release 2019.11.05

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.12.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1**
+- [ ] I've verified that I'm running youtube-dl version **2019.11.05**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [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 2019.09.12.1
+ [debug] youtube-dl version 2019.11.05
  [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: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.12.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1**
+- [ ] I've verified that I'm running youtube-dl version **2019.11.05**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.12.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1**
+- [ ] I've verified that I'm running youtube-dl version **2019.11.05**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.12.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1**
+- [ ] I've verified that I'm running youtube-dl version **2019.11.05**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [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 2019.09.12.1
+ [debug] youtube-dl version 2019.11.05
  [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: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.12.1. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1**
+- [ ] I've verified that I'm running youtube-dl version **2019.11.05**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,185 @@
+version 2019.11.05
+
+Extractors
++ [scte] Add support for learning.scte.org (#22975)
++ [msn] Add support for Vidible and AOL embeds (#22195, #22227)
+* [myspass] Fix video URL extraction and improve metadata extraction (#22448)
+* [jamendo] Improve extraction
+    * Fix album extraction (#18564)
+    * Improve metadata extraction (#18565, #21379)
+* [mediaset] Relax URL guid matching (#18352)
++ [mediaset] Extract unprotected M3U and MPD manifests (#17204)
+* [telegraaf] Fix extraction
++ [bellmedia] Add support for marilyn.ca videos (#22193)
+* [stv] Fix extraction (#22928)
+- [iconosquare] Remove extractor
+- [keek] Remove extractor
+- [gameone] Remove extractor (#21778)
+- [flipagram] Remove extractor
+- [bambuser] Remove extractor
+* [wistia] Reduce embed extraction false positives
++ [wistia] Add support for inline embeds (#22931)
+- [go90] Remove extractor
+* [kakao] Remove raw request
++ [kakao] Extract format total bitrate
+* [daum] Fix VOD and Clip extracton (#15015)
+* [kakao] Improve extraction
+    + Add support for embed URLs
+    + Add support for Kakao Legacy vid based embed URLs
+    * Only extract fields used for extraction
+    * Strip description and extract tags
+* [mixcloud] Fix cloudcast data extraction (#22821)
+* [yahoo] Improve extraction
+    + Add support for live streams (#3597, #3779, #22178)
+    * Bypass cookie consent page for european domains (#16948, #22576)
+    + Add generic support for embeds (#20332)
+* [tv2] Fix and improve extraction (#22787)
++ [tv2dk] Add support for TV2 DK sites
+* [onet] Improve extraction …
+    + Add support for onet100.vod.pl
+    + Extract m3u8 formats
+    * Correct audio only format info
+* [fox9] Fix extraction
+
+
+version 2019.10.29
+
+Core
+* [utils] Actualize major IPv4 address blocks per country
+
+Extractors
++ [go] Add support for abc.com and freeform.com (#22823, #22864)
++ [mtv] Add support for mtvjapan.com
+* [mtv] Fix extraction for mtv.de (#22113)
+* [videodetective] Fix extraction
+* [internetvideoarchive] Fix extraction
+* [nbcnews] Fix extraction (#12569, #12576, #21703, #21923)
+- [hark] Remove extractor
+- [tutv] Remove extractor
+- [learnr] Remove extractor
+- [macgamestore] Remove extractor
+* [la7] Update Kaltura service URL (#22358)
+* [thesun] Fix extraction (#16966)
+- [makertv] Remove extractor
++ [tenplay] Add support for 10play.com.au (#21446)
+* [soundcloud] Improve extraction
+    * Improve format extraction (#22123)
+    + Extract uploader_id and uploader_url (#21916)
+    + Extract all known thumbnails (#19071, #20659)
+    * Fix extration for private playlists (#20976)
+    + Add support for playlist embeds (#20976)
+    * Skip preview formats (#22806)
+* [dplay] Improve extraction
+    + Add support for dplay.fi, dplay.jp and es.dplay.com (#16969)
+    * Fix it.dplay.com extraction (#22826)
+    + Extract creator, tags and thumbnails
+    * Handle playback API call errors
++ [discoverynetworks] Add support for dplay.co.uk
+* [vk] Improve extraction
+    + Add support for Odnoklassniki embeds
+    + Extract more videos from user lists (#4470)
+    + Fix wall post audio extraction (#18332)
+    * Improve error detection (#22568)
++ [odnoklassniki] Add support for embeds
+* [puhutv] Improve extraction
+    * Fix subtitles extraction
+    * Transform HLS URLs to HTTP URLs
+    * Improve metadata extraction
+* [ceskatelevize] Skip DRM media
++ [facebook] Extract subtitles (#22777)
+* [globo] Handle alternative hash signing method
+
+
+version 2019.10.22
+
+Core
+* [utils] Improve subtitles_filename (#22753)
+
+Extractors
+* [facebook] Bypass download rate limits (#21018)
++ [contv] Add support for contv.com
+- [viewster] Remove extractor
+* [xfileshare] Improve extractor (#17032, #17906, #18237, #18239)
+    * Update the list of domains
+    + Add support for aa-encoded video data
+    * Improve jwplayer format extraction
+    + Add support for Clappr sources
+* [mangomolo] Fix video format extraction and add support for player URLs
+* [audioboom] Improve metadata extraction
+* [twitch] Update VOD URL matching (#22395, #22727)
+- [mit] Remove support for video.mit.edu (#22403)
+- [servingsys] Remove extractor (#22639)
+* [dumpert] Fix extraction (#22428, #22564)
+* [atresplayer] Fix extraction (#16277, #16716)
+
+
+version 2019.10.16
+
+Core
+* [extractor/common] Make _is_valid_url more relaxed
+
+Extractors
+* [vimeo] Improve album videos id extraction (#22599)
++ [globo] Extract subtitles (#22713)
+* [bokecc] Improve player params extraction (#22638)
+* [nexx] Handle result list (#22666)
+* [vimeo] Fix VHX embed extraction
+* [nbc] Switch to graphql API (#18581, #22693, #22701)
+- [vessel] Remove extractor
+- [promptfile] Remove extractor (#6239)
+* [kaltura] Fix service URL extraction (#22658)
+* [kaltura] Fix embed info strip (#22658)
+* [globo] Fix format extraction (#20319)
+* [redtube] Improve metadata extraction (#22492, #22615)
+* [pornhub:uservideos:upload] Fix extraction (#22619)
++ [telequebec:squat] Add support for squat.telequebec.tv (#18503)
+- [wimp] Remove extractor (#22088, #22091)
++ [gfycat] Extend URL regular expression (#22225)
++ [chaturbate] Extend URL regular expression (#22309)
+* [peertube] Update instances (#22414)
++ [telequebec] Add support for coucou.telequebec.tv (#22482)
++ [xvideos] Extend URL regular expression (#22471)
+- [youtube] Remove support for invidious.enkirton.net (#22543)
++ [openload] Add support for oload.monster (#22592)
+* [nrktv:seriebase] Fix extraction (#22596)
++ [youtube] Add support for yt.lelux.fi (#22597)
+* [orf:tvthek] Make manifest requests non fatal (#22578)
+* [teachable] Skip login when already logged in (#22572)
+* [viewlift] Improve extraction (#22545)
+* [nonktube] Fix extraction (#22544)
+
+
+version 2019.09.28
+
+Core
+* [YoutubeDL] Honour all --get-* options with --flat-playlist (#22493)
+
+Extractors
+* [vk] Fix extraction (#22522)
+* [heise] Fix kaltura embeds extraction (#22514)
+* [ted] Check for resources validity and extract subtitled downloads (#22513)
++ [youtube] Add support for
+  owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya.b32.i2p (#22292)
++ [nhk] Add support for clips
+* [nhk] Fix video extraction (#22249, #22353)
+* [byutv] Fix extraction (#22070)
++ [openload] Add support for oload.online (#22304)
++ [youtube] Add support for invidious.drycat.fr (#22451)
+* [jwplatfom] Do not match video URLs (#20596, #22148)
+* [youtube:playlist] Unescape playlist uploader (#22483)
++ [bilibili] Add support audio albums and songs (#21094)
++ [instagram] Add support for tv URLs
++ [mixcloud] Allow uppercase letters in format URLs (#19280)
+* [brightcove] Delegate all supported legacy URLs to new extractor (#11523,
+  #12842, #13912, #15669, #16303)
+* [hotstar] Use native HLS downloader by default
++ [hotstar] Extract more formats (#22323)
+* [9now] Fix extraction (#22361)
+* [zdf] Bypass geo restriction
++ [tv4] Extract series metadata
+* [tv4] Fix extraction (#22443)
+
+
 version 2019.09.12.1
 
 Extractors

README.md

@@ -752,8 +752,8 @@ As a last resort, you can also uninstall the version installed by your package m
 Afterwards, simply follow [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html):
 
 ```
-sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
-sudo chmod a+x /usr/local/bin/youtube-dl
+sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
+sudo chmod a+rx /usr/local/bin/youtube-dl
 hash -r
 ```
 

docs/supportedsites.md

@@ -76,8 +76,6 @@
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
  - **BaiduVideo**: 百度视频
- - **bambuser**
- - **bambuser:channel**
  - **Bandcamp**
  - **Bandcamp:album**
  - **Bandcamp:weekly**
@@ -98,6 +96,8 @@
  - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
+ - **BilibiliAudio**
+ - **BilibiliAudioAlbum**
  - **BioBioChileTV**
  - **BIQLE**
  - **BitChute**
@@ -181,6 +181,7 @@
  - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
+ - **CONtv**
  - **Corus**
  - **Coub**
  - **Cracked**
@@ -229,7 +230,6 @@
  - **DouyuShow**
  - **DouyuTV**: 斗鱼
  - **DPlay**
- - **DPlayIt**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
@@ -282,12 +282,12 @@
  - **FiveThirtyEight**
  - **FiveTV**
  - **Flickr**
- - **Flipagram**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **Formula1**
  - **FOX**
  - **FOX9**
+ - **FOX9News**
  - **Foxgay**
  - **foxnews**: Fox News and Fox Business Video
  - **foxnews:article**
@@ -313,8 +313,6 @@
  - **FXNetworks**
  - **Gaia**
  - **GameInformer**
- - **GameOne**
- - **gameone:playlist**
  - **GameSpot**
  - **GameStar**
  - **Gaskrank**
@@ -329,14 +327,12 @@
  - **Globo**
  - **GloboArticle**
  - **Go**
- - **Go90**
  - **GodTube**
  - **Golem**
  - **GoogleDrive**
  - **Goshgay**
  - **GPUTechConf**
  - **Groupon**
- - **Hark**
  - **hbo**
  - **HearThisAt**
  - **Heise**
@@ -365,7 +361,6 @@
  - **Hungama**
  - **HungamaSong**
  - **Hypem**
- - **Iconosquare**
  - **ign.com**
  - **imdb**: Internet Movie Database trailers
  - **imdb:list**: Internet Movie Database lists
@@ -405,7 +400,6 @@
  - **Kankan**
  - **Karaoketv**
  - **KarriereVideos**
- - **keek**
  - **KeezMovies**
  - **Ketnet**
  - **KhanAcademy**
@@ -429,7 +423,6 @@
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
- - **Learnr**
  - **Lecture2Go**
  - **Lecturio**
  - **LecturioCourse**
@@ -463,11 +456,9 @@
  - **lynda**: lynda.com videos
  - **lynda:course**: lynda.com online courses
  - **m6**
- - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
  - **mailru:music**: Музыка@Mail.Ru
  - **mailru:music:search**: Музыка@Mail.Ru
- - **MakerTV**
  - **MallTV**
  - **mangomolo:live**
  - **mangomolo:video**
@@ -523,8 +514,8 @@
  - **mtg**: MTG services
  - **mtv**
  - **mtv.de**
- - **mtv81**
  - **mtv:video**
+ - **mtvjapan**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
@@ -692,7 +683,6 @@
  - **PornoXO**
  - **PornTube**
  - **PressTV**
- - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **puhutv**
  - **puhutv:serie**
@@ -780,10 +770,11 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **scrippsnetworks:watch**
+ - **SCTE**
+ - **SCTECourse**
  - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
- - **ServingSys**
  - **Servus**
  - **Sexu**
  - **SeznamZpravy**
@@ -814,6 +805,7 @@
  - **soundcloud:set**
  - **soundcloud:trackstation**
  - **soundcloud:user**
+ - **SoundcloudEmbed**
  - **soundgasm**
  - **soundgasm:profile**
  - **southpark.cc.com**
@@ -882,9 +874,11 @@
  - **TeleQuebec**
  - **TeleQuebecEmission**
  - **TeleQuebecLive**
+ - **TeleQuebecSquat**
  - **TeleTask**
  - **Telewebion**
  - **TennisTV**
+ - **TenPlay**
  - **TF1**
  - **TFO**
  - **TheIntercept**
@@ -923,11 +917,11 @@
  - **tunein:topic**
  - **TunePk**
  - **Turbo**
- - **Tutv**
  - **tv.dfb.de**
  - **TV2**
  - **tv2.hu**
  - **TV2Article**
+ - **TV2DK**
  - **TV4**: tv4.se and tv4play.se
  - **TV5MondePlus**: TV5MONDE+
  - **TVA**
@@ -989,7 +983,6 @@
  - **VeeHD**
  - **Veoh**
  - **verystream**
- - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
  - **VevoPlaylist**
@@ -1004,7 +997,6 @@
  - **Viddler**
  - **Videa**
  - **video.google:search**: Google Video search
- - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
  - **videomore**
@@ -1022,7 +1014,6 @@
  - **vier:videos**
  - **ViewLift**
  - **ViewLiftEmbed**
- - **Viewster**
  - **Viidea**
  - **viki**
  - **viki:channel**
@@ -1088,7 +1079,6 @@
  - **Weibo**
  - **WeiboMobile**
  - **WeiqiTV**: WQTV
- - **Wimp**
  - **Wistia**
  - **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **WorldStarHipHop**
@@ -1097,7 +1087,7 @@
  - **WWE**
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me
+ - **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
  - **XHamster**
  - **XHamsterEmbed**
  - **XHamsterUser**

test/test_all_urls.py

@@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 
-    def test_yahoo_https(self):
-        # https://github.com/ytdl-org/youtube-dl/issues/2701
-        self.assertMatch(
-            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
-            ['Yahoo'])
-
     def test_no_duplicated_ie_names(self):
         name_accu = collections.defaultdict(list)
         for ie in self.ies:

test/test_utils.py

@@ -74,6 +74,7 @@ from youtube_dl.utils import (
     str_to_int,
     strip_jsonp,
     strip_or_none,
+    subtitles_filename,
     timeconvert,
     unescapeHTML,
     unified_strdate,
@@ -261,6 +262,11 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
+    def test_subtitles_filename(self):
+        self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
+        self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
+        self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt')
+
     def test_remove_start(self):
         self.assertEqual(remove_start(None, 'A - '), None)
         self.assertEqual(remove_start('A - B', 'A - '), 'B')

youtube_dl/YoutubeDL.py

@@ -852,8 +852,9 @@ class YoutubeDL(object):
             extract_flat = self.params.get('extract_flat', False)
             if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
                     or extract_flat is True):
-                if self.params.get('forcejson', False):
-                    self.to_stdout(json.dumps(ie_result))
+                self.__forced_printings(
+                    ie_result, self.prepare_filename(ie_result),
+                    incomplete=True)
                 return ie_result
 
         if result_type == 'video':
@@ -1693,6 +1694,36 @@ class YoutubeDL(object):
             subs[lang] = f
         return subs
 
+    def __forced_printings(self, info_dict, filename, incomplete):
+        def print_mandatory(field):
+            if (self.params.get('force%s' % field, False)
+                    and (not incomplete or info_dict.get(field) is not None)):
+                self.to_stdout(info_dict[field])
+
+        def print_optional(field):
+            if (self.params.get('force%s' % field, False)
+                    and info_dict.get(field) is not None):
+                self.to_stdout(info_dict[field])
+
+        print_mandatory('title')
+        print_mandatory('id')
+        if self.params.get('forceurl', False) and not incomplete:
+            if info_dict.get('requested_formats') is not None:
+                for f in info_dict['requested_formats']:
+                    self.to_stdout(f['url'] + f.get('play_path', ''))
+            else:
+                # For RTMP URLs, also include the playpath
+                self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
+        print_optional('thumbnail')
+        print_optional('description')
+        if self.params.get('forcefilename', False) and filename is not None:
+            self.to_stdout(filename)
+        if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
+            self.to_stdout(formatSeconds(info_dict['duration']))
+        print_mandatory('format')
+        if self.params.get('forcejson', False):
+            self.to_stdout(json.dumps(info_dict))
+
     def process_info(self, info_dict):
         """Process a single resolved IE result."""
 
@@ -1703,9 +1734,8 @@ class YoutubeDL(object):
             if self._num_downloads >= int(max_downloads):
                 raise MaxDownloadsReached()
 
+        # TODO: backward compatibility, to be removed
         info_dict['fulltitle'] = info_dict['title']
-        if len(info_dict['title']) > 200:
-            info_dict['title'] = info_dict['title'][:197] + '...'
 
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
@@ -1720,29 +1750,7 @@ class YoutubeDL(object):
         info_dict['_filename'] = filename = self.prepare_filename(info_dict)
 
         # Forced printings
-        if self.params.get('forcetitle', False):
-            self.to_stdout(info_dict['fulltitle'])
-        if self.params.get('forceid', False):
-            self.to_stdout(info_dict['id'])
-        if self.params.get('forceurl', False):
-            if info_dict.get('requested_formats') is not None:
-                for f in info_dict['requested_formats']:
-                    self.to_stdout(f['url'] + f.get('play_path', ''))
-            else:
-                # For RTMP URLs, also include the playpath
-                self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
-        if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
-            self.to_stdout(info_dict['thumbnail'])
-        if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
-            self.to_stdout(info_dict['description'])
-        if self.params.get('forcefilename', False) and filename is not None:
-            self.to_stdout(filename)
-        if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
-            self.to_stdout(formatSeconds(info_dict['duration']))
-        if self.params.get('forceformat', False):
-            self.to_stdout(info_dict['format'])
-        if self.params.get('forcejson', False):
-            self.to_stdout(json.dumps(info_dict))
+        self.__forced_printings(info_dict, filename, incomplete=False)
 
         # Do nothing else if in simulate mode
         if self.params.get('simulate', False):
@@ -1806,7 +1814,7 @@ class YoutubeDL(object):
             ie = self.get_info_extractor(info_dict['extractor_key'])
             for sub_lang, sub_info in subtitles.items():
                 sub_format = sub_info['ext']
-                sub_filename = subtitles_filename(filename, sub_lang, sub_format)
+                sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext'))
                 if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
                     self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
                 else:

youtube_dl/extractor/atresplayer.py

@@ -1,202 +1,118 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import time
-import hmac
-import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
-    sanitized_Request,
     urlencode_postdata,
-    xpath_text,
 )
 
 
 class AtresPlayerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})'
     _NETRC_MACHINE = 'atresplayer'
     _TESTS = [
         {
-            'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
-            'md5': 'efd56753cda1bb64df52a3074f62e38a',
+            'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/',
             'info_dict': {
-                'id': 'capitulo-10-especial-solidario-nochebuena',
+                'id': '5d4aa2c57ed1a88fc715a615',
                 'ext': 'mp4',
-                'title': 'Especial Solidario de Nochebuena',
-                'description': 'md5:e2d52ff12214fa937107d21064075bf1',
-                'duration': 5527.6,
-                'thumbnail': r're:^https?://.*\.jpg$',
+                'title': 'Capítulo 7: Asuntos pendientes',
+                'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
+                'duration': 3413,
+            },
+            'params': {
+                'format': 'bestvideo',
             },
             'skip': 'This video is only available for registered users'
         },
         {
-            'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
-            'md5': '6e52cbb513c405e403dbacb7aacf8747',
-            'info_dict': {
-                'id': 'capitulo-112-david-bustamante',
-                'ext': 'flv',
-                'title': 'David Bustamante',
-                'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
-                'duration': 1439.0,
-                'thumbnail': r're:^https?://.*\.jpg$',
-            },
+            'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
+            'only_matching': True,
         },
         {
-            'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
+            'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/',
             'only_matching': True,
         },
     ]
-
-    _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
-    _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
-    _TIMESTAMP_SHIFT = 30000
-
-    _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
-    _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
-    _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
-    _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
-
-    _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
-
-    _ERRORS = {
-        'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
-        'DELETED': 'This video has expired and is no longer available for online streaming.',
-        'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
-        # 'PREMIUM': 'PREMIUM',
-    }
+    _API_BASE = 'https://api.atresplayer.com/'
 
     def _real_initialize(self):
         self._login()
 
+    def _handle_error(self, e, code):
+        if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
+            error = self._parse_json(e.cause.read(), None)
+            if error.get('error') == 'required_registered':
+                self.raise_login_required()
+            raise ExtractorError(error['error_description'], expected=True)
+        raise
+
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
             return
 
-        login_form = {
-            'j_username': username,
-            'j_password': password,
-        }
+        self._request_webpage(
+            self._API_BASE + 'login', None, 'Downloading login page')
 
-        request = sanitized_Request(
-            self._LOGIN_URL, urlencode_postdata(login_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        response = self._download_webpage(
-            request, None, 'Logging in')
+        try:
+            target_url = self._download_json(
+                'https://account.atresmedia.com/api/login', None,
+                'Logging in', headers={
+                    'Content-Type': 'application/x-www-form-urlencoded'
+                }, data=urlencode_postdata({
+                    'username': username,
+                    'password': password,
+                }))['targetUrl']
+        except ExtractorError as e:
+            self._handle_error(e, 400)
 
-        error = self._html_search_regex(
-            r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',
-            response, 'error', default=None)
-        if error:
-            raise ExtractorError(
-                'Unable to login: %s' % error, expected=True)
+        self._request_webpage(target_url, None, 'Following Target URL')
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
 
-        webpage = self._download_webpage(url, video_id)
+        try:
+            episode = self._download_json(
+                self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
+        except ExtractorError as e:
+            self._handle_error(e, 403)
 
-        episode_id = self._search_regex(
-            r'episode="([^"]+)"', webpage, 'episode id')
-
-        request = sanitized_Request(
-            self._PLAYER_URL_TEMPLATE % episode_id,
-            headers={'User-Agent': self._USER_AGENT})
-        player = self._download_json(request, episode_id, 'Downloading player JSON')
-
-        episode_type = player.get('typeOfEpisode')
-        error_message = self._ERRORS.get(episode_type)
-        if error_message:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+        title = episode['titulo']
 
         formats = []
-        video_url = player.get('urlVideo')
-        if video_url:
-            format_info = {
-                'url': video_url,
-                'format_id': 'http',
-            }
-            mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
-            if mobj:
-                format_info.update({
-                    'width': int_or_none(mobj.group('width')),
-                    'height': int_or_none(mobj.group('height')),
-                    'tbr': int_or_none(mobj.group('bitrate')),
-                })
-            formats.append(format_info)
-
-        timestamp = int_or_none(self._download_webpage(
-            self._TIME_API_URL,
-            video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
-        timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
-        token = hmac.new(
-            self._MAGIC.encode('ascii'),
-            (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
-        ).hexdigest()
-
-        request = sanitized_Request(
-            self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
-            headers={'User-Agent': self._USER_AGENT})
-
-        fmt_json = self._download_json(
-            request, video_id, 'Downloading windows video JSON')
-
-        result = fmt_json.get('resultDes')
-        if result.lower() != 'ok':
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, result), expected=True)
-
-        for format_id, video_url in fmt_json['resultObject'].items():
-            if format_id == 'token' or not video_url.startswith('http'):
+        for source in episode.get('sources', []):
+            src = source.get('src')
+            if not src:
                 continue
-            if 'geodeswowsmpra3player' in video_url:
-                # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
-                # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
-                # this videos are protected by DRM, the f4m downloader doesn't support them
-                continue
-            video_url_hd = video_url.replace('free_es', 'es')
-            formats.extend(self._extract_f4m_formats(
-                video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds',
-                fatal=False))
-            formats.extend(self._extract_mpd_formats(
-                video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash',
-                fatal=False))
+            src_type = source.get('type')
+            if src_type == 'application/vnd.apple.mpegurl':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif src_type == 'application/dash+xml':
+                formats.extend(self._extract_mpd_formats(
+                    src, video_id, mpd_id='dash', fatal=False))
         self._sort_formats(formats)
 
-        path_data = player.get('pathData')
-
-        episode = self._download_xml(
-            self._EPISODE_URL_TEMPLATE % path_data, video_id,
-            'Downloading episode XML')
-
-        duration = float_or_none(xpath_text(
-            episode, './media/asset/info/technical/contentDuration', 'duration'))
-
-        art = episode.find('./media/asset/info/art')
-        title = xpath_text(art, './name', 'title')
-        description = xpath_text(art, './description', 'description')
-        thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
-
-        subtitles = {}
-        subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
-        if subtitle_url:
-            subtitles['es'] = [{
-                'ext': 'srt',
-                'url': subtitle_url,
-            }]
+        heartbeat = episode.get('heartbeat') or {}
+        omniture = episode.get('omniture') or {}
+        get_meta = lambda x: heartbeat.get(x) or omniture.get(x)
 
         return {
+            'display_id': display_id,
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
+            'description': episode.get('descripcion'),
+            'thumbnail': episode.get('imgPoster'),
+            'duration': int_or_none(episode.get('duration')),
             'formats': formats,
-            'subtitles': subtitles,
+            'channel': get_meta('channel'),
+            'season': get_meta('season'),
+            'episode_number': int_or_none(get_meta('episodeNumber')),
         }

youtube_dl/extractor/audioboom.py

@@ -2,22 +2,25 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..utils import (
+    clean_html,
+    float_or_none,
+)
 
 
 class AudioBoomIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
-        'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
+        'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
+        'md5': '7b00192e593ff227e6a315486979a42d',
         'info_dict': {
-            'id': '4279833',
+            'id': '7398103',
             'ext': 'mp3',
-            'title': '3/09/2016 Czaban Hour 3',
-            'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
-            'duration': 2245.72,
-            'uploader': 'SB Nation A.M.',
-            'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
+            'title': 'Asim Chaudhry',
+            'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc',
+            'duration': 4000.99,
+            'uploader': 'Sue Perkins: An hour or so with...',
+            'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
         }
     }, {
         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
@@ -32,8 +35,8 @@ class AudioBoomIE(InfoExtractor):
         clip = None
 
         clip_store = self._parse_json(
-            self._search_regex(
-                r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
+            self._html_search_regex(
+                r'data-new-clip-store=(["\'])(?P<json>{.+?})\1',
                 webpage, 'clip store', default='{}', group='json'),
             video_id, fatal=False)
         if clip_store:
@@ -47,14 +50,15 @@ class AudioBoomIE(InfoExtractor):
 
         audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
             'audio', webpage, 'audio url')
-        title = from_clip('title') or self._og_search_title(webpage)
-        description = from_clip('description') or self._og_search_description(webpage)
+        title = from_clip('title') or self._html_search_meta(
+            ['og:title', 'og:audio:title', 'audio_title'], webpage)
+        description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage)
 
         duration = float_or_none(from_clip('duration') or self._html_search_meta(
             'weibo:audio:duration', webpage))
 
-        uploader = from_clip('author') or self._og_search_property(
-            'audio:artist', webpage, 'uploader', fatal=False)
+        uploader = from_clip('author') or self._html_search_meta(
+            ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader')
         uploader_url = from_clip('author_url') or self._html_search_meta(
             'audioboo:channel', webpage, 'uploader url')
 

youtube_dl/extractor/bambuser.py

@@ -1,142 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-import itertools
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    ExtractorError,
-    float_or_none,
-    int_or_none,
-    sanitized_Request,
-    urlencode_postdata,
-)
-
-
-class BambuserIE(InfoExtractor):
-    IE_NAME = 'bambuser'
-    _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
-    _API_KEY = '005f64509e19a868399060af746a00aa'
-    _LOGIN_URL = 'https://bambuser.com/user'
-    _NETRC_MACHINE = 'bambuser'
-
-    _TEST = {
-        'url': 'http://bambuser.com/v/4050584',
-        # MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388
-        # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
-        'info_dict': {
-            'id': '4050584',
-            'ext': 'flv',
-            'title': 'Education engineering days - lightning talks',
-            'duration': 3741,
-            'uploader': 'pixelversity',
-            'uploader_id': '344706',
-            'timestamp': 1382976692,
-            'upload_date': '20131028',
-            'view_count': int,
-        },
-        'params': {
-            # It doesn't respect the 'Range' header, it would download the whole video
-            # caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59
-            'skip_download': True,
-        },
-    }
-
-    def _login(self):
-        username, password = self._get_login_info()
-        if username is None:
-            return
-
-        login_form = {
-            'form_id': 'user_login',
-            'op': 'Log in',
-            'name': username,
-            'pass': password,
-        }
-
-        request = sanitized_Request(
-            self._LOGIN_URL, urlencode_postdata(login_form))
-        request.add_header('Referer', self._LOGIN_URL)
-        response = self._download_webpage(
-            request, None, 'Logging in')
-
-        login_error = self._html_search_regex(
-            r'(?s)<div class="messages error">(.+?)</div>',
-            response, 'login error', default=None)
-        if login_error:
-            raise ExtractorError(
-                'Unable to login: %s' % login_error, expected=True)
-
-    def _real_initialize(self):
-        self._login()
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        info = self._download_json(
-            'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
-            % (self._API_KEY, video_id), video_id)
-
-        error = info.get('error')
-        if error:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error), expected=True)
-
-        result = info['result']
-
-        return {
-            'id': video_id,
-            'title': result['title'],
-            'url': result['url'],
-            'thumbnail': result.get('preview'),
-            'duration': int_or_none(result.get('length')),
-            'uploader': result.get('username'),
-            'uploader_id': compat_str(result.get('owner', {}).get('uid')),
-            'timestamp': int_or_none(result.get('created')),
-            'fps': float_or_none(result.get('framerate')),
-            'view_count': int_or_none(result.get('views_total')),
-            'comment_count': int_or_none(result.get('comment_count')),
-        }
-
-
-class BambuserChannelIE(InfoExtractor):
-    IE_NAME = 'bambuser:channel'
-    _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
-    # The maximum number we can get with each request
-    _STEP = 50
-    _TEST = {
-        'url': 'http://bambuser.com/channel/pixelversity',
-        'info_dict': {
-            'title': 'pixelversity',
-        },
-        'playlist_mincount': 60,
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        user = mobj.group('user')
-        urls = []
-        last_id = ''
-        for i in itertools.count(1):
-            req_url = (
-                'http://bambuser.com/xhr-api/index.php?username={user}'
-                '&sort=created&access_mode=0%2C1%2C2&limit={count}'
-                '&method=broadcast&format=json&vid_older_than={last}'
-            ).format(user=user, count=self._STEP, last=last_id)
-            req = sanitized_Request(req_url)
-            # Without setting this header, we wouldn't get any result
-            req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
-            data = self._download_json(
-                req, user, 'Downloading page %d' % i)
-            results = data['result']
-            if not results:
-                break
-            last_id = results[-1]['vid']
-            urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
-
-        return {
-            '_type': 'playlist',
-            'title': user,
-            'entries': urls,
-        }

youtube_dl/extractor/bellmedia.py

@@ -22,7 +22,8 @@ class BellMediaIE(InfoExtractor):
                 bravo|
                 mtv|
                 space|
-                etalk
+                etalk|
+                marilyn
             )\.ca|
             much\.com
         )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
@@ -70,6 +71,7 @@ class BellMediaIE(InfoExtractor):
         'animalplanet': 'aniplan',
         'etalk': 'ctv',
         'bnnbloomberg': 'bnn',
+        'marilyn': 'ctv_marilyn',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/bilibili.py

@@ -15,6 +15,7 @@ from ..utils import (
     float_or_none,
     parse_iso8601,
     smuggle_url,
+    str_or_none,
     strip_jsonp,
     unified_timestamp,
     unsmuggle_url,
@@ -306,3 +307,115 @@ class BiliBiliBangumiIE(InfoExtractor):
         return self.playlist_result(
             entries, bangumi_id,
             season_info.get('bangumi_title'), season_info.get('evaluate'))
+
+
+class BilibiliAudioBaseIE(InfoExtractor):
+    def _call_api(self, path, sid, query=None):
+        if not query:
+            query = {'sid': sid}
+        return self._download_json(
+            'https://www.bilibili.com/audio/music-service-c/web/' + path,
+            sid, query=query)['data']
+
+
+class BilibiliAudioIE(BilibiliAudioBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.bilibili.com/audio/au1003142',
+        'md5': 'fec4987014ec94ef9e666d4d158ad03b',
+        'info_dict': {
+            'id': '1003142',
+            'ext': 'm4a',
+            'title': '【tsukimi】YELLOW / 神山羊',
+            'artist': 'tsukimi',
+            'comment_count': int,
+            'description': 'YELLOW的mp3版！',
+            'duration': 183,
+            'subtitles': {
+                'origin': [{
+                    'ext': 'lrc',
+                }],
+            },
+            'thumbnail': r're:^https?://.+\.jpg',
+            'timestamp': 1564836614,
+            'upload_date': '20190803',
+            'uploader': 'tsukimi-つきみぐー',
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        au_id = self._match_id(url)
+
+        play_data = self._call_api('url', au_id)
+        formats = [{
+            'url': play_data['cdns'][0],
+            'filesize': int_or_none(play_data.get('size')),
+        }]
+
+        song = self._call_api('song/info', au_id)
+        title = song['title']
+        statistic = song.get('statistic') or {}
+
+        subtitles = None
+        lyric = song.get('lyric')
+        if lyric:
+            subtitles = {
+                'origin': [{
+                    'url': lyric,
+                }]
+            }
+
+        return {
+            'id': au_id,
+            'title': title,
+            'formats': formats,
+            'artist': song.get('author'),
+            'comment_count': int_or_none(statistic.get('comment')),
+            'description': song.get('intro'),
+            'duration': int_or_none(song.get('duration')),
+            'subtitles': subtitles,
+            'thumbnail': song.get('cover'),
+            'timestamp': int_or_none(song.get('passtime')),
+            'uploader': song.get('uname'),
+            'view_count': int_or_none(statistic.get('play')),
+        }
+
+
+class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.bilibili.com/audio/am10624',
+        'info_dict': {
+            'id': '10624',
+            'title': '每日新曲推荐（每日11:00更新）',
+            'description': '每天11:00更新，为你推送最新音乐',
+        },
+        'playlist_count': 19,
+    }
+
+    def _real_extract(self, url):
+        am_id = self._match_id(url)
+
+        songs = self._call_api(
+            'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data']
+
+        entries = []
+        for song in songs:
+            sid = str_or_none(song.get('id'))
+            if not sid:
+                continue
+            entries.append(self.url_result(
+                'https://www.bilibili.com/audio/au' + sid,
+                BilibiliAudioIE.ie_key(), sid))
+
+        if entries:
+            album_data = self._call_api('menu/info', am_id) or {}
+            album_title = album_data.get('title')
+            if album_title:
+                for entry in entries:
+                    entry['album'] = album_title
+                return self.playlist_result(
+                    entries, am_id, album_title, album_data.get('intro'))
+
+        return self.playlist_result(entries, am_id)

youtube_dl/extractor/bokecc.py

@@ -11,8 +11,8 @@ from ..utils import ExtractorError
 class BokeCCBaseIE(InfoExtractor):
     def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
         player_params_str = self._html_search_regex(
-            r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
-            webpage, 'player params')
+            r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
+            webpage, 'player params', group='query')
 
         player_params = compat_parse_qs(player_params_str)
 
