release 2018.11.07

[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 *2018.06.25*. 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 Issues with outdated version will be rejected.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 **2018.06.25**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.07*. 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 Issues with outdated version will be rejected.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 **2018.11.07**
 
 ### 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 2018.06.25
+[debug] youtube-dl version 2018.11.07
 [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

AUTHORS

@@ -239,3 +239,10 @@ Martin Weinelt
 Surya Oktafendri
 TingPing
 Alexandre Macabies
+Bastian de Groot
+Niklas Haas
+András Veres-Szentkirályi
+Enes Solak
+Nathan Rossi
+Thomas van der Berg
+Luca Cherubin

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 +1,279 @@
+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
+* [funk:channel] Improve byChannelAlias extraction (#17142)
+* [twitch] Fix authentication (#17024, #17126)
+* [twitch:vod] Improve URL regular expression (#17135)
+* [watchbox] Fix extraction (#17107)
+* [pbs] Fix extraction (#17109)
+* [theplatform] Relax URL regular expression (#16181, #17097)
++ [viqeo] Add support for viqeo.tv (#17066)
+
+
+version 2018.07.29
+
+Extractors
+* [crunchyroll:playlist] Restrict URL regular expression (#17069, #17076)
++ [pornhub] Add support for subtitles (#16924, #17088)
+* [ceskatelevize] Use https for API call (#16997, #16999)
+* [dailymotion:playlist] Fix extraction (#16894)
+* [ted] Improve extraction
+* [ted] Fix extraction for videos without nativeDownloads (#16756, #17085)
+* [telecinco] Fix extraction (#17080)
+* [mitele] Reduce number of requests
+* [rai] Return non HTTP relinker URL intact (#17055)
+* [vk] Fix extraction for inline only videos (#16923)
+* [streamcloud] Fix extraction (#17054)
+* [facebook] Fix tahoe player extraction with authentication (#16655)
++ [puhutv] Add support for puhutv.com (#12712, #16010, #16269)
+
+
+version 2018.07.21
+
+Core
++ [utils] Introduce url_or_none
+* [utils] Allow JSONP without function name (#17028)
++ [extractor/common] Extract DASH and MSS formats from SMIL manifests
+
+Extractors
++ [bbc] Add support for BBC Radio Play pages (#17022)
+* [iwara] Fix download URLs (#17026)
+* [vrtnu] Relax title extraction and extract JSON-LD (#17018)
++ [viu] Pass Referer and Origin headers and area id (#16992)
++ [vimeo] Add another config regular expression (#17013)
++ [facebook] Extract view count (#16942)
+* [dailymotion] Improve description extraction (#16984)
+* [slutload] Fix and improve extraction (#17001)
+* [mediaset] Fix extraction (#16977)
++ [theplatform] Add support for theplatform TLD customization (#16977)
+* [imgur] Relax URL regular expression (#16987)
+* [pornhub] Improve extraction and extract all formats (#12166, #15891, #16262,
+  #16959)
+
+
+version 2018.07.10
+
+Core
+* [utils] Share JSON-LD regular expression
+* [downloader/dash] Improve error handling (#16927)
+
+Extractors
++ [nrktv] Add support for new season and serie URL schema
++ [nrktv] Add support for new episode URL schema (#16909)
++ [frontendmasters] Add support for frontendmasters.com (#3661, #16328)
+* [funk] Fix extraction (#16918)
+* [watchbox] Fix extraction (#16904)
+* [dplayit] Sort formats
+* [dplayit] Fix extraction (#16901)
+* [youtube] Improve login error handling (#13822)
+
+
+version 2018.07.04
+
+Core
+* [extractor/common] Properly escape % in MPD templates (#16867)
+* [extractor/common] Use source URL as Referer for HTML5 entries (16849)
+* Prefer ffmpeg over avconv by default (#8622)
+
+Extractors
+* [pluralsight] Switch to graphql (#16889, #16895, #16896, #16899)
+* [lynda] Simplify login and improve error capturing (#16891)
++ [go90] Add support for embed URLs (#16873)
+* [go90] Detect geo restriction error and pass geo verification headers
+  (#16874)
+* [vlive] Fix live streams extraction (#16871)
+* [npo] Fix typo (#16872)
++ [mediaset] Add support for new videos and extract all formats (#16568)
+* [dctptv] Restore extraction based on REST API (#16850)
+* [svt] Improve extraction and add support for pages (#16802)
+* [porncom] Fix extraction (#16808)
+
+
 version 2018.06.25
 
 Extractors

README.md

@@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 
 # INSTALLATION
 
-To install it right away for all UNIX users (Linux, OS X, etc.), type:
+To install it right away for all UNIX users (Linux, macOS, etc.), type:
 
     sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl
     sudo chmod a+rx /usr/local/bin/youtube-dl
@@ -35,7 +35,7 @@ You can also use pip:
     
 This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
 
-OS X users can install youtube-dl with [Homebrew](https://brew.sh/):
+macOS users can install youtube-dl with [Homebrew](https://brew.sh/):
 
     brew install youtube-dl
 
@@ -427,9 +427,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      default; fix file if we can, warn
                                      otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors (default)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     postprocessors (default)
     --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
                                      either the path to the binary or its
                                      containing directory.
@@ -442,7 +442,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and OS X, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself.
+You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and macOS, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself.
 
