release 2018.12.09

[ci skip]

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.10**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.09**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2018.09.10
+[debug] youtube-dl version 2018.12.09
 [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: {}

.travis.yml

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

CONTRIBUTING.md

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

ChangeLog

@@ -1,3 +1,190 @@
+version 2018.12.09
+
+Core
+* [YoutubeDL] Keep session cookies in cookie file between runs
+* [YoutubeDL] Recognize session cookies with expired set to 0 (#12929)
+
+Extractors
++ [teachable] Add support for teachable platform sites (#5451, #18150, #18272)
++ [aenetworks] Add support for historyvault.com (#18460)
+* [imgur] Improve gallery and album detection and extraction (#9133, #16577,
+  #17223, #18404)
+* [iprima] Relax URL regular expression (#18453)
+* [hotstar] Fix video data extraction (#18386)
+* [ard:mediathek] Fix title and description extraction (#18349, #18371)
+* [xvideos] Switch to HTTPS (#18422, #18427)
++ [lecturio] Add support for lecturio.com (#18405)
++ [nrktv:series] Add support for extra materials
+* [nrktv:season,series] Fix extraction (#17159, #17258)
+* [nrktv] Relax URL regular expression (#18304, #18387)
+* [yourporn] Fix extraction (#18424, #18425)
+* [tbs] Fix info extraction (#18403)
++ [gamespot] Add support for review URLs
+
+
+version 2018.12.03
+
+Core
+* [utils] Fix random_birthday to generate existing dates only (#18284)
+
+Extractors
++ [tiktok] Add support for tiktok.com (#18108, #18135)
+* [pornhub] Use actual URL host for requests (#18359)
+* [lynda] Fix authentication (#18158, #18217)
+* [gfycat] Update API endpoint (#18333, #18343)
++ [hotstar] Add support for alternative app state layout (#18320)
+* [azmedien] Fix extraction (#18334, #18336)
++ [vimeo] Add support for VHX (Vimeo OTT) (#14835)
+* [joj] Fix extraction (#18280, #18281)
++ [wistia] Add support for fast.wistia.com (#18287)
+
+
+version 2018.11.23
+
+Core
++ [setup.py] Add more relevant classifiers
+
+Extractors
+* [mixcloud] Fallback to hardcoded decryption key (#18016)
+* [nbc:news] Fix article extraction (#16194)
+* [foxsports] Fix extraction (#17543)
+* [loc] Relax regular expression and improve formats extraction
++ [ciscolive] Add support for ciscolive.cisco.com (#17984)
+* [nzz] Relax kaltura regex (#18228)
+* [sixplay] Fix formats extraction
+* [bitchute] Improve title extraction
+* [kaltura] Limit requested MediaEntry fields
++ [americastestkitchen] Add support for zype embeds (#18225)
++ [pornhub] Add pornhub.net alias
+* [nova:embed] Fix extraction (#18222)
+
+
+version 2018.11.18
+
+Extractors
++ [wwe] Extract subtitles
++ [wwe] Add support for playlistst (#14781)
++ [wwe] Add support for wwe.com (#14781, #17450)
+* [vk] Detect geo restriction (#17767)
+* [openload] Use original host during extraction (#18211)
+* [atvat] Fix extraction (#18041)
++ [rte] Add support for new API endpoint (#18206)
+* [tnaflixnetwork:embed] Fix extraction (#18205)
+* [picarto] Use API and add token support (#16518)
++ [zype] Add support for player.zype.com (#18143)
+* [vivo] Fix extraction (#18139)
+* [ruutu] Update API endpoint (#18138)
+
+
+version 2018.11.07
+
+Extractors
++ [youtube] Add another JS signature function name regex (#18091, #18093,
+  #18094)
+* [facebook] Fix tahoe request (#17171)
+* [cliphunter] Fix extraction (#18083)
++ [youtube:playlist] Add support for invidio.us (#18077)
+* [zattoo] Arrange API hosts for derived extractors (#18035)
++ [youtube] Add fallback metadata extraction from videoDetails (#18052)
+
+
+version 2018.11.03
+
+Core
+* [extractor/common] Ensure response handle is not prematurely closed before
+  it can be read if it matches expected_status (#17195, #17846, #17447)
+
+Extractors
+* [laola1tv:embed] Set correct stream access URL scheme (#16341)
++ [ehftv] Add support for ehftv.com (#15408)
+* [azmedien] Adopt to major site redesign (#17745, #17746)
++ [twitcasting] Add support for twitcasting.tv (#17981)
+* [orf:tvthek] Fix extraction (#17737, #17956, #18024)
++ [openload] Add support for oload.fun (#18045)
+* [njpwworld] Fix authentication (#17427)
++ [linkedin:learning] Add support for linkedin.com/learning (#13545)
+* [theplatform] Improve error detection (#13222)
+* [cnbc] Simplify extraction (#14280, #17110)
++ [cbnc] Add support for new URL schema (#14193)
+* [aparat] Improve extraction and extract more metadata (#17445, #18008)
+* [aparat] Fix extraction
+
+
+version 2018.10.29
+
+Core
++ [extractor/common] Add validation for JSON-LD URLs
+
+Extractors
++ [sportbox] Add support for matchtv.ru
+* [sportbox] Fix extraction (#17978)
+* [screencast] Fix extraction (#14590, #14617, #17990)
++ [openload] Add support for oload.icu
++ [ivi] Add support for ivi.tv
+* [crunchyroll] Improve extraction failsafeness (#17991)
+* [dailymail] Fix formats extraction (#17976)
+* [viewster] Reduce format requests
+* [cwtv] Handle API errors (#17905)
++ [rutube] Use geo verification headers (#17897)
++ [brightcove:legacy] Add fallbacks to brightcove:new (#13912)
+- [tv3] Remove extractor (#10461, #15339)
+* [ted] Fix extraction for HTTP and RTMP formats (#5941, #17572, #17894)
++ [openload] Add support for oload.cc (#17823)
++ [patreon] Extract post_file URL (#17792)
+* [patreon] Fix extraction (#14502, #10471)
+
+
+version 2018.10.05
+
+Extractors
+* [pluralsight] Improve authentication (#17762)
+* [dailymotion] Fix extraction (#17699)
+* [crunchyroll] Switch to HTTPS for RpcApi (#17749)
++ [philharmoniedeparis] Add support for pad.philharmoniedeparis.fr (#17705)
+* [philharmoniedeparis] Fix extraction (#17705)
++ [jamendo] Add support for licensing.jamendo.com (#17724)
++ [openload] Add support for oload.cloud (#17710)
+* [pluralsight] Fix subtitles extraction (#17726, #17728)
++ [vimeo] Add another config regular expression (#17690)
+* [spike] Fix Paramount Network extraction (#17677)
+* [hotstar] Fix extraction (#14694, #14931, #17637)
+
+
+version 2018.09.26
+
+Extractors
+* [pluralsight] Fix subtitles extraction (#17671)
+* [mediaset] Improve embed support (#17668)
++ [youtube] Add support for invidio.us (#17613)
++ [zattoo] Add support for more zattoo platform sites
+* [zattoo] Fix extraction (#17175, #17542)
+
+
+version 2018.09.18
+
+Core
++ [extractor/common] Introduce channel meta fields
+
+Extractors
+* [adobepass] Don't pollute default headers dict
+* [udemy] Don't pollute default headers dict
+* [twitch] Don't pollute default headers dict
+* [youtube] Don't pollute default query dict (#17593)
+* [crunchyroll] Prefer hardsubless formats and formats in locale language
+* [vrv] Make format ids deterministic
+* [vimeo] Fix ondemand playlist extraction (#14591)
++ [pornhub] Extract upload date (#17574)
++ [porntube] Extract channel meta fields
++ [vimeo] Extract channel meta fields
++ [youtube] Extract channel meta fields (#9676, #12939)
+* [porntube] Fix extraction (#17541)
+* [asiancrush] Fix extraction (#15630)
++ [twitch:clips] Extend URL regular expression (closes #17559)
++ [vzaar] Add support for HLS
+* [tube8] Fix metadata extraction (#17520)
+* [eporner] Extract JSON-LD (#17519)
+
+
 version 2018.09.10
 