@@ -36,9 +36,9 @@ class BokeCCIE(BokeCCBaseIE):
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{
-        'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',
+        'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A',
         'info_dict': {
-            'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30',
+            'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461',
             'ext': 'flv',
             'title': 'BokeCC Video',
         },

youtube_dl/extractor/brightcove.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import base64
-import json
 import re
 import struct
 
@@ -11,14 +10,12 @@ from .adobepass import AdobePassIE
 from ..compat import (
     compat_etree_fromstring,
     compat_parse_qs,
-    compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_xml_parse_error,
     compat_HTTPError,
 )
 from ..utils import (
-    determine_ext,
     ExtractorError,
     extract_attributes,
     find_xpath_attr,
@@ -27,18 +24,19 @@ from ..utils import (
     js_to_json,
     int_or_none,
     parse_iso8601,
+    smuggle_url,
     unescapeHTML,
     unsmuggle_url,
     update_url_query,
     clean_html,
     mimetype2ext,
+    UnsupportedError,
 )
 
 
 class BrightcoveLegacyIE(InfoExtractor):
     IE_NAME = 'brightcove:legacy'
     _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
-    _FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated'
 
     _TESTS = [
         {
@@ -55,7 +53,8 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'timestamp': 1368213670,
                 'upload_date': '20130510',
                 'uploader_id': '1589608506001',
-            }
+            },
+            'skip': 'The player has been deactivated by the content owner',
         },
         {
             # From http://medianetwork.oracle.com/video/player/1785452137001
@@ -70,6 +69,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'upload_date': '20120814',
                 'uploader_id': '1460825906',
             },
+            'skip': 'video not playable',
         },
         {
             # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
@@ -79,7 +79,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'This Bracelet Acts as a Personal Thermostat',
                 'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
-                'uploader': 'Mashable',
+                # 'uploader': 'Mashable',
                 'timestamp': 1382041798,
                 'upload_date': '20131017',
                 'uploader_id': '1130468786001',
@@ -124,6 +124,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'id': '3550319591001',
             },
             'playlist_mincount': 7,
+            'skip': 'Unsupported URL',
         },
         {
             # playlist with 'playlistTab' (https://github.com/ytdl-org/youtube-dl/issues/9965)
@@ -133,6 +134,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'title': 'Lesson 08',
             },
             'playlist_mincount': 10,
+            'skip': 'Unsupported URL',
         },
         {
             # playerID inferred from bcpid
@@ -141,12 +143,6 @@ class BrightcoveLegacyIE(InfoExtractor):
             'only_matching': True,  # Tested in GenericIE
         }
     ]
-    FLV_VCODECS = {
-        1: 'SORENSON',
-        2: 'ON2',
-        3: 'H264',
-        4: 'VP8',
-    }
 
     @classmethod
     def _build_brighcove_url(cls, object_str):
@@ -238,7 +234,8 @@ class BrightcoveLegacyIE(InfoExtractor):
 
     @classmethod
     def _make_brightcove_url(cls, params):
-        return update_url_query(cls._FEDERATED_URL, params)
+        return update_url_query(
+            'http://c.brightcove.com/services/viewer/htmlFederated', params)
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
@@ -297,38 +294,12 @@ class BrightcoveLegacyIE(InfoExtractor):
         videoPlayer = query.get('@videoPlayer')
         if videoPlayer:
             # We set the original url as the default 'Referer' header
-            referer = smuggled_data.get('Referer', url)
+            referer = query.get('linkBaseURL', [None])[0] or smuggled_data.get('Referer', url)
+            video_id = videoPlayer[0]
             if 'playerID' not in query:
                 mobj = re.search(r'/bcpid(\d+)', url)
                 if mobj is not None:
                     query['playerID'] = [mobj.group(1)]
-            return self._get_video_info(
-                videoPlayer[0], query, referer=referer)
-        elif 'playerKey' in query:
-            player_key = query['playerKey']
-            return self._get_playlist_info(player_key[0])
-        else:
-            raise ExtractorError(
-                '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')
-        if linkBase is not None:
-            referer = linkBase[0]
-        if referer is not None:
-            headers['Referer'] = referer
-        webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query)
-
-        error_msg = self._html_search_regex(
-            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]
@@ -339,6 +310,9 @@ class BrightcoveLegacyIE(InfoExtractor):
                 else:
                     player_id = query.get('playerID')
                     if player_id and player_id[0].isdigit():
+                        headers = {}
+                        if referer:
+                            headers['Referer'] = referer
                         player_page = self._download_webpage(
                             'http://link.brightcove.com/services/player/bcpid' + player_id[0],
                             video_id, headers=headers, fatal=False)
@@ -349,136 +323,16 @@ class BrightcoveLegacyIE(InfoExtractor):
                 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)
-
-        self.report_extraction(video_id)
-        info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
-        info = json.loads(info)['data']
-        video_info = info['programmedContent']['videoPlayer']['mediaDTO']
-        video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
-
-        return self._extract_video_info(video_info)
-
-    def _get_playlist_info(self, player_key):
-        info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
-        playlist_info = self._download_webpage(
-            info_url, player_key, 'Downloading playlist information')
-
-        json_data = json.loads(playlist_info)
-        if 'videoList' in json_data:
-            playlist_info = json_data['videoList']
-            playlist_dto = playlist_info['mediaCollectionDTO']
-        elif 'playlistTabs' in json_data:
-            playlist_info = json_data['playlistTabs']
-            playlist_dto = playlist_info['lineupListDTO']['playlistDTOs'][0]
-        else:
-            raise ExtractorError('Empty playlist')
-
-        videos = [self._extract_video_info(video_info) for video_info in playlist_dto['videoDTOs']]
-
-        return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'],
-                                    playlist_title=playlist_dto['displayName'])
-
-    def _extract_video_info(self, video_info):
-        video_id = compat_str(video_info['id'])
-        publisher_id = video_info.get('publisherId')
-        info = {
-            'id': video_id,
-            'title': video_info['displayName'].strip(),
-            'description': video_info.get('shortDescription'),
-            'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
-            'uploader': video_info.get('publisherName'),
-            'uploader_id': compat_str(publisher_id) if publisher_id else None,
-            'duration': float_or_none(video_info.get('length'), 1000),
-            'timestamp': int_or_none(video_info.get('creationDate'), 1000),
-        }
-
-        renditions = video_info.get('renditions', []) + video_info.get('IOSRenditions', [])
-        if renditions:
-            formats = []
-            for rend in renditions:
-                url = rend['defaultURL']
-                if not url:
-                    continue
-                ext = None
-                if rend['remote']:
-                    url_comp = compat_urllib_parse_urlparse(url)
-                    if url_comp.path.endswith('.m3u8'):
-                        formats.extend(
-                            self._extract_m3u8_formats(
-                                url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-                        continue
-                    elif 'akamaihd.net' in url_comp.netloc:
-                        # This type of renditions are served through
-                        # akamaihd.net, but they don't use f4m manifests
-                        url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
-                        ext = 'flv'
-                if ext is None:
-                    ext = determine_ext(url)
-                tbr = int_or_none(rend.get('encodingRate'), 1000)
-                a_format = {
-                    'format_id': 'http%s' % ('-%s' % tbr if tbr else ''),
-                    'url': url,
-                    'ext': ext,
-                    'filesize': int_or_none(rend.get('size')) or None,
-                    'tbr': tbr,
-                }
-                if rend.get('audioOnly'):
-                    a_format.update({
-                        'vcodec': 'none',
-                    })
-                else:
-                    a_format.update({
-                        'height': int_or_none(rend.get('frameHeight')),
-                        'width': int_or_none(rend.get('frameWidth')),
-                        'vcodec': rend.get('videoCodec'),
-                    })
-
-                # m3u8 manifests with remote == false are media playlists
-                # Not calling _extract_m3u8_formats here to save network traffic
-                if ext == 'm3u8':
-                    a_format.update({
-                        'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''),
-                        'ext': 'mp4',
-                        'protocol': 'm3u8_native',
-                    })
-
-                formats.append(a_format)
-            self._sort_formats(formats)
-            info['formats'] = formats
-        elif video_info.get('FLVFullLengthURL') is not None:
-            info.update({
-                'url': video_info['FLVFullLengthURL'],
-                'vcodec': self.FLV_VCODECS.get(video_info.get('FLVFullCodec')),
-                'filesize': int_or_none(video_info.get('FLVFullSize')),
-            })
-
-        if self._downloader.params.get('include_ads', False):
-            adServerURL = video_info.get('_youtubedl_adServerURL')
-            if adServerURL:
-                ad_info = {
-                    '_type': 'url',
-                    'url': adServerURL,
-                }
-                if 'url' in info:
-                    return {
-                        '_type': 'playlist',
-                        'title': info['title'],
-                        'entries': [ad_info, info],
-                    }
-                else:
-                    return ad_info
-
-        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
+            if publisher_id:
+                brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
+                if referer:
+                    brightcove_new_url = smuggle_url(brightcove_new_url, {'referrer': referer})
+                return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
+        # TODO: figure out if it's possible to extract playlistId from playerKey
+        # elif 'playerKey' in query:
+        #     player_key = query['playerKey']
+        #     return self._get_playlist_info(player_key[0])
+        raise UnsupportedError(url)
 
 
 class BrightcoveNewIE(AdobePassIE):

youtube_dl/extractor/byutv.py

@@ -3,7 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_duration
+from ..utils import (
+    determine_ext,
+    merge_dicts,
+    parse_duration,
+    url_or_none,
+)
 
 
 class BYUtvIE(InfoExtractor):
@@ -51,7 +56,7 @@ class BYUtvIE(InfoExtractor):
         video_id = mobj.group('id')
         display_id = mobj.group('display_id') or video_id
 
-        info = self._download_json(
+        video = self._download_json(
             'https://api.byutv.org/api3/catalog/getvideosforcontent',
             display_id, query={
                 'contentid': video_id,
@@ -62,7 +67,7 @@ class BYUtvIE(InfoExtractor):
                 'x-byutv-platformkey': 'xsaaw9c7y5',
             })
 
-        ep = info.get('ooyalaVOD')
+        ep = video.get('ooyalaVOD')
         if ep:
             return {
                 '_type': 'url_transparent',
@@ -75,18 +80,38 @@ class BYUtvIE(InfoExtractor):
                 'thumbnail': ep.get('imageThumbnail'),
             }
 
-        ep = info['dvr']
-        title = ep['title']
-        formats = self._extract_m3u8_formats(
-            ep['videoUrl'], video_id, 'mp4', entry_protocol='m3u8_native',
-            m3u8_id='hls')
+        info = {}
+        formats = []
+        for format_id, ep in video.items():
+            if not isinstance(ep, dict):
+                continue
+            video_url = url_or_none(ep.get('videoUrl'))
+            if not video_url:
+                continue
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, mpd_id='dash', fatal=False))
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                })
+            merge_dicts(info, {
+                'title': ep.get('title'),
+                'description': ep.get('description'),
+                'thumbnail': ep.get('imageThumbnail'),
+                'duration': parse_duration(ep.get('length')),
+            })
         self._sort_formats(formats)
-        return {
+
+        return merge_dicts(info, {
             'id': video_id,
             'display_id': display_id,
-            'title': title,
-            'description': ep.get('description'),
-            'thumbnail': ep.get('imageThumbnail'),
-            'duration': parse_duration(ep.get('length')),
+            'title': display_id,
             'formats': formats,
-        }
+        })

youtube_dl/extractor/ceskatelevize.py

@@ -147,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor):
                 is_live = item.get('type') == 'LIVE'
                 formats = []
                 for format_id, stream_url in item.get('streamUrls', {}).items():
+                    if 'drmOnly=true' in stream_url:
+                        continue
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(
                             stream_url, playlist_id, 'mp4', 'm3u8_native',

youtube_dl/extractor/chaturbate.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://www.chaturbate.com/siswet19/',
         'info_dict': {
@@ -21,6 +21,9 @@ class ChaturbateIE(InfoExtractor):
             'skip_download': True,
         },
         'skip': 'Room is offline',
+    }, {
+        'url': 'https://chaturbate.com/fullvideo/?b=caylin',
+        'only_matching': True,
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,
@@ -32,7 +35,8 @@ class ChaturbateIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            url, video_id, headers=self.geo_verification_headers())
+            'https://chaturbate.com/%s/' % video_id, video_id,
+            headers=self.geo_verification_headers())
 
         m3u8_urls = []
 

youtube_dl/extractor/common.py

@@ -1424,12 +1424,10 @@ class InfoExtractor(object):
         try:
             self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers)
             return True
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_urllib_error.URLError):
-                self.to_screen(
-                    '%s: %s URL is invalid, skipping' % (video_id, item))
-                return False
-            raise
+        except ExtractorError:
+            self.to_screen(
+                '%s: %s URL is invalid, skipping' % (video_id, item))
+            return False
 
     def http_scheme(self):
         """ Either "http:" or "https:", depending on the user's preferences """

youtube_dl/extractor/contv.py

@@ -0,0 +1,118 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
+
+
+class CONtvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter',
+        'info_dict': {
+            'id': 'CEG10022949',
+            'ext': 'mp4',
+            'title': 'Days Of Thrills & Laughter',
+            'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb',
+            'upload_date': '20180703',
+            'timestamp': 1530634789.61,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites',
+        'info_dict': {
+            'id': 'CLIP-show_fotld_bts',
+            'title': 'Fight of the Living Dead: Behind the Scenes Bites',
+        },
+        'playlist_mincount': 7,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        details = self._download_json(
+            'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id,
+            video_id, query={'device': 'web'})
+
+        if details.get('type') == 'episodic':
+            seasons = self._download_json(
+                'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id,
+                video_id)
+            entries = []
+            for season in seasons:
+                for episode in season.get('episodes', []):
+                    episode_id = episode.get('id')
+                    if not episode_id:
+                        continue
+                    entries.append(self.url_result(
+                        'https://www.contv.com/details-movie/' + episode_id,
+                        CONtvIE.ie_key(), episode_id))
+            return self.playlist_result(entries, video_id, details.get('title'))
+
+        m_details = details['details']
+        title = details['title']
+
+        formats = []
+
+        media_hls_url = m_details.get('media_hls_url')
+        if media_hls_url:
+            formats.extend(self._extract_m3u8_formats(
+                media_hls_url, video_id, 'mp4',
+                m3u8_id='hls', fatal=False))
+
+        media_mp4_url = m_details.get('media_mp4_url')
+        if media_mp4_url:
+            formats.append({
+                'format_id': 'http',
+                'url': media_mp4_url,
+            })
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        captions = m_details.get('captions') or {}
+        for caption_url in captions.values():
+            subtitles.setdefault('en', []).append({
+                'url': caption_url
+            })
+
+        thumbnails = []
+        for image in m_details.get('images', []):
+            image_url = 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')),
+            })
+
+        description = None
+        for p in ('large_', 'medium_', 'small_', ''):
+            d = m_details.get(p + 'description')
+            if d:
+                description = d
+                break
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': description,
+            'timestamp': float_or_none(details.get('metax_added_on'), 1000),
+            'subtitles': subtitles,
+            'duration': float_or_none(m_details.get('duration'), 1000),
+            'view_count': int_or_none(details.get('num_watched')),
+            'like_count': int_or_none(details.get('num_fav')),
+            'categories': details.get('category'),
+            'tags': details.get('tags'),
+            'season_number': int_or_none(details.get('season')),
+            'episode_number': int_or_none(details.get('episode')),
+            'release_year': int_or_none(details.get('pub_year')),
+        }

youtube_dl/extractor/daum.py

@@ -2,25 +2,21 @@
 
 from __future__ import unicode_literals
 
-import re
 import itertools
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse_unquote,
-    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
-from ..utils import (
-    int_or_none,
-    str_to_int,
-    xpath_text,
-    unescapeHTML,
-)
 
 
-class DaumIE(InfoExtractor):
+class DaumBaseIE(InfoExtractor):
+    _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/'
+
+
+class DaumIE(DaumBaseIE):
     _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
@@ -36,6 +32,9 @@ class DaumIE(InfoExtractor):
             'duration': 2117,
             'view_count': int,
             'comment_count': int,
+            'uploader_id': 186139,
+            'uploader': '콘간지',
+            'timestamp': 1387310323,
         },
     }, {
         'url': 'http://m.tvpot.daum.net/v/65139429',
@@ -44,11 +43,14 @@ class DaumIE(InfoExtractor):
             'ext': 'mp4',
             'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
             'description': 'md5:79794514261164ff27e36a21ad229fc5',
-            'upload_date': '20150604',
+            'upload_date': '20150118',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 154,
             'view_count': int,
             'comment_count': int,
+            'uploader': 'MBC 예능',
+            'uploader_id': 132251,
+            'timestamp': 1421604228,
         },
     }, {
         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
@@ -59,12 +61,15 @@ class DaumIE(InfoExtractor):
             'id': 'vwIpVpCQsT8$',
             'ext': 'flv',
             'title': '01-Korean War ( Trouble on the horizon )',
-            'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
+            'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름',
             'upload_date': '20080223',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 249,
             'view_count': int,
             'comment_count': int,
+            'uploader': '까칠한 墮落始祖 황비홍님의',
+            'uploader_id': 560824,
+            'timestamp': 1203770745,
         },
     }, {
         # Requires dte_type=WEB (#9972)
@@ -73,60 +78,24 @@ class DaumIE(InfoExtractor):
         'info_dict': {
             'id': 's3794Uf1NZeZ1qMpGpeqeRU',
             'ext': 'mp4',
-            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
-            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
-            'upload_date': '20160611',
+            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
+            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
+            'upload_date': '20170129',
+            'uploader': '쇼! 음악중심',
+            'uploader_id': 2653210,
+            'timestamp': 1485684628,
         },
     }]
 
     def _real_extract(self, url):
         video_id = compat_urllib_parse_unquote(self._match_id(url))
-        movie_data = self._download_json(
-            'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
-            video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
-
-        # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
-        if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
-            return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
-
-        info = self._download_xml(
-            'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
-            'Downloading video info', query={'vid': video_id})
-
-        formats = []
-        for format_el in movie_data['output_list']['output_list']:
-            profile = format_el['profile']
-            format_query = compat_urllib_parse_urlencode({
-                'vid': video_id,
-                'profile': profile,
-            })
-            url_doc = self._download_xml(
-                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note='Downloading video data for %s format' % profile)
-            format_url = url_doc.find('result/url').text
-            formats.append({
-                'url': format_url,
-                'format_id': profile,
-                'width': int_or_none(format_el.get('width')),
-                'height': int_or_none(format_el.get('height')),
-                'filesize': int_or_none(format_el.get('filesize')),
-            })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': info.find('TITLE').text,
-            'formats': formats,
-            'thumbnail': xpath_text(info, 'THUMB_URL'),
-            'description': xpath_text(info, 'CONTENTS'),
-            'duration': int_or_none(xpath_text(info, 'DURATION')),
-            'upload_date': info.find('REGDTTM').text[:8],
-            'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
-            'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
-        }
+        if not video_id.isdigit():
+            video_id += '@my'
+        return self.url_result(
+            self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
 
 
-class DaumClipIE(InfoExtractor):
+class DaumClipIE(DaumBaseIE):
     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
     IE_NAME = 'daum.net:clip'
     _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
@@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 3868,
             'view_count': int,
+            'uploader': 'GOMeXP',
+            'uploader_id': 6667,
+            'timestamp': 1377911092,
         },
     }, {
         'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
@@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        clip_info = self._download_json(
-            'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
-            video_id, 'Downloading clip info')['clip_bean']
-
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
-            'title': unescapeHTML(clip_info['title']),
-            'thumbnail': clip_info.get('thumb_url'),
-            'description': clip_info.get('contents'),
-            'duration': int_or_none(clip_info.get('duration')),
-            'upload_date': clip_info.get('up_date')[:8],
-            'view_count': int_or_none(clip_info.get('play_count')),
-            'ie_key': 'Daum',
-        }
+        return self.url_result(
+            self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
 
 
 class DaumListIE(InfoExtractor):

youtube_dl/extractor/discoverynetworks.py

@@ -3,63 +3,38 @@ from __future__ import unicode_literals
 
 import re
 
-from .brightcove import BrightcoveLegacyIE
 from .dplay import DPlayIE
-from ..compat import (
-    compat_parse_qs,
-    compat_urlparse,
-)
-from ..utils import smuggle_url
 
 
 class DiscoveryNetworksDeIE(DPlayIE):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/
-                        (?:
-                           .*\#(?P<id>\d+)|
-                           (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)|
-                           programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)
-                        )'''
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)'
 
     _TESTS = [{
-        'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
+        'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100',
         'info_dict': {
-            'id': '3235167922001',
+            'id': '78867',
             'ext': 'mp4',
-            'title': 'Breaking Amish: Die Welt da draußen',
-            'description': (
-                'Vier Amische und eine Mennonitin wagen in New York'
-                '  den Sprung in ein komplett anderes Leben. Begleitet sie auf'
-                ' ihrem spannenden Weg.'),
-            'timestamp': 1396598084,
-            'upload_date': '20140404',
-            'uploader_id': '1659832546',
+            'title': 'Die Welt da draußen',
+            'description': 'md5:61033c12b73286e409d99a41742ef608',
+            'timestamp': 1554069600,
+            'upload_date': '20190331',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
         },
     }, {
-        'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/',
+        'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316',
         'only_matching': True,
     }, {
-        'url': 'http://www.discovery.de/#5332316765001',
+        'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B',
         'only_matching': True,
     }]
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        alternate_id = mobj.group('alternate_id')
-        if alternate_id:
-            self._initialize_geo_bypass({
-                'countries': ['DE'],
-            })
-            return self._get_disco_api_info(
-                url, '%s/%s' % (mobj.group('programme'), alternate_id),
-                'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de')
-        brightcove_id = mobj.group('id')
-        if not brightcove_id:
-            title = mobj.group('title')
-            webpage = self._download_webpage(url, title)
-            brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
-            brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
-                brightcove_legacy_url).query)['@videoPlayer'][0]
-        return self.url_result(smuggle_url(
-            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}),
-            'BrightcoveNew', brightcove_id)
+        domain, programme, alternate_id = re.match(self._VALID_URL, url).groups()
+        country = 'GB' if domain == 'dplay.co.uk' else 'DE'
+        realm = 'questuk' if country == 'GB' else domain.replace('.', '')
+        return self._get_disco_api_info(
+            url, '%s/%s' % (programme, alternate_id),
+            'sonic-eu1-prod.disco-api.com', realm, country)

youtube_dl/extractor/dplay.py

@@ -1,74 +1,68 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
-import time
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_str,
-    compat_urlparse,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
     int_or_none,
-    remove_end,
-    try_get,
-    unified_strdate,
     unified_timestamp,
-    update_url_query,
-    urljoin,
-    USER_AGENTS,
 )
 
 
 class DPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)'
+    _VALID_URL = r'''(?x)https?://
+        (?P<domain>
+            (?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
+            (?P<subdomain_country>es|it)\.dplay\.com
+        )/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
 
     _TESTS = [{
         # non geo restricted, via secure api, unsigned download hls URL
-        'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
+        'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
         'info_dict': {
-            'id': '3172',
-            'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet',
+            'id': '13628',
+            'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
             'ext': 'mp4',
             'title': 'Svensken lär sig njuta av livet',
             'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
-            'duration': 2650,
-            'timestamp': 1365454320,
+            'duration': 2649.856,
+            'timestamp': 1365453720,
             'upload_date': '20130408',
-            'creator': 'Kanal 5 (Home)',
+            'creator': 'Kanal 5',
             'series': 'Nugammalt - 77 händelser som format Sverige',
             'season_number': 1,
             'episode_number': 1,
-            'age_limit': 0,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
         },
     }, {
         # geo restricted, via secure api, unsigned download hls URL
-        'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
+        'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
         'info_dict': {
-            'id': '70816',
-            'display_id': 'mig-og-min-mor/season-6-episode-12',
+            'id': '104465',
+            'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
             'ext': 'mp4',
-            'title': 'Episode 12',
-            'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
-            'duration': 2563,
-            'timestamp': 1429696800,
-            'upload_date': '20150422',
-            'creator': 'Kanal 4 (Home)',
-            'series': 'Mig og min mor',
-            'season_number': 6,
-            'episode_number': 12,
-            'age_limit': 0,
+            'title': 'Ted Bundy: Mind Of A Monster',
+            'description': 'md5:8b780f6f18de4dae631668b8a9637995',
+            'duration': 5290.027,
+            'timestamp': 1570694400,
+            'upload_date': '20191010',
+            'creator': 'ID - Investigation Discovery',
+            'series': 'Ted Bundy: Mind Of A Monster',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
         },
-    }, {
-        # geo restricted, via direct unsigned hls URL
-        'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
-        'only_matching': True,
     }, {
         # disco-api
         'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
@@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor):
             'format': 'bestvideo',
             'skip_download': True,
         },
+        'skip': 'Available for Premium users',
     }, {
-
-        'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3',
+        'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
+        'md5': '2b808ffb00fc47b884a172ca5d13053c',
+        'info_dict': {
+            'id': '6918',
+            'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
+            'ext': 'mp4',
+            'title': 'Luigi Di Maio: la psicosi di Stanislawskij',
+            'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
+            'thumbnail': r're:^https?://.*\.jpe?g',
+            'upload_date': '20160524',
+            'timestamp': 1464076800,
+            'series': 'Biografie imbarazzanti',
+            'season_number': 1,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+        },
+    }, {
+        'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/',
+        'info_dict': {
+            'id': '21652',
+            'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1',
+            'ext': 'mp4',
+            'title': 'Episodio 1',
+            'description': 'md5:b9dcff2071086e003737485210675f69',
+            'thumbnail': r're:^https?://.*\.png',
+            'upload_date': '20180709',
+            'timestamp': 1531173540,
+            'series': 'La fiebre del oro',
+            'season_number': 8,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
         'only_matching': True,
     }, {
-        'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001',
+        'url': 'https://www.dplay.jp/video/gold-rush/24086',
         'only_matching': True,
     }]
 
-    def _get_disco_api_info(self, url, display_id, disco_host, realm):
-        disco_base = 'https://' + disco_host
+    def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
+        geo_countries = [country.upper()]
+        self._initialize_geo_bypass({
+            'countries': geo_countries,
+        })
+        disco_base = 'https://%s/' % disco_host
         token = self._download_json(
-            '%s/token' % disco_base, display_id, 'Downloading token',
+            disco_base + 'token', display_id, 'Downloading token',
             query={
                 'realm': realm,
             })['data']['attributes']['token']
@@ -110,17 +144,30 @@ class DPlayIE(InfoExtractor):
             'Authorization': 'Bearer ' + token,
         }
         video = self._download_json(
-            '%s/content/videos/%s' % (disco_base, display_id), display_id,
+            disco_base + 'content/videos/' + display_id, display_id,
             headers=headers, query={
-                'include': 'show'
+                'include': 'images,primaryChannel,show,tags'
             })
         video_id = video['data']['id']
         info = video['data']['attributes']
-        title = info['name']
+        title = info['name'].strip()
         formats = []
-        for format_id, format_dict in self._download_json(
-                '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id),
-                display_id, headers=headers)['data']['attributes']['streaming'].items():
+        try:
+            streaming = self._download_json(
+                disco_base + 'playback/videoPlaybackInfo/' + video_id,
+                display_id, headers=headers)['data']['attributes']['streaming']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
+                error = info['errors'][0]
+                error_code = error.get('code')
+                if error_code == 'access.denied.geoblocked':
+                    self.raise_geo_restricted(countries=geo_countries)
+                elif error_code == 'access.denied.missingpackage':
+                    self.raise_login_required()
+                raise ExtractorError(info['errors'][0]['detail'], expected=True)
+            raise
+        for format_id, format_dict in streaming.items():
             if not isinstance(format_dict, dict):
                 continue
             format_url = format_dict.get('url')
@@ -142,235 +189,55 @@ class DPlayIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
-        series = None
-        try:
-            included = video.get('included')
-            if isinstance(included, list):
-                show = next(e for e in included if e.get('type') == 'show')
-                series = try_get(
-                    show, lambda x: x['attributes']['name'], compat_str)
-        except StopIteration:
-            pass
+        creator = series = None
+        tags = []
+        thumbnails = []
+        included = video.get('included') or []
+        if isinstance(included, list):
+            for e in included:
+                attributes = e.get('attributes')
+                if not attributes:
+                    continue
+                e_type = e.get('type')
+                if e_type == 'channel':
+                    creator = attributes.get('name')
+                elif e_type == 'image':
+                    src = attributes.get('src')
+                    if src:
+                        thumbnails.append({
+                            'url': src,
+                            'width': int_or_none(attributes.get('width')),
+                            'height': int_or_none(attributes.get('height')),
+                        })
+                if e_type == 'show':
+                    series = attributes.get('name')
+                elif e_type == 'tag':
+                    name = attributes.get('name')
+                    if name:
+                        tags.append(name)
 
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': info.get('description'),
-            'duration': float_or_none(
-                info.get('videoDuration'), scale=1000),
+            'duration': float_or_none(info.get('videoDuration'), 1000),
             'timestamp': unified_timestamp(info.get('publishStart')),
             'series': series,
             'season_number': int_or_none(info.get('seasonNumber')),
             'episode_number': int_or_none(info.get('episodeNumber')),
             'age_limit': int_or_none(info.get('minimum_age')),
+            'creator': creator,
+            'tags': tags,
+            'thumbnails': thumbnails,
             'formats': formats,
         }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('id')
-        domain = mobj.group('domain')
-
-        self._initialize_geo_bypass({
-            'countries': [mobj.group('country').upper()],
-        })
-
-        webpage = self._download_webpage(url, display_id)
-
-        video_id = self._search_regex(
-            r'data-video-id=["\'](\d+)', webpage, 'video id', default=None)
-
-        if not video_id:
-            host = mobj.group('host')
-            return self._get_disco_api_info(
-                url, display_id, 'disco-api.' + host, host.replace('.', ''))
-
-        info = self._download_json(
-            'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
-            video_id)['data'][0]
-
-        title = info['title']
-
-        PROTOCOLS = ('hls', 'hds')
-        formats = []
-
-        def extract_formats(protocol, manifest_url):
-            if protocol == 'hls':
-                m3u8_formats = self._extract_m3u8_formats(
-                    manifest_url, video_id, ext='mp4',
-                    entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
-                # Sometimes final URLs inside m3u8 are unsigned, let's fix this
-                # ourselves. Also fragments' URLs are only served signed for
-                # Safari user agent.
-                query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
-                for m3u8_format in m3u8_formats:
-                    m3u8_format.update({
-                        'url': update_url_query(m3u8_format['url'], query),
-                        'http_headers': {
-                            'User-Agent': USER_AGENTS['Safari'],
-                        },
-                    })
-                formats.extend(m3u8_formats)
-            elif protocol == 'hds':
-                formats.extend(self._extract_f4m_formats(
-                    manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
-                    video_id, f4m_id=protocol, fatal=False))
-
-        domain_tld = domain.split('.')[-1]
-        if domain_tld in ('se', 'dk', 'no'):
-            for protocol in PROTOCOLS:
-                # Providing dsc-geo allows to bypass geo restriction in some cases
-                self._set_cookie(
-                    'secure.dplay.%s' % domain_tld, 'dsc-geo',
-                    json.dumps({
-                        'countryCode': domain_tld.upper(),
-                        'expiry': (time.time() + 20 * 60) * 1000,
-                    }))
-                stream = self._download_json(
-                    'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
-                    % (domain_tld, video_id, protocol), video_id,
-                    'Downloading %s stream JSON' % protocol, fatal=False)
-                if stream and stream.get(protocol):
-                    extract_formats(protocol, stream[protocol])
-
-        # The last resort is to try direct unsigned hls/hds URLs from info dictionary.
-        # Sometimes this does work even when secure API with dsc-geo has failed (e.g.
-        # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/).
-        if not formats:
-            for protocol in PROTOCOLS:
-                if info.get(protocol):
-                    extract_formats(protocol, info[protocol])
-
-        self._sort_formats(formats)
-
-        subtitles = {}
-        for lang in ('se', 'sv', 'da', 'nl', 'no'):
-            for format_id in ('web_vtt', 'vtt', 'srt'):
-                subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id))
-                if subtitle_url:
-                    subtitles.setdefault(lang, []).append({'url': subtitle_url})
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': info.get('video_metadata_longDescription'),
-            'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
-            'timestamp': int_or_none(info.get('video_publish_date')),
-            'creator': info.get('video_metadata_homeChannel'),
-            'series': info.get('video_metadata_show'),
-            'season_number': int_or_none(info.get('season')),
-            'episode_number': int_or_none(info.get('episode')),
-            'age_limit': int_or_none(info.get('minimum_age')),
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-
-class DPlayItIE(InfoExtractor):
-    _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
-    _GEO_COUNTRIES = ['IT']
-    _TEST = {
-        'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
-        'md5': '2b808ffb00fc47b884a172ca5d13053c',
-        'info_dict': {
-            'id': '6918',
-            'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
-            'ext': 'mp4',
-            'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
-            'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
-            'thumbnail': r're:^https?://.*\.jpe?g',
-            'upload_date': '20160524',
-            'series': 'Biografie imbarazzanti',
-            'season_number': 1,
-            'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
-            'episode_number': 1,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        title = remove_end(self._og_search_title(webpage), ' | Dplay')
-
-        video_id = None
-
-        info = self._search_regex(
-            r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
-            webpage, 'playback JSON', default=None)
-        if info:
-            for _ in range(2):
-                info = self._parse_json(info, display_id, fatal=False)
-                if not info:
-                    break
-            else:
-                video_id = try_get(info, lambda x: x['data']['id'])
-
-        if not info:
-            info_url = self._search_regex(
-                (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:
-                info = self._download_json(
-                    info_url, display_id, headers={
-                        'Authorization': 'Bearer %s' % self._get_cookies(url).get(
-                            '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)
-                    error = info['errors'][0]
-                    if error.get('code') == 'access.denied.geoblocked':
-                        self.raise_geo_restricted(
-                            msg=error.get('detail'), countries=self._GEO_COUNTRIES)
-                    raise ExtractorError(info['errors'][0]['detail'], expected=True)
-                raise
-
-        hls_url = info['data']['attributes']['streaming']['hls']['url']
-
-        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>',
-            webpage, 'series', fatal=False)
-        episode = self._search_regex(
-            r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
-            webpage, 'episode', fatal=False)
-
-        mobj = re.search(
-            r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
-            webpage)
-        if mobj:
-            season_number = int(mobj.group('season_number'))
-            episode_number = int(mobj.group('episode_number'))
-            upload_date = unified_strdate(mobj.group('upload_date'))
-        else:
-            season_number = episode_number = upload_date = None
-
-        return {
-            'id': compat_str(video_id or display_id),
-            'display_id': display_id,
-            'title': title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'series': series,
-            'season_number': season_number,
-            'episode': episode,
-            'episode_number': episode_number,
-            'upload_date': upload_date,
-            'formats': formats,
-        }
+        domain = mobj.group('domain').lstrip('www.')
+        country = mobj.group('country') or mobj.group('subdomain_country')
+        host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
+        return self._get_disco_api_info(
+            url, display_id, host, 'dplay' + country, country)

youtube_dl/extractor/dumpert.py

@@ -1,20 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import compat_b64decode
 from ..utils import (
+    int_or_none,
     qualities,
-    sanitized_Request,
 )
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
     _TESTS = [{
-        'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
+        'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
         'info_dict': {
             'id': '6646981/951bc60f',
@@ -24,46 +21,60 @@ class DumpertIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
         }
     }, {
-        'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
+        'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
+        'only_matching': True,
+    }, {
+        'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
+        'only_matching': True,
+    }, {
+        'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        protocol = mobj.group('protocol')
-
-        url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'nsfw=1; cpc=10')
-        webpage = self._download_webpage(req, video_id)
-
-        files_base64 = self._search_regex(
-            r'data-files="([^"]+)"', webpage, 'data files')
-
-        files = self._parse_json(
-            compat_b64decode(files_base64).decode('utf-8'),
-            video_id)
+        video_id = self._match_id(url).replace('_', '/')
+        item = self._download_json(
+            'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
+            video_id)['items'][0]
+        title = item['title']
+        media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
 
         quality = qualities(['flv', 'mobile', 'tablet', '720p'])
-
-        formats = [{
-            'url': video_url,
-            'format_id': format_id,
-            'quality': quality(format_id),
-        } for format_id, video_url in files.items() if format_id != 'still']
+        formats = []
+        for variant in media.get('variants', []):
+            uri = variant.get('uri')
+            if not uri:
+                continue
+            version = variant.get('version')
+            formats.append({
+                'url': uri,
+                'format_id': version,
+                'quality': quality(version),
+            })
         self._sort_formats(formats)
 
