': 'Duel: Michal Hrdlička a Petr Suchoň',
-            'description': 'md5:d0cc509858eee1b1374111c588c6f5d5',
-            'thumbnail': r're:^https?://.*\.(?:jpg)',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
-    }, {
         'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
         'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
         'info_dict': {
@@ -38,33 +100,6 @@ class NovaIE(InfoExtractor):
             'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53',
             'thumbnail': r're:^https?://.*\.(?:jpg)',
         }
-    }, {
-        'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove',
-        'info_dict': {
-            'id': '1756825',
-            'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove',
-            'ext': 'flv',
-            'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově',
-            'description': 'md5:dc24e50be5908df83348e50d1431295e',  # Make sure this description is clean of html tags
-            'thumbnail': r're:^https?://.*\.(?:jpg)',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
-    }, {
-        'url': 'http://novaplus.nova.cz/porad/televizni-noviny/video/5585-televizni-noviny-30-5-2015/',
-        'info_dict': {
-            'id': '1756858',
-            'ext': 'flv',
-            'title': 'Televizní noviny - 30. 5. 2015',
-            'thumbnail': r're:^https?://.*\.(?:jpg)',
-            'upload_date': '20150530',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
     }, {
         'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
         'info_dict': {
@@ -79,6 +114,20 @@ class NovaIE(InfoExtractor):
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        # media.cms.nova.cz embed
+        'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
+        'info_dict': {
+            'id': '8o0n0r',
+            'ext': 'mp4',
+            'title': '2180. díl',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 2578,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [NovaEmbedIE.ie_key()],
     }, {
         'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
         'only_matching': True,
@@ -103,6 +152,15 @@ class NovaIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
+        # novaplus
+        embed_id = self._search_regex(
+            r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
+            webpage, 'embed url', default=None)
+        if embed_id:
+            return self.url_result(
+                'https://media.cms.nova.cz/embed/%s' % embed_id,
+                ie=NovaEmbedIE.ie_key(), video_id=embed_id)
+
         video_id = self._search_regex(
             [r"(?:media|video_id)\s*:\s*'(\d+)'",
              r'media=(\d+)',
@@ -111,8 +169,21 @@ class NovaIE(InfoExtractor):
             webpage, 'video id')
 
         config_url = self._search_regex(
-            r'src="(http://tn\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"',
+            r'src="(https?://(?:tn|api)\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"',
             webpage, 'config url', default=None)
+        config_params = {}
+
+        if not config_url:
+            player = self._parse_json(
+                self._search_regex(
+                    r'(?s)Player\s*\(.+?\s*,\s*({.+?\bmedia\b["\']?\s*:\s*["\']?\d+.+?})\s*\)', webpage,
+                    'player', default='{}'),
+                video_id, transform_source=js_to_json, fatal=False)
+            if player:
+                config_url = url_or_none(player.get('configUrl'))
+                params = player.get('configParams')
+                if isinstance(params, dict):
+                    config_params = params
 
         if not config_url:
             DEFAULT_SITE_ID = '23000'
@@ -127,14 +198,20 @@ class NovaIE(InfoExtractor):
             }
 
             site_id = self._search_regex(
-                r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(site, DEFAULT_SITE_ID)
+                r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(
+                site, DEFAULT_SITE_ID)
 
-            config_url = ('http://tn.nova.cz/bin/player/videojs/config.php?site=%s&media=%s&jsVar=vjsconfig'
-                          % (site_id, video_id))
+            config_url = 'https://api.nova.cz/bin/player/videojs/config.php'
+            config_params = {
+                'site': site_id,
+                'media': video_id,
+                'quality': 3,
+                'version': 1,
+            }
 
         config = self._download_json(
             config_url, display_id,
-            'Downloading config JSON',
+            'Downloading config JSON', query=config_params,
             transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
 
         mediafile = config['mediafile']

youtube_dl/extractor/nzz.py

@@ -11,20 +11,27 @@ from ..utils import (
 
 class NZZIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
         'info_dict': {
             'id': '9153',
         },
         'playlist_mincount': 6,
-    }
+    }, {
+        'url': 'https://www.nzz.ch/video/nzz-standpunkte/cvp-auf-der-suche-nach-dem-mass-der-mitte-ld.1368112',
+        'info_dict': {
+            'id': '1368112',
+        },
+        'playlist_count': 1,
+    }]
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
 
         entries = []
-        for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage):
+        for player_element in re.findall(
+                r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage):
             player_params = extract_attributes(player_element)
             if player_params.get('data-type') not in ('kaltura_singleArticle',):
                 self.report_warning('Unsupported player type')

youtube_dl/extractor/openload.py

@@ -243,7 +243,18 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?P<host>
+                            (?:www\.)?
+                            (?:
+                                openload\.(?:co|io|link)|
+                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun)
+                            )
+                        )/
+                        (?:f|embed)/
+                        (?P<id>[a-zA-Z0-9-_]+)
+                    '''
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -307,10 +318,22 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.download/f/kUEfGclsU9o',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.cloud/f/4ZDnBXRWiB8',
+        'only_matching': True,
     }, {
         # Its title has not got its extension but url has it
         'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.cc/embed/5NEAbI2BDSk',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.icu/f/-_i4y_F_Hs8',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.fun/f/gb6G1H4sHXY',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
@@ -322,8 +345,11 @@ class OpenloadIE(InfoExtractor):
             webpage)
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        url_pattern = 'https://openload.co/%%s/%s/' % video_id
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        video_id = mobj.group('id')
+
+        url_pattern = 'https://%s/%%s/%s/' % (host, video_id)
         headers = {
             'User-Agent': self._USER_AGENT,
         }
@@ -356,7 +382,7 @@ class OpenloadIE(InfoExtractor):
                            r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
                           'stream URL'))
 
-        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
+        video_url = 'https://%s/stream/%s?mime=true' % (host, decoded_id)
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -367,7 +393,7 @@ class OpenloadIE(InfoExtractor):
         entry = entries[0] if entries else {}
         subtitles = entry.get('subtitles')
 
-        info_dict = {
+        return {
             'id': video_id,
             'title': title,
             'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
@@ -376,4 +402,3 @@ class OpenloadIE(InfoExtractor):
             'subtitles': subtitles,
             'http_headers': headers,
         }
-        return info_dict

youtube_dl/extractor/orf.py

@@ -15,6 +15,7 @@ from ..utils import (
     strip_jsonp,
     unescapeHTML,
     unified_strdate,
+    url_or_none,
 )
 
 
@@ -68,26 +69,35 @@ class ORFTVthekIE(InfoExtractor):
                 webpage, 'playlist', group='json'),
             playlist_id, transform_source=unescapeHTML)['playlist']['videos']
 
-        def quality_to_int(s):
-            m = re.search('([0-9]+)', s)
-            if m is None:
-                return -1
-            return int(m.group(1))
-
         entries = []
         for sd in data_jsb:
             video_id, title = sd.get('id'), sd.get('title')
             if not video_id or not title:
                 continue
             video_id = compat_str(video_id)
-            formats = [{
-                'preference': -10 if fd['delivery'] == 'hls' else None,
-                'format_id': '%s-%s-%s' % (
-                    fd['delivery'], fd['quality'], fd['quality_string']),
-                'url': fd['src'],
-                'protocol': fd['protocol'],
-                'quality': quality_to_int(fd['quality']),
-            } for fd in sd['sources']]
+            formats = []
+            for fd in sd['sources']:
+                src = url_or_none(fd.get('src'))
+                if not src:
+                    continue
+                format_id_list = []
+                for key in ('delivery', 'quality', 'quality_string'):
+                    value = fd.get(key)
+                    if value:
+                        format_id_list.append(value)
+                format_id = '-'.join(format_id_list)
+                if determine_ext(fd['src']) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        fd['src'], video_id, 'mp4', m3u8_id=format_id))
+                elif determine_ext(fd['src']) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        fd['src'], video_id, f4m_id=format_id))
+                else:
+                    formats.append({
+                        'format_id': format_id,
+                        'url': src,
+                        'protocol': fd.get('protocol'),
+                    })
 