 Core

README.md

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

docs/supportedsites.md

@@ -33,7 +33,7 @@
  - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
- - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
+ - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
  - **afreecatv**: afreecatv.com
  - **AirMozilla**
  - **AliExpressLive**
@@ -84,8 +84,6 @@
  - **awaan:season**
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
- - **AZMedienPlaylist**: AZ Medien playlists
- - **AZMedienShowPlaylist**: AZ Medien show playlists
  - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
@@ -98,6 +96,7 @@
  - **bbc.co.uk:article**: BBC articles
  - **bbc.co.uk:iplayer:playlist**
  - **bbc.co.uk:playlist**
+ - **BBVTV**
  - **Beatport**
  - **Beeg**
  - **BehindKink**
@@ -164,6 +163,8 @@
  - **chirbit**
  - **chirbit:profile**
  - **Cinchcast**
+ - **CiscoLiveSearch**
+ - **CiscoLiveSession**
  - **CJSW**
  - **cliphunter**
  - **Clippit**
@@ -177,6 +178,7 @@
  - **Clyp**
  - **cmt.com**
  - **CNBC**
+ - **CNBCVideo**
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
@@ -250,7 +252,9 @@
  - **EchoMsk**
  - **egghead:course**: egghead.io course
  - **egghead:lesson**: egghead.io lesson
+ - **ehftv**
  - **eHow**
+ - **EinsUndEinsTV**
  - **Einthusan**
  - **eitb.tv**
  - **EllenTube**
@@ -268,6 +272,7 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
+ - **EWETV**
  - **ExpoTV**
  - **Expressen**
  - **ExtremeTube**
@@ -327,6 +332,7 @@
  - **Gfycat**
  - **GiantBomb**
  - **Giga**
+ - **GlattvisionTV**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
@@ -356,7 +362,7 @@
  - **HitRecord**
  - **HornBunny**
  - **HotNewHipHop**
- - **HotStar**
+ - **hotstar**
  - **hotstar:playlist**
  - **Howcast**
  - **HowStuffWorks**
@@ -370,7 +376,8 @@
  - **imdb**: Internet Movie Database trailers
  - **imdb:list**: Internet Movie Database lists
  - **Imgur**
- - **ImgurAlbum**
+ - **imgur:album**
+ - **imgur:gallery**
  - **Ina**
  - **Inc**
  - **IndavideoEmbed**
@@ -429,6 +436,8 @@
  - **Le**: 乐视网
  - **Learnr**
  - **Lecture2Go**
+ - **Lecturio**
+ - **LecturioCourse**
  - **LEGO**
  - **Lemonde**
  - **Lenta**
@@ -441,6 +450,8 @@
  - **limelight:channel**
  - **limelight:channel_list**
  - **LineTV**
+ - **linkedin:learning**
+ - **linkedin:learning:course**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -494,6 +505,7 @@
  - **Mixer:vod**
  - **MLB**
  - **Mnet**
+ - **MNetTV**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **Mojvideo**
@@ -525,6 +537,7 @@
  - **Myvi**
  - **MyVidster**
  - **MyviEmbed**
+ - **MyVisionTV**
  - **n-tv.de**
  - **natgeo**
  - **natgeo:episodeguide**
@@ -550,6 +563,7 @@
  - **netease:program**: 网易云音乐 - 电台节目
  - **netease:singer**: 网易云音乐 - 歌手
  - **netease:song**: 网易云音乐
+ - **NetPlus**
  - **Netzkino**
  - **Newgrounds**
  - **NewgroundsPlaylist**
@@ -626,6 +640,7 @@
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **OsnatelTV**
  - **PacktPub**
  - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
@@ -686,6 +701,7 @@
  - **qqmusic:playlist**: QQ音乐 - 歌单
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
+ - **QuantumTV**
  - **Quickline**
  - **QuicklineLive**
  - **R7**
@@ -753,6 +769,7 @@
  - **safari**: safaribooksonline.com online video
  - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
+ - **SAKTV**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -808,7 +825,7 @@
  - **Spiegeltv**
  - **sport.francetvinfo.fr**
  - **Sport5**
- - **SportBoxEmbed**
+ - **SportBox**
  - **SportDeutschland**
  - **SpringboardPlatform**
  - **Sprout**
@@ -839,6 +856,8 @@
  - **TastyTrade**
  - **TBS**
  - **TDSLifeway**
+ - **Teachable**
+ - **TeachableCourse**
  - **teachertube**: teachertube.com videos
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
@@ -871,6 +890,8 @@
  - **ThisAmericanLife**
  - **ThisAV**
  - **ThisOldHouse**
+ - **TikTok**
+ - **TikTokUser**
  - **tinypic**: tinypic.com videos
  - **TMZ**
  - **TMZArticle**
@@ -899,7 +920,6 @@
  - **TV2**
  - **tv2.hu**
  - **TV2Article**
- - **TV3**
  - **TV4**: tv4.se and tv4play.se
  - **TV5MondePlus**: TV5MONDE+
  - **TVA**
@@ -921,6 +941,7 @@
  - **TVPlayer**
  - **TVPlayHome**
  - **Tweakers**
+ - **TwitCasting**
  - **twitch:chapter**
  - **twitch:clips**
  - **twitch:profile**
@@ -945,8 +966,6 @@
  - **uol.com.br**
  - **uplynk**
  - **uplynk:preplay**
- - **Upskill**
- - **UpskillCourse**
  - **Urort**: NRK P3 Urørt
  - **URPlay**
  - **USANetwork**
@@ -965,6 +984,7 @@
  - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
+ - **vhx:embed**
  - **Viafree**
  - **vice**
  - **vice:article**
@@ -1035,12 +1055,14 @@
  - **vrv**
  - **vrv:series**
  - **VShare**
+ - **VTXTV**
  - **vube**: Vube.com
  - **VuClip**
  - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
  - **Walla**
+ - **WalyTV**
  - **washingtonpost**
  - **washingtonpost:article**
  - **wat.tv**
@@ -1066,6 +1088,7 @@
  - **wrzuta.pl:playlist**
  - **WSJ**: Wall Street Journal
  - **WSJArticle**
+ - **WWE**
  - **XBef**
  - **XboxClips**
  - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me
@@ -1125,3 +1148,4 @@
  - **ZDF**
  - **ZDFChannel**
  - **zingmp3**: mp3.zing.vn
+ - **Zype**

setup.py

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

test/helper.py

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

test/test_InfoExtractor.py

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

test/test_YoutubeDLCookieJar.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import os
+import re
+import sys
+import tempfile
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.utils import YoutubeDLCookieJar
+
+
+class TestYoutubeDLCookieJar(unittest.TestCase):
+    def test_keep_session_cookies(self):
+        cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
+        cookiejar.load(ignore_discard=True, ignore_expires=True)
+        tf = tempfile.NamedTemporaryFile(delete=False)
+        try:
+            cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True)
+            temp = tf.read().decode('utf-8')
+            self.assertTrue(re.search(
+                r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp))
+            self.assertTrue(re.search(
+                r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp))
+        finally:
+            tf.close()
+            os.remove(tf.name)
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_compat.py