-        title = self._html_search_meta(
-            'title', webpage) or self._og_search_title(webpage)
-        description = self._html_search_meta(
-            'description', webpage) or self._og_search_description(webpage)
-        thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
+        thumbnails = []
+        stills = item.get('stills') or {}
+        for t in ('thumb', 'still'):
+            for s in ('', '-medium', '-large'):
+                still_id = t + s
+                still_url = stills.get(still_id)
+                if not still_url:
+                    continue
+                thumbnails.append({
+                    'id': still_id,
+                    'url': still_url,
+                })
+
+        stats = item.get('stats') or {}
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'formats': formats
+            'description': item.get('description'),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'duration': int_or_none(media.get('duration')),
+            'like_count': int_or_none(stats.get('kudos_total')),
+            'view_count': int_or_none(stats.get('views_total')),
         }

youtube_dl/extractor/extractors.py

@@ -80,7 +80,6 @@ from .awaan import (
 )
 from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
-from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
 from .bbc import (
     BBCCoUkIE,
@@ -104,6 +103,8 @@ from .bild import BildIE
 from .bilibili import (
     BiliBiliIE,
     BiliBiliBangumiIE,
+    BilibiliAudioIE,
+    BilibiliAudioAlbumIE,
 )
 from .biobiochiletv import BioBioChileTVIE
 from .bitchute import (
@@ -229,6 +230,7 @@ from .commonprotocols import (
     RtmpIE,
 )
 from .condenast import CondeNastIE
+from .contv import CONtvIE
 from .corus import CorusIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
@@ -274,10 +276,7 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
-from .dplay import (
-    DPlayIE,
-    DPlayItIE,
-)
+from .dplay import DPlayIE
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -356,7 +355,6 @@ from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
 from .flickr import FlickrIE
-from .flipagram import FlipagramIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
 from .formula1 import Formula1IE
@@ -367,7 +365,10 @@ from .fourtube import (
     FuxIE,
 )
 from .fox import FOXIE
-from .fox9 import FOX9IE
+from .fox9 import (
+    FOX9IE,
+    FOX9NewsIE,
+)
 from .foxgay import FoxgayIE
 from .foxnews import (
     FoxNewsIE,
@@ -400,10 +401,6 @@ from .fusion import FusionIE
 from .fxnetworks import FXNetworksIE
 from .gaia import GaiaIE
 from .gameinformer import GameInformerIE
-from .gameone import (
-    GameOneIE,
-    GameOnePlaylistIE,
-)
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
@@ -419,7 +416,6 @@ from .globo import (
     GloboArticleIE,
 )
 from .go import GoIE
-from .go90 import Go90IE
 from .godtube import GodTubeIE
 from .golem import GolemIE
 from .googledrive import GoogleDriveIE
@@ -428,7 +424,6 @@ from .googlesearch import GoogleSearchIE
 from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
-from .hark import HarkIE
 from .hbo import HBOIE
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
@@ -460,7 +455,6 @@ from .hungama import (
     HungamaSongIE,
 )
 from .hypem import HypemIE
-from .iconosquare import IconosquareIE
 from .ign import (
     IGNIE,
     OneUPIE,
@@ -520,7 +514,6 @@ 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
 from .krasview import KrasViewIE
@@ -546,7 +539,6 @@ from .lcp import (
     LcpPlayIE,
     LcpIE,
 )
-from .learnr import LearnrIE
 from .lecture2go import Lecture2GoIE
 from .lecturio import (
     LecturioIE,
@@ -598,13 +590,11 @@ from .lynda import (
     LyndaCourseIE
 )
 from .m6 import M6IE
-from .macgamestore import MacGameStoreIE
 from .mailru import (
     MailRuIE,
     MailRuMusicIE,
     MailRuMusicSearchIE,
 )
-from .makertv import MakerTVIE
 from .malltv import MallTVIE
 from .mangomolo import (
     MangomoloVideoIE,
@@ -642,7 +632,7 @@ from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
 from .minoto import MinotoIE
 from .miomio import MioMioIE
-from .mit import TechTVMITIE, MITIE, OCWMITIE
+from .mit import TechTVMITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import (
     MixcloudIE,
@@ -670,7 +660,7 @@ from .mtv import (
     MTVVideoIE,
     MTVServicesEmbeddedIE,
     MTVDEIE,
-    MTV81IE,
+    MTVJapanIE,
 )
 from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
@@ -891,7 +881,6 @@ from .puhutv import (
     PuhuTVSerieIE,
 )
 from .presstv import PressTVIE
-from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE
 from .pyvideo import PyvideoIE
@@ -991,10 +980,13 @@ from .sbs import SBSIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
 from .scrippsnetworks import ScrippsNetworksWatchIE
+from .scte import (
+    SCTEIE,
+    SCTECourseIE,
+)
 from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
-from .servingsys import ServingSysIE
 from .servus import ServusIE
 from .sevenplus import SevenPlusIE
 from .sexu import SexuIE
@@ -1035,6 +1027,7 @@ from .snotr import SnotrIE
 from .sohu import SohuIE
 from .sonyliv import SonyLIVIE
 from .soundcloud import (
+    SoundcloudEmbedIE,
     SoundcloudIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
@@ -1127,12 +1120,14 @@ from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
 from .telequebec import (
     TeleQuebecIE,
+    TeleQuebecSquatIE,
     TeleQuebecEmissionIE,
     TeleQuebecLiveIE,
 )
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .tennistv import TennisTVIE
+from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .tfo import TFOIE
@@ -1185,11 +1180,11 @@ from .tunein import (
 )
 from .tunepk import TunePkIE
 from .turbo import TurboIE
-from .tutv import TutvIE
 from .tv2 import (
     TV2IE,
     TV2ArticleIE,
 )
+from .tv2dk import TV2DKIE
 from .tv2hu import TV2HuIE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
@@ -1280,7 +1275,6 @@ from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
-from .vessel import VesselIE
 from .vesti import VestiIE
 from .vevo import (
     VevoIE,
@@ -1322,7 +1316,6 @@ from .viewlift import (
     ViewLiftIE,
     ViewLiftEmbedIE,
 )
-from .viewster import ViewsterIE
 from .viidea import ViideaIE
 from .vimeo import (
     VimeoIE,
@@ -1411,7 +1404,6 @@ from .weibo import (
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
-from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wsj import (

youtube_dl/extractor/facebook.py

@@ -379,6 +379,7 @@ class FacebookIE(InfoExtractor):
         if not video_data:
             raise ExtractorError('Cannot parse data')
 
+        subtitles = {}
         formats = []
         for f in video_data:
             format_id = f['stream_type']
@@ -402,9 +403,17 @@ class FacebookIE(InfoExtractor):
             if dash_manifest:
                 formats.extend(self._parse_mpd_formats(
                     compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
+            subtitles_src = f[0].get('subtitles_src')
+            if subtitles_src:
+                subtitles.setdefault('en', []).append({'url': subtitles_src})
         if not formats:
             raise ExtractorError('Cannot find video formats')
 
+        # Downloads with browser's User-Agent are rate limited. Working around
+        # with non-browser User-Agent.
+        for f in formats:
+            f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1'
+
         self._sort_formats(formats)
 
         video_title = self._html_search_regex(
@@ -442,6 +451,7 @@ class FacebookIE(InfoExtractor):
             'timestamp': timestamp,
             'thumbnail': thumbnail,
             'view_count': view_count,
+            'subtitles': subtitles,
         }
 
         return webpage, info_dict

youtube_dl/extractor/flipagram.py

@@ -1,115 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    int_or_none,
-    float_or_none,
-    try_get,
-    unified_timestamp,
-)
-
-
-class FlipagramIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'https://flipagram.com/f/nyvTSJMKId',
-        'md5': '888dcf08b7ea671381f00fab74692755',
-        'info_dict': {
-            'id': 'nyvTSJMKId',
-            'ext': 'mp4',
-            'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
-            'description': 'md5:d55e32edc55261cae96a41fa85ff630e',
-            'duration': 35.571,
-            'timestamp': 1461244995,
-            'upload_date': '20160421',
-            'uploader': 'kitty juria',
-            'uploader_id': 'sjuria101',
-            'creator': 'kitty juria',
-            'view_count': int,
-            'like_count': int,
-            'repost_count': int,
-            'comment_count': int,
-            'comments': list,
-            'formats': 'mincount:2',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        video_data = self._parse_json(
-            self._search_regex(
-                r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'),
-            video_id)
-
-        flipagram = video_data['flipagram']
-        video = flipagram['video']
-
-        json_ld = self._search_json_ld(webpage, video_id, default={})
-        title = json_ld.get('title') or flipagram['captionText']
-        description = json_ld.get('description') or flipagram.get('captionText')
-
-        formats = [{
-            'url': video['url'],
-            'width': int_or_none(video.get('width')),
-            'height': int_or_none(video.get('height')),
-            'filesize': int_or_none(video_data.get('size')),
-        }]
-
-        preview_url = try_get(
-            flipagram, lambda x: x['music']['track']['previewUrl'], compat_str)
-        if preview_url:
-            formats.append({
-                'url': preview_url,
-                'ext': 'm4a',
-                'vcodec': 'none',
-            })
-
-        self._sort_formats(formats)
-
-        counts = flipagram.get('counts', {})
-        user = flipagram.get('user', {})
-        video_data = flipagram.get('video', {})
-
-        thumbnails = [{
-            'url': self._proto_relative_url(cover['url']),
-            'width': int_or_none(cover.get('width')),
-            'height': int_or_none(cover.get('height')),
-            'filesize': int_or_none(cover.get('size')),
-        } for cover in flipagram.get('covers', []) if cover.get('url')]
-
-        # Note that this only retrieves comments that are initially loaded.
-        # For videos with large amounts of comments, most won't be retrieved.
-        comments = []
-        for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):
-            text = comment.get('comment')
-            if not text or not isinstance(text, list):
-                continue
-            comments.append({
-                'author': comment.get('user', {}).get('name'),
-                'author_id': comment.get('user', {}).get('username'),
-                'id': comment.get('id'),
-                'text': text[0],
-                'timestamp': unified_timestamp(comment.get('created')),
-            })
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': float_or_none(flipagram.get('duration'), 1000),
-            'thumbnails': thumbnails,
-            'timestamp': unified_timestamp(flipagram.get('iso8601Created')),
-            'uploader': user.get('name'),
-            'uploader_id': user.get('username'),
-            'creator': user.get('name'),
-            'view_count': int_or_none(counts.get('plays')),
-            'like_count': int_or_none(counts.get('likes')),
-            'repost_count': int_or_none(counts.get('reflips')),
-            'comment_count': int_or_none(counts.get('comments')),
-            'comments': comments,
-            'formats': formats,
-        }

youtube_dl/extractor/fox9.py

@@ -1,13 +1,23 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .anvato import AnvatoIE
+from .common import InfoExtractor
 
 
-class FOX9IE(AnvatoIE):
-    _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
-    _TESTS = [{
-        'url': 'http://www.fox9.com/news/215123287-story',
+class FOX9IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id,
+            'Anvato', video_id)
+
+
+class FOX9NewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota',
         'md5': 'd6e1b2572c3bab8a849c9103615dd243',
         'info_dict': {
             'id': '314473',
@@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE):
             'categories': ['News', 'Sports'],
             'tags': ['news', 'video'],
         },
-    }, {
-        'url': 'http://www.fox9.com/news/investigators/214070684-story',
-        'only_matching': True,
-    }]
+    }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        video_id = self._parse_json(
-            self._search_regex(
-                r"this\.videosJson\s*=\s*'(\[.+?\])';",
-                webpage, 'anvato playlist'),
-            video_id)[0]['video']
-
-        return self._get_anvato_videos(
-            'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
-            video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        anvato_id = self._search_regex(
+            r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id')
+        return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9')

youtube_dl/extractor/gameone.py

@@ -1,134 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    xpath_with_ns,
-    parse_iso8601,
-    float_or_none,
-    int_or_none,
-)
-
-NAMESPACE_MAP = {
-    'media': 'http://search.yahoo.com/mrss/',
-}
-
-# URL prefix to download the mp4 files directly instead of streaming via rtmp
-# Credits go to XBox-Maniac
-# http://board.jdownloader.org/showpost.php?p=185835&postcount=31
-RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
-
-
-class GameOneIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
-    _TESTS = [
-        {
-            'url': 'http://www.gameone.de/tv/288',
-            'md5': '136656b7fb4c9cb4a8e2d500651c499b',
-            'info_dict': {
-                'id': '288',
-                'ext': 'mp4',
-                'title': 'Game One - Folge 288',
-                'duration': 1238,
-                'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
-                'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
-                'age_limit': 16,
-                'upload_date': '20140513',
-                'timestamp': 1399980122,
-            }
-        },
-        {
-            'url': 'http://gameone.de/tv/220',
-            'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
-            'info_dict': {
-                'id': '220',
-                'ext': 'mp4',
-                'upload_date': '20120918',
-                'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
-                'timestamp': 1347971451,
-                'title': 'Game One - Folge 220',
-                'duration': 896.62,
-                'age_limit': 16,
-            }
-        }
-
-    ]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        og_video = self._og_search_video_url(webpage, secure=False)
-        description = self._html_search_meta('description', webpage)
-        age_limit = int(
-            self._search_regex(
-                r'age=(\d+)',
-                self._html_search_meta(
-                    'age-de-meta-label',
-                    webpage),
-                'age_limit',
-                '0'))
-        mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')
-
-        mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
-        title = mrss.find('.//item/title').text
-        thumbnail = mrss.find('.//item/image').get('url')
-        timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ')
-        content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
-        content_url = content.get('url')
-
-        content = self._download_xml(
-            content_url,
-            video_id,
-            'Downloading media:content')
-        rendition_items = content.findall('.//rendition')
-        duration = float_or_none(rendition_items[0].get('duration'))
-        formats = [
-            {
-                'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
-                'width': int_or_none(r.get('width')),
-                'height': int_or_none(r.get('height')),
-                'tbr': int_or_none(r.get('bitrate')),
-            }
-            for r in rendition_items
-        ]
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-            'description': description,
-            'age_limit': age_limit,
-            'timestamp': timestamp,
-        }
-
-
-class GameOnePlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
-    IE_NAME = 'gameone:playlist'
-    _TEST = {
-        'url': 'http://www.gameone.de/tv',
-        'info_dict': {
-            'title': 'GameOne',
-        },
-        'playlist_mincount': 294,
-    }
-
-    def _real_extract(self, url):
-        webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
-        max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
-        entries = [
-            self.url_result('http://www.gameone.de/tv/%d' %
-                            video_id, 'GameOne')
-            for video_id in range(max_id, 0, -1)]
-
-        return {
-            '_type': 'playlist',
-            'title': 'GameOne',
-            'entries': entries,
-        }

youtube_dl/extractor/generic.py

@@ -77,11 +77,10 @@ from .instagram import InstagramIE
 from .liveleak import LiveLeakIE
 from .threeqsdn import ThreeQSDNIE
 from .theplatform import ThePlatformIE
-from .vessel import VesselIE
 from .kaltura import KalturaIE
 from .eagleplatform import EaglePlatformIE
 from .facebook import FacebookIE
-from .soundcloud import SoundcloudIE
+from .soundcloud import SoundcloudEmbedIE
 from .tunein import TuneInBaseIE
 from .vbox7 import Vbox7IE
 from .dbtv import DBTVIE
@@ -119,6 +118,7 @@ from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
 from .zype import ZypeIE
+from .odnoklassniki import OdnoklassnikiIE
 
 
 class GenericIE(InfoExtractor):
@@ -2491,11 +2491,6 @@ class GenericIE(InfoExtractor):
         if tp_urls:
             return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
 
-        # Look for Vessel embeds
-        vessel_urls = VesselIE._extract_urls(webpage)
-        if vessel_urls:
-            return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
-
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
@@ -2633,9 +2628,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'VK')
 
         # Look for embedded Odnoklassniki player
-        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
-        if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Odnoklassniki')
+        odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
+        if odnoklassniki_url:
+            return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
 
         # Look for embedded ivi player
         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
@@ -2754,9 +2749,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(myvi_url)
 
         # Look for embedded soundcloud player
-        soundcloud_urls = SoundcloudIE._extract_urls(webpage)
+        soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
         if soundcloud_urls:
-            return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
+            return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
 
         # Look for tunein player
         tunein_urls = TuneInBaseIE._extract_urls(webpage)
@@ -2968,10 +2963,14 @@ class GenericIE(InfoExtractor):
 
         # Look for Mangomolo embeds
         mobj = re.search(
-            r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
+            r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
+                (?:
+                    admin\.mangomolo\.com/analytics/index\.php/customers/embed|
+                    player\.mangomolo\.com/v1
+                )/
                 (?:
                     video\?.*?\bid=(?P<video_id>\d+)|
-                    index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
+                    (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
                 ).+?)\1''', webpage)
         if mobj is not None:
             info = {

youtube_dl/extractor/gfycat.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class GfycatIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#]+)'
+    _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\.]+)'
     _TESTS = [{
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
@@ -53,6 +53,12 @@ class GfycatIE(InfoExtractor):
     }, {
         'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
         'only_matching': True
+    }, {
+        'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
+        'only_matching': True
+    }, {
+        'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
+        'only_matching': True
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/globo.py

@@ -96,21 +96,31 @@ class GloboIE(InfoExtractor):
         video = self._download_json(
             'http://api.globovideos.com/videos/%s/playlist' % video_id,
             video_id)['videos'][0]
+        if video.get('encrypted') is True:
+            raise ExtractorError('This video is DRM protected.', expected=True)
 
         title = video['title']
 
         formats = []
+        subtitles = {}
         for resource in video['resources']:
             resource_id = resource.get('_id')
             resource_url = resource.get('url')
-            if not resource_id or not resource_url:
+            resource_type = resource.get('type')
+            if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'):
+                continue
+
+            if resource_type == 'subtitle':
+                subtitles.setdefault(resource.get('language') or 'por', []).append({
+                    'url': resource_url,
+                })
                 continue
 
             security = self._download_json(
                 'http://security.video.globo.com/videos/%s/hash' % video_id,
                 video_id, 'Downloading security hash for %s' % resource_id, query={
-                    'player': 'flash',
-                    'version': '17.0.0.132',
+                    'player': 'desktop',
+                    'version': '5.19.1',
                     'resource_id': resource_id,
                 })
 
@@ -123,18 +133,23 @@ class GloboIE(InfoExtractor):
                 continue
 
             hash_code = security_hash[:2]
-            received_time = security_hash[2:12]
-            received_random = security_hash[12:22]
-            received_md5 = security_hash[22:]
-
-            sign_time = compat_str(int(received_time) + 86400)
             padding = '%010d' % random.randint(1, 10000000000)
+            if hash_code in ('04', '14'):
+                received_time = security_hash[3:13]
+                received_md5 = security_hash[24:]
+                hash_prefix = security_hash[:23]
+            elif hash_code in ('02', '12', '03', '13'):
+                received_time = security_hash[2:12]
+                received_md5 = security_hash[22:]
+                padding += '1'
+                hash_prefix = '05' + security_hash[:22]
 
-            md5_data = (received_md5 + sign_time + padding + '0xFF01DD').encode()
+            padded_sign_time = compat_str(int(received_time) + 86400) + padding
+            md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode()
             signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=')
-            signed_hash = hash_code + received_time + received_random + sign_time + padding + signed_md5
+            signed_hash = hash_prefix + padded_sign_time + signed_md5
+            signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '')
 
-            signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
             if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
                 formats.extend(self._extract_m3u8_formats(
                     signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
@@ -164,7 +179,8 @@ class GloboIE(InfoExtractor):
             'duration': duration,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'formats': formats
+            'formats': formats,
+            'subtitles': subtitles,
         }
 
 

youtube_dl/extractor/go.py

@@ -40,8 +40,17 @@ class GoIE(AdobePassIE):
             'resource_id': 'Disney',
         }
     }
-    _VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|(?P<sub_domain_2>disneynow))\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
-                 % '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:(?P<sub_domain>%s)\.)?go|
+                            (?P<sub_domain_2>abc|freeform|disneynow)
+                        )\.com/
+                        (?:
+                            (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
+                            (?:[^/]+/)*(?P<display_id>[^/?\#]+)
+                        )
+                    ''' % '|'.join(list(_SITE_INFO.keys()))
     _TESTS = [{
         'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
         'info_dict': {
@@ -54,6 +63,7 @@ class GoIE(AdobePassIE):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': 'This content is no longer available.',
     }, {
         'url': 'http://watchdisneyxd.go.com/doraemon',
         'info_dict': {
@@ -61,6 +71,34 @@ class GoIE(AdobePassIE):
             'id': 'SH55574025',
         },
         'playlist_mincount': 51,
+    }, {
+        'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
+        'info_dict': {
+            'id': 'VDKA3609139',
+            'ext': 'mp4',
+            'title': 'This Guilty Blood',
+            'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
+            'age_limit': 14,
+        },
+        'params': {
+            'geo_bypass_ip_block': '3.244.239.0/24',
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
+        'info_dict': {
+            'id': 'VDKA13435179',
+            'ext': 'mp4',
+            'title': 'The Bet',
+            'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
+            'age_limit': 14,
+        },
+        'params': {
+            'geo_bypass_ip_block': '3.244.239.0/24',
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
         'only_matching': True,
@@ -95,10 +133,13 @@ class GoIE(AdobePassIE):
         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=video_id)
+                (
+                    # 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+)',
+                    # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
+                    r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
+                ), webpage, 'video id', default=video_id)
             if not site_info:
                 brand = self._search_regex(
                     (r'data-brand=\s*["\']\s*(\d+)',

youtube_dl/extractor/go90.py

@@ -1,149 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_HTTPError
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    int_or_none,
-    parse_age_limit,
-    parse_iso8601,
-)
-
-
-class Go90IE(InfoExtractor):
-    _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': {
-            'id': '84BUqjLpf9D',
-            'ext': 'mp4',
-            'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention',
-            'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.',
-            'timestamp': 1491868800,
-            '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)
-
-        try:
-            headers = self.geo_verification_headers()
-            headers.update({
-                'Content-Type': 'application/json; charset=utf-8',
-            })
-            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']
-
-        episode_number = int_or_none(video_data.get('episode_number'))
-        series = None
-        season = None
-        season_id = None
-        season_number = None
-        for metadata in video_data.get('__children', {}).get('Item', {}).values():
-            if metadata.get('type') == 'show':
-                series = metadata.get('title')
-            elif metadata.get('type') == 'season':
-                season = metadata.get('title')
-                season_id = metadata.get('id')
-                season_number = int_or_none(metadata.get('season_number'))
-
-        title = episode = video_data.get('title') or series
-        if series and series != title:
-            title = '%s - %s' % (series, title)
-
-        thumbnails = []
-        formats = []
-        subtitles = {}
-        for asset in video_data.get('assets'):
-            if asset.get('id') == main_video_asset:
-                for source in asset.get('sources', []):
-                    source_location = source.get('location')
-                    if not source_location:
-                        continue
-                    source_type = source.get('type')
-                    if source_type == 'hls':
-                        m3u8_formats = self._extract_m3u8_formats(
-                            source_location, video_id, 'mp4',
-                            'm3u8_native', m3u8_id='hls', fatal=False)
-                        for f in m3u8_formats:
-                            mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url'])
-                            if mobj:
-                                height, tbr = mobj.groups()
-                                height = int_or_none(height)
-                                f.update({
-                                    'height': f.get('height') or height,
-                                    'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None),
-                                    'tbr': f.get('tbr') or int_or_none(tbr),
-                                })
-                        formats.extend(m3u8_formats)
-                    elif source_type == 'dash':
-                        formats.extend(self._extract_mpd_formats(
-                            source_location, video_id, mpd_id='dash', fatal=False))
-                    else:
-                        formats.append({
-                            'format_id': source.get('name'),
-                            'url': source_location,
-                            'width': int_or_none(source.get('width')),
-                            'height': int_or_none(source.get('height')),
-                            'tbr': int_or_none(source.get('bitrate')),
-                        })
-
-                for caption in asset.get('caption_metadata', []):
-                    caption_url = caption.get('source_url')
-                    if not caption_url:
-                        continue
-                    subtitles.setdefault(caption.get('language', 'en'), []).append({
-                        'url': caption_url,
-                        'ext': determine_ext(caption_url, 'vtt'),
-                    })
-            elif asset.get('type') == 'image':
-                asset_location = asset.get('location')
-                if not asset_location:
-                    continue
-                thumbnails.append({
-                    'url': asset_location,
-                    'width': int_or_none(asset.get('width')),
-                    'height': int_or_none(asset.get('height')),
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'thumbnails': thumbnails,
-            'description': video_data.get('short_description'),
-            'like_count': int_or_none(video_data.get('like_count')),
-            'timestamp': parse_iso8601(video_data.get('released_at')),
-            'series': series,
-            'episode': episode,
-            'season': season,
-            'season_id': season_id,
-            'season_number': season_number,
-            'episode_number': episode_number,
-            'subtitles': subtitles,
-            'age_limit': parse_age_limit(video_data.get('rating')),
-        }

youtube_dl/extractor/hark.py

@@ -1,33 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class HarkIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
-    _TEST = {
-        'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
-        'md5': '6783a58491b47b92c7c1af5a77d4cbee',
-        'info_dict': {
-            'id': 'mmbzyhkgny',
-            'ext': 'mp3',
-            'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
-            'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
-            'duration': 11,
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        data = self._download_json(
-            'http://www.hark.com/clips/%s.json' % video_id, video_id)
-
-        return {
-            'id': video_id,
-            'url': data['url'],
-            'title': data['name'],
-            'description': data.get('description'),
-            'thumbnail': data.get('image_original'),
-            'duration': data.get('duration'),
-        }

youtube_dl/extractor/heise.py

@@ -105,8 +105,7 @@ class HeiseIE(InfoExtractor):
             webpage, default=None) or self._html_search_meta(
             'description', webpage)
 
-        kaltura_url = KalturaIE._extract_url(webpage)
-        if kaltura_url:
+        def _make_kaltura_result(kaltura_url):
             return {
                 '_type': 'url_transparent',
                 'url': smuggle_url(kaltura_url, {'source_url': url}),
@@ -115,6 +114,16 @@ class HeiseIE(InfoExtractor):
                 'description': description,
             }
 
+        kaltura_url = KalturaIE._extract_url(webpage)
+        if kaltura_url:
+            return _make_kaltura_result(kaltura_url)
+
+        kaltura_id = self._search_regex(
+            r'entry-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'kaltura id',
+            default=None, group='id')
+        if kaltura_id:
+            return _make_kaltura_result('kaltura:2238431:%s' % kaltura_id)
+
         yt_urls = YoutubeIE._extract_urls(webpage)
         if yt_urls:
             return self.playlist_from_matches(

youtube_dl/extractor/hotstar.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 import hashlib
 import hmac
+import re
 import time
 import uuid
 
@@ -126,6 +127,8 @@ class HotStarIE(HotStarBaseIE):
             format_url = url_or_none(playback_set.get('playbackUrl'))
             if not format_url:
                 continue
+            format_url = re.sub(
+                r'(?<=//staragvod)(\d)', r'web\1', format_url)
             tags = str_or_none(playback_set.get('tagsCombination')) or ''
             if tags and 'encryption:plain' not in tags:
                 continue
@@ -133,7 +136,8 @@ class HotStarIE(HotStarBaseIE):
             try:
                 if 'package:hls' in tags or ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        format_url, video_id, 'mp4', m3u8_id='hls'))
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls'))
                 elif 'package:dash' in tags or ext == 'mpd':
                     formats.extend(self._extract_mpd_formats(
                         format_url, video_id, mpd_id='dash'))

youtube_dl/extractor/iconosquare.py

@@ -1,85 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    get_element_by_id,
-    remove_end,
-)
-
-
-class IconosquareIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
-    _TEST = {
-        'url': 'http://statigr.am/p/522207370455279102_24101272',
-        'md5': '6eb93b882a3ded7c378ee1d6884b1814',
-        'info_dict': {
-            'id': '522207370455279102_24101272',
-            'ext': 'mp4',
-            'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
-            'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
-            'timestamp': 1376471991,
-            'upload_date': '20130814',
-            'uploader': 'aguynamedpatrick',
-            'uploader_id': '24101272',
-            'comment_count': int,
-            'like_count': int,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        media = self._parse_json(
-            get_element_by_id('mediaJson', webpage),
-            video_id)
-
-        formats = [{
-            'url': f['url'],
-            'format_id': format_id,
-            'width': int_or_none(f.get('width')),
-            'height': int_or_none(f.get('height'))
-        } for format_id, f in media['videos'].items()]
-        self._sort_formats(formats)
-
-        title = remove_end(self._og_search_title(webpage), ' - via Iconosquare')
-
-        timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
-        description = media.get('caption', {}).get('text')
-
-        uploader = media.get('user', {}).get('username')
-        uploader_id = media.get('user', {}).get('id')
-
-        comment_count = int_or_none(media.get('comments', {}).get('count'))
-        like_count = int_or_none(media.get('likes', {}).get('count'))
-
-        thumbnails = [{
-            'url': t['url'],
-            'id': thumbnail_id,
-            'width': int_or_none(t.get('width')),
-            'height': int_or_none(t.get('height'))
-        } for thumbnail_id, t in media.get('images', {}).items()]
-
-        comments = [{
-            'id': comment.get('id'),
-            'text': comment['text'],
-            'timestamp': int_or_none(comment.get('created_time')),
-            'author': comment.get('from', {}).get('full_name'),
-            'author_id': comment.get('from', {}).get('username'),
-        } for comment in media.get('comments', {}).get('data', []) if 'text' in comment]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnails': thumbnails,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'comment_count': comment_count,
-            'like_count': like_count,
-            'formats': formats,
-            'comments': comments,
-        }

youtube_dl/extractor/instagram.py

@@ -22,7 +22,7 @@ from ..utils import (
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+))'
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/(?:p|tv)/(?P<id>[^/?#&]+))'
     _TESTS = [{
         'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
@@ -92,6 +92,9 @@ class InstagramIE(InfoExtractor):
     }, {
         'url': 'http://instagram.com/p/9o6LshA7zy/embed/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.instagram.com/tv/aye83DjauH/',
+        'only_matching': True,
     }]
 
     @staticmethod

youtube_dl/extractor/internetvideoarchive.py

@@ -1,15 +1,13 @@
 from __future__ import unicode_literals
 
+import json
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urlparse,
 )
-from ..utils import (
-    determine_ext,
-    int_or_none,
-    xpath_text,
-)
 
 
 class InternetVideoArchiveIE(InfoExtractor):
@@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor):
         'info_dict': {
             'id': '194487',
             'ext': 'mp4',
-            'title': 'KICK-ASS 2',
+            'title': 'Kick-Ass 2',
             'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
         },
         'params': {
@@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor):
     def _build_json_url(query):
         return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query
 