             # Check for geoblocking.
             # There is a property is_geoprotection, but that's always false

youtube_dl/extractor/patreon.py

@@ -2,52 +2,63 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import js_to_json
+from ..utils import (
+    clean_html,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class PatreonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)'
-    _TESTS = [
-        {
-            'url': 'http://www.patreon.com/creation?hid=743933',
-            'md5': 'e25505eec1053a6e6813b8ed369875cc',
-            'info_dict': {
-                'id': '743933',
-                'ext': 'mp3',
-                'title': 'Episode 166: David Smalley of Dogma Debate',
-                'uploader': 'Cognitive Dissonance Podcast',
-                'thumbnail': 're:^https?://.*$',
-            },
+    _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.patreon.com/creation?hid=743933',
+        'md5': 'e25505eec1053a6e6813b8ed369875cc',
+        'info_dict': {
+            'id': '743933',
+            'ext': 'mp3',
+            'title': 'Episode 166: David Smalley of Dogma Debate',
+            'description': 'md5:713b08b772cd6271b9f3906683cfacdf',
+            'uploader': 'Cognitive Dissonance Podcast',
+            'thumbnail': 're:^https?://.*$',
+            'timestamp': 1406473987,
+            'upload_date': '20140727',
         },
-        {
-            'url': 'http://www.patreon.com/creation?hid=754133',
-            'md5': '3eb09345bf44bf60451b8b0b81759d0a',
-            'info_dict': {
-                'id': '754133',
-                'ext': 'mp3',
-                'title': 'CD 167 Extra',
-                'uploader': 'Cognitive Dissonance Podcast',
-                'thumbnail': 're:^https?://.*$',
-            },
+    }, {
+        'url': 'http://www.patreon.com/creation?hid=754133',
+        'md5': '3eb09345bf44bf60451b8b0b81759d0a',
+        'info_dict': {
+            'id': '754133',
+            'ext': 'mp3',
+            'title': 'CD 167 Extra',
+            'uploader': 'Cognitive Dissonance Podcast',
+            'thumbnail': 're:^https?://.*$',
         },
-        {
-            'url': 'https://www.patreon.com/creation?hid=1682498',
-            'info_dict': {
-                'id': 'SU4fj_aEMVw',
-                'ext': 'mp4',
-                'title': 'I\'m on Patreon!',
-                'uploader': 'TraciJHines',
-                'thumbnail': 're:^https?://.*$',
-                'upload_date': '20150211',
-                'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
-                'uploader_id': 'TraciJHines',
-            },
-            'params': {
-                'noplaylist': True,
-                'skip_download': True,
-            }
+        'skip': 'Patron-only content',
+    }, {
+        'url': 'https://www.patreon.com/creation?hid=1682498',
+        'info_dict': {
+            'id': 'SU4fj_aEMVw',
+            'ext': 'mp4',
+            'title': 'I\'m on Patreon!',
+            'uploader': 'TraciJHines',
+            'thumbnail': 're:^https?://.*$',
+            'upload_date': '20150211',
+            'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
+            'uploader_id': 'TraciJHines',
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': True,
         }
-    ]
+    }, {
+        'url': 'https://www.patreon.com/posts/episode-166-of-743933',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.patreon.com/posts/743933',
+        'only_matching': True,
+    }]
 
     # Currently Patreon exposes download URL via hidden CSS, so login is not
     # needed. Keeping this commented for when this inevitably changes.
@@ -78,38 +89,48 @@ class PatreonIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        title = self._og_search_title(webpage).strip()
-
-        attach_fn = self._html_search_regex(
-            r'<div class="attach"><a target="_blank" href="([^"]+)">',
-            webpage, 'attachment URL', default=None)
-        embed = self._html_search_regex(
-            r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"',
-            webpage, 'embedded URL', default=None)
-
-        if attach_fn is not None:
-            video_url = 'http://www.patreon.com' + attach_fn
-            thumbnail = self._og_search_thumbnail(webpage)
-            uploader = self._html_search_regex(
-                r'<strong>(.*?)</strong> is creating', webpage, 'uploader')
-        elif embed is not None:
-            return self.url_result(embed)
-        else:
-            playlist = self._parse_json(self._search_regex(
-                r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])',
-                webpage, 'playlist JSON'),
-                video_id, transform_source=js_to_json)
-            data = playlist[0]
-            video_url = self._proto_relative_url(data['mp3'])
-            thumbnail = self._proto_relative_url(data.get('cover'))
-            uploader = data.get('artist')
-
-        return {
+        post = self._download_json(
+            'https://www.patreon.com/api/posts/' + video_id, video_id)
+        attributes = post['data']['attributes']
+        title = attributes['title'].strip()
+        image = attributes.get('image') or {}
+        info = {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp3',
             'title': title,
-            'uploader': uploader,
-            'thumbnail': thumbnail,
+            'description': clean_html(attributes.get('content')),
+            'thumbnail': image.get('large_url') or image.get('url'),
+            'timestamp': parse_iso8601(attributes.get('published_at')),
+            'like_count': int_or_none(attributes.get('like_count')),
+            'comment_count': int_or_none(attributes.get('comment_count')),
         }
+
+        def add_file(file_data):
+            file_url = file_data.get('url')
+            if file_url:
+                info.update({
+                    'url': file_url,
+                    'ext': determine_ext(file_data.get('name'), 'mp3'),
+                })
+
+        for i in post.get('included', []):
+            i_type = i.get('type')
+            if i_type == 'attachment':
+                add_file(i.get('attributes') or {})
+            elif i_type == 'user':
+                user_attributes = i.get('attributes')
+                if user_attributes:
+                    info.update({
+                        'uploader': user_attributes.get('full_name'),
+                        'uploader_url': user_attributes.get('url'),
+                    })
+
+        if not info.get('url'):
+            add_file(attributes.get('post_file') or {})
+
+        if not info.get('url'):
+            info.update({
+                '_type': 'url',
+                'url': attributes['embed']['url'],
+            })
+
+        return info

youtube_dl/extractor/philharmoniedeparis.py

@@ -2,31 +2,38 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    float_or_none,
-    int_or_none,
-    parse_iso8601,
-    xpath_text,
+    try_get,
+    urljoin,
 )
 
 
 class PhilharmonieDeParisIE(InfoExtractor):
     IE_DESC = 'Philharmonie de Paris'
-    _VALID_URL = r'https?://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
+                            pad\.philharmoniedeparis\.fr/doc/CIMU/
+                        )
+                        (?P<id>\d+)
+                    '''
     _TESTS = [{
+        'url': 'http://pad.philharmoniedeparis.fr/doc/CIMU/1086697/jazz-a-la-villette-knower',
+        'md5': 'a0a4b195f544645073631cbec166a2c2',
+        'info_dict': {
+            'id': '1086697',
+            'ext': 'mp4',
+            'title': 'Jazz à la Villette : Knower',
+        },
+    }, {
         'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
         'info_dict': {
             'id': '1032066',
-            'ext': 'flv',
-            'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
-            'timestamp': 1428179400,
-            'upload_date': '20150404',
-            'duration': 6592.278,
+            'title': 'md5:0a031b81807b3593cffa3c9a87a167a0',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
+        'playlist_mincount': 2,
     }, {
         'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
         'only_matching': True,
@@ -34,45 +41,60 @@ class PhilharmonieDeParisIE(InfoExtractor):
         'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
         'only_matching': True,
     }]
+    _LIVE_URL = 'https://live.philharmoniedeparis.fr'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        concert = self._download_xml(
-            'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
-            video_id).find('./concert')
+        config = self._download_json(
+            '%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={
+                'id': video_id,
+                'lang': 'fr-FR',
+            })
 