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

test/test_downloader_http.py

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

test/test_http.py

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

test/test_postprocessors.py

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

test/testdata/cookies/session_cookies.txt

@@ -0,0 +1,6 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file!  Do not edit.
+
+www.foobar.foobar	FALSE	/	TRUE	0	YoutubeDLExpires0	YoutubeDLExpires0Value
+www.foobar.foobar	FALSE	/	TRUE	0	YoutubeDLExpiresEmpty	YoutubeDLExpiresEmptyValue

youtube_dl/YoutubeDL.py

@@ -88,6 +88,7 @@ from .utils import (
     version_tuple,
     write_json_file,
     write_string,
+    YoutubeDLCookieJar,
     YoutubeDLCookieProcessor,
     YoutubeDLHandler,
 )
@@ -558,7 +559,7 @@ class YoutubeDL(object):
         self.restore_console_title()
 
         if self.params.get('cookiefile') is not None:
-            self.cookiejar.save()
+            self.cookiejar.save(ignore_discard=True, ignore_expires=True)
 
     def trouble(self, message=None, tb=None):
         """Determine action to take when a download problem appears.
@@ -2297,10 +2298,9 @@ class YoutubeDL(object):
             self.cookiejar = compat_cookiejar.CookieJar()
         else:
             opts_cookiefile = expand_path(opts_cookiefile)
-            self.cookiejar = compat_cookiejar.MozillaCookieJar(
-                opts_cookiefile)
+            self.cookiejar = YoutubeDLCookieJar(opts_cookiefile)
             if os.access(opts_cookiefile, os.R_OK):
-                self.cookiejar.load()
+                self.cookiejar.load(ignore_discard=True, ignore_expires=True)
 
         cookie_processor = YoutubeDLCookieProcessor(self.cookiejar)
         if opts_proxy is not None:

youtube_dl/extractor/adobepass.py

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

youtube_dl/extractor/aenetworks.py

@@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE):
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
-    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
+    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?
                         (?P<domain>
-                            (?:history|aetv|mylifetime|lifetimemovieclub)\.com|
+                            (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
                             fyi\.tv
                         )/
                         (?:
                             shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
                             movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
-                            specials/(?P<special_display_id>[^/]+)/full-special
+                            specials/(?P<special_display_id>[^/]+)/full-special|
+                            collections/[^/]+/(?P<collection_display_id>[^/]+)
                         )
                     '''
     _TESTS = [{
@@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
         'only_matching': True
+    }, {
+        'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
+        'only_matching': True
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',
@@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE):
     }
 
     def _real_extract(self, url):
-        domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
-        display_id = show_path or movie_display_id or special_display_id
-        webpage = self._download_webpage(url, display_id)
+        domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
+        display_id = show_path or movie_display_id or special_display_id or collection_display_id
+        webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
         if show_path:
             url_parts = show_path.split('/')
             url_parts_len = len(url_parts)

youtube_dl/extractor/americastestkitchen.py

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

youtube_dl/extractor/aparat.py

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

youtube_dl/extractor/ard.py

@@ -173,13 +173,18 @@ class ARDMediathekIE(InfoExtractor):
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms\.title" content="(.*?)"/>',
-             r'<h4 class="headline">(.*?)</h4>'],
+             r'<h4 class="headline">(.*?)</h4>',
+             r'<title[^>]*>(.*?)</title>'],
             webpage, 'title')
         description = self._html_search_meta(
             'dcterms.abstract', webpage, 'description', default=None)
         if description is None:
             description = self._html_search_meta(
-                'description', webpage, 'meta description')
+                'description', webpage, 'meta description', default=None)
+        if description is None:
+            description = self._html_search_regex(
+                r'<p\s+class="teasertext">(.+?)</p>',
+                webpage, 'teaser text', default=None)
 
         # Thumbnail is sometimes not present.
         # It is in the mobile version, but that seems to use a different URL

youtube_dl/extractor/asiancrush.py

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

youtube_dl/extractor/atvat.py

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

youtube_dl/extractor/azmedien.py

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

youtube_dl/extractor/bitchute.py

@@ -37,7 +37,7 @@ class BitChuteIE(InfoExtractor):
                 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
             })
 
-        title = self._search_regex(
+        title = self._html_search_regex(
             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
             webpage, 'title', default=None) or self._html_search_meta(
             'description', webpage, 'title',

youtube_dl/extractor/brightcove.py

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

youtube_dl/extractor/ciscolive.py

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

youtube_dl/extractor/cliphunter.py

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

youtube_dl/extractor/cnbc.py

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

youtube_dl/extractor/common.py

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

youtube_dl/extractor/crunchyroll.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import xml.etree.ElementTree as etree
 import zlib
 
 from hashlib import sha1
@@ -45,7 +46,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         data['req'] = 'RpcApi' + method
         data = compat_urllib_parse_urlencode(data).encode('utf-8')
         return self._download_xml(
-            'http://www.crunchyroll.com/xml/',
+            'https://www.crunchyroll.com/xml/',
             video_id, note, fatal=False, data=data, headers={
                 'Content-Type': 'application/x-www-form-urlencoded',
             })
@@ -398,7 +399,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'Downloading subtitles for ' + sub_name, data={
                     'subtitle_script_id': sub_id,
                 })
-            if sub_doc is None:
+            if not isinstance(sub_doc, etree.Element):
                 continue
             sid = sub_doc.get('id')
             iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -445,6 +446,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             webpage, 'vilos media', default='{}'), video_id)
         media_metadata = media.get('metadata') or {}
 
+        language = self._search_regex(
+            r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1',
+            webpage, 'language', default=None, group='lang')
+
         video_title = self._html_search_regex(
             r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
             webpage, 'video_title')
@@ -466,9 +471,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         formats = []
         for stream in media.get('streams', []):
-            formats.extend(self._extract_vrv_formats(
+            audio_lang = stream.get('audio_lang')
+            hardsub_lang = stream.get('hardsub_lang')
+            vrv_formats = self._extract_vrv_formats(
                 stream.get('url'), video_id, stream.get('format'),
-                stream.get('audio_lang'), stream.get('hardsub_lang')))
+                audio_lang, hardsub_lang)
+            for f in vrv_formats:
+                if not hardsub_lang:
+                    f['preference'] = 1
+                language_preference = 0
+                if audio_lang == language:
+                    language_preference += 1
+                if hardsub_lang == language:
+                    language_preference += 1
+                if language_preference:
+                    f['language_preference'] = language_preference
+            formats.extend(vrv_formats)
         if not formats:
             available_fmts = []
             for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
@@ -498,7 +516,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_quality': stream_quality,
                         'current_page': url,
                     })
-                if streamdata is not None:
+                if isinstance(streamdata, etree.Element):
                     stream_info = streamdata.find('./{default}preload/stream_info')
                     if stream_info is not None:
                         stream_infos.append(stream_info)
@@ -509,7 +527,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_format': stream_format,
                         'video_encode_quality': stream_quality,
                     })
-                if stream_info is not None:
+                if isinstance(stream_info, etree.Element):
                     stream_infos.append(stream_info)
                 for stream_info in stream_infos:
                     video_encode_id = xpath_text(stream_info, './video_encode_id')
@@ -557,7 +575,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'ext': 'flv',
                     })
                     formats.append(format_info)
-        self._sort_formats(formats, ('height', 'width', 'tbr', 'fps'))
+        self._sort_formats(formats, ('preference', 'language_preference', 'height', 'width', 'tbr', 'fps'))
 
         metadata = self._call_rpc_api(
             'VideoPlayer_GetMediaMetadata', video_id,
@@ -581,10 +599,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         series = self._html_search_regex(
             r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
             webpage, 'series', fatal=False)
-        season = xpath_text(metadata, 'series_title')
 
-        episode = xpath_text(metadata, 'episode_title') or media_metadata.get('title')
-        episode_number = int_or_none(xpath_text(metadata, 'episode_number') or media_metadata.get('episode_number'))
+        season = episode = episode_number = duration = thumbnail = None
+
+        if isinstance(metadata, etree.Element):
+            season = xpath_text(metadata, 'series_title')
+            episode = xpath_text(metadata, 'episode_title')
+            episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+            duration = float_or_none(media_metadata.get('duration'), 1000)
+            thumbnail = xpath_text(metadata, 'episode_image_url')
+
+        if not episode:
+            episode = media_metadata.get('title')
+        if not episode_number:
+            episode_number = int_or_none(media_metadata.get('episode_number'))
+        if not thumbnail:
+            thumbnail = media_metadata.get('thumbnail', {}).get('url')
 
         season_number = int_or_none(self._search_regex(
             r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
@@ -594,8 +624,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'id': video_id,
             'title': video_title,
             'description': video_description,
-            'duration': float_or_none(media_metadata.get('duration'), 1000),
-            'thumbnail': xpath_text(metadata, 'episode_image_url') or media_metadata.get('thumbnail', {}).get('url'),
+            'duration': duration,
+            'thumbnail': thumbnail,
             'uploader': video_uploader,
             'upload_date': video_upload_date,
             'series': series,

youtube_dl/extractor/cwtv.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
     parse_age_limit,
     parse_iso8601,
@@ -66,9 +67,12 @@ class CWTVIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
+        data = self._download_json(
             'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id,
-            video_id)['video']
+            video_id)
+        if data.get('result') != 'ok':
+            raise ExtractorError(data['msg'], expected=True)
+        video_data = data['video']
         title = video_data['title']
         mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id
 