-    @staticmethod
-    def _build_xml_url(query):
-        return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query
-
     def _real_extract(self, url):
-        query = compat_urlparse.urlparse(url).query
-        query_dic = compat_parse_qs(query)
-        video_id = query_dic['publishedid'][0]
-
-        if '/player/' in url:
-            configuration = self._download_json(url, video_id)
-
-            # There are multiple videos in the playlist whlie only the first one
-            # matches the video played in browsers
-            video_info = configuration['playlist'][0]
-            title = video_info['title']
-
-            formats = []
-            for source in video_info['sources']:
-                file_url = source['file']
-                if determine_ext(file_url) == 'm3u8':
-                    m3u8_formats = self._extract_m3u8_formats(
-                        file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
-                    if m3u8_formats:
-                        formats.extend(m3u8_formats)
-                        file_url = m3u8_formats[0]['url']
-                        formats.extend(self._extract_f4m_formats(
-                            file_url.replace('.m3u8', '.f4m'),
-                            video_id, f4m_id='hds', fatal=False))
-                        formats.extend(self._extract_mpd_formats(
-                            file_url.replace('.m3u8', '.mpd'),
-                            video_id, mpd_id='dash', fatal=False))
-                else:
-                    a_format = {
-                        'url': file_url,
-                    }
-
-                    if source.get('label') and source['label'][-4:] == ' kbs':
-                        tbr = int_or_none(source['label'][:-4])
-                        a_format.update({
-                            'tbr': tbr,
-                            'format_id': 'http-%d' % tbr,
-                        })
-                        formats.append(a_format)
-
-            self._sort_formats(formats)
-
-            description = video_info.get('description')
-            thumbnail = video_info.get('image')
-        else:
-            configuration = self._download_xml(url, video_id)
-            formats = [{
-                'url': xpath_text(configuration, './file', 'file URL', fatal=True),
-            }]
-            thumbnail = xpath_text(configuration, './image', 'thumbnail')
-            title = 'InternetVideoArchive video %s' % video_id
-            description = None
+        query = compat_parse_qs(compat_urlparse.urlparse(url).query)
+        video_id = query['publishedid'][0]
+        data = self._download_json(
+            'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx',
+            video_id, data=json.dumps({
+                'customerid': query['customerid'][0],
+                'publishedid': video_id,
+            }).encode())
+        title = data['Title']
+        formats = self._extract_m3u8_formats(
+            data['VideoUrl'], video_id, 'mp4',
+            'm3u8_native', m3u8_id='hls', fatal=False)
+        file_url = formats[0]['url']
+        if '.ism/' in file_url:
+            replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url)
+            formats.extend(self._extract_f4m_formats(
+                replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
+            formats.extend(self._extract_mpd_formats(
+                replace_url('.mpd'), video_id, mpd_id='dash', fatal=False))
+            formats.extend(self._extract_ism_formats(
+                replace_url('Manifest'), video_id, ism_id='mss', fatal=False))
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
-            'thumbnail': thumbnail,
-            'description': description,
+            'thumbnail': data.get('PosterUrl'),
+            'description': data.get('Description'),
         }

youtube_dl/extractor/jamendo.py

@@ -1,38 +1,26 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import hashlib
+import random
 
-from ..compat import compat_urlparse
+from ..compat import compat_str
 from .common import InfoExtractor
-from ..utils import parse_duration
+from ..utils import (
+    clean_html,
+    int_or_none,
+    try_get,
+)
 
 
-class JamendoBaseIE(InfoExtractor):
-    def _extract_meta(self, webpage, fatal=True):
-        title = self._og_search_title(
-            webpage, default=None) or self._search_regex(
-            r'<title>([^<]+)', webpage,
-            'title', default=None)
-        if title:
-            title = self._search_regex(
-                r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
-        if not title:
-            title = self._html_search_meta(
-                'name', webpage, 'title', fatal=fatal)
-        mobj = re.search(r'(.+) - (.+)', title or '')
-        artist, second = mobj.groups() if mobj else [None] * 2
-        return title, artist, second
-
-
-class JamendoIE(JamendoBaseIE):
+class JamendoIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
                             licensing\.jamendo\.com/[^/]+|
                             (?:www\.)?jamendo\.com
                         )
-                        /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)
+                        /track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))?
                     '''
     _TESTS = [{
         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
@@ -45,7 +33,9 @@ class JamendoIE(JamendoBaseIE):
             'artist': 'Maya Filipič',
             'track': 'Stories from Emona I',
             'duration': 210,
-            'thumbnail': r're:^https?://.*\.jpg'
+            'thumbnail': r're:^https?://.*\.jpg',
+            'timestamp': 1217438117,
+            'upload_date': '20080730',
         }
     }, {
         'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
@@ -53,15 +43,20 @@ class JamendoIE(JamendoBaseIE):
     }]
 
     def _real_extract(self, url):
-        mobj = self._VALID_URL_RE.match(url)
-        track_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
+        track_id, display_id = self._VALID_URL_RE.match(url).groups()
         webpage = self._download_webpage(
-            'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
-            display_id)
-
-        title, artist, track = self._extract_meta(webpage)
+            'https://www.jamendo.com/track/' + track_id, track_id)
+        models = self._parse_json(self._html_search_regex(
+            r"data-bundled-models='([^']+)",
+            webpage, 'bundled models'), track_id)
+        track = models['track']['models'][0]
+        title = track_name = track['name']
+        get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
+        artist = get_model('artist')
+        artist_name = artist.get('name')
+        if artist_name:
+            title = '%s - %s' % (artist_name, title)
+        album = get_model('album')
 
         formats = [{
             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@@ -77,31 +72,58 @@ class JamendoIE(JamendoBaseIE):
         ))]
         self._sort_formats(formats)
 
-        thumbnail = self._html_search_meta(
-            'image', webpage, 'thumbnail', fatal=False)
-        duration = parse_duration(self._search_regex(
-            r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
-            webpage, 'duration', fatal=False))
+        urls = []
+        thumbnails = []
+        for _, covers in track.get('cover', {}).items():
+            for cover_id, cover_url in covers.items():
+                if not cover_url or cover_url in urls:
+                    continue
+                urls.append(cover_url)
+                size = int_or_none(cover_id.lstrip('size'))
+                thumbnails.append({
+                    'id': cover_id,
+                    'url': cover_url,
+                    'width': size,
+                    'height': size,
+                })
+
+        tags = []
+        for tag in track.get('tags', []):
+            tag_name = tag.get('name')
+            if not tag_name:
+                continue
+            tags.append(tag_name)
+
+        stats = track.get('stats') or {}
 
         return {
             'id': track_id,
             'display_id': display_id,
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'title': title,
-            'duration': duration,
-            'artist': artist,
-            'track': track,
-            'formats': formats
+            'description': track.get('description'),
+            'duration': int_or_none(track.get('duration')),
+            'artist': artist_name,
+            'track': track_name,
+            'album': album.get('name'),
+            'formats': formats,
+            'license': '-'.join(track.get('licenseCC', [])) or None,
+            'timestamp': int_or_none(track.get('dateCreated')),
+            'view_count': int_or_none(stats.get('listenedAll')),
+            'like_count': int_or_none(stats.get('favorited')),
+            'average_rating': int_or_none(stats.get('averageNote')),
+            'tags': tags,
         }
 
 
-class JamendoAlbumIE(JamendoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
+class JamendoAlbumIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
         'info_dict': {
             'id': '121486',
-            'title': 'Shearer - Duck On Cover'
+            'title': 'Duck On Cover',
+            'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239',
         },
         'playlist': [{
             'md5': 'e1a2fcb42bda30dfac990212924149a8',
@@ -111,6 +133,8 @@ class JamendoAlbumIE(JamendoBaseIE):
                 'title': 'Shearer - Warmachine',
                 'artist': 'Shearer',
                 'track': 'Warmachine',
+                'timestamp': 1368089771,
+                'upload_date': '20130509',
             }
         }, {
             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
@@ -120,6 +144,8 @@ class JamendoAlbumIE(JamendoBaseIE):
                 'title': 'Shearer - Without Your Ghost',
                 'artist': 'Shearer',
                 'track': 'Without Your Ghost',
+                'timestamp': 1368089771,
+                'upload_date': '20130509',
             }
         }],
         'params': {
@@ -127,24 +153,35 @@ class JamendoAlbumIE(JamendoBaseIE):
         }
     }
 
+    def _call_api(self, resource, resource_id):
+        path = '/api/%ss' % resource
+        rand = compat_str(random.random())
+        return self._download_json(
+            'https://www.jamendo.com' + path, resource_id, query={
+                'id[]': resource_id,
+            }, headers={
+                'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
+            })[0]
+
     def _real_extract(self, url):
-        mobj = self._VALID_URL_RE.match(url)
-        album_id = mobj.group('id')
+        album_id = self._match_id(url)
+        album = self._call_api('album', album_id)
+        album_name = album.get('name')
 
-        webpage = self._download_webpage(url, mobj.group('display_id'))
+        entries = []
+        for track in album.get('tracks', []):
+            track_id = track.get('id')
+            if not track_id:
+                continue
+            track_id = compat_str(track_id)
+            entries.append({
+                '_type': 'url_transparent',
+                'url': 'https://www.jamendo.com/track/' + track_id,
+                'ie_key': JamendoIE.ie_key(),
+                'id': track_id,
+                'album': album_name,
+            })
 
-        title, artist, album = self._extract_meta(webpage, fatal=False)
-
-        entries = [{
-            '_type': 'url_transparent',
-            'url': compat_urlparse.urljoin(url, m.group('path')),
-            'ie_key': JamendoIE.ie_key(),
-            'id': self._search_regex(
-                r'/track/(\d+)', m.group('path'), 'track id', default=None),
-            'artist': artist,
-            'album': album,
-        } for m in re.finditer(
-            r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
-            webpage)]
-
-        return self.playlist_result(entries, album_id, title)
+        return self.playlist_result(
+            entries, album_id, album_name,
+            clean_html(try_get(album, lambda x: x['description']['en'], compat_str)))

youtube_dl/extractor/jwplatform.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class JWPlatformIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
+    _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
     _TESTS = [{
         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',

youtube_dl/extractor/kakao.py

@@ -6,14 +6,15 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    strip_or_none,
     unified_timestamp,
     update_url_query,
 )
 
 
 class KakaoIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)'
-    _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks'
+    _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
+    _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/'
 
     _TESTS = [{
         'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
@@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor):
             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
             'uploader_id': 2653210,
-            'uploader': '쇼 음악중심',
+            'uploader': '쇼! 음악중심',
             'timestamp': 1485684628,
             'upload_date': '20170129',
         }
@@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        display_id = video_id.rstrip('@my')
+        api_base = self._API_BASE_TMPL % video_id
 
         player_header = {
             'Referer': update_url_query(
@@ -55,20 +58,23 @@ class KakaoIE(InfoExtractor):
                 })
         }
 
-        QUERY_COMMON = {
+        query = {
             'player': 'monet_html5',
             'referer': url,
             'uuid': '',
             'service': 'kakao_tv',
             'section': '',
             'dteType': 'PC',
+            'fields': ','.join([
+                '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
+                'description', 'channelId', 'createTime', 'duration', 'playCount',
+                'likeCount', 'commentCount', 'tagList', 'channel', 'name',
+                'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
+                'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
         }
 
-        query = QUERY_COMMON.copy()
-        query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList'
         impress = self._download_json(
-            '%s/%s/impress' % (self._API_BASE, video_id),
-            video_id, 'Downloading video info',
+            api_base + 'impress', display_id, 'Downloading video info',
             query=query, headers=player_header)
 
         clip_link = impress['clipLink']
@@ -76,32 +82,22 @@ class KakaoIE(InfoExtractor):
 
         title = clip.get('title') or clip_link.get('displayTitle')
 
-        tid = impress.get('tid', '')
-
-        query = QUERY_COMMON.copy()
-        query.update({
-            'tid': tid,
-            'profile': 'HIGH',
-        })
-        raw = self._download_json(
-            '%s/%s/raw' % (self._API_BASE, video_id),
-            video_id, 'Downloading video formats info',
-            query=query, headers=player_header)
+        query['tid'] = impress.get('tid', '')
 
         formats = []
-        for fmt in raw.get('outputList', []):
+        for fmt in clip.get('videoOutputList', []):
             try:
                 profile_name = fmt['profile']
+                if profile_name == 'AUDIO':
+                    continue
+                query.update({
+                    'profile': profile_name,
+                    'fields': '-*,url',
+                })
                 fmt_url_json = self._download_json(
-                    '%s/%s/raw/videolocation' % (self._API_BASE, video_id),
-                    video_id,
+                    api_base + 'raw/videolocation', display_id,
                     'Downloading video URL for profile %s' % profile_name,
-                    query={
-                        'service': 'kakao_tv',
-                        'section': '',
-                        'tid': tid,
-                        'profile': profile_name
-                    }, headers=player_header, fatal=False)
+                    query=query, headers=player_header, fatal=False)
 
                 if fmt_url_json is None:
                     continue
@@ -113,7 +109,8 @@ class KakaoIE(InfoExtractor):
                     'width': int_or_none(fmt.get('width')),
                     'height': int_or_none(fmt.get('height')),
                     'format_note': fmt.get('label'),
-                    'filesize': int_or_none(fmt.get('filesize'))
+                    'filesize': int_or_none(fmt.get('filesize')),
+                    'tbr': int_or_none(fmt.get('kbps')),
                 })
             except KeyError:
                 pass
@@ -134,9 +131,9 @@ class KakaoIE(InfoExtractor):
             })
 
         return {
-            'id': video_id,
+            'id': display_id,
             'title': title,
-            'description': clip.get('description'),
+            'description': strip_or_none(clip.get('description')),
             'uploader': clip_link.get('channel', {}).get('name'),
             'uploader_id': clip_link.get('channelId'),
             'thumbnails': thumbs,
@@ -146,4 +143,5 @@ class KakaoIE(InfoExtractor):
             'like_count': int_or_none(clip.get('likeCount')),
             'comment_count': int_or_none(clip.get('commentCount')),
             'formats': formats,
+            'tags': clip.get('tagList'),
         }

youtube_dl/extractor/kaltura.py

@@ -151,14 +151,15 @@ class KalturaIE(InfoExtractor):
         if mobj:
             embed_info = mobj.groupdict()
             for k, v in embed_info.items():
-                embed_info[k] = v.strip()
+                if v:
+                    embed_info[k] = v.strip()
             url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
             escaped_pid = re.escape(embed_info['partner_id'])
-            service_url = re.search(
-                r'<script[^>]+src=["\']((?:https?:)?//.+?)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
+            service_mobj = re.search(
+                r'<script[^>]+src=(["\'])(?P<id>(?:https?:)?//(?:(?!\1).)+)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
                 webpage)
-            if service_url:
-                url = smuggle_url(url, {'service_url': service_url.group(1)})
+            if service_mobj:
+                url = smuggle_url(url, {'service_url': service_mobj.group('id')})
             return url
 
     def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):

youtube_dl/extractor/keek.py

@@ -1,39 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class KeekIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)'
-    IE_NAME = 'keek'
-    _TEST = {
-        'url': 'https://www.keek.com/keek/NODfbab',
-        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
-        'info_dict': {
-            'id': 'NODfbab',
-            'ext': 'mp4',
-            'title': 'md5:35d42050a3ece241d5ddd7fdcc6fd896',
-            'uploader': 'ytdl',
-            'uploader_id': 'eGT5bab',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        return {
-            'id': video_id,
-            'url': self._og_search_video_url(webpage),
-            'ext': 'mp4',
-            'title': self._og_search_description(webpage).strip(),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': self._search_regex(
-                r'data-username=(["\'])(?P<uploader>.+?)\1', webpage,
-                'uploader', fatal=False, group='uploader'),
-            'uploader_id': self._search_regex(
-                r'data-user-id=(["\'])(?P<uploader_id>.+?)\1', webpage,
-                'uploader id', fatal=False, group='uploader_id'),
-        }

youtube_dl/extractor/la7.py

@@ -20,7 +20,7 @@ class LA7IE(InfoExtractor):
         'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722',
         'md5': '8b613ffc0c4bf9b9e377169fc19c214c',
         'info_dict': {
-            'id': 'inccool8-02-10-2015-163722',
+            'id': '0_42j6wd36',
             'ext': 'mp4',
             'title': 'Inc.Cool8',
             'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto  atletico',
@@ -57,7 +57,7 @@ class LA7IE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'url': smuggle_url('kaltura:103:%s' % player_data['vid'], {
-                'service_url': 'http://kdam.iltrovatore.it',
+                'service_url': 'http://nkdam.iltrovatore.it',
             }),
             'id': video_id,
             'title': player_data['title'],

youtube_dl/extractor/learnr.py

@@ -1,33 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class LearnrIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?learnr\.pro/view/video/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.learnr.pro/view/video/51624-web-development-tutorial-for-beginners-1-how-to-build-webpages-with-html-css-javascript',
-        'md5': '3719fdf0a68397f49899e82c308a89de',
-        'info_dict': {
-            'id': '51624',
-            'ext': 'mp4',
-            'title': 'Web Development Tutorial for Beginners (#1) - How to build webpages with HTML, CSS, Javascript',
-            'description': 'md5:b36dbfa92350176cdf12b4d388485503',
-            'uploader': 'LearnCode.academy',
-            'uploader_id': 'learncodeacademy',
-            'upload_date': '20131021',
-        },
-        'add_ie': ['Youtube'],
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        return {
-            '_type': 'url_transparent',
-            'url': self._search_regex(
-                r"videoId\s*:\s*'([^']+)'", webpage, 'youtube id'),
-            'id': video_id,
-        }

youtube_dl/extractor/macgamestore.py

@@ -1,42 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import ExtractorError
-
-
-class MacGameStoreIE(InfoExtractor):
-    IE_NAME = 'macgamestore'
-    IE_DESC = 'MacGameStore trailers'
-    _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
-
-    _TEST = {
-        'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
-        'md5': '8649b8ea684b6666b4c5be736ecddc61',
-        'info_dict': {
-            'id': '2450',
-            'ext': 'm4v',
-            'title': 'Crow',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            url, video_id, 'Downloading trailer page')
-
-        if '>Missing Media<' in webpage:
-            raise ExtractorError(
-                'Trailer %s does not exist' % video_id, expected=True)
-
-        video_title = self._html_search_regex(
-            r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
-
-        video_url = self._html_search_regex(
-            r'(?s)<div\s+id="video-player".*?href="([^"]+)"\s*>',
-            webpage, 'video URL')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': video_title
-        }

youtube_dl/extractor/makertv.py

@@ -1,32 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class MakerTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})'
-    _TEST = {
-        'url': 'http://www.maker.tv/video/Fh3QgymL9gsc',
-        'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
-        'info_dict': {
-            'id': 'Fh3QgymL9gsc',
-            'ext': 'mp4',
-            'title': 'Maze Runner: The Scorch Trials Official Movie Review',
-            'description': 'md5:11ff3362d7ef1d679fdb649f6413975a',
-            'upload_date': '20150918',
-            'timestamp': 1442549540,
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id')
-
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': 'jwplatform:%s' % jwplatform_id,
-            'ie_key': 'JWPlatform',
-        }

youtube_dl/extractor/mangomolo.py

@@ -10,18 +10,21 @@ from ..utils import int_or_none
 
 
 class MangomoloBaseIE(InfoExtractor):
+    _BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
+
     def _get_real_id(self, page_id):
         return page_id
 
     def _real_extract(self, url):
         page_id = self._get_real_id(self._match_id(url))
-        webpage = self._download_webpage(url, page_id)
+        webpage = self._download_webpage(
+            'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id)
         hidden_inputs = self._hidden_inputs(webpage)
         m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
 
         format_url = self._html_search_regex(
             [
-                r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
+                r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
                 r'<a[^>]+href="(rtsp://[^"]+)"'
             ], webpage, 'format url')
         formats = self._extract_wowza_formats(
@@ -39,14 +42,16 @@ class MangomoloBaseIE(InfoExtractor):
 
 
 class MangomoloVideoIE(MangomoloBaseIE):
-    IE_NAME = 'mangomolo:video'
-    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)'
+    _TYPE = 'video'
+    IE_NAME = 'mangomolo:' + _TYPE
+    _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)'
     _IS_LIVE = False
 
 
 class MangomoloLiveIE(MangomoloBaseIE):
-    IE_NAME = 'mangomolo:live'
-    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
+    _TYPE = 'live'
+    IE_NAME = 'mangomolo:' + _TYPE
+    _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
     _IS_LIVE = True
 
     def _get_real_id(self, page_id):

youtube_dl/extractor/mediaset.py

@@ -27,7 +27,7 @@ class MediasetIE(ThePlatformBaseIE):
                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
                                 player/index\.html\?.*?\bprogramGuid=
                             )
-                    )(?P<id>[0-9A-Z]{16})
+                    )(?P<id>[0-9A-Z]{16,})
                     '''
     _TESTS = [{
         # full episode
@@ -62,7 +62,6 @@ class MediasetIE(ThePlatformBaseIE):
             'uploader': 'Canale 5',
             'uploader_id': 'C5',
         },
-        'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
         # clip
         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
@@ -78,6 +77,18 @@ class MediasetIE(ThePlatformBaseIE):
     }, {
         'url': 'mediaset:FAFU000000665924',
         'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -109,6 +120,11 @@ class MediasetIE(ThePlatformBaseIE):
                 entries.append(embed_url)
         return entries
 
+    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
+        for video in smil.findall(self._xpath_ns('.//video', namespace)):
+            video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
+        return super()._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
+
     def _real_extract(self, url):
         guid = self._match_id(url)
         tp_path = 'PR1GhC/media/guid/2702976343/' + guid
@@ -118,14 +134,15 @@ class MediasetIE(ThePlatformBaseIE):
         subtitles = {}
         first_e = None
         for asset_type in ('SD', 'HD'):
-            for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
+            # TODO: fixup ISM+none manifest URLs
+            for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
                 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))
+                        }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type))
                 except ExtractorError as e:
                     if not first_e:
                         first_e = e

youtube_dl/extractor/mit.py

@@ -65,30 +65,6 @@ class TechTVMITIE(InfoExtractor):
         }
 
 
-class MITIE(TechTVMITIE):
-    IE_NAME = 'video.mit.edu'
-    _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
-
-    _TEST = {
-        'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        'md5': '7db01d5ccc1895fc5010e9c9e13648da',
-        'info_dict': {
-            'id': '21783',
-            'ext': 'mp4',
-            'title': 'The Government is Profiling You',
-            'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
-        },
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_title = mobj.group('title')
-        webpage = self._download_webpage(url, page_title)
-        embed_url = self._search_regex(
-            r'<iframe .*?src="(.+?)"', webpage, 'embed url')
-        return self.url_result(embed_url)
-
-
 class OCWMITIE(InfoExtractor):
     IE_NAME = 'ocw.mit.edu'
     _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'

youtube_dl/extractor/mixcloud.py

@@ -86,9 +86,10 @@ class MixcloudIE(InfoExtractor):
                 r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>',
                 webpage, 'play info'), 'play info')
             for item in full_info_json:
-                item_data = try_get(
-                    item, lambda x: x['cloudcast']['data']['cloudcastLookup'],
-                    dict)
+                item_data = try_get(item, [
+                    lambda x: x['cloudcast']['data']['cloudcastLookup'],
+                    lambda x: x['cloudcastLookup']['data']['cloudcastLookup'],
+                ], dict)
                 if try_get(item_data, lambda x: x['streamInfo']['url']):
                     info_json = item_data
                     break
@@ -164,7 +165,7 @@ class MixcloudIE(InfoExtractor):
             def decrypt_url(f_url):
                 for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'):
                     decrypted_url = self._decrypt_xor_cipher(k, f_url)
-                    if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url):
+                    if re.search(r'^https?://[0-9A-Za-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url):
                         return decrypted_url
 
             for url_key in ('url', 'hlsUrl', 'dashUrl'):

youtube_dl/extractor/msn.py

@@ -41,6 +41,14 @@ class MSNIE(InfoExtractor):
     }, {
         'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6',
         'only_matching': True,
+    }, {
+        # Vidible(AOL) Embed
+        'url': 'https://www.msn.com/en-us/video/animals/yellowstone-park-staffers-catch-deer-engaged-in-behavior-they-cant-explain/vi-AAGfdg1',
+        'only_matching': True,
+    }, {
+        # Dailymotion Embed
+        'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -61,6 +69,18 @@ class MSNIE(InfoExtractor):
                 webpage, 'error', group='error'))
             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 
+        player_name = video.get('playerName')
+        if player_name:
+            provider_id = video.get('providerId')
+            if provider_id:
+                if player_name == 'AOL':
+                    return self.url_result(
+                        'aol-video:' + provider_id, 'Aol', provider_id)
+                elif player_name == 'Dailymotion':
+                    return self.url_result(
+                        'https://www.dailymotion.com/video/' + provider_id,
+                        'Dailymotion', provider_id)
+
         title = video['title']
 
         formats = []

youtube_dl/extractor/mtv.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor):
     }]
 
 
-class MTV81IE(InfoExtractor):
-    IE_NAME = 'mtv81'
-    _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)'
+class MTVJapanIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtvjapan'
+    _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
 
     _TEST = {
-        'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/',
-        'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
+        'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
         'info_dict': {
-            'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
+            'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
             'ext': 'mp4',
-            'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
-            'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
-            'timestamp': 1468846800,
-            'upload_date': '20160718',
+            'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
+        },
+        'params': {
+            'skip_download': True,
         },
     }
+    _GEO_COUNTRIES = ['JP']
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
 
-    def _extract_mgid(self, webpage):
-        return self._search_regex(
-            r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage,
-            'mgid', group='id')
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        mgid = self._extract_mgid(webpage)
-        return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
+    def _get_feed_query(self, uri):
+        return {
+            'arcEp': 'mtvjapan.com',
+            'mgid': uri,
+        }
 
 
 class MTVVideoIE(MTVServicesInfoExtractor):
@@ -425,14 +422,14 @@ class MTVVideoIE(MTVServicesInfoExtractor):
 
 class MTVDEIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtv.de'
-    _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
     _TESTS = [{
-        'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
+        'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
         'info_dict': {
-            'id': 'music_video-a50bc5f0b3aa4b3190aa',
-            'ext': 'flv',
-            'title': 'MusicVideo_cro-traum',
-            'description': 'Cro - Traum',
+            'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
+            'ext': 'mp4',
+            'title': 'Traum',
+            'description': 'Traum',
         },
         'params': {
             # rtmp download
@@ -441,11 +438,12 @@ class MTVDEIE(MTVServicesInfoExtractor):
         'skip': 'Blocked at Travis CI',
     }, {
         # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
-        'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
+        'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
         'info_dict': {
-            'id': 'local_playlist-f5ae778b9832cc837189',
-            'ext': 'flv',
-            'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
+            'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
+            'ext': 'mp4',
+            'title': 'Teen Mom 2',
+            'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
         },
         'params': {
             # rtmp download
@@ -453,7 +451,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
         },
         'skip': 'Blocked at Travis CI',
     }, {
-        'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
+        'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
         'info_dict': {
             'id': 'local_playlist-4e760566473c4c8c5344',
             'ext': 'mp4',
@@ -466,25 +464,11 @@ class MTVDEIE(MTVServicesInfoExtractor):
         },
         'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
     }]
+    _GEO_COUNTRIES = ['DE']
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        playlist = self._parse_json(
-            self._search_regex(
-                r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
-            video_id)
-
-        def _mrss_url(item):
-            return item['mrss'] + item.get('mrssvars', '')
-
-        # news pages contain single video in playlist with different id
-        if len(playlist) == 1:
-            return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
-
-        for item in playlist:
-            item_id = item.get('id')
-            if item_id and compat_str(item_id) == video_id:
-                return self._get_videos_info_from_url(_mrss_url(item), video_id)
+    def _get_feed_query(self, uri):
+        return {
+            'arcEp': 'mtv.de',
+            'mgid': uri,
+        }

youtube_dl/extractor/myspass.py

@@ -1,73 +1,56 @@
+# coding: utf-8
 from __future__ import unicode_literals
-import os.path
+
+import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlparse,
-)
+from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
+    int_or_none,
+    parse_duration,
+    xpath_text,
 )
 
 
 class MySpassIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
+    _VALID_URL = r'https?://(?:www\.)?myspass\.de/([^/]+/)*(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
         'md5': '0b49f4844a068f8b33f4b7c88405862b',
         'info_dict': {
             'id': '11741',
             'ext': 'mp4',
-            'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
-            'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2',
+            'description': 'Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
+            'title': '17.02.2013 - Die Highlights, Teil 2',
         },
     }
 
     def _real_extract(self, url):
-        META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+        video_id = self._match_id(url)
 
-        # video id is the last path element of the URL
-        # usually there is a trailing slash, so also try the second but last
-        url_path = compat_urllib_parse_urlparse(url).path
-        url_parent_path, video_id = os.path.split(url_path)
-        if not video_id:
-            _, video_id = os.path.split(url_parent_path)
-
-        # get metadata
-        metadata_url = META_DATA_URL_TEMPLATE % video_id
         metadata = self._download_xml(
-            metadata_url, video_id, transform_source=lambda s: s.strip())
+            'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=' + video_id,
+            video_id)
 
-        # extract values from metadata
-        url_flv_el = metadata.find('url_flv')
-        if url_flv_el is None:
-            raise ExtractorError('Unable to extract download url')
-        video_url = url_flv_el.text
-        title_el = metadata.find('title')
-        if title_el is None:
-            raise ExtractorError('Unable to extract title')
-        title = title_el.text
-        format_id_el = metadata.find('format_id')
-        if format_id_el is None:
-            format = 'mp4'
-        else:
-            format = format_id_el.text
-        description_el = metadata.find('description')
-        if description_el is not None:
-            description = description_el.text
-        else:
-            description = None
-        imagePreview_el = metadata.find('imagePreview')
-        if imagePreview_el is not None:
-            thumbnail = imagePreview_el.text
-        else:
-            thumbnail = None
+        title = xpath_text(metadata, 'title', fatal=True)
+        video_url = xpath_text(metadata, 'url_flv', 'download url', True)
+        video_id_int = int(video_id)
+        for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
+            group_int = int(group)
+            if group_int > video_id_int:
+                video_url = video_url.replace(
+                    group, compat_str(group_int // video_id_int))
 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
-            'format': format,
-            'thumbnail': thumbnail,
-            'description': description,
+            'thumbnail': xpath_text(metadata, 'imagePreview'),
+            'description': xpath_text(metadata, 'description'),
+            'duration': parse_duration(xpath_text(metadata, 'duration')),
+            'series': xpath_text(metadata, 'format'),
+            'season_number': int_or_none(xpath_text(metadata, 'season')),
+            'season_id': xpath_text(metadata, 'season_id'),
+            'episode': title,
+            'episode_number': int_or_none(xpath_text(metadata, 'episode')),
         }

youtube_dl/extractor/nbc.py

@@ -9,10 +9,13 @@ from .theplatform import ThePlatformIE
 from .adobepass import AdobePassIE
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
+    int_or_none,
+    js_to_json,
+    parse_duration,
     smuggle_url,
     try_get,
+    unified_timestamp,
     update_url_query,
-    int_or_none,
 )
 
 
@@ -85,27 +88,41 @@ class NBCIE(AdobePassIE):
         permalink, video_id = re.match(self._VALID_URL, url).groups()
         permalink = 'http' + compat_urllib_parse_unquote(permalink)
         response = self._download_json(
-            'https://api.nbc.com/v3/videos', video_id, query={
-                'filter[permalink]': permalink,
-                'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating',
-                'fields[shows]': 'shortTitle',
-                'include': 'show.shortTitle',
+            'https://friendship.nbc.co/v2/graphql', video_id, query={
+                'query': '''{
+  page(name: "%s", platform: web, type: VIDEO, userId: "0") {
+    data {
+      ... on VideoPageData {
+        description
+        episodeNumber
+        keywords
+        locked
+        mpxAccountId
+        mpxGuid
+        rating
+        seasonNumber
+        secondaryTitle
+        seriesShortTitle
+      }
+    }
+  }
+}''' % permalink,
             })
-        video_data = response['data'][0]['attributes']
+        video_data = response['data']['page']['data']
         query = {
             'mbr': 'true',
             'manifest': 'm3u',
         }
-        video_id = video_data['guid']
-        title = video_data['title']
-        if video_data.get('entitlement') == 'auth':
+        video_id = video_data['mpxGuid']
+        title = video_data['secondaryTitle']
+        if video_data.get('locked'):
             resource = self._get_mvpd_resource(
                 'nbcentertainment', title, video_id,
-                video_data.get('vChipRating'))
+                video_data.get('rating'))
             query['auth'] = self._extract_mvpd_auth(
                 url, video_id, 'nbcentertainment', resource)
         theplatform_url = smuggle_url(update_url_query(
-            'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
+            'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
             query), {'force_smil_url': True})
         return {
             '_type': 'url_transparent',
@@ -117,7 +134,7 @@ class NBCIE(AdobePassIE):
             'season_number': int_or_none(video_data.get('seasonNumber')),
             'episode_number': int_or_none(video_data.get('episodeNumber')),
             'episode': title,
-            'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']),
+            'series': video_data.get('seriesShortTitle'),
             'ie_key': 'ThePlatform',
         }
 