-        formats = []
-        info_dict = {
-            'id': video_id,
-            'title': xpath_text(concert, './titre', 'title', fatal=True),
-            'formats': formats,
-        }
-
-        fichiers = concert.find('./fichiers')
-        stream = fichiers.attrib['serveurstream']
-        for fichier in fichiers.findall('./fichier'):
-            info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
-            for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
-                format_url = fichier.get('url%s' % suffix)
-                if not format_url:
+        def extract_entry(source):
+            if not isinstance(source, dict):
+                return
+            title = source.get('title')
+            if not title:
+                return
+            files = source.get('files')
+            if not isinstance(files, dict):
+                return
+            format_urls = set()
+            formats = []
+            for format_id in ('mobile', 'desktop'):
+                format_url = try_get(
+                    files, lambda x: x[format_id]['file'], compat_str)
+                if not format_url or format_url in format_urls:
                     continue
-                formats.append({
-                    'url': stream,
-                    'play_path': format_url,
-                    'ext': 'flv',
-                    'format_id': format_id,
-                    'width': int_or_none(concert.get('largeur%s' % suffix)),
-                    'height': int_or_none(concert.get('hauteur%s' % suffix)),
-                    'quality': quality,
-                })
-        self._sort_formats(formats)
+                format_urls.add(format_url)
+                m3u8_url = urljoin(self._LIVE_URL, format_url)
+                formats.extend(self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            if not formats:
+                return
+            self._sort_formats(formats)
+            return {
+                'title': title,
+                'formats': formats,
+            }
 
-        date, hour = concert.get('date'), concert.get('heure')
-        if date and hour:
-            info_dict['timestamp'] = parse_iso8601(
-                '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
-        elif date:
-            info_dict['upload_date'] = date
+        thumbnail = urljoin(self._LIVE_URL, config.get('image'))
 
-        return info_dict
+        info = extract_entry(config)
+        if info:
+            info.update({
+                'id': video_id,
+                'thumbnail': thumbnail,
+            })
+            return info
+
+        entries = []
+        for num, chapter in enumerate(config['chapters'], start=1):
+            entry = extract_entry(chapter)
+            entry['id'] = '%s-%d' % (video_id, num)
+            entries.append(entry)
+
+        return self.playlist_result(entries, video_id, config.get('title'))

youtube_dl/extractor/picarto.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
 import time
 
 from .common import InfoExtractor
@@ -15,7 +16,7 @@ from ..utils import (
 
 
 class PicartoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?'
     _TEST = {
         'url': 'https://picarto.tv/Setz',
         'info_dict': {
@@ -33,20 +34,14 @@ class PicartoIE(InfoExtractor):
         return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        channel_id = self._match_id(url)
-        stream_page = self._download_webpage(url, channel_id)
+        mobj = re.match(self._VALID_URL, url)
+        channel_id = mobj.group('id')
 
-        if '>This channel does not exist' in stream_page:
-            raise ExtractorError(
-                'Channel %s does not exist' % channel_id, expected=True)
+        metadata = self._download_json(
+            'https://api.picarto.tv/v1/channel/name/' + channel_id,
+            channel_id)
 
-        player = self._parse_json(
-            self._search_regex(
-                r'(?s)playerSettings\[\d+\]\s*=\s*(\{.+?\}\s*\n)', stream_page,
-                'player settings'),
-            channel_id, transform_source=js_to_json)
-
-        if player.get('online') is False:
+        if metadata.get('online') is False:
             raise ExtractorError('Stream is offline', expected=True)
 
         cdn_data = self._download_json(
@@ -54,20 +49,13 @@ class PicartoIE(InfoExtractor):
             data=urlencode_postdata({'loadbalancinginfo': channel_id}),
             note='Downloading load balancing info')
 
-        def get_event(key):
-            return try_get(player, lambda x: x['event'][key], compat_str) or ''
-
+        token = mobj.group('token') or 'public'
         params = {
-            'token': player.get('token') or '',
-            'ticket': get_event('ticket'),
             'con': int(time.time() * 1000),
-            'type': get_event('ticket'),
-            'scope': get_event('scope'),
+            'token': token,
         }
 
         prefered_edge = cdn_data.get('preferedEdge')
-        default_tech = player.get('defaultTech')
-
         formats = []
 
         for edge in cdn_data['edges']:
@@ -81,8 +69,6 @@ class PicartoIE(InfoExtractor):
                 preference = 0
                 if edge_id == prefered_edge:
                     preference += 1
-                if tech_type == default_tech:
-                    preference += 1
                 format_id = []
                 if edge_id:
                     format_id.append(edge_id)
@@ -109,7 +95,7 @@ class PicartoIE(InfoExtractor):
                     continue
         self._sort_formats(formats)
 
-        mature = player.get('mature')
+        mature = metadata.get('adult')
         if mature is None:
             age_limit = None
         else:
@@ -117,9 +103,11 @@ class PicartoIE(InfoExtractor):
 
         return {
             'id': channel_id,
-            'title': self._live_title(channel_id),
+            'title': self._live_title(metadata.get('title') or channel_id),
             'is_live': True,
-            'thumbnail': player.get('vodThumb'),
+            'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']),
+            'channel': channel_id,
+            'channel_url': 'https://picarto.tv/%s' % channel_id,
             'age_limit': age_limit,
             'formats': formats,
         }

youtube_dl/extractor/pluralsight.py

@@ -4,6 +4,7 @@ import collections
 import json
 import os
 import random
+import re
 
 from .common import InfoExtractor
 from ..compat import (
@@ -196,7 +197,10 @@ query viewClip {
         if error:
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
-        if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
+        if all(not re.search(p, response) for p in (
+                r'__INITIAL_STATE__', r'["\']currentUser["\']',
+                # new layout?
+                r'>\s*Sign out\s*<')):
             BLOCKED = 'Your account has been blocked due to suspicious activity'
             if BLOCKED in response:
                 raise ExtractorError(
@@ -210,18 +214,26 @@ query viewClip {
 
             raise ExtractorError('Unable to log in')
 
-    def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id):
-        captions_post = {
-            'a': author,
-            'cn': clip_idx,
-            'lc': lang,
-            'm': name,
-        }
-        captions = self._download_json(
-            '%s/player/retrieve-captions' % self._API_BASE, video_id,
-            'Downloading captions JSON', 'Unable to download captions JSON',
-            fatal=False, data=json.dumps(captions_post).encode('utf-8'),
-            headers={'Content-Type': 'application/json;charset=utf-8'})
+    def _get_subtitles(self, author, clip_idx, clip_id, lang, name, duration, video_id):
+        captions = None
+        if clip_id:
+            captions = self._download_json(
+                '%s/transcript/api/v1/caption/json/%s/%s'
+                % (self._API_BASE, clip_id, lang), video_id,
+                'Downloading captions JSON', 'Unable to download captions JSON',
+                fatal=False)
+        if not captions:
+            captions_post = {
+                'a': author,
+                'cn': int(clip_idx),
+                'lc': lang,
+                'm': name,
+            }
+            captions = self._download_json(
+                '%s/player/retrieve-captions' % self._API_BASE, video_id,
+                'Downloading captions JSON', 'Unable to download captions JSON',
+                fatal=False, data=json.dumps(captions_post).encode('utf-8'),
+                headers={'Content-Type': 'application/json;charset=utf-8'})
         if captions:
             return {
                 lang: [{
@@ -413,7 +425,7 @@ query viewClip {
 
         # TODO: other languages?
         subtitles = self.extract_subtitles(
-            author, clip_idx, 'en', name, duration, display_id)
+            author, clip_idx, clip.get('clipId'), 'en', name, duration, display_id)
 
         return {
             'id': clip_id,

youtube_dl/extractor/popcorntv.py

@@ -58,8 +58,6 @@ class PopcornTVIE(InfoExtractor):
         thumbnail = self._og_search_thumbnail(webpage)
         timestamp = unified_timestamp(self._html_search_meta(
             'uploadDate', webpage, 'timestamp'))
-        print(self._html_search_meta(
-            'duration', webpage))
         duration = int_or_none(self._html_search_meta(
             'duration', webpage), invscale=60)
         view_count = int_or_none(self._html_search_meta(

youtube_dl/extractor/pornhub.py

@@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -40,6 +40,7 @@ class PornHubIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
             'uploader': 'Babes',
+            'upload_date': '20130628',
             'duration': 361,
             'view_count': int,
             'like_count': int,
@@ -57,6 +58,7 @@ class PornHubIE(InfoExtractor):
             'ext': 'mp4',
             'title': '重庆婷婷女王足交',
             'uploader': 'Unknown',
+            'upload_date': '20150213',
             'duration': 1753,
             'view_count': int,
             'like_count': int,
@@ -119,12 +121,15 @@ class PornHubIE(InfoExtractor):
     }, {
         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
         'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
             webpage)
 
     def _extract_count(self, pattern, webpage, name):
@@ -132,14 +137,16 @@ class PornHubIE(InfoExtractor):
             pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host') or 'pornhub.com'
+        video_id = mobj.group('id')
 