youtube_dl/extractor/dailymail.py

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

youtube_dl/extractor/dailymotion.py

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

youtube_dl/extractor/eporner.py

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

youtube_dl/extractor/extractors.py

@@ -88,11 +88,7 @@ from .awaan import (
     AWAANLiveIE,
     AWAANSeasonIE,
 )
-from .azmedien import (
-    AZMedienIE,
-    AZMedienPlaylistIE,
-    AZMedienShowPlaylistIE,
-)
+from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
@@ -198,6 +194,10 @@ from .chirbit import (
     ChirbitProfileIE,
 )
 from .cinchcast import CinchcastIE
+from .ciscolive import (
+    CiscoLiveSessionIE,
+    CiscoLiveSearchIE,
+)
 from .cjsw import CJSWIE
 from .cliphunter import CliphunterIE
 from .clippit import ClippitIE
@@ -209,7 +209,10 @@ from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .clyp import ClypIE
 from .cmt import CMTIE
-from .cnbc import CNBCIE
+from .cnbc import (
+    CNBCIE,
+    CNBCVideoIE,
+)
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
@@ -480,6 +483,7 @@ from .imdb import (
 from .imgur import (
     ImgurIE,
     ImgurAlbumIE,
+    ImgurGalleryIE,
 )
 from .ina import InaIE
 from .inc import IncIE
@@ -540,6 +544,7 @@ from .la7 import LA7IE
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
+    EHFTVIE,
     ITTFIE,
 )
 from .lci import LCIIE
@@ -549,6 +554,10 @@ from .lcp import (
 )
 from .learnr import LearnrIE
 from .lecture2go import Lecture2GoIE
+from .lecturio import (
+    LecturioIE,
+    LecturioCourseIE,
+)
 from .leeco import (
     LeIE,
     LePlaylistIE,
@@ -569,6 +578,10 @@ from .limelight import (
     LimelightChannelListIE,
 )
 from .line import LineTVIE
+from .linkedin import (
+    LinkedInLearningIE,
+    LinkedInLearningCourseIE,
+)
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -1043,7 +1056,7 @@ from .spike import (
 )
 from .stitcher import StitcherIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxEmbedIE
+from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
 from .springboardplatform import SpringboardPlatformIE
 from .sprout import SproutIE
@@ -1078,6 +1091,10 @@ from .tass import TassIE
 from .tastytrade import TastyTradeIE
 from .tbs import TBSIE
 from .tdslifeway import TDSLifewayIE
+from .teachable import (
+    TeachableIE,
+    TeachableCourseIE,
+)
 from .teachertube import (
     TeacherTubeIE,
     TeacherTubeUserIE,
@@ -1116,6 +1133,10 @@ from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
 from .threeqsdn import ThreeQSDNIE
+from .tiktok import (
+    TikTokIE,
+    TikTokUserIE,
+)
 from .tinypic import TinyPicIE
 from .tmz import (
     TMZIE,
@@ -1153,7 +1174,6 @@ from .tv2 import (
     TV2ArticleIE,
 )
 from .tv2hu import TV2HuIE
-from .tv3 import TV3IE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
 from .tva import TVAIE
@@ -1190,6 +1210,7 @@ from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
 from .twentythreevideo import TwentyThreeVideoIE
+from .twitcasting import TwitCastingIE
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -1223,10 +1244,6 @@ from .uplynk import (
     UplynkIE,
     UplynkPreplayIE,
 )
-from .upskill import (
-    UpskillIE,
-    UpskillCourseIE,
-)
 from .urort import UrortIE
 from .urplay import URPlayIE
 from .usanetwork import USANetworkIE
@@ -1295,6 +1312,7 @@ from .vimeo import (
     VimeoReviewIE,
     VimeoUserIE,
     VimeoWatchLaterIE,
+    VHXEmbedIE,
 )
 from .vimple import VimpleIE
 from .vine import (
@@ -1382,6 +1400,7 @@ from .wsj import (
     WSJIE,
     WSJArticleIE,
 )
+from .wwe import WWEIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xfileshare import XFileShareIE
@@ -1455,10 +1474,23 @@ from .youtube import (
 from .zapiks import ZapiksIE
 from .zaq1 import Zaq1IE
 from .zattoo import (
+    BBVTVIE,
+    EinsUndEinsTVIE,
+    EWETVIE,
+    GlattvisionTVIE,
+    MNetTVIE,
+    MyVisionTVIE,
+    NetPlusIE,
+    OsnatelTVIE,
+    QuantumTVIE,
     QuicklineIE,
     QuicklineLiveIE,
+    SAKTVIE,
+    VTXTVIE,
+    WalyTVIE,
     ZattooIE,
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
 from .zingmp3 import ZingMp3IE
+from .zype import ZypeIE

youtube_dl/extractor/facebook.py

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

youtube_dl/extractor/fourtube.py

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

youtube_dl/extractor/foxsports.py

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

youtube_dl/extractor/gamespot.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class GameSpotIE(OnceIE):
-    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
@@ -41,6 +41,9 @@ class GameSpotIE(OnceIE):
     }, {
         'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/generic.py

@@ -47,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .tvc import TVCIE
-from .sportbox import SportBoxEmbedIE
+from .sportbox import SportBoxIE
 from .smotri import SmotriIE
 from .myvi import MyviIE
 from .condenast import CondeNastIE
@@ -109,11 +109,13 @@ from .vice import ViceIE
 from .xfileshare import XFileShareIE
 from .cloudflarestream import CloudflareStreamIE
 from .peertube import PeerTubeIE
+from .teachable import TeachableIE
 from .indavideo import IndavideoEmbedIE
 from .apa import APAIE
 from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
+from .zype import ZypeIE
 
 
 class GenericIE(InfoExtractor):
@@ -2070,6 +2072,20 @@ class GenericIE(InfoExtractor):
             },
             'playlist_count': 6,
         },
+        {
+            # Zype embed
+            'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
+            'info_dict': {
+                'id': '5b400b834b32992a310622b9',
+                'ext': 'mp4',
+                'title': 'Smoky Barbecue Favorites',
+                'thumbnail': r're:^https?://.*\.jpe?g',
+            },
+            'add_ie': [ZypeIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # videojs embed
             'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
@@ -2636,9 +2652,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(tvc_url, 'TVC')
 
         # Look for embedded SportBox player
-        sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+        sportbox_urls = SportBoxIE._extract_urls(webpage)
         if sportbox_urls:
-            return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
+            return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
 
         # Look for embedded XHamster player
         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
@@ -3023,7 +3039,7 @@ class GenericIE(InfoExtractor):
                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
 
         # Look for Mediaset embeds
-        mediaset_urls = MediasetIE._extract_urls(webpage)
+        mediaset_urls = MediasetIE._extract_urls(self, webpage)
         if mediaset_urls:
             return self.playlist_from_matches(
                 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
@@ -3097,6 +3113,10 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
 
+        teachable_url = TeachableIE._extract_url(webpage, url)
+        if teachable_url:
+            return self.url_result(teachable_url)
+
         indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
         if indavideo_urls:
             return self.playlist_from_matches(
@@ -3129,6 +3149,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
 
+        zype_urls = ZypeIE._extract_urls(webpage)
+        if zype_urls:
+            return self.playlist_from_matches(
+                zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
+
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:

youtube_dl/extractor/gfycat.py

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

youtube_dl/extractor/hotstar.py

@@ -1,49 +1,56 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import hashlib
+import hmac
+import time
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
+    try_get,
 )
 
 
 class HotStarBaseIE(InfoExtractor):
-    _GEO_COUNTRIES = ['IN']
+    _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
 