 For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
 ```
@@ -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
@@ -870,7 +872,7 @@ Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the op
 
 Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
 
-In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
+In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [cookies.txt](https://addons.mozilla.org/en-US/firefox/addon/cookies-txt/) (for Firefox).
 
 Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
 
@@ -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**
@@ -174,6 +176,7 @@
  - **Clyp**
  - **cmt.com**
  - **CNBC**
+ - **CNBCVideo**
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
@@ -189,7 +192,7 @@
  - **Crackle**
  - **Criterion**
  - **CrooksAndLiars**
- - **Crunchyroll**
+ - **crunchyroll**
  - **crunchyroll:playlist**
  - **CSNNE**
  - **CSpan**: C-SPAN
@@ -247,7 +250,9 @@
  - **EchoMsk**
  - **egghead:course**: egghead.io course
  - **egghead:lesson**: egghead.io lesson
+ - **ehftv**
  - **eHow**
+ - **EinsUndEinsTV**
  - **Einthusan**
  - **eitb.tv**
  - **EllenTube**
@@ -265,6 +270,7 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
+ - **EWETV**
  - **ExpoTV**
  - **Expressen**
  - **ExtremeTube**
@@ -302,6 +308,9 @@
  - **Freesound**
  - **freespeech.org**
  - **FreshLive**
+ - **FrontendMasters**
+ - **FrontendMastersCourse**
+ - **FrontendMastersLesson**
  - **Funimation**
  - **FunkChannel**
  - **FunkMix**
@@ -321,6 +330,7 @@
  - **Gfycat**
  - **GiantBomb**
  - **Giga**
+ - **GlattvisionTV**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
@@ -350,7 +360,7 @@
  - **HitRecord**
  - **HornBunny**
  - **HotNewHipHop**
- - **HotStar**
+ - **hotstar**
  - **hotstar:playlist**
  - **Howcast**
  - **HowStuffWorks**
@@ -402,6 +412,7 @@
  - **Ketnet**
  - **KhanAcademy**
  - **KickStarter**
+ - **KinoPoisk**
  - **KonserthusetPlay**
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
@@ -434,6 +445,8 @@
  - **limelight:channel**
  - **limelight:channel_list**
  - **LineTV**
+ - **linkedin:learning**
+ - **linkedin:learning:course**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -487,6 +500,7 @@
  - **Mixer:vod**
  - **MLB**
  - **Mnet**
+ - **MNetTV**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **Mojvideo**
@@ -518,6 +532,7 @@
  - **Myvi**
  - **MyVidster**
  - **MyviEmbed**
+ - **MyVisionTV**
  - **n-tv.de**
  - **natgeo**
  - **natgeo:episodeguide**
@@ -543,6 +558,7 @@
  - **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**
@@ -574,6 +590,7 @@
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
+ - **NovaEmbed**
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**
@@ -589,7 +606,9 @@
  - **NRKSkole**: NRK Skole
  - **NRKTV**: NRK TV and NRK Radio
  - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
+ - **NRKTVEpisode**
  - **NRKTVEpisodes**
+ - **NRKTVSeason**
  - **NRKTVSeries**
  - **ntv.ru**
  - **Nuvid**
@@ -616,6 +635,7 @@
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **OsnatelTV**
  - **PacktPub**
  - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
@@ -667,6 +687,8 @@
  - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
+ - **puhutv**
+ - **puhutv:serie**
  - **Puls4**
  - **Pyvideo**
  - **qqmusic**: QQ音乐
@@ -674,6 +696,7 @@
  - **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**
@@ -689,6 +712,7 @@
  - **RaiPlayLive**
  - **RaiPlayPlaylist**
  - **RayWenderlich**
+ - **RayWenderlichCourse**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedBullTV**
@@ -740,6 +764,7 @@
  - **safari**: safaribooksonline.com online video
  - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
+ - **SAKTV**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -795,7 +820,7 @@
  - **Spiegeltv**
  - **sport.francetvinfo.fr**
  - **Sport5**
- - **SportBoxEmbed**
+ - **SportBox**
  - **SportDeutschland**
  - **SpringboardPlatform**
  - **Sprout**
@@ -813,6 +838,7 @@
  - **StretchInternet**
  - **SunPorno**
  - **SVT**
+ - **SVTPage**
  - **SVTPlay**: SVT Play and Öppet arkiv
  - **SVTSeries**
  - **SWRMediathek**
@@ -833,6 +859,7 @@
  - **techtv.mit.edu**
  - **ted**
  - **Tele13**
+ - **Tele5**
  - **TeleBruxelles**
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
@@ -884,7 +911,6 @@
  - **TV2**
  - **tv2.hu**
  - **TV2Article**
- - **TV3**
  - **TV4**: tv4.se and tv4play.se
  - **TV5MondePlus**: TV5MONDE+
  - **TVA**
@@ -904,7 +930,9 @@
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
  - **TVPlayer**
+ - **TVPlayHome**
  - **Tweakers**
+ - **TwitCasting**
  - **twitch:chapter**
  - **twitch:clips**
  - **twitch:profile**
@@ -993,6 +1021,7 @@
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
+ - **Viqeo**
  - **Viu**
  - **viu:ott**
  - **viu:playlist**
@@ -1018,12 +1047,14 @@
  - **vrv**
  - **vrv:series**
  - **VShare**
+ - **VTXTV**
  - **vube**: Vube.com
  - **VuClip**
  - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
  - **Walla**
+ - **WalyTV**
  - **washingtonpost**
  - **washingtonpost:article**
  - **wat.tv**
@@ -1084,6 +1115,7 @@
  - **YouNowLive**
  - **YouNowMoment**
  - **YouPorn**
+ - **YourPorn**
  - **YourUpload**
  - **youtube**: YouTube.com
  - **youtube:channel**: YouTube.com channels

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_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_utils.py

@@ -78,6 +78,7 @@ from youtube_dl.utils import (
     uppercase_escape,
     lowercase_escape,
     url_basename,
+    url_or_none,
     base_url,
     urljoin,
     urlencode_postdata,
@@ -507,6 +508,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
         self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
 
+    def test_url_or_none(self):
+        self.assertEqual(url_or_none(None), None)
+        self.assertEqual(url_or_none(''), None)
+        self.assertEqual(url_or_none('foo'), None)
+        self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
+        self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
+        self.assertEqual(url_or_none('http$://foo.de'), None)
+        self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
+        self.assertEqual(url_or_none('//foo.de'), '//foo.de')
+
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)
         self.assertEqual(parse_age_limit(False), None)
@@ -717,6 +728,10 @@ class TestUtil(unittest.TestCase):
         d = json.loads(stripped)
         self.assertEqual(d, {'status': 'success'})
 
+        stripped = strip_jsonp('({"status": "success"});')
+        d = json.loads(stripped)
+        self.assertEqual(d, {'status': 'success'})
+
     def test_uppercase_escape(self):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -770,6 +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/YoutubeDL.py

@@ -305,8 +305,8 @@ class YoutubeDL(object):
     http_chunk_size.
 
     The following options are used by the post processors:
-    prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
-                       otherwise prefer avconv.
+    prefer_ffmpeg:     If False, use avconv instead of ffmpeg if both are available,
+                       otherwise prefer ffmpeg.
     postprocessor_args: A list of additional command-line arguments for the
                         postprocessor.
 

youtube_dl/downloader/dash.py

@@ -2,7 +2,10 @@ from __future__ import unicode_literals
 
 from .fragment import FragmentFD
 from ..compat import compat_urllib_error
-from ..utils import urljoin
+from ..utils import (
+    DownloadError,
+    urljoin,
+)
 
 
 class DashSegmentsFD(FragmentFD):
@@ -57,6 +60,14 @@ class DashSegmentsFD(FragmentFD):
                     count += 1
                     if count <= fragment_retries:
                         self.report_retry_fragment(err, frag_index, count, fragment_retries)
+                except DownloadError:
+                    # Don't retry fragment if error occurred during HTTP downloading
+                    # itself since it has own retry settings
+                    if not fatal:
+                        self.report_skip_fragment(frag_index)
+                        break
+                    raise
+
             if count > fragment_retries:
                 if not fatal:
                     self.report_skip_fragment(frag_index)

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/adultswim.py

@@ -7,6 +7,7 @@ from .turner import TurnerBaseIE
 from ..utils import (
     int_or_none,
     strip_or_none,
+    url_or_none,
 )
 
 
@@ -98,7 +99,7 @@ class AdultSwimIE(TurnerBaseIE):
             if not video_id:
                 entries = []
                 for episode in video_data.get('archiveEpisodes', []):
-                    episode_url = episode.get('url')
+                    episode_url = url_or_none(episode.get('url'))
                     if not episode_url:
                         continue
                     entries.append(self.url_result(

youtube_dl/extractor/afreecatv.py

@@ -9,6 +9,7 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
+    url_or_none,
     urlencode_postdata,
     xpath_text,
 )
@@ -304,7 +305,7 @@ class AfreecaTVIE(InfoExtractor):
             file_elements = video_element.findall(compat_xpath('./file'))
             one = len(file_elements) == 1
             for file_num, file_element in enumerate(file_elements, start=1):
-                file_url = file_element.text
+                file_url = url_or_none(file_element.text)
                 if not file_url:
                     continue
                 key = file_element.get('key', '')

youtube_dl/extractor/amp.py

@@ -3,11 +3,12 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
-    parse_iso8601,
-    mimetype2ext,
     determine_ext,
     ExtractorError,
+    int_or_none,
+    mimetype2ext,
+    parse_iso8601,
+    url_or_none,
 )
 
 
@@ -35,7 +36,7 @@ class AMPIE(InfoExtractor):
                 media_thumbnail = [media_thumbnail]
             for thumbnail_data in media_thumbnail:
                 thumbnail = thumbnail_data.get('@attributes', {})
-                thumbnail_url = thumbnail.get('url')
+                thumbnail_url = url_or_none(thumbnail.get('url'))
                 if not thumbnail_url:
                     continue
                 thumbnails.append({
@@ -51,7 +52,7 @@ class AMPIE(InfoExtractor):
                 media_subtitle = [media_subtitle]
             for subtitle_data in media_subtitle:
                 subtitle = subtitle_data.get('@attributes', {})
-                subtitle_href = subtitle.get('href')
+                subtitle_href = url_or_none(subtitle.get('href'))
                 if not subtitle_href:
                     continue
                 subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
@@ -65,7 +66,7 @@ class AMPIE(InfoExtractor):
             media_content = [media_content]
         for media_data in media_content:
             media = media_data.get('@attributes', {})
-            media_url = media.get('url')
+            media_url = url_or_none(media.get('url'))
             if not media_url:
                 continue
             ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
@@ -79,7 +80,7 @@ class AMPIE(InfoExtractor):
             else:
                 formats.append({
                     'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
-                    'url': media['url'],
+                    'url': media_url,
                     'tbr': int_or_none(media.get('bitrate')),
                     'filesize': int_or_none(media.get('fileSize')),
                     'ext': ext,

youtube_dl/extractor/animeondemand.py

@@ -8,6 +8,7 @@ from ..utils import (
     determine_ext,
     extract_attributes,
     ExtractorError,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
@@ -165,7 +166,7 @@ class AnimeOnDemandIE(InfoExtractor):
                         }, fatal=False)
                     if not playlist:
                         continue
-                    stream_url = playlist.get('streamurl')
+                    stream_url = url_or_none(playlist.get('streamurl'))
                     if stream_url:
                         rtmp = re.search(
                             r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',

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/aol.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
 )
 
 
@@ -77,7 +78,7 @@ class AolIE(InfoExtractor):
             formats.extend(self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
         for rendition in video_data.get('renditions', []):
-            video_url = rendition.get('url')
+            video_url = url_or_none(rendition.get('url'))
             if not video_url:
                 continue
             ext = rendition.get('format')

youtube_dl/extractor/apa.py

@@ -4,10 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     js_to_json,
+    url_or_none,
 )
 
 
@@ -68,8 +68,8 @@ class APAIE(InfoExtractor):
         for source in sources:
             if not isinstance(source, dict):
                 continue
-            source_url = source.get('file')
-            if not source_url or not isinstance(source_url, compat_str):
+            source_url = url_or_none(source.get('file'))
+            if not source_url:
                 continue
             ext = determine_ext(source_url)
             if ext == 'm3u8':

youtube_dl/extractor/aparat.py

@@ -4,66 +4,92 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    merge_dicts,
     mimetype2ext,
+    url_or_none,
 )
 
 
 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 = 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

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from .generic import GenericIE
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -15,13 +14,14 @@ from ..utils import (
     unified_strdate,
     xpath_text,
     update_url_query,
+    url_or_none,
 )
 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',
@@ -100,7 +103,7 @@ class ARDMediathekIE(InfoExtractor):
                 quality = stream.get('_quality')
                 server = stream.get('_server')
                 for stream_url in stream_urls:
-                    if not isinstance(stream_url, compat_str) or '//' not in stream_url:
+                    if not url_or_none(stream_url):
                         continue
                     ext = determine_ext(stream_url)
                     if quality != 'auto' and ext in ('f4m', 'm3u8'):
@@ -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/azmedien.py

@@ -1,213 +1,90 @@
 # 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',
+            'description': 'md5:dd9f96751ec9c35e409a698a328402f3',
+            '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)
+        video_id = mobj.group('id')
+        entry_id = mobj.group('kaltura_id')
 
-        entries = []
+        if not entry_id:
+            webpage = self._download_webpage(url, video_id)
+            api_path = self._search_regex(
+                r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']',
+                webpage, 'api path')
+            api_url = 'https://www.%s%s' % (mobj.group('host'), api_path)
+            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
@@ -16,14 +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',
@@ -35,13 +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',
         },
     }]
 
@@ -50,19 +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,
@@ -72,85 +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 = stat.get('retry_url')
-            if not isinstance(retry_url, compat_str):