@@ -272,13 +289,12 @@ class NBCNewsIE(ThePlatformIE):
     _TESTS = [
         {
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
-            'md5': 'af1adfa51312291a017720403826bb64',
+            'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
             'info_dict': {
                 'id': '269389891880',
                 'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
-                'uploader': 'NBCU-NEWS',
                 'timestamp': 1401363060,
                 'upload_date': '20140529',
             },
@@ -296,28 +312,26 @@ class NBCNewsIE(ThePlatformIE):
         },
         {
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
-            'md5': '73135a2e0ef819107bbb55a5a9b2a802',
+            'md5': '8eb831eca25bfa7d25ddd83e85946548',
             'info_dict': {
                 'id': '394064451844',
                 'ext': 'mp4',
                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
                 'timestamp': 1423104900,
-                'uploader': 'NBCU-NEWS',
                 'upload_date': '20150205',
             },
         },
         {
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
-            'md5': 'a49e173825e5fcd15c13fc297fced39d',
+            'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
             'info_dict': {
-                'id': '529953347624',
+                'id': 'n431456',
                 'ext': 'mp4',
-                'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
-                'description': 'md5:c8be487b2d80ff0594c005add88d8351',
+                'title': "Volkswagen U.S. Chief:  We 'Totally Screwed Up'",
+                'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
                 'upload_date': '20150922',
                 'timestamp': 1442917800,
-                'uploader': 'NBCU-NEWS',
             },
         },
         {
@@ -330,7 +344,6 @@ class NBCNewsIE(ThePlatformIE):
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
                 'upload_date': '20160420',
                 'timestamp': 1461152093,
-                'uploader': 'NBCU-NEWS',
             },
         },
         {
@@ -344,7 +357,6 @@ class NBCNewsIE(ThePlatformIE):
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'timestamp': 1406937606,
                 'upload_date': '20140802',
-                'uploader': 'NBCU-NEWS',
             },
         },
         {
@@ -360,20 +372,61 @@ class NBCNewsIE(ThePlatformIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        if not video_id.isdigit():
-            webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-            data = self._parse_json(self._search_regex(
-                r'window\.__data\s*=\s*({.+});', webpage,
-                'bootstrap json'), video_id)
-            video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
+        data = self._parse_json(self._search_regex(
+            r'window\.__data\s*=\s*({.+});', webpage,
+            'bootstrap json'), video_id, js_to_json)
+        video_data = try_get(data, lambda x: x['video']['current'], dict)
+        if not video_data:
+            video_data = data['article']['content'][0]['primaryMedia']['video']
+        title = video_data['headline']['primary']
+
+        formats = []
+        for va in video_data.get('videoAssets', []):
+            public_url = va.get('publicUrl')
+            if not public_url:
+                continue
+            if '://link.theplatform.com/' in public_url:
+                public_url = update_url_query(public_url, {'format': 'redirect'})
+            format_id = va.get('format')
+            if format_id == 'M3U':
+                formats.extend(self._extract_m3u8_formats(
+                    public_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id=format_id, fatal=False))
+                continue
+            tbr = int_or_none(va.get('bitrate'), 1000)
+            if tbr:
+                format_id += '-%d' % tbr
+            formats.append({
+                'format_id': format_id,
+                'url': public_url,
+                'width': int_or_none(va.get('width')),
+                'height': int_or_none(va.get('height')),
+                'tbr': tbr,
+                'ext': 'mp4',
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        closed_captioning = video_data.get('closedCaptioning')
+        if closed_captioning:
+            for cc_url in closed_captioning.values():
+                if not cc_url:
+                    continue
+                subtitles.setdefault('en', []).append({
+                    'url': cc_url,
+                })
 
         return {
-            '_type': 'url_transparent',
             'id': video_id,
-            # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
-            'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
-            'ie_key': 'ThePlatformFeed',
+            'title': title,
+            'description': try_get(video_data, lambda x: x['description']['primary']),
+            'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']),
+            'duration': parse_duration(video_data.get('duration')),
+            'timestamp': unified_timestamp(video_data.get('datePublished')),
+            'formats': formats,
+            'subtitles': subtitles,
         }
 
 

youtube_dl/extractor/nexx.py

@@ -295,13 +295,23 @@ class NexxIE(InfoExtractor):
 
         video = None
 
+        def find_video(result):
+            if isinstance(result, dict):
+                return result
+            elif isinstance(result, list):
+                vid = int(video_id)
+                for v in result:
+                    if try_get(v, lambda x: x['general']['ID'], int) == vid:
+                        return v
+            return None
+
         response = self._download_json(
             'https://arc.nexx.cloud/api/video/%s.json' % video_id,
             video_id, fatal=False)
         if response and isinstance(response, dict):
             result = response.get('result')
-            if result and isinstance(result, dict):
-                video = result
+            if result:
+                video = find_video(result)
 
         # not all videos work via arc, e.g. nexx:741:1269984
         if not video:
@@ -348,7 +358,7 @@ class NexxIE(InfoExtractor):
             request_token = hashlib.md5(
                 ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest()
 
-            video = self._call_api(
+            result = self._call_api(
                 domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={
                     'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description',
                     'addInteractionOptions': '1',
@@ -363,6 +373,7 @@ class NexxIE(InfoExtractor):
                     'X-Request-CID': cid,
                     'X-Request-Token': request_token,
                 })
+            video = find_video(result)
 
         general = video['general']
         title = general['title']

youtube_dl/extractor/nhk.py

@@ -10,6 +10,18 @@ class NhkVodIE(InfoExtractor):
     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{
+        # clip
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
+        'md5': '256a1be14f48d960a7e61e2532d95ec3',
+        'info_dict': {
+            'id': 'a95j5iza',
+            'ext': 'mp4',
+            'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
+            'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
+            'timestamp': 1565965194,
+            'upload_date': '20190816',
+        },
+    }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
         'only_matching': True,
     }, {
@@ -19,7 +31,7 @@ class NhkVodIE(InfoExtractor):
         'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
         'only_matching': True,
     }]
-    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json'
+    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
 
     def _real_extract(self, url):
         lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
@@ -28,7 +40,10 @@ class NhkVodIE(InfoExtractor):
 
         is_video = m_type == 'video'
         episode = self._download_json(
-            self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''),
+            self._API_URL_TEMPLATE % (
+                'v' if is_video else 'r',
+                'clip' if episode_id[:4] == '9999' else 'esd',
+                episode_id, lang, '/all' if is_video else ''),
             episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
         title = episode.get('sub_title_clean') or episode['sub_title']
 
@@ -60,8 +75,8 @@ class NhkVodIE(InfoExtractor):
         if is_video:
             info.update({
                 '_type': 'url_transparent',
-                'ie_key': 'Ooyala',
-                'url': 'ooyala:' + episode['vod_id'],
+                'ie_key': 'Piksel',
+                'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'],
             })
         else:
             audio = episode['audio']

youtube_dl/extractor/ninenow.py

@@ -45,7 +45,11 @@ class NineNowIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
         page_data = self._parse_json(self._search_regex(
             r'window\.__data\s*=\s*({.*?});', webpage,
-            'page data'), display_id)
+            'page data', default='{}'), display_id, fatal=False)
+        if not page_data:
+            page_data = self._parse_json(self._parse_json(self._search_regex(
+                r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
+                webpage, 'page data'), display_id), display_id)
 
         for kind in ('episode', 'clip'):
             current_key = page_data.get(kind, {}).get(

youtube_dl/extractor/nonktube.py

@@ -25,9 +25,14 @@ class NonkTubeIE(NuevoBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        info = self._extract_nuevo(
-            'https://www.nonktube.com/media/nuevo/econfig.php?key=%s'
-            % video_id, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        info['age_limit'] = 18
+        title = self._og_search_title(webpage)
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+        info.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': 18,
+        })
         return info

youtube_dl/extractor/nrk.py

@@ -406,7 +406,7 @@ class NRKTVSerieBaseIE(InfoExtractor):
     def _extract_series(self, webpage, display_id, fatal=True):
         config = self._parse_json(
             self._search_regex(
-                (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;',
+                (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
                  r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
                 webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
             display_id, fatal=False)

youtube_dl/extractor/odnoklassniki.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
@@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
     def _real_extract(self, url):
         start_time = int_or_none(compat_parse_qs(
             compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])

youtube_dl/extractor/onet.py

@@ -20,6 +20,8 @@ from ..utils import (
 
 
 class OnetBaseIE(InfoExtractor):
+    _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/'
+
     def _search_mvp_id(self, webpage):
         return self._search_regex(
             r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
@@ -45,7 +47,7 @@ class OnetBaseIE(InfoExtractor):
         video = response['result'].get('0')
 
         formats = []
-        for _, formats_dict in video['formats'].items():
+        for format_type, formats_dict in video['formats'].items():
             if not isinstance(formats_dict, dict):
                 continue
             for format_id, format_list in formats_dict.items():
@@ -56,21 +58,31 @@ class OnetBaseIE(InfoExtractor):
                     if not video_url:
                         continue
                     ext = determine_ext(video_url)
-                    if format_id == 'ism':
+                    if format_id.startswith('ism'):
                         formats.extend(self._extract_ism_formats(
                             video_url, video_id, 'mss', fatal=False))
                     elif ext == 'mpd':
                         formats.extend(self._extract_mpd_formats(
                             video_url, video_id, mpd_id='dash', fatal=False))
+                    elif format_id.startswith('hls'):
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False))
                     else:
-                        formats.append({
+                        http_f = {
                             'url': video_url,
                             'format_id': format_id,
-                            'height': int_or_none(f.get('vertical_resolution')),
-                            'width': int_or_none(f.get('horizontal_resolution')),
                             'abr': float_or_none(f.get('audio_bitrate')),
-                            'vbr': float_or_none(f.get('video_bitrate')),
-                        })
+                        }
+                        if format_type == 'audio':
+                            http_f['vcodec'] = 'none'
+                        else:
+                            http_f.update({
+                                'height': int_or_none(f.get('vertical_resolution')),
+                                'width': int_or_none(f.get('horizontal_resolution')),
+                                'vbr': float_or_none(f.get('video_bitrate')),
+                            })
+                        formats.append(http_f)
         self._sort_formats(formats)
 
         meta = video.get('meta', {})
@@ -105,12 +117,12 @@ class OnetMVPIE(OnetBaseIE):
 
 
 class OnetIE(OnetBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+    _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
     IE_NAME = 'onet.tv'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
-        'md5': 'e3ffbf47590032ac3f27249204173d50',
+        'md5': '436102770fb095c75b8bb0392d3da9ff',
         'info_dict': {
             'id': 'qbpyqc',
             'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd',
@@ -120,7 +132,10 @@ class OnetIE(OnetBaseIE):
             'upload_date': '20160705',
             'timestamp': 1467721580,
         },
-    }
+    }, {
+        'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -140,18 +155,21 @@ class OnetIE(OnetBaseIE):
 
 
 class OnetChannelIE(OnetBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P<id>[a-z]+)(?:[?#]|$)'
+    _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P<id>[a-z]+)(?:[?#]|$)'
     IE_NAME = 'onet.tv:channel'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://onet.tv/k/openerfestival',
         'info_dict': {
             'id': 'openerfestival',
-            'title': 'Open\'er Festival Live',
-            'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.',
+            'title': "Open'er Festival",
+            'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.",
         },
-        'playlist_mincount': 46,
-    }
+        'playlist_mincount': 35,
+    }, {
+        'url': 'https://onet100.vod.pl/k/openerfestival',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         channel_id = self._match_id(url)
@@ -173,7 +191,7 @@ class OnetChannelIE(OnetBaseIE):
             'Downloading channel %s - add --no-playlist to just download video %s' % (
                 channel_id, video_name))
         matches = re.findall(
-            r'<a[^>]+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)',
+            r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE,
             webpage)
         entries = [
             self.url_result(video_link, OnetIE.ie_key())

youtube_dl/extractor/openload.py

@@ -246,7 +246,7 @@ class OpenloadIE(InfoExtractor):
     _DOMAINS = r'''
                     (?:
                         openload\.(?:co|io|link|pw)|
-                        oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)|
+                        oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|monster|press|pw|life|live|space|services|website|vip)|
                         oladblock\.(?:services|xyz|me)|openloed\.co
                     )
                 '''
@@ -362,6 +362,12 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.services/embed/bs1NWj1dCag/',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.online/f/W8o2UfN1vNY/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.monster/f/W8o2UfN1vNY/',
+        'only_matching': True,
     }, {
         'url': 'https://oload.press/embed/drTBl1aOTvk/',
         'only_matching': True,

youtube_dl/extractor/orf.py

@@ -86,12 +86,13 @@ class ORFTVthekIE(InfoExtractor):
                     if value:
                         format_id_list.append(value)
                 format_id = '-'.join(format_id_list)
-                if determine_ext(fd['src']) == 'm3u8':
+                ext = determine_ext(src)
+                if ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        fd['src'], video_id, 'mp4', m3u8_id=format_id))
-                elif determine_ext(fd['src']) == 'f4m':
+                        src, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+                elif ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(
-                        fd['src'], video_id, f4m_id=format_id))
+                        src, video_id, f4m_id=format_id, fatal=False))
                 else:
                     formats.append({
                         'format_id': format_id,

youtube_dl/extractor/peertube.py

@@ -18,81 +18,385 @@ from ..utils import (
 class PeerTubeIE(InfoExtractor):
     _INSTANCES_RE = r'''(?:
                             # Taken from https://instances.joinpeertube.org/instances
+                            peertube\.rainbowswingers\.net|
+                            tube\.stanisic\.nl|
+                            peer\.suiri\.us|
+                            medias\.libox\.fr|
+                            videomensoif\.ynh\.fr|
+                            peertube\.travelpandas\.eu|
+                            peertube\.rachetjay\.fr|
+                            peertube\.montecsys\.fr|
+                            tube\.eskuero\.me|
+                            peer\.tube|
+                            peertube\.umeahackerspace\.se|
+                            tube\.nx-pod\.de|
+                            video\.monsieurbidouille\.fr|
                             tube\.openalgeria\.org|
-                            peertube\.pointsecu\.fr|
+                            vid\.lelux\.fi|
+                            video\.anormallostpod\.ovh|
+                            tube\.crapaud-fou\.org|
+                            peertube\.stemy\.me|
+                            lostpod\.space|
+                            exode\.me|
+                            peertube\.snargol\.com|
+                            vis\.ion\.ovh|
+                            videosdulib\.re|
+                            v\.mbius\.io|
+                            videos\.judrey\.eu|
+                            peertube\.osureplayviewer\.xyz|
+                            peertube\.mathieufamily\.ovh|
+                            www\.videos-libr\.es|
+                            fightforinfo\.com|
+                            peertube\.fediverse\.ru|
+                            peertube\.oiseauroch\.fr|
+                            video\.nesven\.eu|
+                            v\.bearvideo\.win|
+                            video\.qoto\.org|
+                            justporn\.cc|
+                            video\.vny\.fr|
+                            peervideo\.club|
+                            tube\.taker\.fr|
+                            peertube\.chantierlibre\.org|
+                            tube\.ipfixe\.info|
+                            tube\.kicou\.info|
+                            tube\.dodsorf\.as|
+                            videobit\.cc|
+                            video\.yukari\.moe|
+                            videos\.elbinario\.net|
+                            hkvideo\.live|
+                            pt\.tux\.tf|
+                            www\.hkvideo\.live|
+                            FIGHTFORINFO\.com|
+                            pt\.765racing\.com|
+                            peertube\.gnumeria\.eu\.org|
+                            nordenmedia\.com|
+                            peertube\.co\.uk|
+                            tube\.darfweb\.eu|
+                            tube\.kalah-france\.org|
+                            0ch\.in|
+                            vod\.mochi\.academy|
+                            film\.node9\.org|
+                            peertube\.hatthieves\.es|
+                            video\.fitchfamily\.org|
+                            peertube\.ddns\.net|
+                            video\.ifuncle\.kr|
+                            video\.fdlibre\.eu|
+                            tube\.22decembre\.eu|
+                            peertube\.harmoniescreatives\.com|
+                            tube\.fabrigli\.fr|
+                            video\.thedwyers\.co|
+                            video\.bruitbruit\.com|
+                            peertube\.foxfam\.club|
+                            peer\.philoxweb\.be|
+                            videos\.bugs\.social|
+                            peertube\.malbert\.xyz|
+                            peertube\.bilange\.ca|
+                            libretube\.net|
+                            diytelevision\.com|
+                            peertube\.fedilab\.app|
+                            libre\.video|
+                            video\.mstddntfdn\.online|
+                            us\.tv|
+                            peertube\.sl-network\.fr|
+                            peertube\.dynlinux\.io|
+                            peertube\.david\.durieux\.family|
+                            peertube\.linuxrocks\.online|
+                            peerwatch\.xyz|
+                            v\.kretschmann\.social|
+                            tube\.otter\.sh|
+                            yt\.is\.nota\.live|
+                            tube\.dragonpsi\.xyz|
+                            peertube\.boneheadmedia\.com|
+                            videos\.funkwhale\.audio|
+                            watch\.44con\.com|
+                            peertube\.gcaillaut\.fr|
+                            peertube\.icu|
+                            pony\.tube|
+                            spacepub\.space|
+                            tube\.stbr\.io|
+                            v\.mom-gay\.faith|
+                            tube\.port0\.xyz|
+                            peertube\.simounet\.net|
+                            play\.jergefelt\.se|
+                            peertube\.zeteo\.me|
+                            tube\.danq\.me|
+                            peertube\.kerenon\.com|
+                            tube\.fab-l3\.org|
+                            tube\.calculate\.social|
+                            peertube\.mckillop\.org|
+                            tube\.netzspielplatz\.de|
+                            vod\.ksite\.de|
+                            peertube\.laas\.fr|
+                            tube\.govital\.net|
+                            peertube\.stephenson\.cc|
+                            bistule\.nohost\.me|
+                            peertube\.kajalinifi\.de|
+                            video\.ploud\.jp|
+                            video\.omniatv\.com|
+                            peertube\.ffs2play\.fr|
+                            peertube\.leboulaire\.ovh|
+                            peertube\.tronic-studio\.com|
+                            peertube\.public\.cat|
+                            peertube\.metalbanana\.net|
+                            video\.1000i100\.fr|
+                            peertube\.alter-nativ-voll\.de|
+                            tube\.pasa\.tf|
+                            tube\.worldofhauru\.xyz|
+                            pt\.kamp\.site|
+                            peertube\.teleassist\.fr|
+                            videos\.mleduc\.xyz|
+                            conf\.tube|
+                            media\.privacyinternational\.org|
+                            pt\.forty-two\.nl|
+                            video\.halle-leaks\.de|
+                            video\.grosskopfgames\.de|
+                            peertube\.schaeferit\.de|
+                            peertube\.jackbot\.fr|
+                            tube\.extinctionrebellion\.fr|
+                            peertube\.f-si\.org|
+                            video\.subak\.ovh|
+                            videos\.koweb\.fr|
+                            peertube\.zergy\.net|
+                            peertube\.roflcopter\.fr|
+                            peertube\.floss-marketing-school\.com|
+                            vloggers\.social|
+                            peertube\.iriseden\.eu|
+                            videos\.ubuntu-paris\.org|
+                            peertube\.mastodon\.host|
+                            armstube\.com|
+                            peertube\.s2s\.video|
+                            peertube\.lol|
+                            tube\.open-plug\.eu|
+                            open\.tube|
+                            peertube\.ch|
+                            peertube\.normandie-libre\.fr|
+                            peertube\.slat\.org|
+                            video\.lacaveatonton\.ovh|
+                            peertube\.uno|
+                            peertube\.servebeer\.com|
+                            peertube\.fedi\.quebec|
+                            tube\.h3z\.jp|
+                            tube\.plus200\.com|
+                            peertube\.eric\.ovh|
+                            tube\.metadocs\.cc|
+                            tube\.unmondemeilleur\.eu|
+                            gouttedeau\.space|
+                            video\.antirep\.net|
+                            nrop\.cant\.at|
+                            tube\.ksl-bmx\.de|
+                            tube\.plaf\.fr|
+                            tube\.tchncs\.de|
+                            video\.devinberg\.com|
+                            hitchtube\.fr|
+                            peertube\.kosebamse\.com|
+                            yunopeertube\.myddns\.me|
+                            peertube\.varney\.fr|
+                            peertube\.anon-kenkai\.com|
+                            tube\.maiti\.info|
+                            tubee\.fr|
+                            videos\.dinofly\.com|
+                            toobnix\.org|
+                            videotape\.me|
+                            voca\.tube|
+                            video\.heromuster\.com|
+                            video\.lemediatv\.fr|
+                            video\.up\.edu\.ph|
+                            balafon\.video|
+                            video\.ivel\.fr|
+                            thickrips\.cloud|
+                            pt\.laurentkruger\.fr|
+                            video\.monarch-pass\.net|
+                            peertube\.artica\.center|
+                            video\.alternanet\.fr|
+                            indymotion\.fr|
+                            fanvid\.stopthatimp\.net|
+                            video\.farci\.org|
+                            v\.lesterpig\.com|
+                            video\.okaris\.de|
+                            tube\.pawelko\.net|
+                            peertube\.mablr\.org|
+                            tube\.fede\.re|
+                            pytu\.be|
+                            evertron\.tv|
+                            devtube\.dev-wiki\.de|
+                            raptube\.antipub\.org|
+                            video\.selea\.se|
+                            peertube\.mygaia\.org|
+                            video\.oh14\.de|
+                            peertube\.livingutopia\.org|
+                            peertube\.the-penguin\.de|
+                            tube\.thechangebook\.org|
+                            tube\.anjara\.eu|
+                            pt\.pube\.tk|
+                            video\.samedi\.pm|
+                            mplayer\.demouliere\.eu|
+                            widemus\.de|
+                            peertube\.me|
+                            peertube\.zapashcanon\.fr|
+                            video\.latavernedejohnjohn\.fr|
+                            peertube\.pcservice46\.fr|
+                            peertube\.mazzonetto\.eu|
+                            video\.irem\.univ-paris-diderot\.fr|
+                            video\.livecchi\.cloud|
+                            alttube\.fr|
+                            video\.coop\.tools|
+                            video\.cabane-libre\.org|
+                            peertube\.openstreetmap\.fr|
+                            videos\.alolise\.org|
+                            irrsinn\.video|
+                            video\.antopie\.org|
+                            scitech\.video|
+                            tube2\.nemsia\.org|
+                            video\.amic37\.fr|
+                            peertube\.freeforge\.eu|
+                            video\.arbitrarion\.com|
+                            video\.datsemultimedia\.com|
+                            stoptrackingus\.tv|
+                            peertube\.ricostrongxxx\.com|
+                            docker\.videos\.lecygnenoir\.info|
+                            peertube\.togart\.de|
+                            tube\.postblue\.info|
+                            videos\.domainepublic\.net|
+                            peertube\.cyber-tribal\.com|
+                            video\.gresille\.org|
+                            peertube\.dsmouse\.net|
+                            cinema\.yunohost\.support|
+                            tube\.theocevaer\.fr|
+                            repro\.video|
+                            tube\.4aem\.com|
+                            quaziinc\.com|
+                            peertube\.metawurst\.space|
+                            videos\.wakapo\.com|
+                            video\.ploud\.fr|
+                            video\.freeradical\.zone|
+                            tube\.valinor\.fr|
+                            refuznik\.video|
+                            pt\.kircheneuenburg\.de|
+                            peertube\.asrun\.eu|
+                            peertube\.lagob\.fr|
+                            videos\.side-ways\.net|
+                            91video\.online|
+                            video\.valme\.io|
+                            video\.taboulisme\.com|
+                            videos-libr\.es|
+                            tv\.mooh\.fr|
+                            nuage\.acostey\.fr|
+                            video\.monsieur-a\.fr|
+                            peertube\.librelois\.fr|
+                            videos\.pair2jeux\.tube|
+                            videos\.pueseso\.club|
+                            peer\.mathdacloud\.ovh|
+                            media\.assassinate-you\.net|
+                            vidcommons\.org|
+                            ptube\.rousset\.nom\.fr|
+                            tube\.cyano\.at|
+                            videos\.squat\.net|
+                            video\.iphodase\.fr|
+                            peertube\.makotoworkshop\.org|
+                            peertube\.serveur\.slv-valbonne\.fr|
+                            vault\.mle\.party|
+                            hostyour\.tv|
+                            videos\.hack2g2\.fr|
+                            libre\.tube|
+                            pire\.artisanlogiciel\.net|
+                            videos\.numerique-en-commun\.fr|
+                            video\.netsyms\.com|
+                            video\.die-partei\.social|
+                            video\.writeas\.org|
+                            peertube\.swarm\.solvingmaz\.es|
+                            tube\.pericoloso\.ovh|
+                            watching\.cypherpunk\.observer|
+                            videos\.adhocmusic\.com|
+                            tube\.rfc1149\.net|
+                            peertube\.librelabucm\.org|
+                            videos\.numericoop\.fr|
+                            peertube\.koehn\.com|
+                            peertube\.anarchmusicall\.net|
+                            tube\.kampftoast\.de|
+                            vid\.y-y\.li|
+                            peertube\.xtenz\.xyz|
+                            diode\.zone|
+                            tube\.egf\.mn|
+                            peertube\.nomagic\.uk|
+                            visionon\.tv|
+                            videos\.koumoul\.com|
+                            video\.rastapuls\.com|
+                            video\.mantlepro\.com|
+                            video\.deadsuperhero\.com|
+                            peertube\.musicstudio\.pro|
+                            peertube\.we-keys\.fr|
+                            artitube\.artifaille\.fr|
+                            peertube\.ethernia\.net|
+                            tube\.midov\.pl|
+                            peertube\.fr|
+                            watch\.snoot\.tube|
+                            peertube\.donnadieu\.fr|
+                            argos\.aquilenet\.fr|
+                            tube\.nemsia\.org|
+                            tube\.bruniau\.net|
+                            videos\.darckoune\.moe|
+                            tube\.traydent\.info|
+                            dev\.videos\.lecygnenoir\.info|
+                            peertube\.nayya\.org|
+                            peertube\.live|
+                            peertube\.mofgao\.space|
+                            video\.lequerrec\.eu|
+                            peertube\.amicale\.net|
+                            aperi\.tube|
+                            tube\.ac-lyon\.fr|
+                            video\.lw1\.at|
+                            www\.yiny\.org|
+                            videos\.pofilo\.fr|
+                            tube\.lou\.lt|
+                            choob\.h\.etbus\.ch|
+                            tube\.hoga\.fr|
+                            peertube\.heberge\.fr|
+                            video\.obermui\.de|
+                            videos\.cloudfrancois\.fr|
+                            betamax\.video|
+                            video\.typica\.us|
+                            tube\.piweb\.be|
+                            video\.blender\.org|
+                            peertube\.cat|
+                            tube\.kdy\.ch|
+                            pe\.ertu\.be|
+                            peertube\.social|
+                            videos\.lescommuns\.org|
+                            tv\.datamol\.org|
+                            videonaute\.fr|
+                            dialup\.express|
                             peertube\.nogafa\.org|
-                            peertube\.pl|
                             megatube\.lilomoino\.fr|
                             peertube\.tamanoir\.foucry\.net|
-                            peertube\.inapurna\.org|
-                            peertube\.netzspielplatz\.de|
-                            video\.deadsuperhero\.com|
                             peertube\.devosi\.org|
                             peertube\.1312\.media|
-                            tube\.worldofhauru\.xyz|
                             tube\.bootlicker\.party|
                             skeptikon\.fr|
-                            peertube\.geekshell\.fr|
-                            tube\.opportunis\.me|
-                            peertube\.peshane\.net|
                             video\.blueline\.mg|
                             tube\.homecomputing\.fr|
-                            videos\.cloudfrancois\.fr|
-                            peertube\.viviers-fibre\.net|
                             tube\.ouahpiti\.info|
                             video\.tedomum\.net|
                             video\.g3l\.org|
                             fontube\.fr|
                             peertube\.gaialabs\.ch|
-                            peertube\.extremely\.online|
-                            peertube\.public-infrastructure\.eu|
                             tube\.kher\.nl|
                             peertube\.qtg\.fr|
-                            tube\.22decembre\.eu|
-                            facegirl\.me|
                             video\.migennes\.net|
-                            janny\.moe|
                             tube\.p2p\.legal|
-                            video\.atlanti\.se|
                             troll\.tv|
-                            peertube\.geekael\.fr|
-                            vid\.leotindall\.com|
-                            video\.anormallostpod\.ovh|
-                            p-tube\.h3z\.jp|
-                            tube\.darfweb\.eu|
                             videos\.iut-orsay\.fr|
                             peertube\.solidev\.net|
-                            videos\.symphonie-of-code\.fr|
-                            testtube\.ortg\.de|
                             videos\.cemea\.org|
-                            peertube\.gwendalavir\.eu|
                             video\.passageenseine\.fr|
                             videos\.festivalparminous\.org|
                             peertube\.touhoppai\.moe|
-                            peertube\.duckdns\.org|
                             sikke\.fi|
-                            peertube\.mastodon\.host|
-                            firedragonvideos\.com|
-                            vidz\.dou\.bet|
-                            peertube\.koehn\.com|
                             peer\.hostux\.social|
                             share\.tube|
                             peertube\.walkingmountains\.fr|
-                            medias\.libox\.fr|
-                            peertube\.moe|
-                            peertube\.xyz|
-                            jp\.peertube\.network|
                             videos\.benpro\.fr|
-                            tube\.otter\.sh|
-                            peertube\.angristan\.xyz|
                             peertube\.parleur\.net|
-                            peer\.ecutsa\.fr|
                             peertube\.heraut\.eu|
-                            peertube\.tifox\.fr|
-                            peertube\.maly\.io|
-                            vod\.mochi\.academy|
-                            exode\.me|
-                            coste\.video|
                             tube\.aquilenet\.fr|
                             peertube\.gegeweb\.eu|
                             framatube\.org|
@@ -100,18 +404,11 @@ class PeerTubeIE(InfoExtractor):
                             tube\.conferences-gesticulees\.net|
                             peertube\.datagueule\.tv|
                             video\.lqdn\.fr|
-                            meilleurtube\.delire\.party|
                             tube\.mochi\.academy|
-                            peertube\.dav\.li|
                             media\.zat\.im|
-                            pytu\.be|
-                            peertube\.valvin\.fr|
-                            peertube\.nsa\.ovh|
                             video\.colibris-outilslibres\.org|
-                            video\.hispagatos\.org|
                             tube\.svnet\.fr|
                             peertube\.video|
-                            videos\.lecygnenoir\.info|
                             peertube3\.cpy\.re|
                             peertube2\.cpy\.re|
                             videos\.tcit\.fr|
@@ -126,7 +423,7 @@ class PeerTubeIE(InfoExtractor):
                     (?P<id>%s)
                     ''' % (_INSTANCES_RE, _UUID_RE)
     _TESTS = [{
-        'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
+        'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
         'md5': '80f24ff364cc9d333529506a263e7feb',
         'info_dict': {
             'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c',

youtube_dl/extractor/piksel.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class PikselIE(InfoExtractor):
-    _VALID_URL = r'https?://player\.piksel\.com/v/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P<id>[a-z0-9_]+)'
     _TESTS = [
         {
             'url': 'http://player.piksel.com/v/ums2867l',
@@ -40,6 +40,11 @@ class PikselIE(InfoExtractor):
                 'timestamp': 1486171129,
                 'upload_date': '20170204'
             }
+        },
+        {
+            # https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2019240/
+            'url': 'http://player.piksel.com/v/refid/nhkworld/prefid/nw_vod_v_en_2019_240_20190823233000_02_1566873477',
+            'only_matching': True,
         }
     ]
 
@@ -52,8 +57,11 @@ class PikselIE(InfoExtractor):
             return mobj.group('url')
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'data-de-program-uuid=[\'"]([a-z0-9]+)',
+            webpage, 'program uuid', default=display_id)
         app_token = self._search_regex([
             r'clientAPI\s*:\s*"([^"]+)"',
             r'data-de-api-key\s*=\s*"([^"]+)"'

youtube_dl/extractor/pornhub.py

@@ -403,6 +403,15 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
 
 
 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
+    @staticmethod
+    def _has_more(webpage):
+        return re.search(
+            r'''(?x)
+                <li[^>]+\bclass=["\']page_next|
+                <link[^>]+\brel=["\']next|
+                <button[^>]+\bid=["\']moreDataBtn
+            ''', webpage) is not None
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host')
@@ -411,13 +420,11 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
         page = int_or_none(self._search_regex(
             r'\bpage=(\d+)', url, 'page', default=None))
 
-        page_url = self._make_page_url(url)
-
         entries = []
         for page_num in (page, ) if page is not None else itertools.count(1):
             try:
                 webpage = self._download_webpage(
-                    page_url, item_id, 'Downloading page %d' % page_num,
+                    url, item_id, 'Downloading page %d' % page_num,
                     query={'page': page_num})
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
@@ -547,18 +554,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 
-    def _make_page_url(self, url):
-        return url
-
-    @staticmethod
-    def _has_more(webpage):
-        return re.search(
-            r'''(?x)
-                <li[^>]+\bclass=["\']page_next|
-                <link[^>]+\brel=["\']next|
-                <button[^>]+\bid=["\']moreDataBtn
-            ''', webpage) is not None
-
 
 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
@@ -572,11 +567,3 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
         'only_matching': True,
     }]
-
-    def _make_page_url(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        return '%s/ajax' % mobj.group('url')
-
-    @staticmethod
-    def _has_more(webpage):
-        return True

youtube_dl/extractor/promptfile.py

@@ -1,70 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    urlencode_postdata,
-)
-
-
-class PromptFileIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
-    _TEST = {
-        'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416',
-        'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
-        'info_dict': {
-            'id': '86D1CE8462-576CAAE416',
-            'ext': 'mp4',
-            'title': 'oceans.mp4',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id,
-                                 expected=True)
-
-        chash = self._search_regex(
-            r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash')
-        fields = self._hidden_inputs(webpage)
-        keys = list(fields.keys())
-        chash_key = keys[0] if len(keys) == 1 else next(
-            key for key in keys if key.startswith('cha'))
-        fields[chash_key] = chash + fields[chash_key]
-
-        webpage = self._download_webpage(
-            url, video_id, 'Downloading video page',
-            data=urlencode_postdata(fields),
-            headers={'Content-type': 'application/x-www-form-urlencoded'})
-
-        video_url = self._search_regex(
-            (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File',
-             r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'),
-            webpage, 'video url', group='url')
-        title = self._html_search_regex(
-            r'<span.+title="([^"]+)">', webpage, 'title')
-        thumbnail = self._html_search_regex(
-            r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
-            webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
-
-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-            'ext': determine_ext(title),
-        }]
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

youtube_dl/extractor/puhutv.py

@@ -25,21 +25,21 @@ class PuhuTVIE(InfoExtractor):
     _TESTS = [{
         # film
         'url': 'https://puhutv.com/sut-kardesler-izle',
-        'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7',
+        'md5': 'a347470371d56e1585d1b2c8dab01c96',
         'info_dict': {
             'id': '5085',
             'display_id': 'sut-kardesler',
             'ext': 'mp4',
             'title': 'Süt Kardeşler',
-            'description': 'md5:405fd024df916ca16731114eb18e511a',
+            'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 4832.44,
             'creator': 'Arzu Film',
-            'timestamp': 1469778212,
-            'upload_date': '20160729',
+            'timestamp': 1561062602,
+            'upload_date': '20190620',
             'release_year': 1976,
             'view_count': int,
-            'tags': ['Aile', 'Komedi', 'Klasikler'],
+            'tags': list,
         },
     }, {
         # episode, geo restricted, bypassable with --geo-verification-proxy
@@ -64,9 +64,10 @@ class PuhuTVIE(InfoExtractor):
             display_id)['data']
 
         video_id = compat_str(info['id'])
-        title = info.get('name') or info['title']['name']
+        show = info.get('title') or {}
+        title = info.get('name') or show['name']
         if info.get('display_name'):
-            title = '%s %s' % (title, info.get('display_name'))
+            title = '%s %s' % (title, info['display_name'])
 
         try:
             videos = self._download_json(
@@ -78,17 +79,36 @@ class PuhuTVIE(InfoExtractor):
                 self.raise_geo_restricted()
             raise
 