-        self._set_cookie('pornhub.com', 'age_verified', '1')
+        self._set_cookie(host, 'age_verified', '1')
 
         def dl_webpage(platform):
-            self._set_cookie('pornhub.com', 'platform', platform)
+            self._set_cookie(host, 'platform', platform)
             return self._download_webpage(
-                'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
+                'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
                 video_id, 'Downloading %s webpage' % platform)
 
         webpage = dl_webpage('pc')
@@ -237,8 +244,14 @@ class PornHubIE(InfoExtractor):
                 video_urls.append((video_url, None))
                 video_urls_set.add(video_url)
 
+        upload_date = None
         formats = []
         for video_url, height in video_urls:
+            if not upload_date:
+                upload_date = self._search_regex(
+                    r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
+                if upload_date:
+                    upload_date = upload_date.replace('/', '')
             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:
@@ -254,7 +267,7 @@ class PornHubIE(InfoExtractor):
         self._sort_formats(formats)
 
         video_uploader = self._html_search_regex(
-            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
 
         view_count = self._extract_count(
@@ -278,6 +291,7 @@ class PornHubIE(InfoExtractor):
         return {
             'id': video_id,
             'uploader': video_uploader,
+            'upload_date': upload_date,
             'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
@@ -294,7 +308,7 @@ class PornHubIE(InfoExtractor):
 
 
 class PornHubPlaylistBaseIE(InfoExtractor):
-    def _extract_entries(self, webpage):
+    def _extract_entries(self, webpage, host):
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see
         # https://github.com/rg3/youtube-dl/issues/11594).
@@ -304,7 +318,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
         return [
             self.url_result(
-                'http://www.pornhub.com/%s' % video_url,
+                'http://www.%s/%s' % (host, video_url),
                 PornHubIE.ie_key(), video_title=title)
             for video_url, title in orderedSet(re.findall(
                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
@@ -312,11 +326,13 @@ class PornHubPlaylistBaseIE(InfoExtractor):
         ]
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        playlist_id = mobj.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = self._extract_entries(webpage)
+        entries = self._extract_entries(webpage, host)
 
         playlist = self._parse_json(
             self._search_regex(
@@ -331,7 +347,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {
@@ -346,7 +362,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {
@@ -378,10 +394,18 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }, {
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        user_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        user_id = mobj.group('id')
 
         entries = []
         for page_num in itertools.count(1):
@@ -393,7 +417,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
                 raise
-            page_entries = self._extract_entries(webpage)
+            page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
             entries.extend(page_entries)

youtube_dl/extractor/radiojavan.py

@@ -4,8 +4,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
+    parse_resolution,
     str_to_int,
+    unified_strdate,
+    urlencode_postdata,
+    urljoin,
 )
 
 
@@ -29,13 +32,26 @@ class RadioJavanIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        download_host = self._download_json(
+            'https://www.radiojavan.com/videos/video_host', video_id,
+            data=urlencode_postdata({'id': video_id}),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Referer': url,
+            }).get('host', 'https://host1.rjmusicmedia.com')
+
         webpage = self._download_webpage(url, video_id)
 
-        formats = [{
-            'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
-            'format_id': '%sp' % height,
-            'height': int(height),
-        } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
+        formats = []
+        for format_id, _, video_path in re.findall(
+                r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage):
+            f = parse_resolution(format_id)
+            f.update({
+                'url': urljoin(download_host, video_path),
+                'format_id': format_id,
+            })
+            formats.append(f)
         self._sort_formats(formats)
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/rai.py

@@ -274,7 +274,6 @@ class RaiPlayPlaylistIE(InfoExtractor):
             ('programma', 'nomeProgramma'), webpage, 'title')
         description = unescapeHTML(self._html_search_meta(
             ('description', 'og:description'), webpage, 'description'))
-        print(description)
 
         entries = []
         for mobj in re.finditer(

youtube_dl/extractor/raywenderlich.py

@@ -4,24 +4,37 @@ import re
 
 from .common import InfoExtractor
 from .vimeo import VimeoIE
+from ..compat import compat_str
 from ..utils import (
-    extract_attributes,
     ExtractorError,
-    smuggle_url,
-    unsmuggle_url,
+    int_or_none,
+    merge_dicts,
+    try_get,
+    unescapeHTML,
+    unified_timestamp,
     urljoin,
 )
 
 
 class RayWenderlichIE(InfoExtractor):
-    _VALID_URL = r'https?://videos\.raywenderlich\.com/courses/(?P<course_id>[^/]+)/lessons/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            videos\.raywenderlich\.com/courses|
+                            (?:www\.)?raywenderlich\.com
+                        )/
+                        (?P<course_id>[^/]+)/lessons/(?P<id>\d+)
+                    '''
 
     _TESTS = [{
-        'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
+        'url': 'https://www.raywenderlich.com/3530-testing-in-ios/lessons/1',
         'info_dict': {
             'id': '248377018',
             'ext': 'mp4',
-            'title': 'Testing In iOS Episode 1: Introduction',
+            'title': 'Introduction',
+            'description': 'md5:804d031b3efa9fcb49777d512d74f722',
+            'timestamp': 1513906277,
+            'upload_date': '20171222',
             'duration': 133,
             'uploader': 'Ray Wenderlich',
             'uploader_id': 'user3304672',
@@ -34,69 +47,133 @@ class RayWenderlichIE(InfoExtractor):
         'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
         'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_video_id(data, lesson_id):
+        if not data:
+            return
+        groups = try_get(data, lambda x: x['groups'], list) or []
+        if not groups:
+            return
+        for group in groups:
+            if not isinstance(group, dict):
+                continue
+            contents = try_get(data, lambda x: x['contents'], list) or []
+            for content in contents:
+                if not isinstance(content, dict):
+                    continue
+                ordinal = int_or_none(content.get('ordinal'))
+                if ordinal != lesson_id:
+                    continue
+                video_id = content.get('identifier')
+                if video_id:
+                    return compat_str(video_id)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        course_id, lesson_id = mobj.group('course_id', 'id')
+        display_id = '%s/%s' % (course_id, lesson_id)
+
+        webpage = self._download_webpage(url, display_id)
+
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or self._html_search_meta(
+            'twitter:image', webpage, 'thumbnail')
+
+        if '>Subscribe to unlock' in webpage:
+            raise ExtractorError(
+                'This content is only available for subscribers',
+                expected=True)
+
+        info = {
+            'thumbnail': thumbnail,
+        }
+
+        vimeo_id = self._search_regex(
+            r'data-vimeo-id=["\'](\d+)', webpage, 'vimeo id', default=None)
+
+        if not vimeo_id:
+            data = self._parse_json(
+                self._search_regex(
+                    r'data-collection=(["\'])(?P<data>{.+?})\1', webpage,
+                    'data collection', default='{}', group='data'),
+                display_id, transform_source=unescapeHTML, fatal=False)
+            video_id = self._extract_video_id(
+                data, lesson_id) or self._search_regex(
+                r'/videos/(\d+)/', thumbnail, 'video id')
+            headers = {
+                'Referer': url,
+                'X-Requested-With': 'XMLHttpRequest',
+            }
+            csrf_token = self._html_search_meta(
+                'csrf-token', webpage, 'csrf token', default=None)
+            if csrf_token:
+                headers['X-CSRF-Token'] = csrf_token
+            video = self._download_json(
+                'https://videos.raywenderlich.com/api/v1/videos/%s.json'
+                % video_id, display_id, headers=headers)['video']
+            vimeo_id = video['clips'][0]['provider_id']
+            info.update({
+                '_type': 'url_transparent',
+                'title': video.get('name'),
+                'description': video.get('description') or video.get(
+                    'meta_description'),
+                'duration': int_or_none(video.get('duration')),
+                'timestamp': unified_timestamp(video.get('created_at')),
+            })
+
+        return merge_dicts(info, self.url_result(
+            VimeoIE._smuggle_referrer(
+                'https://player.vimeo.com/video/%s' % vimeo_id, url),
+            ie=VimeoIE.ie_key(), video_id=vimeo_id))
+
+
+class RayWenderlichCourseIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            videos\.raywenderlich\.com/courses|
+                            (?:www\.)?raywenderlich\.com
+                        )/
+                        (?P<id>[^/]+)
+                    '''
+
+    _TEST = {
+        'url': 'https://www.raywenderlich.com/3530-testing-in-ios',
         'info_dict': {
             'title': 'Testing in iOS',
-            'id': '105-testing-in-ios',
+            'id': '3530-testing-in-ios',
         },
         'params': {
             'noplaylist': False,
         },
         'playlist_count': 29,
-    }]
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if RayWenderlichIE.suitable(url) else super(
+            RayWenderlichCourseIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url, {})
+        course_id = self._match_id(url)
 