-                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,
         }
 
@@ -306,7 +369,7 @@ class BandcampWeeklyIE(InfoExtractor):
 
         formats = []
         for format_id, format_url in show['audio_stream'].items():
-            if not isinstance(format_url, compat_str):
+            if not url_or_none(format_url):
                 continue
             for known_ext in KNOWN_EXTENSIONS:
                 if known_ext in format_id:

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'
@@ -778,6 +784,17 @@ class BBCIE(BBCCoUkIE):
         'params': {
             'skip_download': True,
         }
+    }, {
+        # window.__PRELOADED_STATE__
+        'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
+        'info_dict': {
+            'id': 'b0b9z4vz',
+            'ext': 'mp4',
+            'title': 'Prom 6: An American in Paris and Turangalila',
+            'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
+            'uploader': 'Radio 3',
+            'uploader_id': 'bbc_radio_three',
+        },
     }]
 
     @classmethod
@@ -1000,6 +1017,36 @@ class BBCIE(BBCCoUkIE):
                     'subtitles': subtitles,
                 }
 
+        preload_state = self._parse_json(self._search_regex(
+            r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
+            'preload state', default='{}'), playlist_id, fatal=False)
+        if preload_state:
+            current_programme = preload_state.get('programmes', {}).get('current') or {}
+            programme_id = current_programme.get('id')
+            if current_programme and programme_id and current_programme.get('type') == 'playable_item':
+                title = current_programme.get('titles', {}).get('tertiary') or playlist_title
+                formats, subtitles = self._download_media_selector(programme_id)
+                self._sort_formats(formats)
+                synopses = current_programme.get('synopses') or {}
+                network = current_programme.get('network') or {}
+                duration = int_or_none(
+                    current_programme.get('duration', {}).get('value'))
+                thumbnail = None
+                image_url = current_programme.get('image_url')
+                if image_url:
+                    thumbnail = image_url.replace('{recipe}', '1920x1920')
+                return {
+                    'id': programme_id,
+                    'title': title,
+                    'description': dict_get(synopses, ('long', 'medium', 'short')),
+                    'thumbnail': thumbnail,
+                    'duration': duration,
+                    'uploader': network.get('short_title'),
+                    'uploader_id': network.get('id'),
+                    'formats': formats,
+                    'subtitles': subtitles,
+                }
+
         bbc3_config = self._parse_json(
             self._search_regex(
                 r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,

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._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/breakcom.py

@@ -4,8 +4,10 @@ import re
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..compat import compat_str
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    url_or_none,
+)
 
 
 class BreakIE(InfoExtractor):
@@ -55,8 +57,8 @@ class BreakIE(InfoExtractor):
 
         formats = []
         for video in content:
-            video_url = video.get('url')
-            if not video_url or not isinstance(video_url, compat_str):
+            video_url = url_or_none(video.get('url'))
+            if not video_url:
                 continue
             bitrate = int_or_none(self._search_regex(
                 r'(\d+)_kbps', video_url, 'tbr', default=None))

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/cammodels.py

@@ -2,10 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
 )
 
 
@@ -56,8 +56,8 @@ class CamModelsIE(InfoExtractor):
             for media in encodings:
                 if not isinstance(media, dict):
                     continue
-                media_url = media.get('location')
-                if not media_url or not isinstance(media_url, compat_str):
+                media_url = url_or_none(media.get('location'))
+                if not media_url:
                     continue
 
                 format_id_list = [format_id]

youtube_dl/extractor/canvas.py

@@ -11,6 +11,7 @@ from ..utils import (
     strip_or_none,
     float_or_none,
     int_or_none,
+    merge_dicts,
     parse_iso8601,
 )
 
@@ -248,9 +249,13 @@ class VrtNUIE(GigyaBaseIE):
 
         webpage, urlh = self._download_webpage_handle(url, display_id)
 
-        title = self._html_search_regex(
+        info = self._search_json_ld(webpage, display_id, default={})
+
+        # title is optional here since it may be extracted by extractor
+        # that is delegated from here
+        title = strip_or_none(self._html_search_regex(
             r'(?ms)<h1 class="content__heading">(.+?)</h1>',
-            webpage, 'title').strip()
+            webpage, 'title', default=None))
 
         description = self._html_search_regex(
             r'(?ms)<div class="content__description">(.+?)</div>',
@@ -295,7 +300,7 @@ class VrtNUIE(GigyaBaseIE):
         # the first one
         video_id = list(video.values())[0].get('videoid')
 
-        return {
+        return merge_dicts(info, {
             '_type': 'url_transparent',
             'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
             'ie_key': CanvasIE.ie_key(),
@@ -307,4 +312,4 @@ class VrtNUIE(GigyaBaseIE):
             'season_number': season_number,
             'episode_number': episode_number,
             'release_date': release_date,
-        }
+        })

youtube_dl/extractor/ccma.py

@@ -4,13 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     clean_html,
     int_or_none,
     parse_duration,
     parse_iso8601,
     parse_resolution,
+    url_or_none,
 )
 
 
@@ -53,8 +53,8 @@ class CCMAIE(InfoExtractor):
         media_url = media['media']['url']
         if isinstance(media_url, list):
             for format_ in media_url:
-                format_url = format_.get('file')
-                if not format_url or not isinstance(format_url, compat_str):
+                format_url = url_or_none(format_.get('file'))
+                if not format_url:
                     continue
                 label = format_.get('label')
                 f = parse_resolution(label)

youtube_dl/extractor/ceskatelevize.py

@@ -108,7 +108,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(
-                'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
                 data=urlencode_postdata(data))
 
             req.add_header('Content-type', 'application/x-www-form-urlencoded')

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

@@ -52,6 +52,7 @@ from ..utils import (
     GeoUtils,
     int_or_none,
     js_to_json,
+    JSON_LD_RE,
     mimetype2ext,
     orderedSet,
     parse_codecs,
@@ -68,6 +69,7 @@ from ..utils import (
     update_url_query,
     urljoin,
     url_basename,
+    url_or_none,
     xpath_element,
     xpath_text,
     xpath_with_ns,
@@ -210,6 +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
@@ -599,6 +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:
@@ -1149,8 +1161,7 @@ class InfoExtractor(object):
 
     def _search_json_ld(self, html, video_id, expected_type=None, **kwargs):
         json_ld = self._search_regex(
-            r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
-            html, 'JSON-LD', group='json_ld', **kwargs)
+            JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs)
         default = kwargs.get('default', NO_DEFAULT)
         if not json_ld:
             return default if default is not NO_DEFAULT else {}
@@ -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)
@@ -1859,9 +1870,7 @@ class InfoExtractor(object):
                         'height': height,
                     })
                 formats.extend(m3u8_formats)
-                continue
-
-            if src_ext == 'f4m':
+            elif src_ext == 'f4m':
                 f4m_url = src_url
                 if not f4m_params:
                     f4m_params = {
@@ -1871,9 +1880,13 @@ class InfoExtractor(object):
                 f4m_url += '&' if '?' in f4m_url else '?'
                 f4m_url += compat_urllib_parse_urlencode(f4m_params)
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
-                continue
-
-            if src_url.startswith('http') and self._is_valid_url(src, video_id):
+            elif src_ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    src_url, video_id, mpd_id='dash', fatal=False))
+            elif re.search(r'\.ism/[Mm]anifest', src_url):
+                formats.extend(self._extract_ism_formats(
+                    src_url, video_id, ism_id='mss', fatal=False))
+            elif src_url.startswith('http') and self._is_valid_url(src, video_id):
                 http_count += 1
                 formats.append({
                     'url': src_url,
@@ -1884,7 +1897,6 @@ class InfoExtractor(object):
                     'width': width,
                     'height': height,
                 })
-                continue
 
         return formats
 
@@ -2106,7 +2118,21 @@ class InfoExtractor(object):
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
 
                         def prepare_template(template_name, identifiers):
-                            t = representation_ms_info[template_name]
+                            tmpl = representation_ms_info[template_name]
+                            # First of, % characters outside $...$ templates
+                            # must be escaped by doubling for proper processing
+                            # by % operator string formatting used further (see
+                            # https://github.com/rg3/youtube-dl/issues/16867).
+                            t = ''
+                            in_template = False
+                            for c in tmpl:
+                                t += c
+                                if c == '$':
+                                    in_template = not in_template
+                                elif c == '%' and not in_template:
+                                    t += c
+                            # Next, $...$ templates are translated to their
+                            # %(...) counterparts to be used with % operator
                             t = t.replace('$RepresentationID$', representation_id)
                             t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t)
                             t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t)
@@ -2437,6 +2463,8 @@ class InfoExtractor(object):
                         media_info['subtitles'].setdefault(lang, []).append({
                             'url': absolute_url(src),
                         })
+            for f in media_info['formats']:
+                f.setdefault('http_headers', {})['Referer'] = base_url
             if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries

youtube_dl/extractor/crackle.py

@@ -4,16 +4,14 @@ from __future__ import unicode_literals, division
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_HTTPError,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
     parse_age_limit,
     parse_duration,
+    url_or_none,
     ExtractorError
 )
 
@@ -86,8 +84,8 @@ class CrackleIE(InfoExtractor):
             for e in media['MediaURLs']:
                 if e.get('UseDRM') is True:
                     continue
-                format_url = e.get('Path')
-                if not format_url or not isinstance(format_url, compat_str):
+                format_url = url_or_none(e.get('Path'))
+                if not format_url:
                     continue
                 ext = determine_ext(format_url)
                 if ext == 'm3u8':
@@ -124,8 +122,8 @@ class CrackleIE(InfoExtractor):
                 for cc_file in cc_files:
                     if not isinstance(cc_file, dict):
                         continue
-                    cc_url = cc_file.get('Path')
-                    if not cc_url or not isinstance(cc_url, compat_str):
+                    cc_url = url_or_none(cc_file.get('Path'))
+                    if not cc_url:
                         continue
                     lang = cc_file.get('Locale') or 'en'
                     subtitles.setdefault(lang, []).append({'url': cc_url})

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',
@@ -262,6 +266,9 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # Just test metadata extraction
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/media-723735',
+        'only_matching': True,
     }]
 
     _FORMAT_IDS = {
@@ -392,7 +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')
@@ -434,13 +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(
@@ -453,92 +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,
@@ -546,16 +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+)',
@@ -565,7 +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,
@@ -580,7 +640,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     IE_NAME = 'crunchyroll:playlist'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
 
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',

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

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import base64
+import functools
 import hashlib
 import itertools
 import json
@@ -16,11 +17,16 @@ from ..utils import (
     error_to_compat_str,
     ExtractorError,
     int_or_none,
+    mimetype2ext,
+    OnDemandPagedList,
     parse_iso8601,
     sanitized_Request,
     str_to_int,
+    try_get,
     unescapeHTML,
-    mimetype2ext,
+    update_url_query,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -144,7 +150,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
         age_limit = self._rta_search(webpage)
 
-        description = self._og_search_description(webpage) or self._html_search_meta(
+        description = self._og_search_description(
+            webpage, default=None) or self._html_search_meta(
             'description', webpage, 'description')
 
         view_count_str = self._search_regex(
@@ -167,10 +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)
@@ -342,17 +364,93 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     IE_NAME = 'dailymotion:playlist'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>[^/?#&]+)'
-    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
-    _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)'
     _TESTS = [{
         'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
         'info_dict': {
             'title': 'SPORT',
-            'id': 'xv4bw_nqtv_sport',
+            'id': 'xv4bw',
         },
         'playlist_mincount': 20,
     }]
+    _PAGE_SIZE = 100
+
+    def _fetch_page(self, playlist_id, authorizaion, page):
+        page += 1
+        videos = self._download_json(
+            'https://graphql.api.dailymotion.com',
+            playlist_id, 'Downloading page %d' % page,
+            data=json.dumps({
+                'query': '''{
+  collection(xid: "%s") {
+    videos(first: %d, page: %d) {
+      pageInfo {
+        hasNextPage
+        nextPage
+      }
+      edges {
+        node {
+          xid
+          url
+        }
+      }
+    }
+  }
+}''' % (playlist_id, self._PAGE_SIZE, page)
+            }).encode(), headers={