+        urls = []
         formats = []
+
+        def add_http_from_hls(m3u8_f):
+            http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4')
+            if http_url != m3u8_f['url']:
+                f = m3u8_f.copy()
+                f.update({
+                    'format_id': f['format_id'].replace('hls', 'http'),
+                    'protocol': 'http',
+                    'url': http_url,
+                })
+                formats.append(f)
+
         for video in videos['data']['videos']:
             media_url = url_or_none(video.get('url'))
-            if not media_url:
+            if not media_url or media_url in urls:
                 continue
+            urls.append(media_url)
+
             playlist = video.get('is_playlist')
-            if video.get('stream_type') == 'hls' and playlist is True:
-                formats.extend(self._extract_m3u8_formats(
+            if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url:
+                m3u8_formats = self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
+                    m3u8_id='hls', fatal=False)
+                for m3u8_f in m3u8_formats:
+                    formats.append(m3u8_f)
+                    add_http_from_hls(m3u8_f)
                 continue
+
             quality = int_or_none(video.get('quality'))
             f = {
                 'url': media_url,
@@ -96,34 +116,29 @@ class PuhuTVIE(InfoExtractor):
                 'height': quality
             }
             video_format = video.get('video_format')
-            if video_format == 'hls' and playlist is False:
+            is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False
+            if is_hls:
                 format_id = 'hls'
                 f['protocol'] = 'm3u8_native'
             elif video_format == 'mp4':
                 format_id = 'http'
-
             else:
                 continue
             if quality:
                 format_id += '-%sp' % quality
             f['format_id'] = format_id
             formats.append(f)
+            if is_hls:
+                add_http_from_hls(f)
         self._sort_formats(formats)
 
-        description = try_get(
-            info, lambda x: x['title']['description'],
-            compat_str) or info.get('description')
-        timestamp = unified_timestamp(info.get('created_at'))
         creator = try_get(
-            info, lambda x: x['title']['producer']['name'], compat_str)
+            show, lambda x: x['producer']['name'], compat_str)
 
-        duration = float_or_none(
-            try_get(info, lambda x: x['content']['duration_in_ms'], int),
-            scale=1000)
-        view_count = try_get(info, lambda x: x['content']['watch_count'], int)
+        content = info.get('content') or {}
 
         images = try_get(
-            info, lambda x: x['content']['images']['wide'], dict) or {}
+            content, lambda x: x['images']['wide'], dict) or {}
         thumbnails = []
         for image_id, image_url in images.items():
             if not isinstance(image_url, compat_str):
@@ -137,14 +152,8 @@ class PuhuTVIE(InfoExtractor):
             })
             thumbnails.append(t)
 
-        release_year = try_get(info, lambda x: x['title']['released_at'], int)
-
-        season_number = int_or_none(info.get('season_number'))
-        season_id = str_or_none(info.get('season_id'))
-        episode_number = int_or_none(info.get('episode_number'))
-
         tags = []
-        for genre in try_get(info, lambda x: x['title']['genres'], list) or []:
+        for genre in show.get('genres') or []:
             if not isinstance(genre, dict):
                 continue
             genre_name = genre.get('name')
@@ -152,12 +161,11 @@ class PuhuTVIE(InfoExtractor):
                 tags.append(genre_name)
 
         subtitles = {}
-        for subtitle in try_get(
-                info, lambda x: x['content']['subtitles'], list) or []:
+        for subtitle in content.get('subtitles') or []:
             if not isinstance(subtitle, dict):
                 continue
             lang = subtitle.get('language')
-            sub_url = url_or_none(subtitle.get('url'))
+            sub_url = url_or_none(subtitle.get('url') or subtitle.get('file'))
             if not lang or not isinstance(lang, compat_str) or not sub_url:
                 continue
             subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
@@ -168,15 +176,15 @@ class PuhuTVIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': description,
-            'season_id': season_id,
-            'season_number': season_number,
-            'episode_number': episode_number,
-            'release_year': release_year,
-            'timestamp': timestamp,
+            'description': info.get('description') or show.get('description'),
+            'season_id': str_or_none(info.get('season_id')),
+            'season_number': int_or_none(info.get('season_number')),
+            'episode_number': int_or_none(info.get('episode_number')),
+            'release_year': int_or_none(show.get('released_at')),
+            'timestamp': unified_timestamp(info.get('created_at')),
             'creator': creator,
-            'view_count': view_count,
-            'duration': duration,
+            'view_count': int_or_none(content.get('watch_count')),
+            'duration': float_or_none(content.get('duration_in_ms'), 1000),
             'tags': tags,
             'subtitles': subtitles,
             'thumbnails': thumbnails,

youtube_dl/extractor/redtube.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    merge_dicts,
     str_to_int,
     unified_strdate,
     url_or_none,
@@ -45,11 +46,14 @@ class RedTubeIE(InfoExtractor):
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
 
-        title = self._html_search_regex(
-            (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
-             r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
-            webpage, 'title', group='title',
-            default=None) or self._og_search_title(webpage)
+        info = self._search_json_ld(webpage, video_id, default={})
+
+        if not info.get('title'):
+            info['title'] = self._html_search_regex(
+                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+                 r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
+                webpage, 'title', group='title',
+                default=None) or self._og_search_title(webpage)
 
         formats = []
         sources = self._parse_json(
@@ -88,28 +92,28 @@ class RedTubeIE(InfoExtractor):
 
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._search_regex(
-            r'<span[^>]+>ADDED ([^<]+)<',
-            webpage, 'upload date', fatal=False))
+            r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<',
+            webpage, 'upload date', default=None))
         duration = int_or_none(self._og_search_property(
             'video:duration', webpage, default=None) or self._search_regex(
                 r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
         view_count = str_to_int(self._search_regex(
             (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
-             r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'),
-            webpage, 'view count', fatal=False))
+             r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)',
+             r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'),
+            webpage, 'view count', default=None))
 
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"
         age_limit = 18
 
-        return {
+        return merge_dicts(info, {
             'id': video_id,
             'ext': 'mp4',
-            'title': title,
             'thumbnail': thumbnail,
             'upload_date': upload_date,
             'duration': duration,
             'view_count': view_count,
             'age_limit': age_limit,
             'formats': formats,
-        }
+        })

youtube_dl/extractor/scte.py

@@ -0,0 +1,144 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    decode_packed_codes,
+    ExtractorError,
+    urlencode_postdata,
+)
+
+
+class SCTEBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx'
+    _NETRC_MACHINE = 'scte'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        login_popup = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login popup')
+
+        def is_logged(webpage):
+            return any(re.search(p, webpage) for p in (
+                r'class=["\']welcome\b', r'>Sign Out<'))
+
+        # already logged in
+        if is_logged(login_popup):
+            return
+
+        login_form = self._hidden_inputs(login_popup)
+
+        login_form.update({
+            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username,
+            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password,
+            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on',
+        })
+
+        response = self._download_webpage(
+            self._LOGIN_URL, None, 'Logging in',
+            data=urlencode_postdata(login_form))
+
+        if '|pageRedirect|' not in response and not is_logged(response):
+            error = self._html_search_regex(
+                r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+
+class SCTEIE(SCTEBaseIE):
+    _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484',
+        'info_dict': {
+            'title': 'Introduction to DOCSIS Engineering Professional',
+            'id': '31484',
+        },
+        'playlist_count': 5,
+        'skip': 'Requires account credentials',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
+
+        context_id = self._search_regex(r'context-(\d+)', webpage, video_id)
+        content_base = 'https://learning.scte.org/pluginfile.php/%s/mod_scorm/content/8/' % context_id
+        context = decode_packed_codes(self._download_webpage(
+            '%smobile/data.js' % content_base, video_id))
+
+        data = self._parse_xml(
+            self._search_regex(
+                r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"),
+            video_id)
+
+        entries = []
+        for asset in data.findall('.//asset'):
+            asset_url = asset.get('url')
+            if not asset_url or not asset_url.endswith('.mp4'):
+                continue
+            asset_id = self._search_regex(
+                r'video_([^_]+)_', asset_url, 'asset id', default=None)
+            if not asset_id:
+                continue
+            entries.append({
+                'id': asset_id,
+                'title': title,
+                'url': content_base + asset_url,
+            })
+
+        return self.playlist_result(entries, video_id, title)
+
+
+class SCTECourseIE(SCTEBaseIE):
+    _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.scte.org/course/view.php?id=3639',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.scte.org/course/view.php?id=3073',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, course_id)
+
+        title = self._search_regex(
+            r'<h1>(.+?)</h1>', webpage, 'title', default=None)
+
+        entries = []
+        for mobj in re.finditer(
+                r'''(?x)
+                    <a[^>]+
+                        href=(["\'])
+                        (?P<url>
+                            https?://learning\.scte\.org/mod/
+                            (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*?
+                            \bid=\d+
+                        )
+                    ''',
+                webpage):
+            item_url = mobj.group('url')
+            if item_url == url:
+                continue
+            ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm'
+                  else SCTECourseIE.ie_key())
+            entries.append(self.url_result(item_url, ie=ie))
+
+        return self.playlist_result(entries, course_id, title)

youtube_dl/extractor/servingsys.py

@@ -1,72 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-)
-
-
-class ServingSysIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)'
-
-    _TEST = {
-        'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
-        'info_dict': {
-            'id': '5349193',
-            'title': 'AdAPPter_Hyundai_demo',
-        },
-        'playlist': [{
-            'md5': 'baed851342df6846eb8677a60a011a0f',
-            'info_dict': {
-                'id': '29955898',
-                'ext': 'flv',
-                'title': 'AdAPPter_Hyundai_demo (1)',
-                'duration': 74,
-                'tbr': 1378,
-                'width': 640,
-                'height': 400,
-            },
-        }, {
-            'md5': '979b4da2655c4bc2d81aeb915a8c5014',
-            'info_dict': {
-                'id': '29907998',
-                'ext': 'flv',
-                'title': 'AdAPPter_Hyundai_demo (2)',
-                'duration': 34,
-                'width': 854,
-                'height': 480,
-                'tbr': 516,
-            },
-        }],
-        'params': {
-            'playlistend': 2,
-        },
-        '_skip': 'Blocked in the US [sic]',
-    }
-
-    def _real_extract(self, url):
-        pl_id = self._match_id(url)
-        vast_doc = self._download_xml(url, pl_id)
-
-        title = vast_doc.find('.//AdTitle').text
-        media = vast_doc.find('.//MediaFile').text
-        info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')
-
-        doc = self._download_xml(info_url, pl_id, 'Downloading video info')
-        entries = [{
-            '_type': 'video',
-            'id': a.attrib['id'],
-            'title': '%s (%s)' % (title, a.attrib['assetID']),
-            'url': a.attrib['URL'],
-            'duration': int_or_none(a.attrib.get('length')),
-            'tbr': int_or_none(a.attrib.get('bitrate')),
-            'height': int_or_none(a.attrib.get('height')),
-            'width': int_or_none(a.attrib.get('width')),
-        } for a in doc.findall('.//AdditionalAssets/asset')]
-
-        return {
-            '_type': 'playlist',
-            'id': pl_id,
-            'title': title,
-            'entries': entries,
-        }

youtube_dl/extractor/soundcloud.py

@@ -11,14 +11,13 @@ from .common import (
 from ..compat import (
     compat_str,
     compat_urlparse,
-    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     ExtractorError,
     float_or_none,
+    HEADRequest,
     int_or_none,
     KNOWN_EXTENSIONS,
-    merge_dicts,
     mimetype2ext,
     str_or_none,
     try_get,
@@ -28,6 +27,20 @@ from ..utils import (
 )
 
 
+class SoundcloudEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?url=(?P<id>.*)'
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [m.group('url') for m in re.finditer(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        return self.url_result(compat_urlparse.parse_qs(
+            compat_urlparse.urlparse(url).query)['url'][0])
+
+
 class SoundcloudIE(InfoExtractor):
     """Information extractor for soundcloud.com
        To access the media, the uid of the song and a stream token
@@ -44,9 +57,8 @@ class SoundcloudIE(InfoExtractor):
                             (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
-                       |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
+                       |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+)
                           (?:/?\?secret_token=(?P<secret_token>[^&]+))?)
-                       |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
                     )
                     '''
     IE_NAME = 'soundcloud'
@@ -60,6 +72,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
                 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
                 'uploader': 'E.T. ExTerrestrial Music',
+                'uploader_id': '1571244',
                 'timestamp': 1349920598,
                 'upload_date': '20121011',
                 'duration': 143.216,
@@ -79,6 +92,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Goldrushed',
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
+                'uploader_id': '9615865',
                 'timestamp': 1337635207,
                 'upload_date': '20120521',
                 'duration': 30,
@@ -92,6 +106,7 @@ class SoundcloudIE(InfoExtractor):
                 # rtmp
                 'skip_download': True,
             },
+            'skip': 'Preview',
         },
         # private link
         {
@@ -103,6 +118,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
                 'description': 'test chars:  \"\'/\\ä↭',
                 'uploader': 'jaimeMF',
+                'uploader_id': '69767071',
                 'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9.927,
@@ -123,6 +139,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
                 'description': 'test chars:  \"\'/\\ä↭',
                 'uploader': 'jaimeMF',
+                'uploader_id': '69767071',
                 'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9.927,
@@ -143,6 +160,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Bus Brakes',
                 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
                 'uploader': 'oddsamples',
+                'uploader_id': '73680509',
                 'timestamp': 1389232924,
                 'upload_date': '20140109',
                 'duration': 17.346,
@@ -163,6 +181,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
                 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
                 'uploader': 'Ori Uplift Music',
+                'uploader_id': '12563093',
                 'timestamp': 1504206263,
                 'upload_date': '20170831',
                 'duration': 7449.096,
@@ -183,6 +202,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Sideways (Prod. Mad Real)',
                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
                 'uploader': 'garyvee',
+                'uploader_id': '2366352',
                 'timestamp': 1488152409,
                 'upload_date': '20170226',
                 'duration': 207.012,
@@ -207,6 +227,7 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Mezzo Valzer',
                 'description': 'md5:4138d582f81866a530317bae316e8b61',
                 'uploader': 'Giovanni Sarani',
+                'uploader_id': '3352531',
                 'timestamp': 1551394171,
                 'upload_date': '20190228',
                 'duration': 180.157,
@@ -221,114 +242,81 @@ class SoundcloudIE(InfoExtractor):
         }
     ]
 
+    _API_BASE = 'https://api.soundcloud.com/'
+    _API_V2_BASE = 'https://api-v2.soundcloud.com/'
+    _BASE_URL = 'https://soundcloud.com/'
     _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI'
+    _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [m.group('url') for m in re.finditer(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
-            webpage)]
+    _ARTWORK_MAP = {
+        'mini': 16,
+        'tiny': 20,
+        'small': 32,
+        'badge': 47,
+        't67x67': 67,
+        'large': 100,
+        't300x300': 300,
+        'crop': 400,
+        't500x500': 500,
+        'original': 0,
+    }
 
     @classmethod
     def _resolv_url(cls, url):
-        return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
+        return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url + '&client_id=' + cls._CLIENT_ID
 
-    def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
+    def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2):
         track_id = compat_str(info['id'])
         title = info['title']
-        name = full_title or track_id
-        if quiet:
-            self.report_extraction(name)
-        thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
-        if isinstance(thumbnail, compat_str):
-            thumbnail = thumbnail.replace('-large', '-t500x500')
-        username = try_get(info, lambda x: x['user']['username'], compat_str)
-
-        def extract_count(key):
-            return int_or_none(info.get('%s_count' % key))
-
-        like_count = extract_count('favoritings')
-        if like_count is None:
-            like_count = extract_count('likes')
-
-        result = {
-            'id': track_id,
-            'uploader': username,
-            'timestamp': unified_timestamp(info.get('created_at')),
-            'title': title,
-            'description': info.get('description'),
-            'thumbnail': thumbnail,
-            'duration': float_or_none(info.get('duration'), 1000),
-            'webpage_url': info.get('permalink_url'),
-            'license': info.get('license'),
-            'view_count': extract_count('playback'),
-            'like_count': like_count,
-            'comment_count': extract_count('comment'),
-            'repost_count': extract_count('reposts'),
-            'genre': info.get('genre'),
-        }
+        track_base_url = self._API_BASE + 'tracks/%s' % track_id
 
         format_urls = set()
         formats = []
         query = {'client_id': self._CLIENT_ID}
-        if secret_token is not None:
+        if secret_token:
             query['secret_token'] = secret_token
-        if info.get('downloadable', False):
-            # We can build a direct link to the song
+
+        if info.get('downloadable'):
             format_url = update_url_query(
-                'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
+                info.get('download_url') or track_base_url + '/download', query)
             format_urls.add(format_url)
+            if version == 2:
+                v1_info = self._download_json(
+                    track_base_url, track_id, query=query, fatal=False) or {}
+            else:
+                v1_info = info
             formats.append({
                 'format_id': 'download',
-                'ext': info.get('original_format', 'mp3'),
+                'ext': v1_info.get('original_format') or 'mp3',
+                'filesize': int_or_none(v1_info.get('original_content_size')),
                 'url': format_url,
-                'vcodec': 'none',
                 'preference': 10,
             })
 
-        # Old API, does not work for some tracks (e.g.
-        # https://soundcloud.com/giovannisarani/mezzo-valzer)
-        format_dict = self._download_json(
-            'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
-            track_id, 'Downloading track url', query=query, fatal=False)
+        def invalid_url(url):
+            return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url)
 
-        if format_dict:
-            for key, stream_url in format_dict.items():
-                if stream_url in format_urls:
-                    continue
-                format_urls.add(stream_url)
-                ext, abr = 'mp3', None
-                mobj = re.search(r'_([^_]+)_(\d+)_url', key)
-                if mobj:
-                    ext, abr = mobj.groups()
-                    abr = int(abr)
-                if key.startswith('http'):
-                    stream_formats = [{
-                        'format_id': key,
-                        'ext': ext,
-                        'url': stream_url,
-                    }]
-                elif key.startswith('rtmp'):
-                    # The url doesn't have an rtmp app, we have to extract the playpath
-                    url, path = stream_url.split('mp3:', 1)
-                    stream_formats = [{
-                        'format_id': key,
-                        'url': url,
-                        'play_path': 'mp3:' + path,
-                        'ext': 'flv',
-                    }]
-                elif key.startswith('hls'):
-                    stream_formats = self._extract_m3u8_formats(
-                        stream_url, track_id, ext, entry_protocol='m3u8_native',
-                        m3u8_id=key, fatal=False)
-                else:
-                    continue
-
-                if abr:
-                    for f in stream_formats:
-                        f['abr'] = abr
-
-                formats.extend(stream_formats)
+        def add_format(f, protocol):
+            mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
+            if mobj:
+                for k, v in mobj.groupdict().items():
+                    if not f.get(k):
+                        f[k] = v
+            format_id_list = []
+            if protocol:
+                format_id_list.append(protocol)
+            for k in ('ext', 'abr'):
+                v = f.get(k)
+                if v:
+                    format_id_list.append(v)
+            abr = f.get('abr')
+            if abr:
+                f['abr'] = int(abr)
+            f.update({
+                'format_id': '_'.join(format_id_list),
+                'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
+            })
+            formats.append(f)
 
         # New API
         transcodings = try_get(
@@ -337,129 +325,165 @@ class SoundcloudIE(InfoExtractor):
             if not isinstance(t, dict):
                 continue
             format_url = url_or_none(t.get('url'))
-            if not format_url:
+            if not format_url or t.get('snipped') or '/preview/' in format_url:
                 continue
             stream = self._download_json(
-                update_url_query(format_url, query), track_id, fatal=False)
+                format_url, track_id, query=query, fatal=False)
             if not isinstance(stream, dict):
                 continue
             stream_url = url_or_none(stream.get('url'))
-            if not stream_url:
-                continue
-            if stream_url in format_urls:
+            if invalid_url(stream_url):
                 continue
             format_urls.add(stream_url)
-            protocol = try_get(t, lambda x: x['format']['protocol'], compat_str)
+            stream_format = t.get('format') or {}
+            protocol = stream_format.get('protocol')
             if protocol != 'hls' and '/hls' in format_url:
                 protocol = 'hls'
             ext = None
             preset = str_or_none(t.get('preset'))
             if preset:
                 ext = preset.split('_')[0]
-                if ext not in KNOWN_EXTENSIONS:
-                    mimetype = try_get(
-                        t, lambda x: x['format']['mime_type'], compat_str)
-                    ext = mimetype2ext(mimetype) or 'mp3'
-            format_id_list = []
-            if protocol:
-                format_id_list.append(protocol)
-            format_id_list.append(ext)
-            format_id = '_'.join(format_id_list)
-            formats.append({
+            if ext not in KNOWN_EXTENSIONS:
+                ext = mimetype2ext(stream_format.get('mime_type'))
+            add_format({
                 'url': stream_url,
-                'format_id': format_id,
                 'ext': ext,
-                'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
-            })
+            }, 'http' if protocol == 'progressive' else protocol)
+
+        if not formats:
+            # Old API, does not work for some tracks (e.g.
+            # https://soundcloud.com/giovannisarani/mezzo-valzer)
+            # and might serve preview URLs (e.g.
+            # http://www.soundcloud.com/snbrn/ele)
+            format_dict = self._download_json(
+                track_base_url + '/streams', track_id,
+                'Downloading track url', query=query, fatal=False) or {}
+
+            for key, stream_url in format_dict.items():
+                if invalid_url(stream_url):
+                    continue
+                format_urls.add(stream_url)
+                mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key)
+                if mobj:
+                    protocol, ext, abr = mobj.groups()
+                    add_format({
+                        'abr': abr,
+                        'ext': ext,
+                        'url': stream_url,
+                    }, protocol)
 
         if not formats:
             # We fallback to the stream_url in the original info, this
             # cannot be always used, sometimes it can give an HTTP 404 error
-            formats.append({
-                'format_id': 'fallback',
-                'url': update_url_query(info['stream_url'], query),
-                'ext': 'mp3',
-            })
-            self._check_formats(formats, track_id)
+            urlh = self._request_webpage(
+                HEADRequest(info.get('stream_url') or track_base_url + '/stream'),
+                track_id, query=query, fatal=False)
+            if urlh:
+                stream_url = urlh.geturl()
+                if not invalid_url(stream_url):
+                    add_format({'url': stream_url}, 'http')
 
         for f in formats:
             f['vcodec'] = 'none'
 
         self._sort_formats(formats)
-        result['formats'] = formats
 
-        return result
+        user = info.get('user') or {}
+
+        thumbnails = []
+        artwork_url = info.get('artwork_url')
+        thumbnail = artwork_url or user.get('avatar_url')
+        if isinstance(thumbnail, compat_str):
+            if re.search(self._IMAGE_REPL_RE, thumbnail):
+                for image_id, size in self._ARTWORK_MAP.items():
+                    i = {
+                        'id': image_id,
+                        'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail),
+                    }
+                    if image_id == 'tiny' and not artwork_url:
+                        size = 18
+                    elif image_id == 'original':
+                        i['preference'] = 10
+                    if size:
+                        i.update({
+                            'width': size,
+                            'height': size,
+                        })
+                    thumbnails.append(i)
+            else:
+                thumbnails = [{'url': thumbnail}]
+
+        def extract_count(key):
+            return int_or_none(info.get('%s_count' % key))
+
+        return {
+            'id': track_id,
+            'uploader': user.get('username'),
+            'uploader_id': str_or_none(user.get('id')) or user.get('permalink'),
+            'uploader_url': user.get('permalink_url'),
+            'timestamp': unified_timestamp(info.get('created_at')),
+            'title': title,
+            'description': info.get('description'),
+            'thumbnails': thumbnails,
+            'duration': float_or_none(info.get('duration'), 1000),
+            'webpage_url': info.get('permalink_url'),
+            'license': info.get('license'),
+            'view_count': extract_count('playback'),
+            'like_count': extract_count('favoritings') or extract_count('likes'),
+            'comment_count': extract_count('comment'),
+            'repost_count': extract_count('reposts'),
+            'genre': info.get('genre'),
+            'formats': formats
+        }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
+        mobj = re.match(self._VALID_URL, url)
 
         track_id = mobj.group('track_id')
-        new_info = {}
 
-        if track_id is not None:
-            info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
+        query = {
+            'client_id': self._CLIENT_ID,
+        }
+        if track_id:
+            info_json_url = self._API_V2_BASE + 'tracks/' + track_id
             full_title = track_id
             token = mobj.group('secret_token')
             if token:
-                info_json_url += '&secret_token=' + token
-        elif mobj.group('player'):
-            query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
-            real_url = query['url'][0]
-            # If the token is in the query of the original url we have to
-            # manually add it
-            if 'secret_token' in query:
-                real_url += '?secret_token=' + query['secret_token'][0]
-            return self.url_result(real_url)
+                query['secret_token'] = token
         else:
-            # extract uploader (which is in the url)
-            uploader = mobj.group('uploader')
-            # extract simple title (uploader + slug of song title)
-            slug_title = mobj.group('title')
+            full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title')
             token = mobj.group('token')
-            full_title = resolve_title = '%s/%s' % (uploader, slug_title)
             if token:
                 resolve_title += '/%s' % token
+            info_json_url = self._resolv_url(self._BASE_URL + resolve_title)
 
-            webpage = self._download_webpage(url, full_title, fatal=False)
-            if webpage:
-                entries = self._parse_json(
-                    self._search_regex(
-                        r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage,
-                        'data', default='[]'), full_title, fatal=False)
-                if entries:
-                    for e in entries:
-                        if not isinstance(e, dict):
-                            continue
-                        if e.get('id') != 67:
-                            continue
-                        data = try_get(e, lambda x: x['data'][0], dict)
-                        if data:
-                            new_info = data
-                            break
-                info_json_url = self._resolv_url(
-                    'https://soundcloud.com/%s' % resolve_title)
-
-        # Contains some additional info missing from new_info
+        version = 2
         info = self._download_json(
-            info_json_url, full_title, 'Downloading info JSON')
+            info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False)
+        if not info:
+            info = self._download_json(
+                info_json_url.replace(self._API_V2_BASE, self._API_BASE),
+                full_title, 'Downloading info JSON', query=query)
+            version = 1
 
-        return self._extract_info_dict(
-            merge_dicts(info, new_info), full_title, secret_token=token)
+        return self._extract_info_dict(info, full_title, token, version)
 
 
 class SoundcloudPlaylistBaseIE(SoundcloudIE):
-    @staticmethod
-    def _extract_id(e):
-        return compat_str(e['id']) if e.get('id') else None
-
-    def _extract_track_entries(self, tracks):
-        return [
-            self.url_result(
-                track['permalink_url'], SoundcloudIE.ie_key(),
-                video_id=self._extract_id(track))
-            for track in tracks if track.get('permalink_url')]
+    def _extract_track_entries(self, tracks, token=None):
+        entries = []
+        for track in tracks:
+            track_id = str_or_none(track.get('id'))
+            url = track.get('permalink_url')
+            if not url:
+                if not track_id:
+                    continue
+                url = self._API_V2_BASE + 'tracks/' + track_id
+                if token:
+                    url += '?secret_token=' + token
+            entries.append(self.url_result(
+                url, SoundcloudIE.ie_key(), track_id))
+        return entries
 
 
 class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
@@ -480,41 +504,28 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
-        # extract uploader (which is in the url)
-        uploader = mobj.group('uploader')
-        # extract simple title (uploader + slug of song title)
-        slug_title = mobj.group('slug_title')
-        full_title = '%s/sets/%s' % (uploader, slug_title)
-        url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
-
+        full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title')
         token = mobj.group('token')
         if token:
             full_title += '/' + token
-            url += '/' + token
 
-        resolv_url = self._resolv_url(url)
-        info = self._download_json(resolv_url, full_title)
+        info = self._download_json(self._resolv_url(
+            self._BASE_URL + full_title), full_title)
 
         if 'errors' in info:
             msgs = (compat_str(err['error_message']) for err in info['errors'])
             raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
 
-        entries = self._extract_track_entries(info['tracks'])
+        entries = self._extract_track_entries(info['tracks'], token)
 
-        return {
-            '_type': 'playlist',
-            'entries': entries,
-            'id': '%s' % info['id'],
-            'title': info['title'],
-        }
+        return self.playlist_result(
+            entries, str_or_none(info.get('id')), info.get('title'))
 
 
 class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
-    _API_V2_BASE = 'https://api-v2.soundcloud.com'
-
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
         COMMON_QUERY = {
-            'limit': 50,
+            'limit': 2000000000,
             'client_id': self._CLIENT_ID,
             'linked_partitioning': '1',
         }
@@ -522,12 +533,13 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
         query = COMMON_QUERY.copy()
         query['offset'] = 0
 
-        next_href = base_url + '?' + compat_urllib_parse_urlencode(query)
+        next_href = base_url
 
         entries = []
         for i in itertools.count():
             response = self._download_json(
-                next_href, playlist_id, 'Downloading track page %s' % (i + 1))
+                next_href, playlist_id,
+                'Downloading track page %s' % (i + 1), query=query)
 
             collection = response['collection']
 
@@ -546,9 +558,8 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
                         continue
                     return self.url_result(
                         permalink_url,
-                        ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
-                        video_id=self._extract_id(cand),
-                        video_title=cand.get('title'))
+                        SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
+                        str_or_none(cand.get('id')), cand.get('title'))
 
             for e in collection:
                 entry = resolve_entry((e, e.get('track'), e.get('playlist')))
@@ -559,11 +570,10 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
             if not next_href:
                 break
 
-            parsed_next_href = compat_urlparse.urlparse(response['next_href'])
-            qs = compat_urlparse.parse_qs(parsed_next_href.query)
-            qs.update(COMMON_QUERY)
-            next_href = compat_urlparse.urlunparse(
-                parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True)))
+            next_href = response['next_href']
+            parsed_next_href = compat_urlparse.urlparse(next_href)
+            query = compat_urlparse.parse_qs(parsed_next_href.query)
+            query.update(COMMON_QUERY)
 
         return {
             '_type': 'playlist',
@@ -609,7 +619,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
         'url': 'https://soundcloud.com/jcv246/sets',
         'info_dict': {
             'id': '12982173',
-            'title': 'Jordi / cv (Playlists)',
+            'title': 'Jordi / cv (Sets)',
         },
         'playlist_mincount': 2,
     }, {
@@ -636,39 +646,29 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     }]
 
     _BASE_URL_MAP = {
-        'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-    }
-
-    _TITLE_MAP = {
-        'all': 'All',
-        'tracks': 'Tracks',
-        'albums': 'Albums',
-        'sets': 'Playlists',
-        'reposts': 'Reposts',
-        'likes': 'Likes',
-        'spotlight': 'Spotlight',
+        'all': 'stream/users/%s',
+        'tracks': 'users/%s/tracks',
+        'albums': 'users/%s/albums',
+        'sets': 'users/%s/playlists',
+        'reposts': 'stream/users/%s/reposts',
+        'likes': 'users/%s/likes',
+        'spotlight': 'users/%s/spotlight',
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group('user')
 
-        url = 'https://soundcloud.com/%s/' % uploader
-        resolv_url = self._resolv_url(url)
         user = self._download_json(
-            resolv_url, uploader, 'Downloading user info')
+            self._resolv_url(self._BASE_URL + uploader),
+            uploader, 'Downloading user info')
 
         resource = mobj.group('rsrc') or 'all'
 
         return self._extract_playlist(
-            self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']),
-            '%s (%s)' % (user['username'], self._TITLE_MAP[resource]))
+            self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'],
+            str_or_none(user.get('id')),
+            '%s (%s)' % (user['username'], resource.capitalize()))
 
 
 class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
@@ -678,7 +678,7 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
         'url': 'https://soundcloud.com/stations/track/officialsundial/your-text',
         'info_dict': {
             'id': '286017854',
-            'title': 'Track station: your-text',
+            'title': 'Track station: your text',
         },
         'playlist_mincount': 47,
     }]
@@ -686,19 +686,17 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
     def _real_extract(self, url):
         track_name = self._match_id(url)
 
-        webpage = self._download_webpage(url, track_name)
-
+        track = self._download_json(self._resolv_url(url), track_name)
         track_id = self._search_regex(
-            r'soundcloud:track-stations:(\d+)', webpage, 'track id')
+            r'soundcloud:track-stations:(\d+)', track['id'], 'track id')
 
         return self._extract_playlist(
-            '%s/stations/soundcloud:track-stations:%s/tracks'
-            % (self._API_V2_BASE, track_id),
-            track_id, 'Track station: %s' % track_name)
+            self._API_V2_BASE + 'stations/%s/tracks' % track['id'],
+            track_id, 'Track station: %s' % track['title'])
 
 
 class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
-    _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
+    _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
     IE_NAME = 'soundcloud:playlist'
     _TESTS = [{
         'url': 'https://api.soundcloud.com/playlists/4110309',
@@ -713,29 +711,22 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         playlist_id = mobj.group('id')
-        base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id)
 
-        data_dict = {
+        query = {
             'client_id': self._CLIENT_ID,
         }
         token = mobj.group('token')
-
         if token:
-            data_dict['secret_token'] = token
+            query['secret_token'] = token
 
-        data = compat_urllib_parse_urlencode(data_dict)
         data = self._download_json(
-            base_url + data, playlist_id, 'Downloading playlist')
+            self._API_V2_BASE + 'playlists/' + playlist_id,
+            playlist_id, 'Downloading playlist', query=query)
 
-        entries = self._extract_track_entries(data['tracks'])
+        entries = self._extract_track_entries(data['tracks'], token)
 
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'title': data.get('title'),
-            'description': data.get('description'),
-            'entries': entries,
-        }
+        return self.playlist_result(
+            entries, playlist_id, data.get('title'), data.get('description'))
 
 
 class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
@@ -753,18 +744,18 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
     _SEARCH_KEY = 'scsearch'
     _MAX_RESULTS_PER_PAGE = 200
     _DEFAULT_RESULTS_PER_PAGE = 50
-    _API_V2_BASE = 'https://api-v2.soundcloud.com'
 
     def _get_collection(self, endpoint, collection_id, **query):
         limit = min(
             query.get('limit', self._DEFAULT_RESULTS_PER_PAGE),
             self._MAX_RESULTS_PER_PAGE)
-        query['limit'] = limit
-        query['client_id'] = self._CLIENT_ID
-        query['linked_partitioning'] = '1'
-        query['offset'] = 0
-        data = compat_urllib_parse_urlencode(query)
-        next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data)
+        query.update({
+            'limit': limit,
+            'client_id': self._CLIENT_ID,
+            'linked_partitioning': 1,
+            'offset': 0,
+        })
+        next_url = update_url_query(self._API_V2_BASE + endpoint, query)
 
         collected_results = 0
 
@@ -791,5 +782,5 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
                 break
 
     def _get_n_results(self, query, n):
-        tracks = self._get_collection('/search/tracks', query, limit=n, q=query)
+        tracks = self._get_collection('search/tracks', query, limit=n, q=query)
         return self.playlist_result(tracks, playlist_title=query)

youtube_dl/extractor/stv.py

@@ -4,15 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urllib_parse_urlparse
-)
 from ..utils import (
-    extract_attributes,
+    compat_str,
     float_or_none,
     int_or_none,
-    str_or_none,
 )
 