-        mobj = re.match(self._VALID_URL, url)
-        course_id, lesson_id = mobj.group('course_id', 'id')
-        video_id = '%s/%s' % (course_id, lesson_id)
-
-        webpage = self._download_webpage(url, video_id)
-
-        no_playlist = self._downloader.params.get('noplaylist')
-        if no_playlist or smuggled_data.get('force_video', False):
-            if no_playlist:
-                self.to_screen(
-                    'Downloading just video %s because of --no-playlist'
-                    % video_id)
-            if '>Subscribe to unlock' in webpage:
-                raise ExtractorError(
-                    'This content is only available for subscribers',
-                    expected=True)
-            vimeo_id = self._search_regex(
-                r'data-vimeo-id=["\'](\d+)', webpage, 'video id')
-            return self.url_result(
-                VimeoIE._smuggle_referrer(
-                    'https://player.vimeo.com/video/%s' % vimeo_id, url),
-                ie=VimeoIE.ie_key(), video_id=vimeo_id)
-
-        self.to_screen(
-            'Downloading playlist %s - add --no-playlist to just download video'
-            % course_id)
-
-        lesson_ids = set((lesson_id, ))
-        for lesson in re.findall(
-                r'(<a[^>]+\bclass=["\']lesson-link[^>]+>)', webpage):
-            attrs = extract_attributes(lesson)
-            if not attrs:
-                continue
-            lesson_url = attrs.get('href')
-            if not lesson_url:
-                continue
-            lesson_id = self._search_regex(
-                r'/lessons/(\d+)', lesson_url, 'lesson id', default=None)
-            if not lesson_id:
-                continue
-            lesson_ids.add(lesson_id)
+        webpage = self._download_webpage(url, course_id)
 
         entries = []
-        for lesson_id in sorted(lesson_ids):
+        lesson_urls = set()
+        for lesson_url in re.findall(
+                r'<a[^>]+\bhref=["\'](/%s/lessons/\d+)' % course_id, webpage):
+            if lesson_url in lesson_urls:
+                continue
+            lesson_urls.add(lesson_url)
             entries.append(self.url_result(
-                smuggle_url(urljoin(url, lesson_id), {'force_video': True}),
-                ie=RayWenderlichIE.ie_key()))
+                urljoin(url, lesson_url), ie=RayWenderlichIE.ie_key()))
 
-        title = self._search_regex(
-            r'class=["\']course-title[^>]+>([^<]+)', webpage, 'course title',
-            default=None)
+        title = self._og_search_title(
+            webpage, default=None) or self._html_search_meta(
+            'twitter:title', webpage, 'title', default=None)
 
         return self.playlist_result(entries, course_id, title)

youtube_dl/extractor/redbulltv.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class RedBullTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?redbull\.tv/video/(?P<id>AP-\w+)'
+    _VALID_URL = r'https?://(?:www\.)?redbull(?:\.tv|\.com/(?:[^/]+/)?tv)/video/(?P<id>AP-\w+)'
     _TESTS = [{
         # film
         'url': 'https://www.redbull.tv/video/AP-1Q6XCDTAN1W11',
@@ -35,6 +35,9 @@ class RedBullTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.redbull.com/int-en/tv/video/AP-1UWHCAR9S1W11/rob-meets-sam-gaze?playlist=playlists::3f81040a-2f31-4832-8e2e-545b1d39d173',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/rte.py

@@ -8,7 +8,10 @@ from ..compat import compat_HTTPError
 from ..utils import (
     float_or_none,
     parse_iso8601,
+    str_or_none,
+    try_get,
     unescapeHTML,
+    url_or_none,
     ExtractorError,
 )
 
@@ -17,65 +20,87 @@ class RteBaseIE(InfoExtractor):
     def _real_extract(self, url):
         item_id = self._match_id(url)
 
-        try:
-            json_string = self._download_json(
-                'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
-                item_id)
-        except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
-                error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False)
-                if error_info:
-                    raise ExtractorError(
-                        '%s said: %s' % (self.IE_NAME, error_info['message']),
-                        expected=True)
-            raise
-
-        # NB the string values in the JSON are stored using XML escaping(!)
-        show = json_string['shows'][0]
-        title = unescapeHTML(show['title'])
-        description = unescapeHTML(show.get('description'))
-        thumbnail = show.get('thumbnail')
-        duration = float_or_none(show.get('duration'), 1000)
-        timestamp = parse_iso8601(show.get('published'))
-
-        mg = show['media:group'][0]
-
+        info_dict = {}
         formats = []
 
-        if mg.get('url'):
-            m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url'])
-            if m:
-                m = m.groupdict()
-                formats.append({
-                    'url': m['url'] + '/' + m['app'],
-                    'app': m['app'],
-                    'play_path': m['playpath'],
-                    'player_url': url,
-                    'ext': 'flv',
-                    'format_id': 'rtmp',
-                })
+        ENDPOINTS = (
+            'https://feeds.rasset.ie/rteavgen/player/playlist?type=iptv&format=json&showId=',
+            'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=',
+        )
 
-        if mg.get('hls_server') and mg.get('hls_url'):
-            formats.extend(self._extract_m3u8_formats(
-                mg['hls_server'] + mg['hls_url'], item_id, 'mp4',
-                entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+        for num, ep_url in enumerate(ENDPOINTS, start=1):
+            try:
+                data = self._download_json(ep_url + item_id, item_id)
+            except ExtractorError as ee:
+                if num < len(ENDPOINTS) or formats:
+                    continue
+                if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                    error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False)
+                    if error_info:
+                        raise ExtractorError(
+                            '%s said: %s' % (self.IE_NAME, error_info['message']),
+                            expected=True)
+                raise
 
-        if mg.get('hds_server') and mg.get('hds_url'):
-            formats.extend(self._extract_f4m_formats(
-                mg['hds_server'] + mg['hds_url'], item_id,
-                f4m_id='hds', fatal=False))
+            # NB the string values in the JSON are stored using XML escaping(!)
+            show = try_get(data, lambda x: x['shows'][0], dict)
+            if not show:
+                continue
+
+            if not info_dict:
+                title = unescapeHTML(show['title'])
+                description = unescapeHTML(show.get('description'))
+                thumbnail = show.get('thumbnail')
+                duration = float_or_none(show.get('duration'), 1000)
+                timestamp = parse_iso8601(show.get('published'))
+                info_dict = {
+                    'id': item_id,
+                    'title': title,
+                    'description': description,
+                    'thumbnail': thumbnail,
+                    'timestamp': timestamp,
+                    'duration': duration,
+                }
+
+            mg = try_get(show, lambda x: x['media:group'][0], dict)
+            if not mg:
+                continue
+
+            if mg.get('url'):
+                m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url'])
+                if m:
+                    m = m.groupdict()
+                    formats.append({
+                        'url': m['url'] + '/' + m['app'],
+                        'app': m['app'],
+                        'play_path': m['playpath'],
+                        'player_url': url,
+                        'ext': 'flv',
+                        'format_id': 'rtmp',
+                    })
+
+            if mg.get('hls_server') and mg.get('hls_url'):
+                formats.extend(self._extract_m3u8_formats(
+                    mg['hls_server'] + mg['hls_url'], item_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+            if mg.get('hds_server') and mg.get('hds_url'):
+                formats.extend(self._extract_f4m_formats(
+                    mg['hds_server'] + mg['hds_url'], item_id,
+                    f4m_id='hds', fatal=False))
+
+            mg_rte_server = str_or_none(mg.get('rte:server'))
+            mg_url = str_or_none(mg.get('url'))
+            if mg_rte_server and mg_url:
+                hds_url = url_or_none(mg_rte_server + mg_url)
+                if hds_url:
+                    formats.extend(self._extract_f4m_formats(
+                        hds_url, item_id, f4m_id='hds', fatal=False))
 
         self._sort_formats(formats)
 