-    def _download_json(self, *args, **kwargs):
-        response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
-        if response['resultCode'] != 'OK':
-            if kwargs.get('fatal'):
-                raise ExtractorError(
-                    response['errorDescription'], expected=True)
-            return None
-        return response['resultObj']
-
-    def _download_content_info(self, content_id):
-        return self._download_json(
-            'https://account.hotstar.com/AVS/besc', content_id, query={
-                'action': 'GetAggregatedContentDetails',
-                'appVersion': '5.0.40',
-                'channel': 'PCTV',
-                'contentId': content_id,
-            })['contentInfo'][0]
+    def _call_api(self, path, video_id, query_name='contentId'):
+        st = int(time.time())
+        exp = st + 6000
+        auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
+        auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
+        response = self._download_json(
+            'https://api.hotstar.com/' + path,
+            video_id, headers={
+                'hotstarauth': auth,
+                'x-country-code': 'IN',
+                'x-platform-code': 'JIO',
+            }, query={
+                query_name: video_id,
+                'tas': 10000,
+            })
+        if response['statusCode'] != 'OK':
+            raise ExtractorError(
+                response['body']['message'], expected=True)
+        return response['body']['results']
 
 
 class HotStarIE(HotStarBaseIE):
+    IE_NAME = 'hotstar'
     _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
     _TESTS = [{
-        'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
+        # contentData
+        'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
         'info_dict': {
             'id': '1000076273',
             'ext': 'mp4',
-            'title': 'On Air With AIB',
+            'title': 'Can You Not Spread Rumours?',
             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
-            'timestamp': 1447227000,
+            'timestamp': 1447248600,
             'upload_date': '20151111',
             'duration': 381,
         },
@@ -51,6 +58,10 @@ class HotStarIE(HotStarBaseIE):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # contentDetail
+        'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
+        'only_matching': True,
     }, {
         'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
         'only_matching': True,
@@ -58,47 +69,52 @@ class HotStarIE(HotStarBaseIE):
         'url': 'http://www.hotstar.com/1000000515',
         'only_matching': True,
     }]
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        video_data = self._download_content_info(video_id)
+        webpage = self._download_webpage(url, video_id)
+        app_state = self._parse_json(self._search_regex(
+            r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
+            webpage, 'app state'), video_id)
+        video_data = {}
+        getters = list(
+            lambda x, k=k: x['initialState']['content%s' % k]['content']
+            for k in ('Data', 'Detail')
+        )
+        for v in app_state.values():
+            content = try_get(v, getters, dict)
+            if content and content.get('contentId') == video_id:
+                video_data = content
+                break
 
-        title = video_data['episodeTitle']
+        title = video_data['title']
 
-        if video_data.get('encrypted') == 'Y':
+        if video_data.get('drmProtected'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = []
-        for f in ('JIO',):
-            format_data = self._download_json(
-                'http://getcdn.hotstar.com/AVS/besc',
-                video_id, 'Downloading %s JSON metadata' % f,
-                fatal=False, query={
-                    'action': 'GetCDN',
-                    'asJson': 'Y',
-                    'channel': f,
-                    'id': video_id,
-                    'type': 'VOD',
-                })
-            if format_data:
-                format_url = format_data.get('src')
-                if not format_url:
-                    continue
-                ext = determine_ext(format_url)
-                if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        format_url, video_id, 'mp4',
-                        m3u8_id='hls', fatal=False))
-                elif ext == 'f4m':
-                    # produce broken files
-                    continue
-                else:
-                    formats.append({
-                        'url': format_url,
-                        'width': int_or_none(format_data.get('width')),
-                        'height': int_or_none(format_data.get('height')),
-                    })
+        format_data = self._call_api('h/v1/play', video_id)['item']
+        format_url = format_data['playbackUrl']
+        ext = determine_ext(format_url)
+        if ext == 'm3u8':
+            try:
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id='hls'))
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                    self.raise_geo_restricted(countries=['IN'])
+                raise
+        elif ext == 'f4m':
+            # produce broken files
+            pass
+        else:
+            formats.append({
+                'url': format_url,
+                'width': int_or_none(format_data.get('width')),
+                'height': int_or_none(format_data.get('height')),
+            })
         self._sort_formats(formats)
 
         return {
@@ -106,57 +122,43 @@ class HotStarIE(HotStarBaseIE):
             'title': title,
             'description': video_data.get('description'),
             'duration': int_or_none(video_data.get('duration')),
-            'timestamp': int_or_none(video_data.get('broadcastDate')),
+            'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
             'formats': formats,
+            'channel': video_data.get('channelName'),
+            'channel_id': video_data.get('channelId'),
+            'series': video_data.get('showName'),
+            'season': video_data.get('seasonName'),
+            'season_number': int_or_none(video_data.get('seasonNo')),
+            'season_id': video_data.get('seasonId'),
             'episode': title,
-            'episode_number': int_or_none(video_data.get('episodeNumber')),
-            'series': video_data.get('contentTitle'),
+            'episode_number': int_or_none(video_data.get('episodeNo')),
         }
 
 
 class HotStarPlaylistIE(HotStarBaseIE):
     IE_NAME = 'hotstar:playlist'
-    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
     _TESTS = [{
-        'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
+        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
         'info_dict': {
-            'id': '14812',
+            'id': '3_2_26',
         },
-        'playlist_mincount': 75,
+        'playlist_mincount': 20,
     }, {
-        'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
+        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
         'only_matching': True,
     }]
-    _ITEM_TYPES = {
-        'episodes': 'EPISODE',
-        'popular-clips': 'CLIPS',
-    }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        base_url = mobj.group('url')
-        content_id = mobj.group('content_id')
-        playlist_type = mobj.group('type')
+        playlist_id = self._match_id(url)
 
-        content_info = self._download_content_info(content_id)
-        playlist_id = compat_str(content_info['categoryId'])
-
-        collection = self._download_json(
-            'https://search.hotstar.com/AVS/besc', playlist_id, query={
-                'action': 'SearchContents',
-                'appVersion': '5.0.40',
-                'channel': 'PCTV',
-                'moreFilters': 'series:%s;' % playlist_id,
-                'query': '*',
-                'searchOrder': 'last_broadcast_date desc,year desc,title asc',
-                'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
-            })
+        collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')
 
         entries = [
             self.url_result(
-                '%s/_/%s' % (base_url, video['contentId']),
+                'https://www.hotstar.com/%s' % video['contentId'],
                 ie=HotStarIE.ie_key(), video_id=video['contentId'])
-            for video in collection['response']['docs']
+            for video in collection['assets']['items']
             if video.get('contentId')]
 
         return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/imgur.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class ImgurIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P<id>[a-zA-Z0-9]+)'
 
     _TESTS = [{
         'url': 'https://i.imgur.com/A61SaA1.gifv',
@@ -20,28 +20,9 @@ class ImgurIE(InfoExtractor):
             'id': 'A61SaA1',
             'ext': 'mp4',
             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 'Imgur: The magic of the Internet',
         },
     }, {
         'url': 'https://imgur.com/A61SaA1',
-        'info_dict': {
-            'id': 'A61SaA1',
-            'ext': 'mp4',
-            'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 'Imgur: The magic of the Internet',
-        },
-    }, {
-        'url': 'https://imgur.com/gallery/YcAQlkx',
-        'info_dict': {
-            'id': 'YcAQlkx',
-            'ext': 'mp4',
-            'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
-        }
-    }, {
-        'url': 'http://imgur.com/topic/Funny/N8rOudd',
-        'only_matching': True,
-    }, {
-        'url': 'http://imgur.com/r/aww/VQcQPhM',
         'only_matching': True,
     }, {
         'url': 'https://i.imgur.com/crGpqCV.mp4',
@@ -50,8 +31,8 @@ class ImgurIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        gifv_url = 'https://i.imgur.com/{id}.gifv'.format(id=video_id)
-        webpage = self._download_webpage(gifv_url, video_id)
+        webpage = self._download_webpage(
+            'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id)
 
         width = int_or_none(self._og_search_property(
             'video:width', webpage, default=None))
@@ -72,7 +53,6 @@ class ImgurIE(InfoExtractor):
                 'format_id': m.group('type').partition('/')[2],
                 'url': self._proto_relative_url(m.group('src')),
                 'ext': mimetype2ext(m.group('type')),
-                'acodec': 'none',
                 'width': width,
                 'height': height,
                 'http_headers': {
@@ -107,44 +87,64 @@ class ImgurIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'description': self._og_search_description(webpage, default=None),
             'title': self._og_search_title(webpage),
         }
 
 
-class ImgurAlbumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{5})(?:[/?#&]+)?$'
+class ImgurGalleryIE(InfoExtractor):
+    IE_NAME = 'imgur:gallery'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P<id>[a-zA-Z0-9]+)'
 