+                'Authorization': authorizaion,
+                'Origin': 'https://www.dailymotion.com',
+            })['data']['collection']['videos']
+        for edge in videos['edges']:
+            node = edge['node']
+            yield self.url_result(
+                node['url'], DailymotionIE.ie_key(), node['xid'])
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        api = self._parse_json(self._search_regex(
+            r'__PLAYER_CONFIG__\s*=\s*({.+?});',
+            webpage, 'player config'), playlist_id)['context']['api']
+        auth = self._download_json(
+            api.get('auth_url', 'https://graphql.api.dailymotion.com/oauth/token'),
+            playlist_id, data=urlencode_postdata({
+                'client_id': api.get('client_id', 'f1a362d288c1b98099c7'),
+                'client_secret': api.get('client_secret', 'eea605b96e01c796ff369935357eca920c5da4c5'),
+                'grant_type': 'client_credentials',
+            }))
+        authorizaion = '%s %s' % (auth.get('token_type', 'Bearer'), auth['access_token'])
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, playlist_id, authorizaion), self._PAGE_SIZE)
+        return self.playlist_result(
+            entries, playlist_id,
+            self._og_search_title(webpage))
+
+
+class DailymotionUserIE(DailymotionBaseInfoExtractor):
+    IE_NAME = 'dailymotion:user'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
+    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
+    _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+    _TESTS = [{
+        'url': 'https://www.dailymotion.com/user/nqtv',
+        'info_dict': {
+            'id': 'nqtv',
+            'title': 'Rémi Gaillard',
+        },
+        'playlist_mincount': 100,
+    }, {
+        'url': 'http://www.dailymotion.com/user/UnderProject',
+        'info_dict': {
+            'id': 'UnderProject',
+            'title': 'UnderProject',
+        },
+        'playlist_mincount': 1800,
+        'expected_warnings': [
+            'Stopped at duplicated page',
+        ],
+        'skip': 'Takes too long time',
+    }]
 
     def _extract_entries(self, id):
         video_ids = set()
@@ -378,43 +476,6 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
-        webpage = self._download_webpage(url, playlist_id)
-
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'title': self._og_search_title(webpage),
-            'entries': self._extract_entries(playlist_id),
-        }
-
-
-class DailymotionUserIE(DailymotionPlaylistIE):
-    IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
-    _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
-    _TESTS = [{
-        'url': 'https://www.dailymotion.com/user/nqtv',
-        'info_dict': {
-            'id': 'nqtv',
-            'title': 'Rémi Gaillard',
-        },
-        'playlist_mincount': 100,
-    }, {
-        'url': 'http://www.dailymotion.com/user/UnderProject',
-        'info_dict': {
-            'id': 'UnderProject',
-            'title': 'UnderProject',
-        },
-        'playlist_mincount': 1800,
-        'expected_warnings': [
-            'Stopped at duplicated page',
-        ],
-        'skip': 'Takes too long time',
-    }]
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')

youtube_dl/extractor/dctp.py

@@ -5,13 +5,16 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     float_or_none,
-    unified_strdate,
+    int_or_none,
+    unified_timestamp,
+    url_or_none,
 )
 
 
 class DctpTvIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(?:#/)?filme/(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
+        # 4x3
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
         'info_dict': {
             'id': '95eaa4f33dad413aa17b4ee613cccc6c',
@@ -19,37 +22,55 @@ class DctpTvIE(InfoExtractor):
             'ext': 'flv',
             'title': 'Videoinstallation für eine Kaufhausfassade',
             'description': 'Kurzfilm',
-            'upload_date': '20110407',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 71.24,
+            'timestamp': 1302172322,
+            'upload_date': '20110407',
         },
         'params': {
             # rtmp download
             'skip_download': True,
         },
-    }
+    }, {
+        # 16x9
+        'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/',
+        'only_matching': True,
+    }]
+
+    _BASE_URL = 'http://dctp-ivms2-restapi.s3.amazonaws.com'
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, display_id)
+        version = self._download_json(
+            '%s/version.json' % self._BASE_URL, display_id,
+            'Downloading version JSON')
 
-        video_id = self._html_search_meta(
-            'DC.identifier', webpage, 'video id',
-            default=None) or self._search_regex(
-            r'id=["\']uuid[^>]+>([^<]+)<', webpage, 'video id')
+        restapi_base = '%s/%s/restapi' % (
+            self._BASE_URL, version['version_name'])
 
-        title = self._og_search_title(webpage)
+        info = self._download_json(
+            '%s/slugs/%s.json' % (restapi_base, display_id), display_id,
+            'Downloading video info JSON')
+
+        media = self._download_json(
+            '%s/media/%s.json' % (restapi_base, compat_str(info['object_id'])),
+            display_id, 'Downloading media JSON')
+
+        uuid = media['uuid']
+        title = media['title']
+        ratio = '16x9' if media.get('is_wide') else '4x3'
+        play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio)
 
         servers = self._download_json(
             'http://www.dctp.tv/streaming_servers/', display_id,
-            note='Downloading server list', fatal=False)
+            note='Downloading server list JSON', fatal=False)
 
         if servers:
             endpoint = next(
                 server['endpoint']
                 for server in servers
-                if isinstance(server.get('endpoint'), compat_str) and
+                if url_or_none(server.get('endpoint')) and
                 'cloudfront' in server['endpoint'])
         else:
             endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
@@ -60,27 +81,35 @@ class DctpTvIE(InfoExtractor):
         formats = [{
             'url': endpoint,
             'app': app,
-            'play_path': 'mp4:%s_dctp_0500_4x3.m4v' % video_id,
+            'play_path': play_path,
             'page_url': url,
-            'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-109.swf',
+            'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf',
             'ext': 'flv',
         }]
 
-        description = self._html_search_meta('DC.description', webpage)
-        upload_date = unified_strdate(
-            self._html_search_meta('DC.date.created', webpage))
-        thumbnail = self._og_search_thumbnail(webpage)
-        duration = float_or_none(self._search_regex(
-            r'id=["\']duration_in_ms[^+]>(\d+)', webpage, 'duration',
-            default=None), scale=1000)
+        thumbnails = []
+        images = media.get('images')
+        if isinstance(images, list):
+            for image in images:
+                if not isinstance(image, dict):
+                    continue
+                image_url = url_or_none(image.get('url'))
+                if not image_url:
+                    continue
+                thumbnails.append({
+                    'url': image_url,
+                    'width': int_or_none(image.get('width')),
+                    'height': int_or_none(image.get('height')),
+                })
 
         return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
+            'id': uuid,
             'display_id': display_id,
-            'description': description,
-            'upload_date': upload_date,
-            'thumbnail': thumbnail,
-            'duration': duration,
+            'title': title,
+            'alt_title': media.get('subtitle'),
+            'description': media.get('description') or media.get('teaser'),
+            'timestamp': unified_timestamp(media.get('created')),
+            'duration': float_or_none(media.get('duration_in_ms'), scale=1000),
+            'thumbnails': thumbnails,
+            'formats': formats,
         }

youtube_dl/extractor/discoverygo.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     extract_attributes,
@@ -12,6 +11,7 @@ from ..utils import (
     parse_age_limit,
     remove_end,
     unescapeHTML,
+    url_or_none,
 )
 
 
@@ -69,9 +69,8 @@ class DiscoveryGoBaseIE(InfoExtractor):
         captions = stream.get('captions')
         if isinstance(captions, list):
             for caption in captions:
-                subtitle_url = caption.get('fileUrl')
-                if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
-                        not subtitle_url.startswith('http')):
+                subtitle_url = url_or_none(caption.get('fileUrl'))
+                if not subtitle_url or not subtitle_url.startswith('http'):
                     continue
                 lang = caption.get('fileLang', 'en')
                 ext = determine_ext(subtitle_url)

youtube_dl/extractor/dplay.py

@@ -21,6 +21,7 @@ from ..utils import (
     unified_strdate,
     unified_timestamp,
     update_url_query,
+    urljoin,
     USER_AGENTS,
 )
 
@@ -310,9 +311,11 @@ class DPlayItIE(InfoExtractor):
 
         if not info:
             info_url = self._search_regex(
-                r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)',
-                webpage, 'info url')
+                (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+                 r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'),
+                webpage, 'info url', group='url')
 
+            info_url = urljoin(url, info_url)
             video_id = info_url.rpartition('/')[-1]
 
             try:
@@ -322,6 +325,8 @@ class DPlayItIE(InfoExtractor):
                             'dplayit_token').value,
                         'Referer': url,
                     })
+                if isinstance(info, compat_str):
+                    info = self._parse_json(info, display_id)
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
                     info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
@@ -337,6 +342,7 @@ class DPlayItIE(InfoExtractor):
         formats = self._extract_m3u8_formats(
             hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
             m3u8_id='hls')
+        self._sort_formats(formats)
 
         series = self._html_search_regex(
             r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',

youtube_dl/extractor/dramafever.py

@@ -7,7 +7,6 @@ import json
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
-    compat_str,
     compat_urlparse,
 )
 from ..utils import (
@@ -17,6 +16,7 @@ from ..utils import (
     parse_age_limit,
     parse_duration,
     unified_timestamp,
+    url_or_none,
 )
 
 
@@ -139,8 +139,8 @@ class DramaFeverIE(DramaFeverBaseIE):
         for sub in subs:
             if not isinstance(sub, dict):
                 continue
-            sub_url = sub.get('url')
-            if not sub_url or not isinstance(sub_url, compat_str):
+            sub_url = url_or_none(sub.get('url'))
+            if not sub_url:
                 continue
             subtitles.setdefault(
                 sub.get('code') or sub.get('language') or 'en', []).append({
@@ -163,8 +163,8 @@ class DramaFeverIE(DramaFeverBaseIE):
             for format_id, format_dict in download_assets.items():
                 if not isinstance(format_dict, dict):
                     continue
-                format_url = format_dict.get('url')
-                if not format_url or not isinstance(format_url, compat_str):
+                format_url = url_or_none(format_dict.get('url'))
+                if not format_url:
                     continue
                 formats.append({
                     'url': format_url,

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/eagleplatform.py

@@ -4,14 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_str,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
     int_or_none,
     unsmuggle_url,
+    url_or_none,
 )
 
 
@@ -177,7 +175,7 @@ class EaglePlatformIE(InfoExtractor):
             video_id, 'Downloading mp4 JSON', fatal=False)
         if mp4_data:
             for format_id, format_url in mp4_data.get('data', {}).items():
-                if not isinstance(format_url, compat_str):
+                if not url_or_none(format_url):
                     continue
                 height = int_or_none(format_id)
                 if height is not None and m3u8_formats_dict.get(height):

youtube_dl/extractor/egghead.py

@@ -8,6 +8,7 @@ from ..utils import (
     int_or_none,
     try_get,
     unified_timestamp,
+    url_or_none,
 )
 
 
@@ -34,8 +35,8 @@ class EggheadCourseIE(InfoExtractor):
 
         entries = []
         for lesson in lessons:
-            lesson_url = lesson.get('http_url')
-            if not lesson_url or not isinstance(lesson_url, compat_str):
+            lesson_url = url_or_none(lesson.get('http_url'))
+            if not lesson_url:
                 continue
             lesson_id = lesson.get('id')
             if lesson_id:
@@ -95,7 +96,8 @@ class EggheadLessonIE(InfoExtractor):
 
         formats = []
         for _, format_url in lesson['media_urls'].items():
-            if not format_url or not isinstance(format_url, compat_str):
+            format_url = url_or_none(format_url)
+            if not format_url:
                 continue
             ext = determine_ext(format_url)
             if ext == 'm3u8':

youtube_dl/extractor/eporner.py

@@ -9,8 +9,10 @@ from ..utils import (
     encode_base_n,
     ExtractorError,
     int_or_none,
+    merge_dicts,
     parse_duration,
     str_to_int,
+    url_or_none,
 )
 
 
@@ -24,10 +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/',
@@ -82,8 +90,8 @@ class EpornerIE(InfoExtractor):
             for format_id, format_dict in formats_dict.items():
                 if not isinstance(format_dict, dict):
                     continue
-                src = format_dict.get('src')
-                if not isinstance(src, compat_str) or not src.startswith('http'):
+                src = url_or_none(format_dict.get('src'))
+                if not src or not src.startswith('http'):
                     continue
                 if kind == 'hls':
                     formats.extend(self._extract_m3u8_formats(
@@ -103,12 +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,
@@ -116,4 +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,
@@ -204,7 +205,10 @@ 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,
@@ -390,6 +394,11 @@ from .francetv import (
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .freshlive import FreshLiveIE
+from .frontendmasters import (
+    FrontendMastersIE,
+    FrontendMastersLessonIE,
+    FrontendMastersCourseIE
+)
 from .funimation import FunimationIE
 from .funk import (
     FunkMixIE,
@@ -511,6 +520,7 @@ 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
@@ -529,6 +539,7 @@ from .la7 import LA7IE
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
+    EHFTVIE,
     ITTFIE,
 )
 from .lci import LCIIE
@@ -558,6 +569,10 @@ from .limelight import (
     LimelightChannelListIE,
 )
 from .line import LineTVIE
+from .linkedin import (
+    LinkedInLearningIE,
+    LinkedInLearningCourseIE,
+)