-        return {
-            'id': item_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
-            'formats': formats,
-        }
+        info_dict['formats'] = formats
+        return info_dict
 
 
 class RteIE(RteBaseIE):

youtube_dl/extractor/rutube.py

@@ -103,7 +103,8 @@ class RutubeIE(RutubeBaseIE):
 
         options = self._download_json(
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
-            video_id, 'Downloading options JSON')
+            video_id, 'Downloading options JSON',
+            headers=self.geo_verification_headers())
 
         formats = []
         for format_id, format_url in options['video_balancer'].items():

youtube_dl/extractor/ruutu.py

@@ -65,7 +65,8 @@ class RuutuIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video_xml = self._download_xml(
-            'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
+            'https://gatling.nelonenmedia.fi/media-xml-cache', video_id,
+            query={'id': video_id})
 
         formats = []
         processed_urls = []

youtube_dl/extractor/screencast.py

@@ -90,6 +90,15 @@ class ScreencastIE(InfoExtractor):
                     r'src=(.*?)(?:$|&)', video_meta,
                     'meta tag video URL', default=None)
 
+        if video_url is None:
+            video_url = self._html_search_regex(
+                r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1',
+                webpage, 'video url', default=None, group='url')
+
+        if video_url is None:
+            video_url = self._html_search_meta(
+                'og:video', webpage, default=None)
+
         if video_url is None:
             raise ExtractorError('Cannot find video')
 

youtube_dl/extractor/seznamzpravy.py

@@ -164,6 +164,6 @@ class SeznamZpravyArticleIE(InfoExtractor):
         description = info.get('description') or self._og_search_description(webpage)
 
         return self.playlist_result([
-            self.url_result(url, ie=SeznamZpravyIE.ie_key())
-            for url in SeznamZpravyIE._extract_urls(webpage)],
+            self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
+            for entry_url in SeznamZpravyIE._extract_urls(webpage)],
             article_id, title, description)

youtube_dl/extractor/shared.py

@@ -5,6 +5,7 @@ from ..compat import compat_b64decode
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
     urlencode_postdata,
 )
 
@@ -86,9 +87,16 @@ class VivoIE(SharedBaseIE):
     }
 
     def _extract_video_url(self, webpage, video_id, *args):
+        def decode_url(encoded_url):
+            return compat_b64decode(encoded_url).decode('utf-8')
+
+        stream_url = url_or_none(decode_url(self._search_regex(
+            r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'stream url', default=None, group='url')))
+        if stream_url:
+            return stream_url
         return self._parse_json(
             self._search_regex(
                 r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
                 webpage, 'stream', group='url'),
-            video_id,
-            transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0]
+            video_id, transform_source=decode_url)[0]

youtube_dl/extractor/sixplay.py

@@ -19,7 +19,7 @@ from ..utils import (
 
 class SixPlayIE(InfoExtractor):
     IE_NAME = '6play'
-    _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay.be)/.+?-c_)(?P<id>[0-9]+)'
+    _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr)/.+?-c_)(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
         'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
@@ -32,6 +32,9 @@ class SixPlayIE(InfoExtractor):
     }, {
         'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
         'only_matching': True,
+    }, {
+        'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -39,6 +42,7 @@ class SixPlayIE(InfoExtractor):
         service, consumer_name = {
             '6play.fr': ('6play', 'm6web'),
             'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
+            'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
         }.get(domain, ('6play', 'm6web'))
 
         data = self._download_json(
@@ -60,7 +64,7 @@ class SixPlayIE(InfoExtractor):
         for asset in clip_data['assets']:
             asset_url = asset.get('full_physical_path')
             protocol = asset.get('protocol')
-            if not asset_url or protocol == 'primetime' or asset_url in urls:
+            if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls:
                 continue
             urls.append(asset_url)
             container = asset.get('video_container')
@@ -77,19 +81,17 @@ class SixPlayIE(InfoExtractor):
                         if not urlh:
                             continue
                         asset_url = urlh.geturl()
-                    asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
-                    formats.extend(self._extract_m3u8_formats(
-                        asset_url, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
-                    formats.extend(self._extract_f4m_formats(
-                        asset_url.replace('.m3u8', '.f4m'),
-                        video_id, f4m_id='hds', fatal=False))
-                    formats.extend(self._extract_mpd_formats(
-                        asset_url.replace('.m3u8', '.mpd'),
-                        video_id, mpd_id='dash', fatal=False))
-                    formats.extend(self._extract_ism_formats(
-                        re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
-                        video_id, ism_id='mss', fatal=False))
+                    for i in range(3, 0, -1):
+                        asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i)
+                        m3u8_formats = self._extract_m3u8_formats(
+                            asset_url, video_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False)
+                        formats.extend(m3u8_formats)
+                        formats.extend(self._extract_mpd_formats(
+                            asset_url.replace('.m3u8', '.mpd'),
+                            video_id, mpd_id='dash', fatal=False))
+                        if m3u8_formats:
+                            break
                 else:
                     formats.extend(self._extract_m3u8_formats(
                         asset_url, video_id, 'mp4', 'm3u8_native',

youtube_dl/extractor/slideslive.py

@@ -8,6 +8,7 @@ from ..utils import ExtractorError
 class SlidesLiveIE(InfoExtractor):
     _VALID_URL = r'https?://slideslive\.com/(?P<id>[0-9]+)'
     _TESTS = [{
+        # video_service_name = YOUTUBE
         'url': 'https://slideslive.com/38902413/gcc-ia16-backend',
         'md5': 'b29fcd6c6952d0c79c5079b0e7a07e6f',
         'info_dict': {
@@ -19,14 +20,18 @@ class SlidesLiveIE(InfoExtractor):
             'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
             'upload_date': '20170925',
         }
+    }, {
+        # video_service_name = youtube
+        'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_data = self._download_json(
             url, video_id, headers={'Accept': 'application/json'})
-        service_name = video_data['video_service_name']
-        if service_name == 'YOUTUBE':
+        service_name = video_data['video_service_name'].lower()
+        if service_name == 'youtube':
             yt_video_id = video_data['video_service_id']
             return self.url_result(yt_video_id, 'Youtube', video_id=yt_video_id)
         else:

youtube_dl/extractor/spike.py

@@ -44,3 +44,10 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
 
     _FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/'
     _GEO_COUNTRIES = ['US']
+
+    def _extract_mgid(self, webpage):
+        cs = self._parse_json(self._search_regex(
+            r'window\.__DATA__\s*=\s*({.+})',
+            webpage, 'data'), None)['children']
+        c = next(c for c in cs if c.get('type') == 'VideoPlayer')
+        return c['props']['media']['video']['config']['uri']

youtube_dl/extractor/sportbox.py

@@ -8,20 +8,24 @@ from ..utils import (
     determine_ext,
     int_or_none,
     js_to_json,
+    merge_dicts,
 )
 