     _TESTS = [{
         'url': 'http://imgur.com/gallery/Q95ko',
         'info_dict': {
             'id': 'Q95ko',
+            'title': 'Adding faces make every GIF better',
         },
         'playlist_count': 25,
     }, {
-        'url': 'http://imgur.com/a/j6Orj',
+        'url': 'http://imgur.com/topic/Aww/ll5Vk',
         'only_matching': True,
     }, {
-        'url': 'http://imgur.com/topic/Aww/ll5Vk',
+        'url': 'https://imgur.com/gallery/YcAQlkx',
+        'info_dict': {
+            'id': 'YcAQlkx',
+            'ext': 'mp4',
+            'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
+        }
+    }, {
+        'url': 'http://imgur.com/topic/Funny/N8rOudd',
+        'only_matching': True,
+    }, {
+        'url': 'http://imgur.com/r/aww/VQcQPhM',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        album_id = self._match_id(url)
+        gallery_id = self._match_id(url)
 
-        album_images = self._download_json(
-            'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
-            album_id, fatal=False)
+        data = self._download_json(
+            'https://imgur.com/gallery/%s.json' % gallery_id,
+            gallery_id)['data']['image']
 
-        if album_images:
-            data = album_images.get('data')
-            if data and isinstance(data, dict):
-                images = data.get('images')
-                if images and isinstance(images, list):
-                    entries = [
-                        self.url_result('http://imgur.com/%s' % image['hash'])
-                        for image in images if image.get('hash')]
-                    return self.playlist_result(entries, album_id)
+        if data.get('is_album'):
+            entries = [
+                self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash'])
+                for image in data['album_images']['images'] if image.get('hash')]
+            return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description'))
 
-        # Fallback to single video
-        return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key())
+        return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id)
+
+
+class ImgurAlbumIE(ImgurGalleryIE):
+    IE_NAME = 'imgur:album'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://imgur.com/a/j6Orj',
+        'info_dict': {
+            'id': 'j6Orj',
+            'title': 'A Literary Analysis of "Star Wars: The Force Awakens"',
+        },
+        'playlist_count': 12,
+    }]

youtube_dl/extractor/iprima.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _GEO_BYPASS = False
 
     _TESTS = [{
@@ -41,6 +41,9 @@ class IPrimaIE(InfoExtractor):
         # iframe prima.iprima.cz
         'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
         'only_matching': True,
+    }, {
+        'url': 'http://www.iprima.cz/filmy/desne-rande',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/ivi.py

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

youtube_dl/extractor/jamendo.py

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

youtube_dl/extractor/joj.py

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

youtube_dl/extractor/kaltura.py

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

youtube_dl/extractor/laola1tv.py

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

youtube_dl/extractor/lecturio.py

@@ -0,0 +1,186 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    extract_attributes,
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    str_or_none,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class LecturioBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://app.lecturio.com/en/login'
+    _NETRC_MACHINE = 'lecturio'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        # Sets some cookies
+        _, urlh = self._download_webpage_handle(
+            self._LOGIN_URL, None, 'Downloading login popup')
+
+        def is_logged(url_handle):
+            return self._LOGIN_URL not in compat_str(url_handle.geturl())
+
+        # Already logged in
+        if is_logged(urlh):
+            return
+
+        login_form = {
+            'signin[email]': username,
+            'signin[password]': password,
+            'signin[remember]': 'on',
+        }
+
+        response, urlh = self._download_webpage_handle(
+            self._LOGIN_URL, None, 'Logging in',
+            data=urlencode_postdata(login_form))
+
+        # Logged in successfully
+        if is_logged(urlh):
+            return
+
+        errors = self._html_search_regex(
+            r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
+            'errors', default=None)
+        if errors:
+            raise ExtractorError('Unable to login: %s' % errors, expected=True)
+        raise ExtractorError('Unable to log in')
+
+
+class LecturioIE(LecturioBaseIE):
+    _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture'
+    _TEST = {
+        'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
+        'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
+        'info_dict': {
+            'id': '39634',
+            'ext': 'mp4',
+            'title': 'Important Concepts and Terms – Introduction to Microbiology',
+        },
+        'skip': 'Requires lecturio account credentials',
+    }
+
+    _CC_LANGS = {
+        'German': 'de',
+        'English': 'en',
+        'Spanish': 'es',
+        'French': 'fr',
+        'Polish': 'pl',
+        'Russian': 'ru',
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
+            display_id)
+
+        lecture_id = self._search_regex(
+            r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
+
+        api_url = self._search_regex(
+            r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'api url', group='url')
+
+        video = self._download_json(api_url, display_id)
+
+        title = video['title'].strip()
+
+        formats = []
+        for format_ in video['content']['media']:
+            if not isinstance(format_, dict):
+                continue
+            file_ = format_.get('file')
+            if not file_:
+                continue
+            ext = determine_ext(file_)
+            if ext == 'smil':
+                # smil contains only broken RTMP formats anyway
+                continue
+            file_url = url_or_none(file_)
+            if not file_url:
+                continue
+            label = str_or_none(format_.get('label'))
+            filesize = int_or_none(format_.get('fileSize'))
+            formats.append({
+                'url': file_url,
+                'format_id': label,
+                'filesize': float_or_none(filesize, invscale=1000)
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        automatic_captions = {}
+        cc = self._parse_json(
+            self._search_regex(
+                r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
+                default='{}'), display_id, fatal=False)
+        for cc_label, cc_url in cc.items():
+            cc_url = url_or_none(cc_url)
+            if not cc_url:
+                continue
+            sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles
+            lang = self._search_regex(
+                r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0])
+            sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
+                'url': cc_url,
+            })
+
+        return {
+            'id': lecture_id,
+            'title': title,
+            'formats': formats,
+            'subtitles': subtitles,
+            'automatic_captions': automatic_captions,
+        }
+
+
+class LecturioCourseIE(LecturioBaseIE):
+    _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
+    _TEST = {
+        'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
+        'info_dict': {
+            'id': 'microbiology-introduction',
+            'title': 'Microbiology: Introduction',
+        },
+        'playlist_count': 45,
+        'skip': 'Requires lecturio account credentials',
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        entries = []
+        for mobj in re.finditer(
+                r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
+                webpage):
+            params = extract_attributes(mobj.group(0))
+            lecture_url = urljoin(url, params.get('data-url'))
+            lecture_id = params.get('data-id')
+            entries.append(self.url_result(
+                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
+
+        title = self._search_regex(
+            r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
+            'title', default=None)
+
+        return self.playlist_result(entries, display_id, title)

youtube_dl/extractor/libraryofcongress.py

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

youtube_dl/extractor/linkedin.py

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

youtube_dl/extractor/lynda.py

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

youtube_dl/extractor/mediaset.py

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

youtube_dl/extractor/mixcloud.py

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

youtube_dl/extractor/nbc.py

@@ -9,10 +9,8 @@ from .theplatform import ThePlatformIE
 from .adobepass import AdobePassIE
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
-    find_xpath_attr,
     smuggle_url,
     try_get,
-    unescapeHTML,
     update_url_query,
     int_or_none,
 )
@@ -269,27 +267,14 @@ class CSNNEIE(InfoExtractor):
 
 
 class NBCNewsIE(ThePlatformIE):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
-        (?:video/.+?/(?P<id>\d+)|
-        ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
-        '''
+    _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
 
     _TESTS = [
-        {
-            'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
-            'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
-            'info_dict': {
-                'id': '52753292',
-                'ext': 'flv',
-                'title': 'Crew emerges after four-month Mars food study',
-                'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
-            },
-        },
         {
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
             'md5': 'af1adfa51312291a017720403826bb64',
             'info_dict': {
-                'id': 'p_tweet_snow_140529',
+                'id': '269389891880',
                 'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
@@ -313,7 +298,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
             'info_dict': {
-                'id': 'nn_netcast_150204',
+                'id': '394064451844',
                 'ext': 'mp4',
                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
@@ -326,7 +311,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
             'md5': 'a49e173825e5fcd15c13fc297fced39d',
             'info_dict': {
-                'id': 'x_lon_vwhorn_150922',
+                'id': '529953347624',
                 'ext': 'mp4',
                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
@@ -339,7 +324,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
             'md5': '118d7ca3f0bea6534f119c68ef539f71',
             'info_dict': {
-                'id': 'tdy_al_space_160420',
+                'id': '669831235788',
                 'ext': 'mp4',
                 'title': 'See the aurora borealis from space in stunning new NASA video',
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
@@ -352,7 +337,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
             'info_dict': {
-                'id': 'n_hayes_Aimm_140801_272214',
+                'id': '314487875924',
                 'ext': 'mp4',
                 'title': 'The chaotic GOP immigration vote',
                 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
@@ -374,60 +359,22 @@ class NBCNewsIE(ThePlatformIE):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        if video_id is not None:
-            all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
-            info = all_info.find('video')
-
-            return {
-                'id': video_id,
-                'title': info.find('headline').text,
-                'ext': 'flv',
-                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-                'description': info.find('caption').text,
-                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-            }
-        else:
-            # "feature" and "nightly-news" pages use theplatform.com
-            video_id = mobj.group('mpx_id')
+        video_id = self._match_id(url)
+        if not video_id.isdigit():
             webpage = self._download_webpage(url, video_id)
 