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -731,7 +746,10 @@ 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,
@@ -763,7 +781,9 @@ from .nrk import (
     NRKSkoleIE,
     NRKTVIE,
     NRKTVDirekteIE,
+    NRKTVEpisodeIE,
     NRKTVEpisodesIE,
+    NRKTVSeasonIE,
     NRKTVSeriesIE,
 )
 from .ntvde import NTVDeIE
@@ -853,6 +873,10 @@ from .pornhub import (
 from .pornotube import PornotubeIE
 from .pornovoisines import PornoVoisinesIE
 from .pornoxo import PornoXOIE
+from .puhutv import (
+    PuhuTVIE,
+    PuhuTVSerieIE,
+)
 from .presstv import PressTVIE
 from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
@@ -884,7 +908,10 @@ 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
@@ -1020,7 +1047,7 @@ 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
@@ -1040,6 +1067,7 @@ from .stretchinternet import StretchInternetIE
 from .sunporno import SunPornoIE
 from .svt import (
     SVTIE,
+    SVTPageIE,
     SVTPlayIE,
     SVTSeriesIE,
 )
@@ -1062,6 +1090,7 @@ 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
@@ -1128,7 +1157,6 @@ from .tv2 import (
     TV2ArticleIE,
 )
 from .tv2hu import TV2HuIE
-from .tv3 import TV3IE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
 from .tva import TVAIE
@@ -1158,12 +1186,14 @@ 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,
@@ -1279,6 +1309,7 @@ from .viki import (
     VikiIE,
     VikiChannelIE,
 )
+from .viqeo import ViqeoIE
 from .viu import (
     ViuIE,
     ViuPlaylistIE,
@@ -1404,6 +1435,7 @@ from .younow import (
     YouNowMomentIE,
 )
 from .youporn import YouPornIE
+from .yourporn import YourPornIE
 from .yourupload import YourUploadIE
 from .youtube import (
     YoutubeIE,
@@ -1427,8 +1459,20 @@ 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,
 )

youtube_dl/extractor/facebook.py

@@ -20,6 +20,7 @@ from ..utils import (
     int_or_none,
     js_to_json,
     limit_length,
+    parse_count,
     sanitized_Request,
     try_get,
     urlencode_postdata,
@@ -56,7 +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',
@@ -75,7 +76,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',
-            'title': 'Asif Nawab Butt posted a video to his Timeline.',
+            'title': 're:^Asif Nawab Butt posted a video',
             'uploader': 'Asif Nawab Butt',
             'upload_date': '20140506',
             'timestamp': 1399398998,
@@ -133,7 +134,7 @@ class FacebookIE(InfoExtractor):
     }, {
         # have 1080P, but only up to 720p in swf params
         'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
-        'md5': '0d9813160b146b3bc8744e006027fcc6',
+        'md5': '9571fae53d4165bbbadb17a94651dcdc',
         'info_dict': {
             'id': '10155529876156509',
             'ext': 'mp4',
@@ -142,6 +143,7 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20161030',
             'uploader': 'CNN',
             'thumbnail': r're:^https?://.*',
+            'view_count': int,
         },
     }, {
         # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
@@ -149,7 +151,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '1417995061575415',
             'ext': 'mp4',
-            'title': 'md5:a7b86ca673f51800cd54687b7f4012fe',
+            'title': 'md5:1db063d6a8c13faa8da727817339c857',
             'timestamp': 1486648217,
             'upload_date': '20170209',
             'uploader': 'Yaroslav Korpan',
@@ -176,7 +178,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '1396382447100162',
             'ext': 'mp4',
-            'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3',
+            'title': 'md5:19a428bbde91364e3de815383b54a235',
             'timestamp': 1486035494,
             'upload_date': '20170202',
             'uploader': 'Elisabeth Ahtn',
@@ -353,7 +355,6 @@ class FacebookIE(InfoExtractor):
             tahoe_data = self._download_webpage(
                 self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
                 data=urlencode_postdata({
-                    '__user': 0,
                     '__a': 1,
                     '__pc': self._search_regex(
                         r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,
@@ -361,6 +362,9 @@ class FacebookIE(InfoExtractor):
                     '__rev': self._search_regex(
                         r'client_revision["\']\s*:\s*(\d+),', webpage,
                         'client revision', default='3944515'),
+                    'fb_dtsg': self._search_regex(
+                        r'"DTSGInitialData"\s*,\s*\[\]\s*,\s*{\s*"token"\s*:\s*"([^"]+)"',
+                        webpage, 'dtsg token', default=''),
                 }),
                 headers={
                     'Content-Type': 'application/x-www-form-urlencoded',
@@ -426,6 +430,10 @@ class FacebookIE(InfoExtractor):
             'timestamp', default=None))
         thumbnail = self._og_search_thumbnail(webpage)
 
+        view_count = parse_count(self._search_regex(
+            r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
+            default=None))
+
         info_dict = {
             'id': video_id,
             'title': video_title,
@@ -433,6 +441,7 @@ class FacebookIE(InfoExtractor):
             'uploader': uploader,
             'timestamp': timestamp,
             'thumbnail': thumbnail,
+            'view_count': view_count,
         }
 
         return webpage, info_dict

youtube_dl/extractor/firsttv.py

@@ -10,6 +10,7 @@ from ..utils import (
     int_or_none,
     qualities,
     unified_strdate,
+    url_or_none,
 )
 
 
@@ -88,8 +89,8 @@ class FirstTVIE(InfoExtractor):
             formats = []
             path = None
             for f in item.get('mbr', []):
-                src = f.get('src')
-                if not src or not isinstance(src, compat_str):
+                src = url_or_none(f.get('src'))
+                if not src:
                     continue
                 tbr = int_or_none(self._search_regex(
                     r'_(\d{3,})\.mp4', src, 'tbr', default=None))

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/francetv.py

@@ -16,6 +16,7 @@ from ..utils import (
     int_or_none,
     parse_duration,
     try_get,
+    url_or_none,
 )
 from .dailymotion import DailymotionIE
 
@@ -115,14 +116,13 @@ class FranceTVIE(InfoExtractor):
 
         def sign(manifest_url, manifest_id):
             for host in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'):
-                signed_url = self._download_webpage(
+                signed_url = url_or_none(self._download_webpage(
                     'https://%s/esi/TA' % host, video_id,
                     'Downloading signed %s manifest URL' % manifest_id,
                     fatal=False, query={
                         'url': manifest_url,
-                    })
-                if (signed_url and isinstance(signed_url, compat_str) and
-                        re.search(r'^(?:https?:)?//', signed_url)):
+                    }))
+                if signed_url:
                     return signed_url
             return manifest_url
 

youtube_dl/extractor/frontendmasters.py

@@ -0,0 +1,263 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+    url_or_none,
+    urlencode_postdata,
+)
+
+
+class FrontendMastersBaseIE(InfoExtractor):
+    _API_BASE = 'https://api.frontendmasters.com/v1/kabuki'
+    _LOGIN_URL = 'https://frontendmasters.com/login/'
+
+    _NETRC_MACHINE = 'frontendmasters'
+
+    _QUALITIES = {
+        'low': {'width': 480, 'height': 360},
+        'mid': {'width': 1280, 'height': 720},
+        'high': {'width': 1920, 'height': 1080}
+    }
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'username': username,
+            'password': password
+        })
+
+        post_url = self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
+            'post_url', default=self._LOGIN_URL, group='url')
+
+        if not post_url.startswith('http'):
+            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+
+        response = self._download_webpage(
+            post_url, None, 'Logging in', data=urlencode_postdata(login_form),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})
+
+        # Successful login
+        if any(p in response for p in (
+                'wp-login.php?action=logout', '>Logout')):
+            return
+
+        error = self._html_search_regex(
+            r'class=(["\'])(?:(?!\1).)*\bMessageAlert\b(?:(?!\1).)*\1[^>]*>(?P<error>[^<]+)<',
+            response, 'error message', default=None, group='error')
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+        raise ExtractorError('Unable to log in')
+
+
+class FrontendMastersPageBaseIE(FrontendMastersBaseIE):
+    def _download_course(self, course_name, url):
+        return self._download_json(
+            '%s/courses/%s' % (self._API_BASE, course_name), course_name,
+            'Downloading course JSON', headers={'Referer': url})
+
+    @staticmethod
+    def _extract_chapters(course):
+        chapters = []
+        lesson_elements = course.get('lessonElements')
+        if isinstance(lesson_elements, list):
+            chapters = [url_or_none(e) for e in lesson_elements if url_or_none(e)]
+        return chapters
+
+    @staticmethod
+    def _extract_lesson(chapters, lesson_id, lesson):
+        title = lesson.get('title') or lesson_id
+        display_id = lesson.get('slug')
+        description = lesson.get('description')
+        thumbnail = lesson.get('thumbnail')
+
+        chapter_number = None
+        index = lesson.get('index')
+        element_index = lesson.get('elementIndex')
+        if (isinstance(index, int) and isinstance(element_index, int) and
+                index < element_index):
+            chapter_number = element_index - index
+        chapter = (chapters[chapter_number - 1]
+                   if chapter_number - 1 < len(chapters) else None)
+
+        duration = None
+        timestamp = lesson.get('timestamp')
+        if isinstance(timestamp, compat_str):
+            mobj = re.search(
+                r'(?P<start>\d{1,2}:\d{1,2}:\d{1,2})\s*-(?P<end>\s*\d{1,2}:\d{1,2}:\d{1,2})',
+                timestamp)
+            if mobj:
+                duration = parse_duration(mobj.group('end')) - parse_duration(
+                    mobj.group('start'))
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'frontendmasters:%s' % lesson_id,
+            'ie_key': FrontendMastersIE.ie_key(),
+            'id': lesson_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'chapter': chapter,
+            'chapter_number': chapter_number,
+        }
+
+
+class FrontendMastersIE(FrontendMastersBaseIE):
+    _VALID_URL = r'(?:frontendmasters:|https?://api\.frontendmasters\.com/v\d+/kabuki/video/)(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://api.frontendmasters.com/v1/kabuki/video/a2qogef6ba',
+        'md5': '7f161159710d6b7016a4f4af6fcb05e2',
+        'info_dict': {
+            'id': 'a2qogef6ba',
+            'ext': 'mp4',
+            'title': 'a2qogef6ba',
+        },
+        'skip': 'Requires FrontendMasters account credentials',
+    }, {
+        'url': 'frontendmasters:a2qogef6ba',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        lesson_id = self._match_id(url)
+
+        source_url = '%s/video/%s/source' % (self._API_BASE, lesson_id)
+
+        formats = []
+        for ext in ('webm', 'mp4'):
+            for quality in ('low', 'mid', 'high'):
+                resolution = self._QUALITIES[quality].copy()
+                format_id = '%s-%s' % (ext, quality)
+                format_url = self._download_json(
+                    source_url, lesson_id,
+                    'Downloading %s source JSON' % format_id, query={
+                        'f': ext,
+                        'r': resolution['height'],
+                    }, headers={
+                        'Referer': url,
+                    }, fatal=False)['url']
+
+                if not format_url:
+                    continue
+
+                f = resolution.copy()
+                f.update({
+                    'url': format_url,
+                    'ext': ext,
+                    'format_id': format_id,
+                })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        subtitles = {
+            'en': [{
+                'url': '%s/transcripts/%s.vtt' % (self._API_BASE, lesson_id),
+            }]
+        }
+
+        return {
+            'id': lesson_id,
+            'title': lesson_id,
+            'formats': formats,
+            'subtitles': subtitles
+        }
+
+
+class FrontendMastersLessonIE(FrontendMastersPageBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<course_name>[^/]+)/(?P<lesson_name>[^/]+)'
+    _TEST = {
+        'url': 'https://frontendmasters.com/courses/web-development/tools',
+        'info_dict': {
+            'id': 'a2qogef6ba',
+            'display_id': 'tools',
+            'ext': 'mp4',
+            'title': 'Tools',
+            'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'chapter': 'Introduction',
+            'chapter_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Requires FrontendMasters account credentials',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        course_name, lesson_name = mobj.group('course_name', 'lesson_name')
+
+        course = self._download_course(course_name, url)
+
+        lesson_id, lesson = next(
+            (video_id, data)
+            for video_id, data in course['lessonData'].items()
+            if data.get('slug') == lesson_name)
+
+        chapters = self._extract_chapters(course)
+        return self._extract_lesson(chapters, lesson_id, lesson)
+
+
+class FrontendMastersCourseIE(FrontendMastersPageBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'https://frontendmasters.com/courses/web-development/',
+        'info_dict': {
+            'id': 'web-development',
+            'title': 'Introduction to Web Development',
+            'description': 'md5:9317e6e842098bf725d62360e52d49a6',
+        },
+        'playlist_count': 81,
+        'skip': 'Requires FrontendMasters account credentials',
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if FrontendMastersLessonIE.suitable(url) else super(
+            FrontendMastersBaseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        course_name = self._match_id(url)
+
+        course = self._download_course(course_name, url)
+
+        chapters = self._extract_chapters(course)
+
+        lessons = sorted(
+            course['lessonData'].values(), key=lambda data: data['index'])
+
+        entries = []
+        for lesson in lessons:
+            lesson_name = lesson.get('slug')
+            if not lesson_name:
+                continue
+            lesson_id = lesson.get('hash') or lesson.get('statsId')
+            entries.append(self._extract_lesson(chapters, lesson_id, lesson))
+
+        title = course.get('title')
+        description = course.get('description')
+
+        return self.playlist_result(entries, course_name, title, description)

youtube_dl/extractor/funk.py

@@ -1,10 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
 from .nexx import NexxIE
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     try_get,
@@ -12,6 +14,19 @@ from ..utils import (
 
 
 class FunkBaseIE(InfoExtractor):
+    _HEADERS = {
+        'Accept': '*/*',
+        'Accept-Language': 'en-US,en;q=0.9,ru;q=0.8',
+        'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4',
+    }
+    _AUTH = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4'
+
+    @staticmethod
+    def _make_headers(referer):