 
-class SportBoxEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
+class SportBoxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
         'info_dict': {
-            'id': '211355',
+            'id': '109158',
             'ext': 'mp4',
-            'title': '211355',
+            'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 292,
             'view_count': int,
+            'timestamp': 1426237001,
+            'upload_date': '20150313',
         },
         'params': {
             # m3u8 download
@@ -33,12 +37,18 @@ class SportBoxEmbedIE(InfoExtractor):
     }, {
         'url': 'https://news.sportbox.ru/vdl/player/media/193095',
         'only_matching': True,
+    }, {
+        'url': 'https://news.sportbox.ru/vdl/player/media/109158',
+        'only_matching': True,
+    }, {
+        'url': 'https://matchtv.ru/vdl/player/media/109158',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"',
+            r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"',
             webpage)
 
     def _real_extract(self, url):
@@ -46,13 +56,14 @@ class SportBoxEmbedIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        wjplayer_data = self._parse_json(
+        sources = self._parse_json(
             self._search_regex(
-                r'(?s)wjplayer\(({.+?})\);', webpage, 'wjplayer settings'),
+                r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n',
+                webpage, 'sources'),
             video_id, transform_source=js_to_json)
 
         formats = []
-        for source in wjplayer_data['sources']:
+        for source in sources:
             src = source.get('src')
             if not src:
                 continue
@@ -66,14 +77,23 @@ class SportBoxEmbedIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        player = self._parse_json(
+            self._search_regex(
+                r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage,
+                'player options', default='{}'),
+            video_id, transform_source=js_to_json)
+        media_id = player['mediaId']
+
+        info = self._search_json_ld(webpage, media_id, default={})
+
         view_count = int_or_none(self._search_regex(
             r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))
 
-        return {
-            'id': video_id,
-            'title': video_id,
-            'thumbnail': wjplayer_data.get('poster'),
-            'duration': int_or_none(wjplayer_data.get('duration')),
+        return merge_dicts(info, {
+            'id': media_id,
+            'title': self._og_search_title(webpage, default=None) or media_id,
+            'thumbnail': player.get('poster'),
+            'duration': int_or_none(player.get('duration')),
             'view_count': view_count,
             'formats': formats,
-        }
+        })

youtube_dl/extractor/ted.py

@@ -212,8 +212,6 @@ class TEDIE(InfoExtractor):
 
         http_url = None
         for format_id, resources in resources_.items():
-            if not isinstance(resources, dict):
-                continue
             if format_id == 'h264':
                 for resource in resources:
                     h264_url = resource.get('file')
@@ -242,6 +240,8 @@ class TEDIE(InfoExtractor):
                         'tbr': int_or_none(resource.get('bitrate')),
                     })
             elif format_id == 'hls':
+                if not isinstance(resources, dict):
+                    continue
                 stream_url = url_or_none(resources.get('stream'))
                 if not stream_url:
                     continue

youtube_dl/extractor/tele5.py

@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .nexx import NexxIE
+from ..compat import compat_urlparse
+
+
+class Tele5IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
+        'info_dict': {
+            'id': '1549416',
+            'ext': 'mp4',
+            'upload_date': '20180814',
+            'timestamp': 1534290623,
+            'title': 'Pandorum',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/tv/dark-matter/videos',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
+
+        if not video_id:
+            display_id = self._match_id(url)
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._html_search_regex(
+                r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
+                webpage, 'video id')
+
+        return self.url_result(
+            'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
+            ie=NexxIE.ie_key(), video_id=video_id)

youtube_dl/extractor/theplatform.py

@@ -39,9 +39,17 @@ class ThePlatformBaseIE(OnceIE):
             smil_url, video_id, note=note, query={'format': 'SMIL'},
             headers=self.geo_verification_headers())
         error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src')
-        if error_element is not None and error_element.attrib['src'].startswith(
-                'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD):
-            raise ExtractorError(error_element.attrib['abstract'], expected=True)
+        if error_element is not None:
+            exception = find_xpath_attr(
+                error_element, _x('.//smil:param'), 'name', 'exception')
+            if exception is not None:
+                if exception.get('value') == 'GeoLocationBlocked':
+                    self.raise_geo_restricted(error_element.attrib['abstract'])
+                elif error_element.attrib['src'].startswith(
+                        'http://link.theplatform.%s/s/errorFiles/Unavailable.'
+                        % self._TP_TLD):
+                    raise ExtractorError(
+                        error_element.attrib['abstract'], expected=True)
 
         smil_formats = self._parse_smil_formats(
             meta, smil_url, video_id, namespace=default_ns,
@@ -335,7 +343,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
     def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None):
         real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
         entry = self._download_json(real_url, video_id)['entries'][0]
-        main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None
+        main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else entry.get('plmedia$publicUrl')
 
         formats = []
         subtitles = {}
@@ -348,7 +356,8 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
             if first_video_id is None:
                 first_video_id = cur_video_id
                 duration = float_or_none(item.get('plfile$duration'))
-            for asset_type in item['plfile$assetTypes']:
+            file_asset_types = item.get('plfile$assetTypes') or compat_parse_qs(compat_urllib_parse_urlparse(smil_url).query)['assetTypes']
+            for asset_type in file_asset_types:
                 if asset_type in asset_types:
                     continue
                 asset_types.append(asset_type)

youtube_dl/extractor/tiktok.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    try_get,
+    url_or_none,
+)
+
+
+class TikTokBaseIE(InfoExtractor):
+    def _extract_aweme(self, data):
+        video = data['video']
+        description = str_or_none(try_get(data, lambda x: x['desc']))
+        width = int_or_none(try_get(data, lambda x: video['width']))
+        height = int_or_none(try_get(data, lambda x: video['height']))
+
+        format_urls = set()
+        formats = []
+        for format_id in (
+                'play_addr_lowbr', 'play_addr', 'play_addr_h264',
+                'download_addr'):
+            for format in try_get(
+                    video, lambda x: x[format_id]['url_list'], list) or []:
+                format_url = url_or_none(format)
+                if not format_url:
+                    continue
+                if format_url in format_urls:
+                    continue
+                format_urls.add(format_url)
+                formats.append({
+                    'url': format_url,
+                    'ext': 'mp4',
+                    'height': height,
+                    'width': width,
+                })
+        self._sort_formats(formats)
+
+        thumbnail = url_or_none(try_get(
+            video, lambda x: x['cover']['url_list'][0], compat_str))
+        uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
+        timestamp = int_or_none(data.get('create_time'))
+        comment_count = int_or_none(data.get('comment_count')) or int_or_none(
+            try_get(data, lambda x: x['statistics']['comment_count']))
+        repost_count = int_or_none(try_get(
+            data, lambda x: x['statistics']['share_count']))
+
+        aweme_id = data['aweme_id']
+
+        return {
+            'id': aweme_id,
+            'title': uploader or aweme_id,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'timestamp': timestamp,
+            'comment_count': comment_count,
+            'repost_count': repost_count,
+            'formats': formats,
+        }
+
+
+class TikTokIE(TikTokBaseIE):
+    _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://m.tiktok.com/v/6606727368545406213.html',
+        'md5': 'd584b572e92fcd48888051f238022420',
+        'info_dict': {
+            'id': '6606727368545406213',
+            'ext': 'mp4',
+            'title': 'Zureeal',
+            'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
+            'thumbnail': r're:^https?://.*~noop.image',
+            'uploader': 'Zureeal',
+            'timestamp': 1538248586,
+            'upload_date': '20180929',
+            'comment_count': int,
+            'repost_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        data = self._parse_json(self._search_regex(
+            r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id)
+        return self._extract_aweme(data)
+
+
+class TikTokUserIE(TikTokBaseIE):
+    _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html',
+        'info_dict': {
+            'id': '188294915489964032',
+        },
+        'playlist_mincount': 24,
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        data = self._download_json(
+            'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id,
+            query={'_signature': '_'})
+        entries = []
+        for aweme in data['aweme_list']:
+            try:
+                entry = self._extract_aweme(aweme)
+            except ExtractorError:
+                continue
+            entry['extractor_key'] = TikTokIE.ie_key()
+            entries.append(entry)
+        return self.playlist_result(entries, user_id)

youtube_dl/extractor/tnaflix.py

@@ -18,8 +18,9 @@ from ..utils import (
 class TNAFlixNetworkBaseIE(InfoExtractor):
     # May be overridden in descendants if necessary
     _CONFIG_REGEX = [
-        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
-        r'<input[^>]+name="config\d?" value="([^"]+)"',
+        r'flashvars\.config\s*=\s*escape\("(?P<url>[^"]+)"',
+        r'<input[^>]+name="config\d?" value="(?P<url>[^"]+)"',
+        r'config\s*=\s*(["\'])(?P<url>(?:https?:)?//(?:(?!\1).)+)\1',
     ]
     _HOST = 'tna'
     _VKEY_SUFFIX = ''
@@ -85,7 +86,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         cfg_url = self._proto_relative_url(self._html_search_regex(
-            self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
+            self._CONFIG_REGEX, webpage, 'flashvars.config', default=None,
+            group='url'), 'http:')
 