-            filter_param = 'byId'
-            bootstrap_json = self._search_regex(
-                [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
-                 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
-                 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
-                webpage, 'bootstrap json', default=None)
-            if bootstrap_json:
-                bootstrap = self._parse_json(
-                    bootstrap_json, video_id, transform_source=unescapeHTML)
+            data = self._parse_json(self._search_regex(
+                r'window\.__data\s*=\s*({.+});', webpage,
+                'bootstrap json'), video_id)
+            video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
 
-                info = None
-                if 'results' in bootstrap:
-                    info = bootstrap['results'][0]['video']
-                elif 'video' in bootstrap:
-                    info = bootstrap['video']
-                elif 'msnbcVideoInfo' in bootstrap:
-                    info = bootstrap['msnbcVideoInfo']['meta']
-                elif 'msnbcThePlatform' in bootstrap:
-                    info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
-                else:
-                    info = bootstrap
-
-                if 'guid' in info:
-                    video_id = info['guid']
-                    filter_param = 'byGuid'
-                elif 'mpxId' in info:
-                    video_id = info['mpxId']
-
-            return {
-                '_type': 'url_transparent',
-                'id': video_id,
-                # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
-                'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
-                'ie_key': 'ThePlatformFeed',
-            }
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
+            'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
+            'ie_key': 'ThePlatformFeed',
+        }
 
 
 class NBCOlympicsIE(InfoExtractor):

youtube_dl/extractor/njpwworld.py

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

youtube_dl/extractor/nova.py

@@ -35,7 +35,7 @@ class NovaEmbedIE(InfoExtractor):
 
         bitrates = self._parse_json(
             self._search_regex(
-                r'(?s)bitrates\s*=\s*({.+?})\s*;', webpage, 'formats'),
+                r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'),
             video_id, transform_source=js_to_json)
 
         QUALITIES = ('lq', 'mq', 'hq', 'hd')

youtube_dl/extractor/nrk.py

@@ -211,13 +211,13 @@ class NRKIE(NRKBaseIE):
     _TESTS = [{
         # video
         'url': 'http://www.nrk.no/video/PS*150533',
-        'md5': '2f7f6eeb2aacdd99885f355428715cfa',
+        'md5': '706f34cdf1322577589e369e522b50ef',
         'info_dict': {
             'id': '150533',
             'ext': 'mp4',
             'title': 'Dompap og andre fugler i Piip-Show',
             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
-            'duration': 263,
+            'duration': 262,
         }
     }, {
         # audio
@@ -248,7 +248,7 @@ class NRKTVIE(NRKBaseIE):
     _VALID_URL = r'''(?x)
                         https?://
                             (?:tv|radio)\.nrk(?:super)?\.no/
-                            (?:serie/[^/]+|program)/
+                            (?:serie(?:/[^/]+){1,2}|program)/
                             (?![Ee]pisodes)%s
                             (?:/\d{2}-\d{2}-\d{4})?
                             (?:\#del=(?P<part_id>\d+))?
@@ -256,14 +256,14 @@ class NRKTVIE(NRKBaseIE):
     _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
     _TESTS = [{
         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
-        'md5': '4e9ca6629f09e588ed240fb11619922a',
+        'md5': '9a167e54d04671eb6317a37b7bc8a280',
         'info_dict': {
             'id': 'MUHH48000314AA',
             'ext': 'mp4',
             'title': '20 spørsmål 23.05.2014',
             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
             'duration': 1741,
-            'series': '20 spørsmål - TV',
+            'series': '20 spørsmål',
             'episode': '23.05.2014',
         },
     }, {
@@ -301,7 +301,7 @@ class NRKTVIE(NRKBaseIE):
                 'id': 'MSPO40010515AH',
                 'ext': 'mp4',
                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
-                'description': 'md5:c03aba1e917561eface5214020551b7a',
+                'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
                 'duration': 772,
                 'series': 'Tour de Ski',
                 'episode': '06.01.2015',
@@ -314,7 +314,7 @@ class NRKTVIE(NRKBaseIE):
                 'id': 'MSPO40010515BH',
                 'ext': 'mp4',
                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
-                'description': 'md5:c03aba1e917561eface5214020551b7a',
+                'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
                 'duration': 6175,
                 'series': 'Tour de Ski',
                 'episode': '06.01.2015',
@@ -326,7 +326,7 @@ class NRKTVIE(NRKBaseIE):
         'info_dict': {
             'id': 'MSPO40010515',
             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
-            'description': 'md5:c03aba1e917561eface5214020551b7a',
+            'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
         },
         'expected_warnings': ['Video is geo restricted'],
     }, {
@@ -362,6 +362,9 @@ class NRKTVIE(NRKBaseIE):
     }, {
         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
         'only_matching': True,
+    }, {
+        'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
+        'only_matching': True,
     }]
 
 
@@ -403,21 +406,35 @@ class NRKTVSerieBaseIE(InfoExtractor):
     def _extract_series(self, webpage, display_id, fatal=True):
         config = self._parse_json(
             self._search_regex(
-                r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config',
-                default='{}' if not fatal else NO_DEFAULT),
+                (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;',
+                 r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
+                webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
             display_id, fatal=False)
         if not config:
             return
-        return try_get(config, lambda x: x['series'], dict)
+        return try_get(
+            config,
+            (lambda x: x['initialState']['series'], lambda x: x['series']),
+            dict)
+
+    def _extract_seasons(self, seasons):
+        if not isinstance(seasons, list):
+            return []
+        entries = []
+        for season in seasons:
+            entries.extend(self._extract_episodes(season))
+        return entries
 
     def _extract_episodes(self, season):
-        entries = []
         if not isinstance(season, dict):
-            return entries
-        episodes = season.get('episodes')
-        if not isinstance(episodes, list):
-            return entries
-        for episode in episodes:
+            return []
+        return self._extract_entries(season.get('episodes'))
+
+    def _extract_entries(self, entry_list):
+        if not isinstance(entry_list, list):
+            return []
+        entries = []
+        for episode in entry_list:
             nrk_id = episode.get('prfId')
             if not nrk_id or not isinstance(nrk_id, compat_str):
                 continue
@@ -462,7 +479,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
     _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
     _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
     _TESTS = [{
-        # new layout
+        # new layout, seasons
         'url': 'https://tv.nrk.no/serie/backstage',
         'info_dict': {
             'id': 'backstage',
@@ -471,20 +488,21 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         },
         'playlist_mincount': 60,
     }, {
-        # old layout
+        # new layout, instalments
         'url': 'https://tv.nrk.no/serie/groenn-glede',
         'info_dict': {
             'id': 'groenn-glede',
             'title': 'Grønn glede',
             'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
         },
-        'playlist_mincount': 9,
+        'playlist_mincount': 10,
     }, {
-        'url': 'http://tv.nrksuper.no/serie/labyrint',
+        # old layout
+        'url': 'https://tv.nrksuper.no/serie/labyrint',
         'info_dict': {
             'id': 'labyrint',
             'title': 'Labyrint',
-            'description': 'md5:58afd450974c89e27d5a19212eee7115',
+            'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
         },
         'playlist_mincount': 3,
     }, {
@@ -517,11 +535,12 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
             description = try_get(
                 series, lambda x: x['titles']['subtitle'], compat_str)
             entries = []
-            for season in series['seasons']:
-                entries.extend(self._extract_episodes(season))
+            entries.extend(self._extract_seasons(series.get('seasons')))
+            entries.extend(self._extract_entries(series.get('instalments')))
+            entries.extend(self._extract_episodes(series.get('extraMaterial')))
             return self.playlist_result(entries, series_id, title, description)
 