+        headers = FunkBaseIE._HEADERS.copy()
+        headers['Referer'] = referer
+        return headers
+
     def _make_url_result(self, video):
         return {
             '_type': 'url_transparent',
@@ -48,19 +63,19 @@ class FunkMixIE(FunkBaseIE):
 
         lists = self._download_json(
             'https://www.funk.net/api/v3.1/curation/curatedLists/',
-            mix_id, headers={
-                'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbC12Mi4wIiwic2NvcGUiOiJzdGF0aWMtY29udGVudC1hcGksY3VyYXRpb24tc2VydmljZSxzZWFyY2gtYXBpIn0.SGCC1IXHLtZYoo8PvRKlU2gXH1su8YSu47sB3S4iXBI',
-                'Referer': url,
-            }, query={
+            mix_id, headers=self._make_headers(url), query={
                 'size': 100,
-            })['result']['lists']
+            })['_embedded']['curatedListList']
 
         metas = next(
             l for l in lists
             if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas']
         video = next(
             meta['videoDataDelegate']
-            for meta in metas if meta.get('alias') == alias)
+            for meta in metas
+            if try_get(
+                meta, lambda x: x['videoDataDelegate']['alias'],
+                compat_str) == alias)
 
         return self._make_url_result(video)
 
@@ -104,25 +119,53 @@ class FunkChannelIE(FunkBaseIE):
         channel_id = mobj.group('id')
         alias = mobj.group('alias')
 
-        headers = {
-            'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbCIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxzZWFyY2gtYXBpIn0.q4Y2xZG8PFHai24-4Pjx2gym9RmJejtmK6lMXP5wAgc',
-            'Referer': url,
-        }
+        headers = self._make_headers(url)
 
         video = None
 
-        by_id_list = self._download_json(
-            'https://www.funk.net/api/v3.0/content/videos/byIdList', channel_id,
-            headers=headers, query={
-                'ids': alias,
-            }, fatal=False)
-        if by_id_list:
-            video = try_get(by_id_list, lambda x: x['result'][0], dict)
+        # Id-based channels are currently broken on their side: webplayer
+        # tries to process them via byChannelAlias endpoint and fails
+        # predictably.
+        for page_num in itertools.count():
+            by_channel_alias = self._download_json(
+                'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s'
+                % channel_id,
+                'Downloading byChannelAlias JSON page %d' % (page_num + 1),
+                headers=headers, query={
+                    'filterFsk': 'false',
+                    'sort': 'creationDate,desc',
+                    'size': 100,
+                    'page': page_num,
+                }, fatal=False)
+            if not by_channel_alias:
+                break
+            video_list = try_get(
+                by_channel_alias, lambda x: x['_embedded']['videoList'], list)
+            if not video_list:
+                break
+            try:
+                video = next(r for r in video_list if r.get('alias') == alias)
+                break
+            except StopIteration:
+                pass
+            if not try_get(
+                    by_channel_alias, lambda x: x['_links']['next']):
+                break
+
+        if not video:
+            by_id_list = self._download_json(
+                'https://www.funk.net/api/v3.0/content/videos/byIdList',
+                channel_id, 'Downloading byIdList JSON', headers=headers,
+                query={
+                    'ids': alias,
+                }, fatal=False)
+            if by_id_list:
+                video = try_get(by_id_list, lambda x: x['result'][0], dict)
 
         if not video:
             results = self._download_json(
-                'https://www.funk.net/api/v3.0/content/videos/filter', channel_id,
-                headers=headers, query={
+                'https://www.funk.net/api/v3.0/content/videos/filter',
+                channel_id, 'Downloading filter JSON', headers=headers, query={
                     'channelId': channel_id,
                     'size': 100,
                 })['result']

youtube_dl/extractor/generic.py

@@ -47,7 +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
@@ -112,6 +112,8 @@ from .peertube import PeerTubeIE
 from .indavideo import IndavideoEmbedIE
 from .apa import APAIE
 from .foxnews import FoxNewsIE
+from .viqeo import ViqeoIE
+from .expressen import ExpressenIE
 
 
 class GenericIE(InfoExtractor):
@@ -1395,17 +1397,6 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
-        # SVT embed
-        {
-            'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
-            'info_dict': {
-                'id': '2900353',
-                'ext': 'flv',
-                'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
-                'duration': 27,
-                'age_limit': 0,
-            },
-        },
         # Crooks and Liars embed
         {
             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
@@ -2070,6 +2061,30 @@ class GenericIE(InfoExtractor):
             },
             'skip': 'TODO: fix nested playlists processing in tests',
         },
+        {
+            # Viqeo embeds
+            'url': 'https://viqeo.tv/',
+            'info_dict': {
+                'id': 'viqeo',
+                'title': 'All-new video platform',
+            },
+            'playlist_count': 6,
+        },
+        {
+            # 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 +2636,9 @@ 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 +3023,7 @@ 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())
@@ -3097,13 +3112,23 @@ 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:
             return self.playlist_from_matches(
                 sharevideos_urls, video_id, video_title)
 
+        viqeo_urls = ViqeoIE._extract_urls(webpage)
+        if viqeo_urls:
+            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())
+
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:
@@ -3125,9 +3150,13 @@ 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(

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/go90.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -14,8 +15,8 @@ from ..utils import (
 
 
 class Go90IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'https://www.go90.com/videos/84BUqjLpf9D',
         'md5': 'efa7670dbbbf21a7b07b360652b24a32',
         'info_dict': {
@@ -27,15 +28,31 @@ class Go90IE(InfoExtractor):
             'upload_date': '20170411',
             'age_limit': 14,
         }
-    }
+    }, {
+        'url': 'https://www.go90.com/embed/261MflWkD3N',
+        'only_matching': True,
+    }]
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'https://www.go90.com/api/view/items/' + video_id,
-            video_id, headers={
+
+        try:
+            headers = self.geo_verification_headers()
+            headers.update({
                 'Content-Type': 'application/json; charset=utf-8',
-            }, data=b'{"client":"web","device_type":"pc"}')
+            })
+            video_data = self._download_json(
+                'https://www.go90.com/api/view/items/' + video_id, video_id,
+                headers=headers, data=b'{"client":"web","device_type":"pc"}')
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                message = self._parse_json(e.cause.read().decode(), None)['error']['message']
+                if 'region unavailable' in message:
+                    self.raise_geo_restricted(countries=['US'])
+                raise ExtractorError(message, expected=True)
+            raise
+
         if video_data.get('requires_drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
         main_video_asset = video_data['main_video_asset']

youtube_dl/extractor/hidive.py

@@ -8,6 +8,7 @@ from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
     urlencode_postdata,
 )
 
@@ -80,8 +81,8 @@ class HiDiveIE(InfoExtractor):
             bitrates = rendition.get('bitrates')
             if not isinstance(bitrates, dict):
                 continue
-            m3u8_url = bitrates.get('hls')
-            if not isinstance(m3u8_url, compat_str):
+            m3u8_url = url_or_none(bitrates.get('hls'))
+            if not m3u8_url:
                 continue
             formats.extend(self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
@@ -93,9 +94,8 @@ class HiDiveIE(InfoExtractor):
                 if not isinstance(cc_file, list) or len(cc_file) < 3:
                     continue
                 cc_lang = cc_file[0]
-                cc_url = cc_file[2]
-                if not isinstance(cc_lang, compat_str) or not isinstance(
-                        cc_url, compat_str):
+                cc_url = url_or_none(cc_file[2])
+                if not isinstance(cc_lang, compat_str) or not cc_url:
                     continue
                 subtitles.setdefault(cc_lang, []).append({
                     'url': cc_url,

youtube_dl/extractor/hotstar.py

@@ -1,49 +1,55 @@
 # 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',
+        '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,
         },
@@ -58,47 +64,47 @@ 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 = {}
+        for v in app_state.values():
+            content = try_get(v, lambda x: x['initialState']['contentData']['content'], 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 +112,43 @@ 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

@@ -3,12 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     mimetype2ext,
     parse_duration,
     qualities,
+    url_or_none,
 )
 
 
@@ -61,10 +61,11 @@ class ImdbIE(InfoExtractor):
         for encoding in video_metadata.get('encodings', []):
             if not encoding or not isinstance(encoding, dict):
                 continue
-            video_url = encoding.get('videoUrl')
-            if not video_url or not isinstance(video_url, compat_str):
+            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/imgur.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class ImgurIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$'
 
     _TESTS = [{
         'url': 'https://i.imgur.com/A61SaA1.gifv',
@@ -43,6 +43,9 @@ class ImgurIE(InfoExtractor):
     }, {
         'url': 'http://imgur.com/r/aww/VQcQPhM',
         'only_matching': True,
+    }, {
+        'url': 'https://i.imgur.com/crGpqCV.mp4',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/instagram.py

@@ -17,6 +17,7 @@ from ..utils import (
     lowercase_escape,
     std_headers,
     try_get,
+    url_or_none,
 )
 
 
@@ -170,7 +171,7 @@ class InstagramIE(InfoExtractor):
                             node = try_get(edge, lambda x: x['node'], dict)
                             if not node:
                                 continue
-                            node_video_url = try_get(node, lambda x: x['video_url'], compat_str)
+                            node_video_url = url_or_none(node.get('video_url'))
                             if not node_video_url:
                                 continue
                             entries.append({

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/itv.py

@@ -20,6 +20,7 @@ from ..utils import (
     merge_dicts,
     parse_duration,
     smuggle_url,
+    url_or_none,
     xpath_with_ns,
     xpath_element,
     xpath_text,
@@ -250,8 +251,8 @@ class ITVIE(InfoExtractor):
                     for sub in subs:
                         if not isinstance(sub, dict):
                             continue
-                        href = sub.get('Href')
-                        if isinstance(href, compat_str):
+                        href = url_or_none(sub.get('Href'))
+                        if href:
                             extract_subtitle(href)
                 if not info.get('duration'):
                     info['duration'] = parse_duration(video_data.get('Duration'))

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/iwara.py

@@ -7,6 +7,7 @@ from ..utils import (
     int_or_none,
     mimetype2ext,
     remove_end,
+    url_or_none,
 )
 
 
@@ -73,11 +74,14 @@ class IwaraIE(InfoExtractor):
 
         formats = []
         for a_format in video_data:
+            format_uri = url_or_none(a_format.get('uri'))
+            if not format_uri:
+                continue
             format_id = a_format.get('resolution')
             height = int_or_none(self._search_regex(
                 r'(\d+)p', format_id, 'height', default=None))
             formats.append({
-                'url': a_format['uri'],
+                'url': self._proto_relative_url(format_uri, 'https:'),
                 'format_id': format_id,
                 'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
                 'height': height,

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/keezmovies.py

@@ -4,16 +4,14 @@ import re
 
 from .common import InfoExtractor
 from ..aes import aes_decrypt_text
-from ..compat import (
-    compat_str,
-    compat_urllib_parse_unquote,
-)
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
     str_to_int,
     strip_or_none,
+    url_or_none,
 )
 
 
@@ -55,7 +53,8 @@ class KeezMoviesIE(InfoExtractor):
         encrypted = False
 
         def extract_format(format_url, height=None):
-            if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//')):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//')):
                 return
             if format_url in format_urls:
                 return

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/konserthusetplay.py

@@ -2,11 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    url_or_none,
 )
 
 
@@ -109,7 +109,8 @@ class KonserthusetPlayIE(InfoExtractor):
         captions = source.get('captionsAvailableLanguages')
         if isinstance(captions, dict):
             for lang, subtitle_url in captions.items():
-                if lang != 'none' and isinstance(subtitle_url, compat_str):
+                subtitle_url = url_or_none(subtitle_url)
+                if lang != 'none' and subtitle_url:
                     subtitles.setdefault(lang, []).append({'url': subtitle_url})
 
         return {

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/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

@@ -4,7 +4,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_HTTPError,
     compat_str,
     compat_urlparse,
 )
@@ -44,21 +43,15 @@ class LyndaBaseIE(InfoExtractor):
         form_data = self._hidden_inputs(form_html)
         form_data.update(extra_form_data)
 
-        try:
-            response = self._download_json(
-                action_url, None, note,
-                data=urlencode_postdata(form_data),
-                headers={
-                    'Referer': referrer_url,
-                    'X-Requested-With': 'XMLHttpRequest',
-                })
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
-                response = self._parse_json(e.cause.read().decode('utf-8'), None)
-                self._check_error(response, ('email', 'password'))
-            raise
+        response = self._download_json(
+            action_url, None, note,
+            data=urlencode_postdata(form_data),
+            headers={
+                'Referer': referrer_url,
+                'X-Requested-With': 'XMLHttpRequest',
+            }, expected_status=(418, 500, ))
 
-        self._check_error(response, 'ErrorMessage')
+        self._check_error(response, ('email', 'password', 'ErrorMessage'))
 