         if not cfg_url:
             inputs = self._hidden_inputs(webpage)

youtube_dl/extractor/tube8.py

@@ -45,7 +45,7 @@ class Tube8IE(KeezMoviesIE):
                 r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
 
         description = self._html_search_regex(
-            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
+            r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
         uploader = self._html_search_regex(
             r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
@@ -55,19 +55,19 @@ class Tube8IE(KeezMoviesIE):
         dislike_count = int_or_none(self._search_regex(
             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
         view_count = str_to_int(self._search_regex(
-            r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
+            r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._search_regex(
             r'<span id="allCommentsCount">(\d+)</span>',
             webpage, 'comment count', fatal=False))
 
         category = self._search_regex(
-            r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)',
+            r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
             webpage, 'category', fatal=False)
         categories = [category] if category else None
 
         tags_str = self._search_regex(
-            r'(?s)Tags:\s*</strong>(.+?)</(?!a)',
+            r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
             webpage, 'tags', fatal=False)
         tags = [t for t in re.findall(
             r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None

youtube_dl/extractor/tv3.py

@@ -1,34 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class TV3IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tv3\.co\.nz/(?P<id>[^/]+)/tabid/\d+/articleID/\d+/MCat/\d+/Default\.aspx'
-    _TEST = {
-        'url': 'http://www.tv3.co.nz/MOTORSPORT-SRS-SsangYong-Hampton-Downs-Round-3/tabid/3692/articleID/121615/MCat/2915/Default.aspx',
-        'info_dict': {
-            'id': '4659127992001',
-            'ext': 'mp4',
-            'title': 'CRC Motorsport: SRS SsangYong Hampton Downs Round 3 - S2015 Ep3',
-            'description': 'SsangYong Racing Series returns for Round 3 with drivers from New Zealand and Australia taking to the grid at Hampton Downs raceway.',
-            'uploader_id': '3812193411001',
-            'upload_date': '20151213',
-            'timestamp': 1449975272,
-        },
-        'expected_warnings': [
-            'Failed to download MPD manifest'
-        ],
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/3812193411001/default_default/index.html?videoId=%s'
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        brightcove_id = self._search_regex(r'<param\s*name="@videoPlayer"\s*value="(\d+)"', webpage, 'brightcove id')
-        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/tvplay.py

@@ -32,12 +32,12 @@ class TVPlayIE(InfoExtractor):
                         https?://
                             (?:www\.)?
                             (?:
-                                tvplay(?:\.skaties)?\.lv/parraides|
-                                (?:tv3play|play\.tv3)\.lt/programos|
+                                tvplay(?:\.skaties)?\.lv(?:/parraides)?|
+                                (?:tv3play|play\.tv3)\.lt(?:/programos)?|
                                 tv3play(?:\.tv3)?\.ee/sisu|
                                 (?:tv(?:3|6|8|10)play|viafree)\.se/program|
                                 (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
-                                play\.novatv\.bg/programi
+                                play\.nova(?:tv)?\.bg/programi
                             )
                             /(?:[^/]+/)+
                         )
@@ -203,10 +203,18 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
+            'only_matching': True,
+        },
         {
             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
             'only_matching': True,
         },
+        {
+            'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
+            'only_matching': True,
+        },
         {
             # views is null
             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
@@ -288,6 +296,7 @@ class TVPlayIE(InfoExtractor):
                         'url': m.group('url'),
                         'app': m.group('app'),
                         'play_path': m.group('playpath'),
+                        'preference': -1,
                     })
                 else:
                     fmt.update({
@@ -447,3 +456,102 @@ class ViafreeIE(InfoExtractor):
                     'skip_rtmp': True,
                 }),
             ie=TVPlayIE.ie_key(), video_id=video_id)
+
+
+class TVPlayHomeIE(InfoExtractor):
+    _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
+        'info_dict': {
+            'id': '366367',
+            'ext': 'mp4',
+            'title': 'Aferistai',
+            'description': 'Aferistai. Kalėdinė pasaka.',
+            'series': 'Aferistai [N-7]',
+            'season': '1 sezonas',
+            'season_number': 1,
+            'duration': 464,
+            'timestamp': 1394209658,
+            'upload_date': '20140307',
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [TVPlayIE.ie_key()],
+    }, {
+        'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
+        'only_matching': True,
+    }, {
+        'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id',
+            default=None)
+
+        if video_id:
+            return self.url_result(
+                'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
+
+        m3u8_url = self._search_regex(
+            r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'm3u8 url', group='url')
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'title', default=None, group='value') or self._html_search_meta(
+            'title', webpage, default=None) or self._og_search_title(
+            webpage)
+
+        description = self._html_search_meta(
+            'description', webpage,
+            default=None) or self._og_search_description(webpage)
+
+        thumbnail = self._search_regex(
+            r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'thumbnail', default=None, group='url') or self._html_search_meta(
+            'thumbnail', webpage, default=None) or self._og_search_thumbnail(
+            webpage)
+
+        duration = int_or_none(self._search_regex(
+            r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
+            fatal=False))
+
+        season = self._search_regex(
+            (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
+             r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'season', default=None, group='value')
+        season_number = int_or_none(self._search_regex(
+            r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
+            default=None))
+        episode = self._search_regex(
+            r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode',
+            default=None, group='value')
+        episode_number = int_or_none(self._search_regex(
+            r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
+            default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'season': season,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'formats': formats,
+        }

youtube_dl/extractor/twitcasting.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import re
+
+
+class TwitCastingIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?twitcasting\.tv/(?P<uploader_id>[^/]+)/movie/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609',
+        'md5': '745243cad58c4681dc752490f7540d7f',
+        'info_dict': {
+            'id': '2357609',
+            'ext': 'mp4',
+            'title': 'Recorded Live #2357609',
+            'uploader_id': 'ivetesangalo',
+            'description': "Moi! I'm live on TwitCasting from my iPhone.",
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        uploader_id = mobj.group('uploader_id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'(?s)<[^>]+id=["\']movietitle[^>]+>(.+?)</',
+            webpage, 'title', default=None) or self._html_search_meta(
+            'twitter:title', webpage, fatal=True)
+
+        m3u8_url = self._search_regex(
+            (r'data-movie-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+             r'(["\'])(?P<url>http.+?\.m3u8.*?)\1'),
+            webpage, 'm3u8 url', group='url')
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(
+            webpage, default=None) or self._html_search_meta(
+            'twitter:description', webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/twitch.py

@@ -51,7 +51,9 @@ class TwitchBaseIE(InfoExtractor):
                 expected=True)
 
     def _call_api(self, path, item_id, *args, **kwargs):
-        kwargs.setdefault('headers', {})['Client-ID'] = self._CLIENT_ID
+        headers = kwargs.get('headers', {}).copy()
+        headers['Client-ID'] = self._CLIENT_ID
+        kwargs['headers'] = headers
         response = self._download_json(
             '%s/%s' % (self._API_BASE, path), item_id,
             *args, **compat_kwargs(kwargs))
@@ -559,7 +561,8 @@ class TwitchStreamIE(TwitchBaseIE):
                     TwitchAllVideosIE,
                     TwitchUploadsIE,
                     TwitchPastBroadcastsIE,
-                    TwitchHighlightsIE))
+                    TwitchHighlightsIE,
+                    TwitchClipsIE))
                 else super(TwitchStreamIE, cls).suitable(url))
 
     def _real_extract(self, url):
@@ -633,7 +636,7 @@ class TwitchStreamIE(TwitchBaseIE):
 
 class TwitchClipsIE(TwitchBaseIE):
     IE_NAME = 'twitch:clips'
-    _VALID_URL = r'https?://clips\.twitch\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat',
@@ -653,6 +656,9 @@ class TwitchClipsIE(TwitchBaseIE):
         # multiple formats
         'url': 'https://clips.twitch.tv/rflegendary/UninterestedBeeDAESuppy',
         'only_matching': True,
+    }, {
+        'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):