 
@@ -20,20 +15,20 @@ class STVPlayerIE(InfoExtractor):
     IE_NAME = 'stv:player'
     _VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
     _TEST = {
-        'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/',
-        'md5': '2ad867d4afd641fa14187596e0fbc91b',
+        'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/',
+        'md5': '5adf9439c31d554f8be0707c7abe7e0a',
         'info_dict': {
-            'id': '6016487034001',
+            'id': '5333973339001',
             'ext': 'mp4',
-            'upload_date': '20190321',
-            'title': 'Interview with the cast ahead of new Victoria',
-            'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.',
-            'timestamp': 1553179628,
+            'upload_date': '20170301',
+            'title': '60 seconds on set with Laura Norton',
+            'description': "How many questions can Laura - a.k.a Kerry Wyatt - answer in 60 seconds? Let\'s find out!",
+            'timestamp': 1488388054,
             'uploader_id': '1486976045',
         },
         'skip': 'this resource is unavailable outside of the UK',
     }
-    _PUBLISHER_ID = '1486976045'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s'
     _PTYPE_MAP = {
         'episode': 'episodes',
         'video': 'shortform',
@@ -41,54 +36,32 @@ class STVPlayerIE(InfoExtractor):
 
     def _real_extract(self, url):
         ptype, video_id = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(url, video_id)
+        resp = self._download_json(
+            'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], video_id),
+            video_id)
 
-        qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex(
-            r'itemprop="embedURL"[^>]+href="([^"]+)',
-            webpage, 'embed URL', default=None)).query)
-        publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID
+        result = resp['results']
+        video = result['video']
+        video_id = compat_str(video['id'])
 
-        player_attr = extract_attributes(self._search_regex(
-            r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {}
+        subtitles = {}
+        _subtitles = result.get('_subtitles') or {}
+        for ext, sub_url in _subtitles.items():
+            subtitles.setdefault('en', []).append({
+                'ext': 'vtt' if ext == 'webvtt' else ext,
+                'url': sub_url,
+            })
 
-        info = {}
-        duration = ref_id = series = video_id = None
-        api_ref_id = player_attr.get('data-player-api-refid')
-        if api_ref_id:
-            resp = self._download_json(
-                'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id),
-                api_ref_id, fatal=False)
-            if resp:
-                result = resp.get('results') or {}
-                video = result.get('video') or {}
-                video_id = str_or_none(video.get('id'))
-                ref_id = video.get('guid')
-                duration = video.get('length')
-                programme = result.get('programme') or {}
-                series = programme.get('name') or programme.get('shortName')
-                subtitles = {}
-                _subtitles = result.get('_subtitles') or {}
-                for ext, sub_url in _subtitles.items():
-                    subtitles.setdefault('en', []).append({
-                        'ext': 'vtt' if ext == 'webvtt' else ext,
-                        'url': sub_url,
-                    })
-                info.update({
-                    'description': result.get('summary'),
-                    'subtitles': subtitles,
-                    'view_count': int_or_none(result.get('views')),
-                })
-        if not video_id:
-            video_id = qs.get('videoId', [None])[0] or self._search_regex(
-                r'<link\s+itemprop="url"\s+href="(\d+)"',
-                webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid'])
+        programme = result.get('programme') or {}
 
-        info.update({
+        return {
             '_type': 'url_transparent',
-            'duration': float_or_none(duration or player_attr.get('data-duration'), 1000),
             'id': video_id,
+            'url': self.BRIGHTCOVE_URL_TEMPLATE % video_id,
+            'description': result.get('summary'),
+            'duration': float_or_none(video.get('length'), 1000),
+            'subtitles': subtitles,
+            'view_count': int_or_none(result.get('views')),
+            'series': programme.get('name') or programme.get('shortName'),
             'ie_key': 'BrightcoveNew',
-            'series': series or player_attr.get('data-programme-name'),
-            'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id),
-        })
-        return info
+        }

youtube_dl/extractor/teachable.py

@@ -48,6 +48,16 @@ class TeachableBaseIE(InfoExtractor):
             'https://%s/sign_in' % site, None,
             'Downloading %s login page' % site)
 
+        def is_logged(webpage):
+            return any(re.search(p, webpage) for p in (
+                r'class=["\']user-signout',
+                r'<a[^>]+\bhref=["\']/sign_out',
+                r'Log\s+[Oo]ut\s*<'))
+
+        if is_logged(login_page):
+            self._logged_in = True
+            return
+
         login_url = compat_str(urlh.geturl())
 
         login_form = self._hidden_inputs(login_page)
@@ -78,10 +88,7 @@ class TeachableBaseIE(InfoExtractor):
                 'Go to https://%s/ and accept.' % (site, site), expected=True)
 
         # Successful login
-        if any(re.search(p, response) for p in (
-                r'class=["\']user-signout',
-                r'<a[^>]+\bhref=["\']/sign_out',
-                r'>\s*Log out\s*<')):
+        if is_logged(response):
             self._logged_in = True
             return
 

youtube_dl/extractor/ted.py

@@ -182,20 +182,29 @@ class TEDIE(InfoExtractor):
 
         title = talk_info['title'].strip()
 
-        native_downloads = try_get(
-            talk_info,
-            (lambda x: x['downloads']['nativeDownloads'],
-             lambda x: x['nativeDownloads']),
-            dict) or {}
+        downloads = talk_info.get('downloads') or {}
+        native_downloads = downloads.get('nativeDownloads') or talk_info.get('nativeDownloads') or {}
 
         formats = [{
             'url': format_url,
             'format_id': format_id,
-            'format': format_id,
         } for (format_id, format_url) in native_downloads.items() if format_url is not None]
+
+        subtitled_downloads = downloads.get('subtitledDownloads') or {}
+        for lang, subtitled_download in subtitled_downloads.items():
+            for q in self._NATIVE_FORMATS:
+                q_url = subtitled_download.get(q)
+                if not q_url:
+                    continue
+                formats.append({
+                    'url': q_url,
+                    'format_id': '%s-%s' % (q, lang),
+                    'language': lang,
+                })
+
         if formats:
             for f in formats:
-                finfo = self._NATIVE_FORMATS.get(f['format_id'])
+                finfo = self._NATIVE_FORMATS.get(f['format_id'].split('-')[0])
                 if finfo:
                     f.update(finfo)
 
@@ -215,34 +224,7 @@ class TEDIE(InfoExtractor):
 
         http_url = None
         for format_id, resources in resources_.items():
-            if format_id == 'h264':
-                for resource in resources:
-                    h264_url = resource.get('file')
-                    if not h264_url:
-                        continue
-                    bitrate = int_or_none(resource.get('bitrate'))
-                    formats.append({
-                        'url': h264_url,
-                        'format_id': '%s-%sk' % (format_id, bitrate),
-                        'tbr': bitrate,
-                    })
-                    if re.search(r'\d+k', h264_url):
-                        http_url = h264_url
-            elif format_id == 'rtmp':
-                streamer = talk_info.get('streamer')
-                if not streamer:
-                    continue
-                for resource in resources:
-                    formats.append({
-                        'format_id': '%s-%s' % (format_id, resource.get('name')),
-                        'url': streamer,
-                        'play_path': resource['file'],
-                        'ext': 'flv',
-                        'width': int_or_none(resource.get('width')),
-                        'height': int_or_none(resource.get('height')),
-                        'tbr': int_or_none(resource.get('bitrate')),
-                    })
-            elif format_id == 'hls':
+            if format_id == 'hls':
                 if not isinstance(resources, dict):
                     continue
                 stream_url = url_or_none(resources.get('stream'))
@@ -251,6 +233,36 @@ class TEDIE(InfoExtractor):
                 formats.extend(self._extract_m3u8_formats(
                     stream_url, video_name, 'mp4', m3u8_id=format_id,
                     fatal=False))
+            else:
+                if not isinstance(resources, list):
+                    continue
+                if format_id == 'h264':
+                    for resource in resources:
+                        h264_url = resource.get('file')
+                        if not h264_url:
+                            continue
+                        bitrate = int_or_none(resource.get('bitrate'))
+                        formats.append({
+                            'url': h264_url,
+                            'format_id': '%s-%sk' % (format_id, bitrate),
+                            'tbr': bitrate,
+                        })
+                        if re.search(r'\d+k', h264_url):
+                            http_url = h264_url
+                elif format_id == 'rtmp':
+                    streamer = talk_info.get('streamer')
+                    if not streamer:
+                        continue
+                    for resource in resources:
+                        formats.append({
+                            'format_id': '%s-%s' % (format_id, resource.get('name')),
+                            'url': streamer,
+                            'play_path': resource['file'],
+                            'ext': 'flv',
+                            'width': int_or_none(resource.get('width')),
+                            'height': int_or_none(resource.get('height')),
+                            'tbr': int_or_none(resource.get('bitrate')),
+                        })
 
         m3u8_formats = list(filter(
             lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',

youtube_dl/extractor/telegraaf.py

@@ -4,21 +4,25 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    remove_end,
+    int_or_none,
+    parse_iso8601,
+    try_get,
 )
 
 
 class TelegraafIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html'
+    _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/video/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html',
+        'url': 'https://www.telegraaf.nl/video/734366489/historisch-scheepswrak-slaat-na-100-jaar-los',
         'info_dict': {
-            'id': '24353229',
+            'id': 'gaMItuoSeUg2',
             'ext': 'mp4',
-            'title': 'Tikibad ontruimd wegens brand',
-            'description': 'md5:05ca046ff47b931f9b04855015e163a4',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 33,
+            'title': 'Historisch scheepswrak slaat na 100 jaar los',
+            'description': 'md5:6f53b7c4f55596722ac24d6c0ec00cfb',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 55,
+            'timestamp': 1572805527,
+            'upload_date': '20191103',
         },
         'params': {
             # m3u8 download
@@ -27,23 +31,30 @@ class TelegraafIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        article_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        video_id = self._download_json(
+            'https://www.telegraaf.nl/graphql', article_id, query={
+                'query': '''{
+  article(uid: %s) {
+    videos {
+      videoId
+    }
+  }
+}''' % article_id,
+            })['data']['article']['videos'][0]['videoId']
 
-        player_url = self._html_search_regex(
-            r'<iframe[^>]+src="([^"]+")', webpage, 'player URL')
-        player_page = self._download_webpage(
-            player_url, video_id, note='Download player webpage')
-        playlist_url = self._search_regex(
-            r'playlist\s*:\s*"([^"]+)"', player_page, 'playlist URL')
-        playlist_data = self._download_json(playlist_url, video_id)
+        item = self._download_json(
+            'https://content.tmgvideo.nl/playlist/item=%s/playlist.json' % video_id,
+            video_id)['items'][0]
+        title = item['title']
 
-        item = playlist_data['items'][0]
         formats = []
-        locations = item['locations']
+        locations = item.get('locations') or {}
         for location in locations.get('adaptive', []):
-            manifest_url = location['src']
+            manifest_url = location.get('src')
+            if not manifest_url:
+                continue
             ext = determine_ext(manifest_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
@@ -54,25 +65,25 @@ class TelegraafIE(InfoExtractor):
             else:
                 self.report_warning('Unknown adaptive format %s' % ext)
         for location in locations.get('progressive', []):
+            src = try_get(location, lambda x: x['sources'][0]['src'])
+            if not src:
+                continue
+            label = location.get('label')
             formats.append({
-                'url': location['sources'][0]['src'],
-                'width': location.get('width'),
-                'height': location.get('height'),
-                'format_id': 'http-%s' % location['label'],
+                'url': src,
+                'width': int_or_none(location.get('width')),
+                'height': int_or_none(location.get('height')),
+                'format_id': 'http' + ('-%s' % label if label else ''),
             })
 
         self._sort_formats(formats)
 
-        title = remove_end(self._og_search_title(webpage), ' - VIDEO')
-        description = self._og_search_description(webpage)
-        duration = item.get('duration')
-        thumbnail = item.get('poster')
-
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': item.get('description'),
             'formats': formats,
-            'duration': duration,
-            'thumbnail': thumbnail,
+            'duration': int_or_none(item.get('duration')),
+            'thumbnail': item.get('poster'),
+            'timestamp': parse_iso8601(item.get('datecreated'), ' '),
         }

youtube_dl/extractor/telequebec.py

@@ -7,6 +7,7 @@ from ..utils import (
     int_or_none,
     smuggle_url,
     try_get,
+    unified_timestamp,
 )
 
 
@@ -22,7 +23,13 @@ class TeleQuebecBaseIE(InfoExtractor):
 
 
 class TeleQuebecIE(TeleQuebecBaseIE):
-    _VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            zonevideo\.telequebec\.tv/media|
+                            coucou\.telequebec\.tv/videos
+                        )/(?P<id>\d+)
+                    '''
     _TESTS = [{
         # available till 01.01.2023
         'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
@@ -41,6 +48,9 @@ class TeleQuebecIE(TeleQuebecBaseIE):
         # no description
         'url': 'http://zonevideo.telequebec.tv/media/30261',
         'only_matching': True,
+    }, {
+        'url': 'https://coucou.telequebec.tv/videos/41788/idee-de-genie/l-heure-du-bain',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -61,6 +71,52 @@ class TeleQuebecIE(TeleQuebecBaseIE):
         return info
 
 
+class TeleQuebecSquatIE(InfoExtractor):
+    _VALID_URL = r'https://squat\.telequebec\.tv/videos/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://squat.telequebec.tv/videos/9314',
+        'info_dict': {
+            'id': 'd59ae78112d542e793d83cc9d3a5b530',
+            'ext': 'mp4',
+            'title': 'Poupeflekta',
+            'description': 'md5:2f0718f8d2f8fece1646ee25fb7bce75',
+            'duration': 1351,
+            'timestamp': 1569057600,
+            'upload_date': '20190921',
+            'series': 'Miraculous : Les Aventures de Ladybug et Chat Noir',
+            'season': 'Saison 3',
+            'season_number': 3,
+            'episode_number': 57,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'https://squat.api.telequebec.tv/v1/videos/%s' % video_id,
+            video_id)
+
+        media_id = video['sourceId']
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'http://zonevideo.telequebec.tv/media/%s' % media_id,
+            'ie_key': TeleQuebecIE.ie_key(),
+            'id': media_id,
+            'title': video.get('titre'),
+            'description': video.get('description'),
+            'timestamp': unified_timestamp(video.get('datePublication')),
+            'series': video.get('container'),
+            'season': video.get('saison'),
+            'season_number': int_or_none(video.get('noSaison')),
+            'episode_number': int_or_none(video.get('episode')),
+        }
+
+
 class TeleQuebecEmissionIE(TeleQuebecBaseIE):
     _VALID_URL = r'''(?x)
                     https?://

youtube_dl/extractor/tenplay.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_age_limit,
+    parse_iso8601,
+    smuggle_url,
+)
+
+
+class TenPlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})'
+    _TEST = {
+        'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga',
+        'info_dict': {
+            'id': '6060533435001',
+            'ext': 'mp4',
+            'title': 'MasterChef - S1 Ep. 1',
+            'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c',
+            'age_limit': 10,
+            'timestamp': 1240828200,
+            'upload_date': '20090427',
+            'uploader_id': '2199827728001',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        }
+    }
+    BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        content_id = self._match_id(url)
+        data = self._download_json(
+            'https://10play.com.au/api/video/' + content_id, content_id)
+        video = data.get('video') or {}
+        metadata = data.get('metaData') or {}
+        brightcove_id = video.get('videoId') or metadata['showContentVideoId']
+        brightcove_url = smuggle_url(
+            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+            {'geo_countries': ['AU']})
+
+        return {
+            '_type': 'url_transparent',
+            'url': brightcove_url,
+            'id': content_id,
+            'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'),
+            'description': video.get('description'),
+            'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')),
+            'series': metadata.get('showName'),
+            'season': metadata.get('showContentSeason'),
+            'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')),
+            'ie_key': 'BrightcoveNew',
+        }

youtube_dl/extractor/thesun.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
+from ..utils import extract_attributes
 
 
 class TheSunIE(InfoExtractor):
@@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor):
         },
         'playlist_count': 2,
     }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
         article_id = self._match_id(url)
@@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor):
         webpage = self._download_webpage(url, article_id)
 
         entries = []
-        for ooyala_id in re.findall(
-                r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)',
+        for video in re.findall(
+                r'<video[^>]+data-video-id-pending=[^>]+>',
                 webpage):
-            entries.append(OoyalaIE._build_url_result(ooyala_id))
+            attrs = extract_attributes(video)
+            video_id = attrs['data-video-id-pending']
+            account_id = attrs.get('data-account', '5067014667001')
+            entries.append(self.url_result(
+                self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id),
+                'BrightcoveNew', video_id))
 
         return self.playlist_result(
             entries, article_id, self._og_search_title(webpage, fatal=False))

youtube_dl/extractor/tutv.py

@@ -1,36 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_b64decode,
-    compat_parse_qs,
-)
-
-
-class TutvIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
-    _TEST = {
-        'url': 'http://tu.tv/videos/robots-futbolistas',
-        'md5': '0cd9e28ad270488911b0d2a72323395d',
-        'info_dict': {
-            'id': '2973058',
-            'ext': 'mp4',
-            'title': 'Robots futbolistas',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
-
-        data_content = self._download_webpage(
-            'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
-        video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
-
-        return {
-            'id': internal_id,
-            'url': video_url,
-            'title': self._og_search_title(webpage),
-        }

youtube_dl/extractor/tv2.py

@@ -11,6 +11,7 @@ from ..utils import (
     js_to_json,
     parse_iso8601,
     remove_end,
+    try_get,
 )
 
 
@@ -44,7 +45,14 @@ class TV2IE(InfoExtractor):
             data = self._download_json(
                 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol),
                 video_id, 'Downloading play JSON')['playback']
-            for item in data['items']['item']:
+            items = try_get(data, lambda x: x['items']['item'])
+            if not items:
+                continue
+            if not isinstance(items, list):
+                items = [items]
+            for item in items:
+                if not isinstance(item, dict):
+                    continue
                 video_url = item.get('url')
                 if not video_url or video_url in format_urls:
                     continue

youtube_dl/extractor/tv2dk.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import extract_attributes
+
+
+class TV2DKIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            tvsyd|
+                            tv2ostjylland|
+                            tvmidtvest|
+                            tv2fyn|
+                            tv2east|
+                            tv2lorry|
+                            tv2nord
+                        )\.dk/
+                        (:[^/]+/)*
+                        (?P<id>[^/?\#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player',
+        'info_dict': {
+            'id': '0_52jmwa0p',
+            'ext': 'mp4',
+            'title': '19:30 - 28. okt. 2019',
+            'timestamp': 1572290248,
+            'upload_date': '20191028',
+            'uploader_id': 'tvsyd',
+            'duration': 1347,
+            'view_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Kaltura'],
+    }, {
+        'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        entries = []
+        for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
+            video = extract_attributes(video_el)
+            kaltura_id = video.get('data-entryid')
+            if not kaltura_id:
+                continue
+            partner_id = video.get('data-partnerid')
+            if not partner_id:
+                continue
+            entries.append(self.url_result(
+                'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
+                video_id=kaltura_id))
+        return self.playlist_result(entries)

youtube_dl/extractor/tv4.py

@@ -72,8 +72,13 @@ class TV4IE(InfoExtractor):
         video_id = self._match_id(url)
 
         info = self._download_json(
-            'http://www.tv4play.se/player/assets/%s.json' % video_id,
-            video_id, 'Downloading video info JSON')
+            'https://playback-api.b17g.net/asset/%s' % video_id,
+            video_id, 'Downloading video info JSON', query={
+                'service': 'tv4',
+                'device': 'browser',
+                'protocol': 'hls,dash',
+                'drm': 'widevine',
+            })['metadata']
 
         title = info['title']
 
@@ -111,5 +116,9 @@ class TV4IE(InfoExtractor):
             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
             'duration': int_or_none(info.get('duration')),
             'thumbnail': info.get('image'),
-            'is_live': info.get('is_live') is True,
+            'is_live': info.get('isLive') is True,
+            'series': info.get('seriesTitle'),
+            'season_number': int_or_none(info.get('seasonNumber')),
+            'episode': info.get('episodeTitle'),
+            'episode_number': int_or_none(info.get('episodeNumber')),
         }

youtube_dl/extractor/twitch.py

@@ -248,7 +248,7 @@ class TwitchVodIE(TwitchItemBaseIE):
                     https?://
                         (?:
                             (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/|
-                            player\.twitch\.tv/\?.*?\bvideo=v
+                            player\.twitch\.tv/\?.*?\bvideo=v?
                         )
                         (?P<id>\d+)
                     '''
@@ -306,6 +306,9 @@ class TwitchVodIE(TwitchItemBaseIE):
     }, {
         'url': 'https://www.twitch.tv/northernlion/video/291940395',
         'only_matching': True,
+    }, {
+        'url': 'https://player.twitch.tv/?video=480452374',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/vessel.py

@@ -1,157 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import json
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    parse_iso8601,
-    sanitized_Request,
-)
-
-
-class VesselIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)'
-    _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
-    _LOGIN_URL = 'https://www.vessel.com/api/account/login'
-    _NETRC_MACHINE = 'vessel'
-    _TESTS = [{
-        'url': 'https://www.vessel.com/videos/HDN7G5UMs',
-        'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
-        'info_dict': {
-            'id': 'HDN7G5UMs',
-            'ext': 'mp4',
-            'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20150317',
-            'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
-            'timestamp': int,
-        },
-    }, {
-        'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.vessel.com/videos/F01_dsLj1',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.vessel.com/videos/RRX-sir-J',
-        'only_matching': True,
-    }]
-
-    @staticmethod
-    def _extract_urls(webpage):
-        return [url for _, url in re.findall(
-            r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1',
-            webpage)]
-
-    @staticmethod
-    def make_json_request(url, data):
-        payload = json.dumps(data).encode('utf-8')
-        req = sanitized_Request(url, payload)
-        req.add_header('Content-Type', 'application/json; charset=utf-8')
-        return req
-
-    @staticmethod
-    def find_assets(data, asset_type, asset_id=None):
-        for asset in data.get('assets', []):
-            if not asset.get('type') == asset_type:
-                continue
-            elif asset_id is not None and not asset.get('id') == asset_id:
-                continue
-            else:
-                yield asset
-
-    def _check_access_rights(self, data):
-        access_info = data.get('__view', {})
-        if not access_info.get('allow_access', True):
-            err_code = access_info.get('error_code') or ''
-            if err_code == 'ITEM_PAID_ONLY':
-                raise ExtractorError(
-                    'This video requires subscription.', expected=True)
-            else:
-                raise ExtractorError(
-                    'Access to this content is restricted. (%s said: %s)' % (self.IE_NAME, err_code), expected=True)
-
-    def _login(self):
-        username, password = self._get_login_info()
-        if username is None:
-            return
-        self.report_login()
-        data = {
-            'client_id': 'web',
-            'type': 'password',
-            'user_key': username,
-            'password': password,
-        }
-        login_request = VesselIE.make_json_request(self._LOGIN_URL, data)
-        self._download_webpage(login_request, None, False, 'Wrong login info')
-
-    def _real_initialize(self):
-        self._login()
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        data = self._parse_json(self._search_regex(
-            r'App\.bootstrapData\((.*?)\);', webpage, 'data'), video_id)
-        asset_id = data['model']['data']['id']
-
-        req = VesselIE.make_json_request(
-            self._API_URL_TEMPLATE % asset_id, {'client': 'web'})
-        data = self._download_json(req, video_id)
-        video_asset_id = data.get('main_video_asset')
-
-        self._check_access_rights(data)
-
-        try:
-            video_asset = next(
-                VesselIE.find_assets(data, 'video', asset_id=video_asset_id))
-        except StopIteration:
-            raise ExtractorError('No video assets found')
-
-        formats = []
-        for f in video_asset.get('sources', []):
-            location = f.get('location')
-            if not location:
-                continue
-            name = f.get('name')
-            if name == 'hls-index':
-                formats.extend(self._extract_m3u8_formats(
-                    location, video_id, ext='mp4',
-                    entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False))
-            elif name == 'dash-index':
-                formats.extend(self._extract_mpd_formats(
-                    location, video_id, mpd_id='dash', fatal=False))
-            else:
-                formats.append({
-                    'format_id': name,
-                    'tbr': f.get('bitrate'),
-                    'height': f.get('height'),
-                    'width': f.get('width'),
-                    'url': location,
-                })
-        self._sort_formats(formats)
-
-        thumbnails = []
-        for im_asset in VesselIE.find_assets(data, 'image'):
-            thumbnails.append({
-                'url': im_asset['location'],
-                'width': im_asset.get('width', 0),
-                'height': im_asset.get('height', 0),
-            })
-
-        return {
-            'id': video_id,
-            'title': data['title'],
-            'formats': formats,
-            'thumbnails': thumbnails,
-            'description': data.get('short_description'),
-            'duration': data.get('duration'),
-            'comment_count': data.get('comment_count'),
-            'like_count': data.get('like_count'),
-            'view_count': data.get('view_count'),
-            'timestamp': parse_iso8601(data.get('released_at')),
-        }

youtube_dl/extractor/videodetective.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from .internetvideoarchive import InternetVideoArchiveIE
 
 
@@ -13,7 +12,7 @@ class VideoDetectiveIE(InfoExtractor):
         'info_dict': {
             'id': '194487',
             'ext': 'mp4',
-            'title': 'KICK-ASS 2',
+            'title': 'Kick-Ass 2',
             'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
         },
         'params': {
@@ -24,7 +23,7 @@ class VideoDetectiveIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        og_video = self._og_search_video_url(webpage)
-        query = compat_urlparse.urlparse(og_video).query
-        return self.url_result(InternetVideoArchiveIE._build_json_url(query), ie=InternetVideoArchiveIE.ie_key())
+        query = 'customerid=69249&publishedid=' + video_id
+        return self.url_result(
+            InternetVideoArchiveIE._build_json_url(query),
+            ie=InternetVideoArchiveIE.ie_key())

youtube_dl/extractor/viewlift.py

@@ -13,11 +13,12 @@ from ..utils import (
     js_to_json,
     parse_age_limit,
     parse_duration,
+    try_get,
 )
 
 
 class ViewLiftBaseIE(InfoExtractor):
-    _DOMAINS_REGEX = r'(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv'
+    _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv'
 
 
 class ViewLiftEmbedIE(ViewLiftBaseIE):
@@ -113,7 +114,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
 
 
 class ViewLiftIE(ViewLiftBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)/(?:films/title|show|(?:news/)?videos?)/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
     _TESTS = [{
         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
         'md5': '19844f897b35af219773fd63bdec2942',
@@ -128,7 +129,7 @@ class ViewLiftIE(ViewLiftBaseIE):
             'categories': 'mincount:3',
             'age_limit': 14,
             'upload_date': '20150421',
-            'timestamp': 1429656819,
+            'timestamp': 1429656820,
         }
     }, {
         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
@@ -141,10 +142,26 @@ class ViewLiftIE(ViewLiftBaseIE):
             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 979,
-            'categories': 'mincount:2',
             'timestamp': 1399478279,
             'upload_date': '20140507',
         }
+    }, {
+        'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
+        'info_dict': {
+            'id': '00000148-7b53-de26-a9fb-fbf306f70020',
+            'display_id': 'augie_alone/s_2_ep_12_love',
+            'ext': 'mp4',
+            'title': 'Augie, Alone:S. 2 Ep. 12 - Love',
+            'description': 'md5:db2a5c72d994f16a780c1eb353a8f403',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 107,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://main.snagfilms.com/films/title/the_freebie',
+        'only_matching': True,
     }, {
         # Film is not playable in your area.
         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
@@ -162,6 +179,10 @@ class ViewLiftIE(ViewLiftBaseIE):
         'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
+
     def _real_extract(self, url):
         domain, display_id = re.match(self._VALID_URL, url).groups()
 
@@ -181,7 +202,21 @@ class ViewLiftIE(ViewLiftBaseIE):
             gist = content_data['gist']
             film_id = gist['id']
             title = gist['title']
-            video_assets = content_data['streamingInfo']['videoAssets']
+            video_assets = try_get(
+                content_data, lambda x: x['streamingInfo']['videoAssets'], dict)
+            if not video_assets:
+                token = self._download_json(
+                    'https://prod-api.viewlift.com/identity/anonymous-token',
+                    film_id, 'Downloading authorization token',
+                    query={'site': 'snagfilms'})['authorizationToken']
+                video_assets = self._download_json(
+                    'https://prod-api.viewlift.com/entitlement/video/status',
+                    film_id, headers={
+                        'Authorization': token,
+                        'Referer': url,
+                    }, query={
+                        'id': film_id
+                    })['video']['streamingInfo']['videoAssets']
 
             formats = []
             mpeg_video_assets = video_assets.get('mpeg') or []
@@ -241,8 +276,9 @@ class ViewLiftIE(ViewLiftBaseIE):
                         if category.get('title')]
                     break
             else:
-                title = self._search_regex(
-                    r'itemprop="title">([^<]+)<', webpage, 'title')
+                title = self._html_search_regex(
+                    (r'itemprop="title">([^<]+)<',
+                     r'(?s)itemprop="title">(.+?)<div'), webpage, 'title')
                 description = self._html_search_regex(
                     r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
                     webpage, 'description', default=None) or self._og_search_description(webpage)

youtube_dl/extractor/viewster.py

@@ -1,217 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_urllib_parse_unquote,
-)
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    int_or_none,
-    parse_iso8601,
-    sanitized_Request,
-    HEADRequest,
-    url_basename,
-)
-
-
-class ViewsterIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
-    _TESTS = [{
-        # movie, Type=Movie
-        'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
-        'md5': 'e642d1b27fcf3a4ffa79f194f5adde36',
-        'info_dict': {
-            'id': '1140-11855-000',
-            'ext': 'mp4',
-            'title': 'The listening Project',
-            'description': 'md5:bac720244afd1a8ea279864e67baa071',
-            'timestamp': 1214870400,
-            'upload_date': '20080701',
-            'duration': 4680,
-        },
-    }, {
-        # series episode, Type=Episode
-        'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/',
-        'md5': '9243079a8531809efe1b089db102c069',
-        'info_dict': {
-            'id': '1284-19427-001',
-            'ext': 'mp4',
-            'title': 'The World and a Wall',
-            'description': 'md5:24814cf74d3453fdf5bfef9716d073e3',
-            'timestamp': 1428192000,
-            'upload_date': '20150405',
-            'duration': 1500,
-        },
-    }, {
-        # serie, Type=Serie
-        'url': 'http://www.viewster.com/serie/1303-19426-000/',
-        'info_dict': {
-            'id': '1303-19426-000',
-            'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?',
-            'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11',
-        },
-        'playlist_count': 13,
-    }, {
-        # unfinished serie, no Type
-        'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/',
-        'info_dict': {
-            'id': '1284-19427-000',
-            'title': 'Baby Steps—Season 2',
-            'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1',
-        },
-        'playlist_mincount': 16,
-    }, {
-        # geo restricted series
-        'url': 'https://www.viewster.com/serie/1280-18794-002/',
-        'only_matching': True,
-    }, {
-        # geo restricted video
-        'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/',
-        'only_matching': True,
-    }]
-
-    _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
-
-    def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}):
-        request = sanitized_Request(url)
-        request.add_header('Accept', self._ACCEPT_HEADER)
-        request.add_header('Auth-token', self._AUTH_TOKEN)
-        return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        # Get 'api_token' cookie
-        self._request_webpage(
-            HEADRequest('http://www.viewster.com/'),
-            video_id, headers=self.geo_verification_headers())
-        cookies = self._get_cookies('http://www.viewster.com/')
-        self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
-
-        info = self._download_json(
-            'https://public-api.viewster.com/search/%s' % video_id,
-            video_id, 'Downloading entry JSON')
-
-        entry_id = info.get('Id') or info['id']
-
-        # unfinished serie has no Type
-        if info.get('Type') in ('Serie', None):
-            try:
-                episodes = self._download_json(
-                    'https://public-api.viewster.com/series/%s/episodes' % entry_id,
-                    video_id, 'Downloading series JSON')
-            except ExtractorError as e:
-                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
-                    self.raise_geo_restricted()
-                else:
-                    raise
-            entries = [
-                self.url_result(
-                    'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster')
-                for episode in episodes]
-            title = (info.get('Title') or info['Synopsis']['Title']).strip()
-            description = info.get('Synopsis', {}).get('Detailed')
-            return self.playlist_result(entries, video_id, title, description)
-
-        formats = []
-        for language_set in info.get('LanguageSets', []):
-            manifest_url = None
-            m3u8_formats = []
-            audio = language_set.get('Audio') or ''
-            subtitle = language_set.get('Subtitle') or ''
-            base_format_id = audio
-            if subtitle:
-                base_format_id += '-%s' % subtitle
-
-            def concat(suffix, sep='-'):
-                return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix
-
-            medias = self._download_json(
-                'https://public-api.viewster.com/movies/%s/videos' % entry_id,
-                video_id, fatal=False, query={
-                    'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'],
-                    'language': audio,
-                    'subtitle': subtitle,
-                })
-            if not medias:
-                continue
-            for media in medias:
-                video_url = media.get('Uri')
-                if not video_url:
-                    continue
-                ext = determine_ext(video_url)
-                if ext == 'f4m':
-                    manifest_url = video_url
-                    video_url += '&' if '?' in video_url else '?'
-                    video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
-                    formats.extend(self._extract_f4m_formats(
-                        video_url, video_id, f4m_id=concat('hds')))
-                elif ext == 'm3u8':
-                    manifest_url = video_url
-                    m3u8_formats = self._extract_m3u8_formats(
-                        video_url, video_id, 'mp4', m3u8_id=concat('hls'),
-                        fatal=False)  # m3u8 sometimes fail
-                    if m3u8_formats:
-                        formats.extend(m3u8_formats)
-                else:
-                    qualities_basename = self._search_regex(
-                        r'/([^/]+)\.csmil/',
-                        manifest_url, 'qualities basename', default=None)
-                    if not qualities_basename:
-                        continue
-                    QUALITIES_RE = r'((,\d+k)+,?)'
-                    qualities = self._search_regex(
-                        QUALITIES_RE, qualities_basename,
-                        'qualities', default=None)
-                    if not qualities:
-                        continue
-                    qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(',')))
-                    qualities.sort()
-                    http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename)
-                    http_url_basename = url_basename(video_url)
-                    if m3u8_formats:
-                        self._sort_formats(m3u8_formats)
-                        m3u8_formats = list(filter(
-                            lambda f: f.get('vcodec') != 'none', m3u8_formats))
-                    if len(qualities) == len(m3u8_formats):
-                        for q, m3u8_format in zip(qualities, m3u8_formats):
-                            f = m3u8_format.copy()
-                            f.update({
-                                'url': video_url.replace(http_url_basename, http_template % q),
-                                'format_id': f['format_id'].replace('hls', 'http'),
-                                'protocol': 'http',
-                            })
-                            formats.append(f)
-                    else:
-                        for q in qualities:
-                            formats.append({
-                                'url': video_url.replace(http_url_basename, http_template % q),
-                                'ext': 'mp4',
-                                'format_id': 'http-%d' % q,
-                                'tbr': q,
-                            })
-
-        if not formats and not info.get('VODSettings'):
-            self.raise_geo_restricted()
-
-        self._sort_formats(formats)
-
-        synopsis = info.get('Synopsis') or {}
-        # Prefer title outside synopsis since it's less messy
-        title = (info.get('Title') or synopsis['Title']).strip()
-        description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short')
-        duration = int_or_none(info.get('Duration'))
-        timestamp = parse_iso8601(info.get('ReleaseDate'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'duration': duration,
-            'formats': formats,
-        }

youtube_dl/extractor/vimeo.py

@@ -23,7 +23,6 @@ from ..utils import (
     NO_DEFAULT,
     OnDemandPagedList,
     parse_filesize,
-    qualities,
     RegexNotFoundError,
     sanitized_Request,
     smuggle_url,
@@ -211,6 +210,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         video_uploader_url = owner.get('url')
 
         return {
+            'id': video_id,
             'title': self._live_title(video_title) if is_live else video_title,
             'uploader': owner.get('name'),
             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
@@ -730,7 +730,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 
         info_dict = {
-            'id': video_id,
             'formats': formats,
             'timestamp': unified_timestamp(timestamp),
             'description': video_description,
@@ -939,7 +938,7 @@ class VimeoAlbumIE(VimeoChannelIE):
     def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
         api_page = page + 1
         query = {
-            'fields': 'link',
+            'fields': 'link,uri',
             'page': api_page,
             'per_page': self._PAGE_SIZE,
         }
@@ -954,7 +953,9 @@ class VimeoAlbumIE(VimeoChannelIE):
             link = video.get('link')
             if not link:
                 continue
-            yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link))
+            uri = video.get('uri')
+            video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
+            yield self.url_result(link, VimeoIE.ie_key(), video_id)
 
     def _real_extract(self, url):
         album_id = self._match_id(url)
@@ -1061,7 +1062,6 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
         if source_format:
             info_dict['formats'].append(source_format)
         self._vimeo_sort_formats(info_dict['formats'])
-        info_dict['id'] = video_id
         return info_dict
 