         return response, action_url
 

youtube_dl/extractor/mediaset.py

@@ -3,116 +3,161 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
-from ..compat import compat_str
+from .theplatform import ThePlatformBaseIE
+from ..compat import (
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
-    determine_ext,
-    parse_duration,
-    try_get,
-    unified_strdate,
+    ExtractorError,
+    int_or_none,
+    update_url_query,
 )
 
 
-class MediasetIE(InfoExtractor):
+class MediasetIE(ThePlatformBaseIE):
+    _TP_TLD = 'eu'
     _VALID_URL = r'''(?x)
                     (?:
                         mediaset:|
                         https?://
-                            (?:www\.)?video\.mediaset\.it/
+                            (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
                             (?:
                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
-                                player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=
+                                player/index\.html\?.*?\bprogramGuid=
                             )
-                    )(?P<id>[0-9]+)
+                    )(?P<id>[0-9A-Z]{16})
                     '''
     _TESTS = [{
         # full episode
-        'url': 'http://www.video.mediaset.it/video/hello_goodbye/full/quarta-puntata_661824.html',
+        'url': 'https://www.mediasetplay.mediaset.it/video/hellogoodbye/quarta-puntata_FAFU000000661824',
         'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
         'info_dict': {
-            'id': '661824',
+            'id': 'FAFU000000661824',
             'ext': 'mp4',
             'title': 'Quarta puntata',
-            'description': 'md5:7183696d6df570e3412a5ef74b27c5e2',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 1414,
-            'creator': 'mediaset',
+            'duration': 1414.26,
             'upload_date': '20161107',
             'series': 'Hello Goodbye',
-            'categories': ['reality'],
+            'timestamp': 1478532900,
+            'uploader': 'Rete 4',
+            'uploader_id': 'R4',
         },
-        'expected_warnings': ['is not a supported codec'],
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
+        'md5': '288532f0ad18307705b01e581304cd7b',
+        'info_dict': {
+            'id': 'F309013801000501',
+            'ext': 'mp4',
+            'title': 'Puntata del 25 maggio',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 6565.007,
+            'upload_date': '20180526',
+            'series': 'Matrix',
+            'timestamp': 1527326245,
+            'uploader': 'Canale 5',
+            'uploader_id': 'C5',
+        },
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
         # clip
-        'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html',
+        'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
         'only_matching': True,
     }, {
         # iframe simple
-        'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true',
+        'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
         'only_matching': True,
     }, {
         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
-        'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true',
+        'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
         'only_matching': True,
     }, {
-        'url': 'mediaset:661824',
+        'url': 'mediaset:FAFU000000665924',
         'only_matching': True,
     }]
 
     @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):
-        video_id = self._match_id(url)
-
-        video_list = self._download_json(
-            'http://cdnsel01.mediaset.net/GetCdn.aspx',
-            video_id, 'Downloading video CDN JSON', query={
-                'streamid': video_id,
-                'format': 'json',
-            })['videoList']
+        guid = self._match_id(url)
+        tp_path = 'PR1GhC/media/guid/2702976343/' + guid
+        info = self._extract_theplatform_metadata(tp_path, guid)
 
         formats = []
-        for format_url in video_list:
-            if '.ism' in format_url:
-                formats.extend(self._extract_ism_formats(
-                    format_url, video_id, ism_id='mss', fatal=False))
-            else:
-                formats.append({
-                    'url': format_url,
-                    'format_id': determine_ext(format_url),
-                })
+        subtitles = {}
+        first_e = None
+        for asset_type in ('SD', 'HD'):
+            for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
+                try:
+                    tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                        update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
+                            'mbr': 'true',
+                            'formats': f,
+                            'assetTypes': asset_type,
+                        }), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
+                except ExtractorError as e:
+                    if not first_e:
+                        first_e = e
+                    break
+                for tp_f in tp_formats:
+                    tp_f['quality'] = 1 if asset_type == 'HD' else 0
+                formats.extend(tp_formats)
+                subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        if first_e and not formats:
+            raise first_e
         self._sort_formats(formats)
 
-        mediainfo = self._download_json(
-            'http://plr.video.mediaset.it/html/metainfo.sjson',
-            video_id, 'Downloading video info JSON', query={
-                'id': video_id,
-            })['video']
+        fields = []
+        for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))):
+            fields.extend(templ % repl for repl in repls)
+        feed_data = self._download_json(
+            'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid,
+            guid, fatal=False, query={'fields': ','.join(fields)})
+        if feed_data:
+            publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
+            info.update({
+                'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
+                'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
+                'series': feed_data.get('mediasetprogram$brandTitle'),
+                'uploader': publish_info.get('description'),
+                'uploader_id': publish_info.get('channel'),
+                'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
+            })
 
-        title = mediainfo['title']
-
-        creator = try_get(
-            mediainfo, lambda x: x['brand-info']['publisher'], compat_str)
-        category = try_get(
-            mediainfo, lambda x: x['brand-info']['category'], compat_str)
-        categories = [category] if category else None
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': mediainfo.get('short-description'),
-            'thumbnail': mediainfo.get('thumbnail'),
-            'duration': parse_duration(mediainfo.get('duration')),
-            'creator': creator,
-            'upload_date': unified_strdate(mediainfo.get('production-date')),
-            'webpage_url': mediainfo.get('url'),
-            'series': mediainfo.get('brand-value'),
-            'categories': categories,
+        info.update({
+            'id': guid,
             'formats': formats,
-        }
+            'subtitles': subtitles,
+        })
+        return info

youtube_dl/extractor/mediasite.py

@@ -15,6 +15,7 @@ from ..utils import (
     mimetype2ext,
     unescapeHTML,
     unsmuggle_url,
+    url_or_none,
     urljoin,
 )
 
@@ -156,8 +157,8 @@ class MediasiteIE(InfoExtractor):
 
             stream_formats = []
             for unum, VideoUrl in enumerate(video_urls):
-                video_url = VideoUrl.get('Location')
-                if not video_url or not isinstance(video_url, compat_str):
+                video_url = url_or_none(VideoUrl.get('Location'))
+                if not video_url:
                     continue
                 # XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS
 

youtube_dl/extractor/mitele.py

@@ -1,84 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import uuid
-
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
-from ..compat import (
-    compat_str,
-    compat_urlparse,
-)
 from ..utils import (
     int_or_none,
-    extract_attributes,
-    determine_ext,
     smuggle_url,
     parse_duration,
 )
 
 
-class MiTeleBaseIE(InfoExtractor):
-    def _get_player_info(self, url, webpage):
-        player_data = extract_attributes(self._search_regex(
-            r'(?s)(<ms-video-player.+?</ms-video-player>)',
-            webpage, 'ms video player'))
-        video_id = player_data['data-media-id']
-        if player_data.get('data-cms-id') == 'ooyala':
-            return self.url_result(
-                'ooyala:%s' % video_id, ie=OoyalaIE.ie_key(), video_id=video_id)
-        config_url = compat_urlparse.urljoin(url, player_data['data-config'])
-        config = self._download_json(
-            config_url, video_id, 'Downloading config JSON')
-        mmc_url = config['services']['mmc']
-
-        duration = None
-        formats = []
-        for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
-            mmc = self._download_json(
-                m_url, video_id, 'Downloading mmc JSON')
-            if not duration:
-                duration = int_or_none(mmc.get('duration'))
-            for location in mmc['locations']:
-                gat = self._proto_relative_url(location.get('gat'), 'http:')
-                gcp = location.get('gcp')
-                ogn = location.get('ogn')
-                if None in (gat, gcp, ogn):
-                    continue
-                token_data = {
-                    'gcp': gcp,
-                    'ogn': ogn,
-                    'sta': 0,
-                }
-                media = self._download_json(
-                    gat, video_id, data=json.dumps(token_data).encode('utf-8'),
-                    headers={
-                        'Content-Type': 'application/json;charset=utf-8',
-                        'Referer': url,
-                    })
-                stream = media.get('stream') or media.get('file')
-                if not stream:
-                    continue
-                ext = determine_ext(stream)
-                if ext == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
-                        video_id, f4m_id='hds', fatal=False))
-                elif ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        stream, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
-            'duration': duration,
-        }
-
-
 class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
     _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
@@ -86,7 +16,7 @@ class MiTeleIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
         'info_dict': {
-            'id': '57b0dfb9c715da65618b4afa',
+            'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
             'ext': 'mp4',
             'title': 'Tor, la web invisible',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
@@ -104,7 +34,7 @@ class MiTeleIE(InfoExtractor):
         # no explicit title
         'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
         'info_dict': {
-            'id': '57b0de3dc915da14058b4876',
+            'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq',
             'ext': 'mp4',
             'title': 'Cuarto Milenio Temporada 6 Programa 226',
             'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
@@ -128,40 +58,21 @@ class MiTeleIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        gigya_url = self._search_regex(
-            r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
-            webpage, 'gigya', default=None)
-        gigya_sc = self._download_webpage(
-            compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
-            video_id, 'Downloading gigya script')
-
-        # Get a appKey/uuid for getting the session key
-        appKey = self._search_regex(
-            r'constant\s*\(\s*["\']_appGridApplicationKey["\']\s*,\s*["\']([0-9a-f]+)',
-            gigya_sc, 'appKey')
-
-        session_json = self._download_json(
-            'https://appgrid-api.cloud.accedo.tv/session',
-            video_id, 'Downloading session keys', query={
-                'appKey': appKey,
-                'uuid': compat_str(uuid.uuid4()),
-            })
 
         paths = self._download_json(
-            'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
-            video_id, 'Downloading paths JSON',
-            query={'sessionKey': compat_str(session_json['sessionKey'])})
+            'https://www.mitele.es/amd/agp/web/metadata/general_configuration',
+            video_id, 'Downloading paths JSON')
 
         ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
+        base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com')
+        full_path = ooyala_s.get('full_path', '/search/v1/full/providers/')
         source = self._download_json(
-            'http://%s%s%s/docs/%s' % (
-                ooyala_s['base_url'], ooyala_s['full_path'],
-                ooyala_s['provider_id'], video_id),
+            '%s://%s%s%s/docs/%s' % (
+                ooyala_s.get('protocol', 'https'), base_url, full_path,
+                ooyala_s.get('provider_id', '104951'), video_id),
             video_id, 'Downloading data JSON', query={
                 'include_titles': 'Series,Season',
-                'product_name': 'test',
+                'product_name': ooyala_s.get('product_name', 'test'),
                 'format': 'full',
             })['hits']['hits'][0]['_source']
 

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

@@ -7,6 +7,7 @@ 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,
@@ -75,11 +76,16 @@ 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,

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)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/npo.py

@@ -282,7 +282,7 @@ class NPOIE(NPOBaseIE):
                 video_url = stream_info.get('url')
             if not video_url or video_url in urls:
                 continue
-            urls.add(item_url)
+            urls.add(video_url)
             if determine_ext(video_url) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     video_url, video_id, ext='mp4',

youtube_dl/extractor/nrk.py

@@ -4,12 +4,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
+    JSON_LD_RE,
+    NO_DEFAULT,
     parse_age_limit,
     parse_duration,
+    try_get,
 )
 
 
@@ -359,6 +365,182 @@ class NRKTVIE(NRKBaseIE):
     }]
 
 
+class NRKTVEpisodeIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
+    _TEST = {
+        'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
+        'info_dict': {
+            'id': 'MSUI14000816AA',
+            'ext': 'mp4',
+            'title': 'Backstage 8:30',
+            'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',
+            'duration': 1320,
+            'series': 'Backstage',
+            'season_number': 1,
+            'episode_number': 8,
+            'episode': '8:30',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        nrk_id = self._parse_json(
+            self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'),
+            display_id)['@id']
+
+        assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