 
@@ -1115,94 +1115,17 @@ class VimeoLikesIE(VimeoChannelIE):
         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
 
 
-class VHXEmbedIE(InfoExtractor):
+class VHXEmbedIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vhx:embed'
     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
 
-    def _call_api(self, video_id, access_token, path='', query=None):
-        return self._download_json(
-            'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={
-                'Authorization': 'Bearer ' + access_token,
-            }, query=query)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        credentials = self._parse_json(self._search_regex(
-            r'(?s)credentials\s*:\s*({.+?}),', webpage,
-            'config'), video_id, js_to_json)
-        access_token = credentials['access_token']
-
-        query = {}
-        for k, v in credentials.items():
-            if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined':
-                if k == 'authUserToken':
-                    query['auth_user_token'] = v
-                else:
-                    query[k] = v
-        files = self._call_api(video_id, access_token, '/files', query)
-
-        formats = []
-        for f in files:
-            href = try_get(f, lambda x: x['_links']['source']['href'])
-            if not href:
-                continue
-            method = f.get('method')
-            if method == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    href, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
-            elif method == 'dash':
-                formats.extend(self._extract_mpd_formats(
-                    href, video_id, mpd_id='dash', fatal=False))
-            else:
-                fmt = {
-                    'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])),
-                    'format_id': 'http',
-                    'preference': 1,
-                    'url': href,
-                    'vcodec': f.get('codec'),
-                }
-                quality = f.get('quality')
-                if quality:
-                    fmt.update({
-                        'format_id': 'http-' + quality,
-                        'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)),
-                    })
-                formats.append(fmt)
-        self._sort_formats(formats)
-
-        video_data = self._call_api(video_id, access_token)
-        title = video_data.get('title') or video_data['name']
-
-        subtitles = {}
-        for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []:
-            lang = subtitle.get('srclang') or subtitle.get('label')
-            for _link in subtitle.get('_links', {}).values():
-                href = _link.get('href')
-                if not href:
-                    continue
-                subtitles.setdefault(lang, []).append({
-                    'url': href,
-                })
-
-        q = qualities(['small', 'medium', 'large', 'source'])
-        thumbnails = []
-        for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items():
-            thumbnails.append({
-                'id': thumbnail_id,
-                'url': thumbnail_url,
-                'preference': q(thumbnail_id),
-            })
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video_data.get('description'),
-            'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])),
-            'formats': formats,
-            'subtitles': subtitles,
-            'thumbnails': thumbnails,
-            'timestamp': unified_timestamp(video_data.get('created_at')),
-            'view_count': int_or_none(video_data.get('plays_count')),
-        }
+        config_url = self._parse_json(self._search_regex(
+            r'window\.OTTData\s*=\s*({.+})', webpage,
+            'ott data'), video_id, js_to_json)['config_url']
+        config = self._download_json(config_url, video_id)
+        info = self._parse_config(config, video_id)
+        self._vimeo_sort_formats(info['formats'])
+        return info

youtube_dl/extractor/vk.py

@@ -12,7 +12,6 @@ from ..utils import (
     get_element_by_class,
     int_or_none,
     orderedSet,
-    remove_start,
     str_or_none,
     str_to_int,
     unescapeHTML,
@@ -21,6 +20,7 @@ from ..utils import (
     urlencode_postdata,
 )
 from .dailymotion import DailymotionIE
+from .odnoklassniki import OdnoklassnikiIE
 from .pladform import PladformIE
 from .vimeo import VimeoIE
 from .youtube import YoutubeIE
@@ -60,6 +60,18 @@ class VKBaseIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
+    def _download_payload(self, path, video_id, data, fatal=True):
+        data['al'] = 1
+        code, payload = self._download_json(
+            'https://vk.com/%s.php' % path, video_id,
+            data=urlencode_postdata(data), fatal=fatal,
+            headers={'X-Requested-With': 'XMLHttpRequest'})['payload']
+        if code == '3':
+            self.raise_login_required()
+        elif code == '8':
+            raise ExtractorError(clean_html(payload[0][1:-1]), expected=True)
+        return payload
+
 
 class VKIE(VKBaseIE):
     IE_NAME = 'vk'
@@ -96,7 +108,6 @@ class VKIE(VKBaseIE):
         },
         {
             'url': 'http://vk.com/video205387401_165548505',
-            'md5': '6c0aeb2e90396ba97035b9cbde548700',
             'info_dict': {
                 'id': '205387401_165548505',
                 'ext': 'mp4',
@@ -110,18 +121,18 @@ class VKIE(VKBaseIE):
         },
         {
             'note': 'Embedded video',
-            'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
-            'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
+            'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
+            'md5': '7babad3b85ea2e91948005b1b8b0cb84',
             'info_dict': {
-                'id': '32194266_162925554',
+                'id': '-77521_162222515',
                 'ext': 'mp4',
-                'uploader': 'Vladimir Gavrin',
-                'title': 'Lin Dan',
-                'duration': 101,
-                'upload_date': '20120730',
-                'view_count': int,
+                'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
+                'title': 'ProtivoGunz - Хуёвая песня',
+                'duration': 195,
+                'upload_date': '20120212',
+                'timestamp': 1329049880,
+                'uploader_id': '-77521',
             },
-            'skip': 'This video has been removed from public access.',
         },
         {
             # VIDEO NOW REMOVED
@@ -138,18 +149,19 @@ class VKIE(VKBaseIE):
                 'upload_date': '20121218',
                 'view_count': int,
             },
-            'skip': 'Requires vk account credentials',
+            'skip': 'Removed',
         },
         {
             'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
-            'md5': '4d7a5ef8cf114dfa09577e57b2993202',
             'info_dict': {
                 'id': '-43215063_168067957',
                 'ext': 'mp4',
-                'uploader': 'Киномания - лучшее из мира кино',
+                'uploader': 'Bro Mazter',
                 'title': ' ',
                 'duration': 7291,
                 'upload_date': '20140328',
+                'uploader_id': '223413403',
+                'timestamp': 1396018030,
             },
             'skip': 'Requires vk account credentials',
         },
@@ -165,7 +177,7 @@ class VKIE(VKBaseIE):
                 'upload_date': '20140626',
                 'view_count': int,
             },
-            'skip': 'Only works from Russia',
+            'skip': 'Removed',
         },
         {
             # video (removed?) only available with list id
@@ -247,6 +259,9 @@ class VKIE(VKBaseIE):
                 'uploader_id': '-387766',
                 'timestamp': 1475137527,
             },
+            'params': {
+                'skip_download': True,
+            },
         },
         {
             # live stream, hls and rtmp links, most likely already finished live
@@ -288,80 +303,94 @@ class VKIE(VKBaseIE):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
+        mv_data = {}
         if video_id:
-            info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id
+            data = {
+                'act': 'show_inline',
+                'video': video_id,
+            }
             # Some videos (removed?) can only be downloaded with list id specified
             list_id = mobj.group('list_id')
             if list_id:
-                info_url += '&list=%s' % list_id
+                data['list'] = list_id
+
+            payload = self._download_payload('al_video', video_id, data)
+            info_page = payload[1]
+            opts = payload[-1]
+            mv_data = opts.get('mvData') or {}
+            player = opts.get('player') or {}
         else:
-            info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
-        info_page = self._download_webpage(info_url, video_id)
+            info_page = self._download_webpage(
+                'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
 
-        error_message = self._html_search_regex(
-            [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
-                r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
-            info_page, 'error message', default=None)
-        if error_message:
-            raise ExtractorError(error_message, expected=True)
+            error_message = self._html_search_regex(
+                [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
+                    r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
+                info_page, 'error message', default=None)
+            if error_message:
+                raise ExtractorError(error_message, expected=True)
 
-        if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
-            raise ExtractorError(
-                'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
-                expected=True)
+            if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
+                raise ExtractorError(
+                    'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
+                    expected=True)
 
-        ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
+            ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
 
-        ERRORS = {
-            r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
-            ERROR_COPYRIGHT,
+            ERRORS = {
+                r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
+                ERROR_COPYRIGHT,
 
-            r'>The video .*? was removed from public access by request of the copyright holder.<':
-            ERROR_COPYRIGHT,
+                r'>The video .*? was removed from public access by request of the copyright holder.<':
+                ERROR_COPYRIGHT,
 
-            r'<!>Please log in or <':
-            'Video %s is only available for registered users, '
-            'use --username and --password options to provide account credentials.',
+                r'<!>Please log in or <':
+                'Video %s is only available for registered users, '
+                'use --username and --password options to provide account credentials.',
 
-            r'<!>Unknown error':
-            'Video %s does not exist.',
+                r'<!>Unknown error':
+                'Video %s does not exist.',
 
-            r'<!>Видео временно недоступно':
-            'Video %s is temporarily unavailable.',
+                r'<!>Видео временно недоступно':
+                'Video %s is temporarily unavailable.',
 
-            r'<!>Access denied':
-            'Access denied to video %s.',
+                r'<!>Access denied':
+                'Access denied to video %s.',
 
-            r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
-            'Video %s is no longer available, because its author has been blocked.',
+                r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
+                'Video %s is no longer available, because its author has been blocked.',
 
-            r'<!>This video is no longer available, because its author has been blocked.':
-            'Video %s is no longer available, because its author has been blocked.',
+                r'<!>This video is no longer available, because its author has been blocked.':
+                'Video %s is no longer available, because its author has been blocked.',
 
-            r'<!>This video is no longer available, because it has been deleted.':
-            'Video %s is no longer available, because it has been deleted.',
+                r'<!>This video is no longer available, because it has been deleted.':
+                'Video %s is no longer available, because it has been deleted.',
 
-            r'<!>The video .+? is not available in your region.':
-            'Video %s is not available in your region.',
-        }
+                r'<!>The video .+? is not available in your region.':
+                'Video %s is not available in your region.',
+            }
 
-        for error_re, error_msg in ERRORS.items():
-            if re.search(error_re, info_page):
-                raise ExtractorError(error_msg % video_id, expected=True)
+            for error_re, error_msg in ERRORS.items():
+                if re.search(error_re, info_page):
+                    raise ExtractorError(error_msg % video_id, expected=True)
+
+            player = self._parse_json(self._search_regex(
+                r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n',
+                info_page, 'player params'), video_id)
 
         youtube_url = YoutubeIE._extract_url(info_page)
         if youtube_url:
-            return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
+            return self.url_result(youtube_url, YoutubeIE.ie_key())
 
         vimeo_url = VimeoIE._extract_url(url, info_page)
         if vimeo_url is not None:
-            return self.url_result(vimeo_url)
+            return self.url_result(vimeo_url, VimeoIE.ie_key())
 
         pladform_url = PladformIE._extract_url(info_page)
         if pladform_url:
-            return self.url_result(pladform_url)
+            return self.url_result(pladform_url, PladformIE.ie_key())
 
         m_rutube = re.search(
             r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
@@ -374,6 +403,10 @@ class VKIE(VKBaseIE):
         if dailymotion_urls:
             return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
 
+        odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
+        if odnoklassniki_url:
+            return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
+
         m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
         if m_opts:
             m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
@@ -383,29 +416,7 @@ class VKIE(VKBaseIE):
                     opts_url = 'http:' + opts_url
                 return self.url_result(opts_url)
 
-        # vars does not look to be served anymore since 24.10.2016
-        data = self._parse_json(
-            self._search_regex(
-                r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
-            video_id, fatal=False)
-
-        # <!json> is served instead
-        if not data:
-            data = self._parse_json(
-                self._search_regex(
-                    [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
-                    info_page, 'json', default='{}'),
-                video_id)
-            if data:
-                data = data['player']['params'][0]
-
-        if not data:
-            data = self._parse_json(
-                self._search_regex(
-                    r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
-                    'player params'),
-                video_id)['params'][0]
-
+        data = player['params'][0]
         title = unescapeHTML(data['md_title'])
 
         # 2 = live
@@ -454,12 +465,12 @@ class VKIE(VKBaseIE):
             'title': title,
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
-            'uploader_id': str_or_none(data.get('author_id')),
-            'duration': data.get('duration'),
+            'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')),
+            'duration': int_or_none(data.get('duration') or mv_data.get('duration')),
             'timestamp': timestamp,
             'view_count': view_count,
-            'like_count': int_or_none(data.get('liked')),
-            'dislike_count': int_or_none(data.get('nolikes')),
+            'like_count': int_or_none(mv_data.get('likes')),
+            'comment_count': int_or_none(mv_data.get('commcount')),
             'is_live': is_live,
         }
 
@@ -473,7 +484,6 @@ class VKUserVideosIE(VKBaseIE):
         'url': 'http://vk.com/videos205387401',
         'info_dict': {
             'id': '205387401',
-            'title': "Tom Cruise's Videos",
         },
         'playlist_mincount': 4,
     }, {
@@ -489,22 +499,25 @@ class VKUserVideosIE(VKBaseIE):
         'url': 'http://new.vk.com/videos205387401',
         'only_matching': True,
     }]
+    _VIDEO = collections.namedtuple(
+        'Video', ['owner_id', 'id', 'thumb', 'title', 'flags', 'duration', 'hash', 'moder_acts', 'owner', 'date', 'views', 'platform', 'blocked', 'music_video_meta'])
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, page_id)
+        l = self._download_payload('al_video', page_id, {
+            'act': 'load_videos_silent',
+            'oid': page_id,
+        })[0]['']['list']
 
-        entries = [
-            self.url_result(
-                'http://vk.com/video' + video_id, 'VK', video_id=video_id)
-            for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
+        entries = []
+        for video in l:
+            v = self._VIDEO._make(video)
+            video_id = '%d_%d' % (v.owner_id, v.id)
+            entries.append(self.url_result(
+                'http://vk.com/video' + video_id, 'VK', video_id=video_id))
 
-        title = unescapeHTML(self._search_regex(
-            r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
-            webpage, 'title', default=page_id))
-
-        return self.playlist_result(entries, page_id, title)
+        return self.playlist_result(entries, page_id)
 
 
 class VKWallPostIE(VKBaseIE):
@@ -514,15 +527,15 @@ class VKWallPostIE(VKBaseIE):
         # public page URL, audio playlist
         'url': 'https://vk.com/bs.official?w=wall-23538238_35',
         'info_dict': {
-            'id': '23538238_35',
-            'title': 'Black Shadow - Wall post 23538238_35',
+            'id': '-23538238_35',
+            'title': 'Black Shadow - Wall post -23538238_35',
             'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
         },
         'playlist': [{
             'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
             'info_dict': {
                 'id': '135220665_111806521',
-                'ext': 'mp3',
+                'ext': 'mp4',
                 'title': 'Black Shadow - Слепое Верование',
                 'duration': 370,
                 'uploader': 'Black Shadow',
@@ -533,18 +546,16 @@ class VKWallPostIE(VKBaseIE):
             'md5': '4cc7e804579122b17ea95af7834c9233',
             'info_dict': {
                 'id': '135220665_111802303',
-                'ext': 'mp3',
+                'ext': 'mp4',
                 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
                 'duration': 423,
                 'uploader': 'Black Shadow',
                 'artist': 'Black Shadow',
                 'track': 'Война - Негасимое Бездны Пламя!',
             },
-            'params': {
-                'skip_download': True,
-            },
         }],
         'params': {
+            'skip_download': True,
             'usenetrc': True,
         },
         'skip': 'Requires vk account credentials',
@@ -553,7 +564,7 @@ class VKWallPostIE(VKBaseIE):
         'url': 'https://vk.com/wall85155021_6319',
         'info_dict': {
             'id': '85155021_6319',
-            'title': 'Sergey Gorbunov - Wall post 85155021_6319',
+            'title': 'Сергей Горбунов - Wall post 85155021_6319',
         },
         'playlist_count': 1,
         'params': {
@@ -569,58 +580,72 @@ class VKWallPostIE(VKBaseIE):
         'url': 'https://m.vk.com/wall-23538238_35',
         'only_matching': True,
     }]
+    _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
+    _AUDIO = collections.namedtuple(
+        'Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads', 'subtitle', 'main_artists', 'feat_artists', 'album', 'track_code', 'restriction', 'album_part', 'new_stats', 'access_key'])
+
+    def _decode(self, enc):
+        dec = ''
+        e = n = 0
+        for c in enc:
+            r = self._BASE64_CHARS.index(c)
+            cond = n % 4
+            e = 64 * e + r if cond else r
+            n += 1
+            if cond:
+                dec += chr(255 & e >> (-2 * n & 6))
+        return dec
+
+    def _unmask_url(self, mask_url, vk_id):
+        if 'audio_api_unavailable' in mask_url:
+            extra = mask_url.split('?extra=')[1].split('#')
+            func, base = self._decode(extra[1]).split(chr(11))
+            mask_url = list(self._decode(extra[0]))
+            url_len = len(mask_url)
+            indexes = [None] * url_len
+            index = int(base) ^ vk_id
+            for n in range(url_len - 1, -1, -1):
+                index = (url_len * (n + 1) ^ index + n) % url_len
+                indexes[n] = index
+            for n in range(1, url_len):
+                c = mask_url[n]
+                index = indexes[url_len - 1 - n]
+                mask_url[n] = mask_url[index]
+                mask_url[index] = c
+            mask_url = ''.join(mask_url)
+        return mask_url
 
     def _real_extract(self, url):
         post_id = self._match_id(url)
 
-        wall_url = 'https://vk.com/wall%s' % post_id
-
-        post_id = remove_start(post_id, '-')
-
-        webpage = self._download_webpage(wall_url, post_id)
-
-        error = self._html_search_regex(
-            r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
-            webpage, 'error', default=None)
-        if error:
-            raise ExtractorError('VK said: %s' % error, expected=True)
+        webpage = self._download_payload('wkview', post_id, {
+            'act': 'show',
+            'w': 'wall' + post_id,
+        })[1]
 
         description = clean_html(get_element_by_class('wall_post_text', webpage))
         uploader = clean_html(get_element_by_class('author', webpage))
-        thumbnail = self._og_search_thumbnail(webpage)
 
         entries = []
 
-        audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
-        if audio_ids:
-            al_audio = self._download_webpage(
-                'https://vk.com/al_audio.php', post_id,
-                note='Downloading audio info', fatal=False,
-                data=urlencode_postdata({
-                    'act': 'reload_audio',
-                    'al': '1',
-                    'ids': ','.join(audio_ids)
-                }))
-            if al_audio:
-                Audio = collections.namedtuple(
-                    'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
-                audios = self._parse_json(
-                    self._search_regex(
-                        r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
-                    post_id, fatal=False, transform_source=unescapeHTML)
-                if isinstance(audios, list):
-                    for audio in audios:
-                        a = Audio._make(audio[:6])
-                        entries.append({
-                            'id': '%s_%s' % (a.user_id, a.id),
-                            'url': a.url,
-                            'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
-                            'thumbnail': thumbnail,
-                            'duration': a.duration,
-                            'uploader': uploader,
-                            'artist': a.artist,
-                            'track': a.track,
-                        })
+        for audio in re.findall(r'data-audio="([^"]+)', webpage):
+            audio = self._parse_json(unescapeHTML(audio), post_id)
+            a = self._AUDIO._make(audio)
+            if not a.url:
+                continue
+            title = unescapeHTML(a.title)
+            entries.append({
+                'id': '%s_%s' % (a.owner_id, a.id),
+                'url': self._unmask_url(a.url, a.ads['vk_id']),
+                'title': '%s - %s' % (a.performer, title) if a.performer else title,
+                'thumbnail': a.cover_url.split(',') if a.cover_url else None,
+                'duration': a.duration,
+                'uploader': uploader,
+                'artist': a.performer,
+                'track': title,
+                'ext': 'mp4',
+                'protocol': 'm3u8',
+            })
 
         for video in re.finditer(
                 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):

youtube_dl/extractor/wimp.py

@@ -1,54 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from .youtube import YoutubeIE
-
-
-class WimpIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
-    _TESTS = [{
-        'url': 'http://www.wimp.com/maru-is-exhausted/',
-        'md5': 'ee21217ffd66d058e8b16be340b74883',
-        'info_dict': {
-            'id': 'maru-is-exhausted',
-            'ext': 'mp4',
-            'title': 'Maru is exhausted.',
-            'description': 'md5:57e099e857c0a4ea312542b684a869b8',
-        }
-    }, {
-        'url': 'http://www.wimp.com/clowncar/',
-        'md5': '5c31ad862a90dc5b1f023956faec13fe',
-        'info_dict': {
-            'id': 'cG4CEr2aiSg',
-            'ext': 'webm',
-            'title': 'Basset hound clown car...incredible!',
-            'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom',
-            'upload_date': '20140303',
-            'uploader': 'Gretchen Hoey',
-            'uploader_id': 'gretchenandjeff1',
-        },
-        'add_ie': ['Youtube'],
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        youtube_id = self._search_regex(
-            (r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
-             r'data-id=["\']([0-9A-Za-z_-]{11})'),
-            webpage, 'video URL', default=None)
-        if youtube_id:
-            return self.url_result(youtube_id, YoutubeIE.ie_key())
-
-        info_dict = self._extract_jwplayer_data(
-            webpage, video_id, require_title=False)
-
-        info_dict.update({
-            'id': video_id,
-            'title': self._og_search_title(webpage),
-            'description': self._og_search_description(webpage),
-        })
-
-        return info_dict

youtube_dl/extractor/wistia.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class WistiaIE(InfoExtractor):
-    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]{10})'
     _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
     _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
 
@@ -43,25 +43,26 @@ class WistiaIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    # https://wistia.com/support/embed-and-share/video-on-your-website
     @staticmethod
     def _extract_url(webpage):
         match = re.search(
-            r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage)
+            r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage)
         if match:
             return unescapeHTML(match.group('url'))
 
-        match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
-        if match:
-            return 'wistia:%s' % match.group('id')
-
         match = re.search(
             r'''(?sx)
                 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
-                <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
+                <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
             ''', webpage)
         if match:
             return 'wistia:%s' % match.group('id')
 
+        match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage)
+        if match:
+            return 'wistia:%s' % match.group('id')
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

youtube_dl/extractor/xfileshare.py

@@ -4,37 +4,64 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_chr
 from ..utils import (
     decode_packed_codes,
     determine_ext,
     ExtractorError,
     int_or_none,
-    NO_DEFAULT,
+    js_to_json,
     urlencode_postdata,
 )
 
 
+# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
+def aa_decode(aa_code):
+    symbol_table = [
+        ('7', '((ﾟｰﾟ) + (o^_^o))'),
+        ('6', '((o^_^o) +(o^_^o))'),
+        ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
+        ('2', '((o^_^o) - (ﾟΘﾟ))'),
+        ('4', '(ﾟｰﾟ)'),
+        ('3', '(o^_^o)'),
+        ('1', '(ﾟΘﾟ)'),
+        ('0', '(c^_^o)'),
+    ]
+    delim = '(ﾟДﾟ)[ﾟεﾟ]+'
+    ret = ''
+    for aa_char in aa_code.split(delim):
+        for val, pat in symbol_table:
+            aa_char = aa_char.replace(pat, val)
+        aa_char = aa_char.replace('+ ', '')
+        m = re.match(r'^\d+', aa_char)
+        if m:
+            ret += compat_chr(int(m.group(0), 8))
+        else:
+            m = re.match(r'^u([\da-f]+)', aa_char)
+            if m:
+                ret += compat_chr(int(m.group(1), 16))
+    return ret
+
+
 class XFileShareIE(InfoExtractor):
     _SITES = (
-        (r'daclips\.(?:in|com)', 'DaClips'),
-        (r'filehoot\.com', 'FileHoot'),
-        (r'gorillavid\.(?:in|com)', 'GorillaVid'),
-        (r'movpod\.in', 'MovPod'),
-        (r'powerwatch\.pw', 'PowerWatch'),
-        (r'rapidvideo\.ws', 'Rapidvideo.ws'),
+        (r'clipwatching\.com', 'ClipWatching'),
+        (r'gounlimited\.to', 'GoUnlimited'),
+        (r'govid\.me', 'GoVid'),
+        (r'holavid\.com', 'HolaVid'),
+        (r'streamty\.com', 'Streamty'),
         (r'thevideobee\.to', 'TheVideoBee'),
-        (r'vidto\.(?:me|se)', 'Vidto'),
-        (r'streamin\.to', 'Streamin.To'),
-        (r'xvidstage\.com', 'XVIDSTAGE'),
-        (r'vidabc\.com', 'Vid ABC'),
+        (r'uqload\.com', 'Uqload'),
         (r'vidbom\.com', 'VidBom'),
         (r'vidlo\.us', 'vidlo'),
-        (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'),
-        (r'fastvideo\.me', 'FastVideo.me'),
+        (r'vidlocker\.xyz', 'VidLocker'),
+        (r'vidshare\.tv', 'VidShare'),
+        (r'vup\.to', 'VUp'),
+        (r'xvideosharing\.com', 'XVideoSharing'),
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
-    _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                   % '|'.join(site for site in list(zip(*_SITES))[0]))
 
     _FILE_NOT_FOUND_REGEXES = (
@@ -43,82 +70,14 @@ class XFileShareIE(InfoExtractor):
     )
 
     _TESTS = [{
-        'url': 'http://gorillavid.in/06y9juieqpmi',
-        'md5': '5ae4a3580620380619678ee4875893ba',
+        'url': 'http://xvideosharing.com/fq65f94nd2ve',
+        'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
         'info_dict': {
-            'id': '06y9juieqpmi',
+            'id': 'fq65f94nd2ve',
             'ext': 'mp4',
-            'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
+            'title': 'sample',
             'thumbnail': r're:http://.*\.jpg',
         },
-    }, {
-        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://daclips.in/3rso4kdn6f9m',
-        'md5': '1ad8fd39bb976eeb66004d3a4895f106',
-        'info_dict': {
-            'id': '3rso4kdn6f9m',
-            'ext': 'mp4',
-            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
-            'thumbnail': r're:http://.*\.jpg',
-        }
-    }, {
-        'url': 'http://movpod.in/0wguyyxi1yca',
-        'only_matching': True,
-    }, {
-        'url': 'http://filehoot.com/3ivfabn7573c.html',
-        'info_dict': {
-            'id': '3ivfabn7573c',
-            'ext': 'mp4',
-            'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
-            'thumbnail': r're:http://.*\.jpg',
-        },
-        'skip': 'Video removed',
-    }, {
-        'url': 'http://vidto.me/ku5glz52nqe1.html',
-        'info_dict': {
-            'id': 'ku5glz52nqe1',
-            'ext': 'mp4',
-            'title': 'test'
-        }
-    }, {
-        'url': 'http://powerwatch.pw/duecjibvicbu',
-        'info_dict': {
-            'id': 'duecjibvicbu',
-            'ext': 'mp4',
-            'title': 'Big Buck Bunny trailer',
-        },
-    }, {
-        'url': 'http://xvidstage.com/e0qcnl03co6z',
-        'info_dict': {
-            'id': 'e0qcnl03co6z',
-            'ext': 'mp4',
-            'title': 'Chucky Prank 2015.mp4',
-        },
-    }, {
-        # removed by administrator
-        'url': 'http://xvidstage.com/amfy7atlkx25',
-        'only_matching': True,
-    }, {
-        'url': 'http://vidabc.com/i8ybqscrphfv',
-        'info_dict': {
-            'id': 'i8ybqscrphfv',
-            'ext': 'mp4',
-            'title': 're:Beauty and the Beast 2017',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.rapidvideo.cool/b667kprndr8w',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://vidto.se/1tx1pf6t12cg.html',
-        'only_matching': True,
     }]
 
     @staticmethod
@@ -131,10 +90,9 @@ class XFileShareIE(InfoExtractor):
                 webpage)]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        host, video_id = re.match(self._VALID_URL, url).groups()
 
-        url = 'http://%s/%s' % (mobj.group('host'), video_id)
+        url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
         webpage = self._download_webpage(url, video_id)
 
         if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
@@ -142,7 +100,7 @@ class XFileShareIE(InfoExtractor):
 
         fields = self._hidden_inputs(webpage)
 
-        if fields['op'] == 'download1':
+        if fields.get('op') == 'download1':
             countdown = int_or_none(self._search_regex(
                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
                 webpage, 'countdown', default=None))
@@ -160,13 +118,37 @@ class XFileShareIE(InfoExtractor):
             (r'style="z-index: [0-9]+;">([^<]+)</span>',
              r'<td nowrap>([^<]+)</td>',
              r'h4-fine[^>]*>([^<]+)<',
-             r'>Watch (.+) ',
+             r'>Watch (.+)[ <]',
              r'<h2 class="video-page-head">([^<]+)</h2>',
-             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
+             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to
+             r'title\s*:\s*"([^"]+)"'),  # govid.me
             webpage, 'title', default=None) or self._og_search_title(
             webpage, default=None) or video_id).strip()
 
-        def extract_formats(default=NO_DEFAULT):
+        for regex, func in (
+                (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
+                (r'(ﾟ.+)', aa_decode)):
+            obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
+            if obf_code:
+                webpage = webpage.replace(obf_code, func(obf_code))
+
+        formats = []
+
+        jwplayer_data = self._search_regex(
+            [
+                r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
+                r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
+            ], webpage,
+            'jwplayer data', default=None)
+        if jwplayer_data:
+            jwplayer_data = self._parse_json(
+                jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
+            if jwplayer_data:
+                formats = self._parse_jwplayer_data(
+                    jwplayer_data, video_id, False,
+                    m3u8_id='hls', mpd_id='dash')['formats']
+
+        if not formats:
             urls = []
             for regex in (
                     r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
@@ -177,6 +159,12 @@ class XFileShareIE(InfoExtractor):
                     video_url = mobj.group('url')
                     if video_url not in urls:
                         urls.append(video_url)
+
+            sources = self._search_regex(
+                r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
+            if sources:
+                urls.extend(self._parse_json(sources, video_id))
+
             formats = []
             for video_url in urls:
                 if determine_ext(video_url) == 'm3u8':
@@ -189,21 +177,13 @@ class XFileShareIE(InfoExtractor):
                         'url': video_url,
                         'format_id': 'sd',
                     })
-            if not formats and default is not NO_DEFAULT:
-                return default
-            self._sort_formats(formats)
-            return formats
-
-        formats = extract_formats(default=None)
-
-        if not formats:
-            webpage = decode_packed_codes(self._search_regex(
-                r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
-                webpage, 'packed code'))
-            formats = extract_formats()
+        self._sort_formats(formats)
 
         thumbnail = self._search_regex(
-            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
+            [
+                r'<video[^>]+poster="([^"]+)"',
+                r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
+            ], webpage, 'thumbnail', default=None)
 
         return {
             'id': video_id,

youtube_dl/extractor/xvideos.py

@@ -17,7 +17,8 @@ class XVideosIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?xvideos\.com/video|
+                            (?:[^/]+\.)?xvideos2?\.com/video|
+                            (?:www\.)?xvideos\.es/video|
                             flashservice\.xvideos\.com/embedframe/|
                             static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
                         )
@@ -39,6 +40,42 @@ class XVideosIE(InfoExtractor):
     }, {
         'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
         'only_matching': True,
+    }, {
+        'url': 'http://xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://xvideos.es/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://www.xvideos.es/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'http://xvideos.es/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'http://www.xvideos.es/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'http://fr.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://fr.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'http://it.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://it.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'http://de.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
+    }, {
+        'url': 'https://de.xvideos.com/video4588838/biker_takes_his_girl',
+        'only_matching': True
     }]
 
     def _real_extract(self, url):