+        return self.url_result(
+            'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)
+
+
+class NRKTVSerieBaseIE(InfoExtractor):
+    def _extract_series(self, webpage, display_id, fatal=True):
+        config = self._parse_json(
+            self._search_regex(
+                r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config',
+                default='{}' if not fatal else NO_DEFAULT),
+            display_id, fatal=False)
+        if not config:
+            return
+        return try_get(config, lambda x: x['series'], dict)
+
+    def _extract_episodes(self, season):
+        entries = []
+        if not isinstance(season, dict):
+            return entries
+        episodes = season.get('episodes')
+        if not isinstance(episodes, list):
+            return entries
+        for episode in episodes:
+            nrk_id = episode.get('prfId')
+            if not nrk_id or not isinstance(nrk_id, compat_str):
+                continue
+            entries.append(self.url_result(
+                'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
+        return entries
+
+
+class NRKTVSeasonIE(NRKTVSerieBaseIE):
+    _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
+        'info_dict': {
+            'id': '1',
+            'title': 'Sesong 1',
+        },
+        'playlist_mincount': 30,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url)
+                else super(NRKTVSeasonIE, cls).suitable(url))
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        series = self._extract_series(webpage, display_id)
+
+        season = next(
+            s for s in series['seasons']
+            if int(display_id) == s.get('seasonNumber'))
+
+        title = try_get(season, lambda x: x['titles']['title'], compat_str)
+        return self.playlist_result(
+            self._extract_episodes(season), display_id, title)
+
+
+class NRKTVSeriesIE(NRKTVSerieBaseIE):
+    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
+    _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
+    _TESTS = [{
+        # new layout
+        'url': 'https://tv.nrk.no/serie/backstage',
+        'info_dict': {
+            'id': 'backstage',
+            'title': 'Backstage',
+            'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
+        },
+        'playlist_mincount': 60,
+    }, {
+        # old layout
+        'url': 'https://tv.nrk.no/serie/groenn-glede',
+        'info_dict': {
+            'id': 'groenn-glede',
+            'title': 'Grønn glede',
+            'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
+        },
+        'playlist_mincount': 9,
+    }, {
+        'url': 'http://tv.nrksuper.no/serie/labyrint',
+        'info_dict': {
+            'id': 'labyrint',
+            'title': 'Labyrint',
+            'description': 'md5:58afd450974c89e27d5a19212eee7115',
+        },
+        'playlist_mincount': 3,
+    }, {
+        'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
+        'only_matching': True,
+    }, {
+        'url': 'https://tv.nrk.no/serie/saving-the-human-race',
+        'only_matching': True,
+    }, {
+        'url': 'https://tv.nrk.no/serie/postmann-pat',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return (
+            False if any(ie.suitable(url)
+                         for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE))
+            else super(NRKTVSeriesIE, cls).suitable(url))
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, series_id)
+
+        # New layout (e.g. https://tv.nrk.no/serie/backstage)
+        series = self._extract_series(webpage, series_id, fatal=False)
+        if series:
+            title = try_get(series, lambda x: x['titles']['title'], compat_str)
+            description = try_get(
+                series, lambda x: x['titles']['subtitle'], compat_str)
+            entries = []
+            for season in series['seasons']:
+                entries.extend(self._extract_episodes(season))
+            return self.playlist_result(entries, series_id, title, description)
+
+        # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede)
+        entries = [
+            self.url_result(
+                'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
+                    series=series_id, season=season_id))
+            for season_id in re.findall(self._ITEM_RE, webpage)
+        ]
+
+        title = self._html_search_meta(
+            'seriestitle', webpage,
+            'title', default=None) or self._og_search_title(
+            webpage, fatal=False)
+
+        description = self._html_search_meta(
+            'series_description', webpage,
+            'description', default=None) or self._og_search_description(webpage)
+
+        return self.playlist_result(entries, series_id, title, description)
+
+
 class NRKTVDirekteIE(NRKTVIE):
     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
@@ -438,64 +620,6 @@ class NRKTVEpisodesIE(NRKPlaylistBaseIE):
             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 
 
-class NRKTVSeriesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
-    _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://tv.nrk.no/serie/groenn-glede',
-        'info_dict': {
-            'id': 'groenn-glede',
-            'title': 'Grønn glede',
-            'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
-        },
-        'playlist_mincount': 9,
-    }, {
-        'url': 'http://tv.nrksuper.no/serie/labyrint',
-        'info_dict': {
-            'id': 'labyrint',
-            'title': 'Labyrint',
-            'description': 'md5:58afd450974c89e27d5a19212eee7115',
-        },
-        'playlist_mincount': 3,
-    }, {
-        'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
-        'only_matching': True,
-    }, {
-        'url': 'https://tv.nrk.no/serie/saving-the-human-race',
-        'only_matching': True,
-    }, {
-        'url': 'https://tv.nrk.no/serie/postmann-pat',
-        'only_matching': True,
-    }]
-
-    @classmethod
-    def suitable(cls, url):
-        return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url)
-
-    def _real_extract(self, url):
-        series_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, series_id)
-
-        entries = [
-            self.url_result(
-                'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
-                    series=series_id, season=season_id))
-            for season_id in re.findall(self._ITEM_RE, webpage)
-        ]
-
-        title = self._html_search_meta(
-            'seriestitle', webpage,
-            'title', default=None) or self._og_search_title(
-            webpage, fatal=False)
-
-        description = self._html_search_meta(
-            'series_description', webpage,
-            'description', default=None) or self._og_search_description(webpage)
-
-        return self.playlist_result(entries, series_id, title, description)
-
-
 class NRKSkoleIE(InfoExtractor):
     IE_DESC = 'NRK Skole'
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'

youtube_dl/extractor/openload.py

@@ -243,7 +243,7 @@ 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'https?://(?: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 +307,22 @@ 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'

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/pbs.py

@@ -15,6 +15,7 @@ from ..utils import (
     strip_jsonp,
     strip_or_none,
     unified_strdate,
+    url_or_none,
     US_RATINGS,
 )
 
@@ -557,6 +558,13 @@ class PBSIE(InfoExtractor):
                 if redirect_url and redirect_url not in redirect_urls:
                     redirects.append(redirect)
                     redirect_urls.add(redirect_url)
+            encodings = info.get('encodings')
+            if isinstance(encodings, list):
+                for encoding in encodings:
+                    encoding_url = url_or_none(encoding)
+                    if encoding_url and encoding_url not in redirect_urls:
+                        redirects.append({'url': encoding_url})
+                        redirect_urls.add(encoding_url)
 
         chapters = []
         # Player pages may also serve different qualities

youtube_dl/extractor/peertube.py

@@ -10,6 +10,7 @@ from ..utils import (
     parse_resolution,
     try_get,
     unified_timestamp,
+    url_or_none,
     urljoin,
 )
 
@@ -200,8 +201,8 @@ class PeerTubeIE(InfoExtractor):
         for file_ in video['files']:
             if not isinstance(file_, dict):
                 continue
-            file_url = file_.get('fileUrl')
-            if not file_url or not isinstance(file_url, compat_str):
+            file_url = url_or_none(file_.get('fileUrl'))
+            if not file_url:
                 continue
             file_size = int_or_none(file_.get('size'))
             format_id = try_get(

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/pluralsight.py

@@ -4,6 +4,7 @@ import collections
 import json
 import os
 import random
+import re
 
 from .common import InfoExtractor
 from ..compat import (
@@ -27,6 +28,60 @@ from ..utils import (
 class PluralsightBaseIE(InfoExtractor):
     _API_BASE = 'https://app.pluralsight.com'
 
+    _GRAPHQL_EP = '%s/player/api/graphql' % _API_BASE
+    _GRAPHQL_HEADERS = {
+        'Content-Type': 'application/json;charset=UTF-8',
+    }
+    _GRAPHQL_COURSE_TMPL = '''
+query BootstrapPlayer {
+  rpc {
+    bootstrapPlayer {
+      profile {
+        firstName
+        lastName
+        email
+        username
+        userHandle
+        authed
+        isAuthed
+        plan
+      }
+      course(courseId: "%s") {
+        name
+        title
+        courseHasCaptions
+        translationLanguages {
+          code
+          name
+        }
+        supportsWideScreenVideoFormats
+        timestamp
+        modules {
+          name
+          title
+          duration
+          formattedDuration
+          author
+          authorized
+          clips {
+            authorized
+            clipId
+            duration
+            formattedDuration
+            id
+            index
+            moduleIndex
+            moduleTitle
+            name
+            title
+            watched
+          }
+        }
+      }
+    }
+  }
+}'''
+
     def _download_course(self, course_id, url, display_id):
         try:
             return self._download_course_rpc(course_id, url, display_id)
@@ -39,20 +94,14 @@ class PluralsightBaseIE(InfoExtractor):
 
     def _download_course_rpc(self, course_id, url, display_id):
         response = self._download_json(
-            '%s/player/functions/rpc' % self._API_BASE, display_id,
-            'Downloading course JSON',
-            data=json.dumps({
-                'fn': 'bootstrapPlayer',
-                'payload': {
-                    'courseId': course_id,
-                },
-            }).encode('utf-8'),
-            headers={
-                'Content-Type': 'application/json;charset=utf-8',
-                'Referer': url,
-            })
+            self._GRAPHQL_EP, display_id, data=json.dumps({
+                'query': self._GRAPHQL_COURSE_TMPL % course_id,
+                'variables': {}
+            }).encode('utf-8'), headers=self._GRAPHQL_HEADERS)
 
-        course = try_get(response, lambda x: x['payload']['course'], dict)
+        course = try_get(
+            response, lambda x: x['data']['rpc']['bootstrapPlayer']['course'],
+            dict)
         if course:
             return course
 
@@ -90,6 +139,28 @@ class PluralsightIE(PluralsightBaseIE):
         'only_matching': True,
     }]
 
+    GRAPHQL_VIEWCLIP_TMPL = '''
+query viewClip {
+  viewClip(input: {
+    author: "%(author)s",
+    clipIndex: %(clipIndex)d,
+    courseName: "%(courseName)s",
+    includeCaptions: %(includeCaptions)s,
+    locale: "%(locale)s",
+    mediaType: "%(mediaType)s",
+    moduleName: "%(moduleName)s",
+    quality: "%(quality)s"
+  }) {
+    urls {
+      url
+      cdn
+      rank
+      source
+    },
+    status
+  }
+}'''
+
     def _real_initialize(self):
         self._login()
 
@@ -126,7 +197,10 @@ class PluralsightIE(PluralsightBaseIE):
         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(
@@ -140,18 +214,26 @@ class PluralsightIE(PluralsightBaseIE):
 
             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: [{
@@ -277,7 +359,7 @@ class PluralsightIE(PluralsightBaseIE):
                 f = QUALITIES[quality].copy()
                 clip_post = {
                     'author': author,
-                    'includeCaptions': False,
+                    'includeCaptions': 'false',
                     'clipIndex': int(clip_idx),
                     'courseName': course_name,
                     'locale': 'en',
@@ -286,11 +368,23 @@ class PluralsightIE(PluralsightBaseIE):
                     'quality': '%dx%d' % (f['width'], f['height']),
                 }
                 format_id = '%s-%s' % (ext, quality)
-                viewclip = self._download_json(
-                    '%s/video/clips/viewclip' % self._API_BASE, display_id,
-                    'Downloading %s viewclip JSON' % format_id, fatal=False,
-                    data=json.dumps(clip_post).encode('utf-8'),
-                    headers={'Content-Type': 'application/json;charset=utf-8'})
+
+                try:
+                    viewclip = self._download_json(
+                        self._GRAPHQL_EP, display_id,
+                        'Downloading %s viewclip graphql' % format_id,
+                        data=json.dumps({
+                            'query': self.GRAPHQL_VIEWCLIP_TMPL % clip_post,
+                            'variables': {}
+                        }).encode('utf-8'),
+                        headers=self._GRAPHQL_HEADERS)['data']['viewClip']
+                except ExtractorError:
+                    # Still works but most likely will go soon
+                    viewclip = self._download_json(
+                        '%s/video/clips/viewclip' % self._API_BASE, display_id,
+                        'Downloading %s viewclip JSON' % format_id, fatal=False,
+                        data=json.dumps(clip_post).encode('utf-8'),
+                        headers={'Content-Type': 'application/json;charset=utf-8'})
 
                 # Pluralsight tracks multiple sequential calls to ViewClip API and start
                 # to return 429 HTTP errors after some time (see
@@ -331,7 +425,7 @@ class PluralsightIE(PluralsightBaseIE):
 
         # 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/porncom.py

@@ -43,7 +43,8 @@ class PornComIE(InfoExtractor):
 
         config = self._parse_json(
             self._search_regex(
-                r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=',
+                (r'=\s*({.+?})\s*;\s*v1ar\b',
+                 r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='),
                 webpage, 'config', default='{}'),
             display_id, transform_source=js_to_json, fatal=False)
 
@@ -69,7 +70,7 @@ class PornComIE(InfoExtractor):
                 'height': int(height),
                 'filesize_approx': parse_filesize(filesize),
             } for format_url, height, filesize in re.findall(
-                r'<a[^>]+href="(/download/[^"]+)">MPEG4 (\d+)p<span[^>]*>(\d+\s+[a-zA-Z]+)<',
+                r'<a[^>]+href="(/download/[^"]+)">[^<]*?(\d+)p<span[^>]*>(\d+\s*[a-zA-Z]+)<',
                 webpage)]
             thumbnail = None
             duration = None