-        # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede)
+        # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
         entries = [
             self.url_result(
                 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
@@ -533,6 +552,9 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
             'seriestitle', webpage,
             'title', default=None) or self._og_search_title(
             webpage, fatal=False)
+        if title:
+            title = self._search_regex(
+                r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title)
 
         description = self._html_search_meta(
             'series_description', webpage,
@@ -593,7 +615,7 @@ class NRKPlaylistIE(NRKPlaylistBaseIE):
             'title': 'Rivertonprisen til Karin Fossum',
             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
         },
-        'playlist_count': 5,
+        'playlist_count': 2,
     }]
 
     def _extract_title(self, webpage):

youtube_dl/extractor/nzz.py

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

youtube_dl/extractor/openload.py

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

youtube_dl/extractor/orf.py

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

youtube_dl/extractor/patreon.py

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

youtube_dl/extractor/philharmoniedeparis.py

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

youtube_dl/extractor/picarto.py

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

youtube_dl/extractor/pluralsight.py

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

youtube_dl/extractor/popcorntv.py

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

youtube_dl/extractor/pornhub.py

@@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -40,6 +40,7 @@ class PornHubIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
             'uploader': 'Babes',
+            'upload_date': '20130628',
             'duration': 361,
             'view_count': int,
             'like_count': int,
@@ -57,6 +58,7 @@ class PornHubIE(InfoExtractor):
             'ext': 'mp4',
             'title': '重庆婷婷女王足交',
             'uploader': 'Unknown',
+            'upload_date': '20150213',
             'duration': 1753,
             'view_count': int,
             'like_count': int,
@@ -119,12 +121,15 @@ class PornHubIE(InfoExtractor):
     }, {
         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
         'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
             webpage)
 
     def _extract_count(self, pattern, webpage, name):
@@ -132,14 +137,16 @@ class PornHubIE(InfoExtractor):
             pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host') or 'pornhub.com'
+        video_id = mobj.group('id')
 
-        self._set_cookie('pornhub.com', 'age_verified', '1')
+        self._set_cookie(host, 'age_verified', '1')
 
         def dl_webpage(platform):
-            self._set_cookie('pornhub.com', 'platform', platform)
+            self._set_cookie(host, 'platform', platform)
             return self._download_webpage(
-                'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
+                'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
                 video_id, 'Downloading %s webpage' % platform)
 
         webpage = dl_webpage('pc')
@@ -237,8 +244,14 @@ class PornHubIE(InfoExtractor):
                 video_urls.append((video_url, None))
                 video_urls_set.add(video_url)
 
+        upload_date = None
         formats = []
         for video_url, height in video_urls:
+            if not upload_date:
+                upload_date = self._search_regex(
+                    r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
+                if upload_date:
+                    upload_date = upload_date.replace('/', '')
             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:
@@ -278,6 +291,7 @@ class PornHubIE(InfoExtractor):
         return {
             'id': video_id,
             'uploader': video_uploader,
+            'upload_date': upload_date,
             'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
@@ -294,7 +308,7 @@ class PornHubIE(InfoExtractor):
 
 
 class PornHubPlaylistBaseIE(InfoExtractor):
-    def _extract_entries(self, webpage):
+    def _extract_entries(self, webpage, host):
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see
         # https://github.com/rg3/youtube-dl/issues/11594).
@@ -304,7 +318,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
         return [
             self.url_result(
-                'http://www.pornhub.com/%s' % video_url,
+                'http://www.%s/%s' % (host, video_url),
                 PornHubIE.ie_key(), video_title=title)
             for video_url, title in orderedSet(re.findall(
                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
@@ -312,11 +326,13 @@ class PornHubPlaylistBaseIE(InfoExtractor):
         ]
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        playlist_id = mobj.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = self._extract_entries(webpage)
+        entries = self._extract_entries(webpage, host)
 
         playlist = self._parse_json(
             self._search_regex(
@@ -331,7 +347,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {
@@ -346,7 +362,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {
@@ -387,7 +403,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }]
 
     def _real_extract(self, url):
-        user_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        user_id = mobj.group('id')
 
         entries = []
         for page_num in itertools.count(1):
@@ -399,7 +417,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
                 raise
-            page_entries = self._extract_entries(webpage)
+            page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
             entries.extend(page_entries)

youtube_dl/extractor/rai.py

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

youtube_dl/extractor/rte.py

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

youtube_dl/extractor/rutube.py

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

youtube_dl/extractor/ruutu.py

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

youtube_dl/extractor/screencast.py

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

youtube_dl/extractor/shared.py

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

youtube_dl/extractor/sixplay.py

@@ -64,7 +64,7 @@ class SixPlayIE(InfoExtractor):
         for asset in clip_data['assets']:
             asset_url = asset.get('full_physical_path')
             protocol = asset.get('protocol')
-            if not asset_url or protocol == 'primetime' or asset_url in urls:
+            if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls:
                 continue
             urls.append(asset_url)
             container = asset.get('video_container')
@@ -81,19 +81,17 @@ class SixPlayIE(InfoExtractor):
                         if not urlh:
                             continue
                         asset_url = urlh.geturl()
-                    asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
-                    formats.extend(self._extract_m3u8_formats(
-                        asset_url, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
-                    formats.extend(self._extract_f4m_formats(
-                        asset_url.replace('.m3u8', '.f4m'),
-                        video_id, f4m_id='hds', fatal=False))
-                    formats.extend(self._extract_mpd_formats(
-                        asset_url.replace('.m3u8', '.mpd'),
-                        video_id, mpd_id='dash', fatal=False))
-                    formats.extend(self._extract_ism_formats(
-                        re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
-                        video_id, ism_id='mss', fatal=False))
+                    for i in range(3, 0, -1):
+                        asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i)
+                        m3u8_formats = self._extract_m3u8_formats(
+                            asset_url, video_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False)
+                        formats.extend(m3u8_formats)
+                        formats.extend(self._extract_mpd_formats(
+                            asset_url.replace('.m3u8', '.mpd'),
+                            video_id, mpd_id='dash', fatal=False))
+                        if m3u8_formats:
+                            break
                 else:
                     formats.extend(self._extract_m3u8_formats(
                         asset_url, video_id, 'mp4', 'm3u8_native',

youtube_dl/extractor/spike.py

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

youtube_dl/extractor/sportbox.py

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

youtube_dl/extractor/tbs.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class TBSIE(TurnerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))'
     _TESTS = [{
         'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
         'info_dict': {
@@ -40,12 +40,12 @@ class TBSIE(TurnerBaseIE):
     }]
 
     def _real_extract(self, url):
-        site, display_id = re.match(self._VALID_URL, url).groups()
+        site, path, display_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, display_id)
         drupal_settings = self._parse_json(self._search_regex(
             r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>',
             webpage, 'drupal setting'), display_id)
-        video_data = drupal_settings['turner_playlist'][0]
+        video_data = next(v for v in drupal_settings['turner_playlist'] if v.get('url') == path)
 
         media_id = video_data['mediaID']
         title = video_data['title']

youtube_dl/extractor/teachable.py

@@ -14,20 +14,38 @@ from ..utils import (
 )
 
 
-class UpskillBaseIE(InfoExtractor):
-    _LOGIN_URL = 'http://upskillcourses.com/sign_in'
-    _NETRC_MACHINE = 'upskill'
+class TeachableBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'teachable'
+    _URL_PREFIX = 'teachable:'
+
+    _SITES = {
+        # Only notable ones here
+        'upskillcourses.com': 'upskill',
+        'academy.gns3.com': 'gns3',
+        'academyhacker.com': 'academyhacker',
+        'stackskills.com': 'stackskills',
+        'market.saleshacker.com': 'saleshacker',
+        'learnability.org': 'learnability',
+        'edurila.com': 'edurila',
+    }
+
+    _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
 
     def _real_initialize(self):
-        self._login()
+        self._logged_in = False
 
-    def _login(self):
-        username, password = self._get_login_info()
+    def _login(self, site):
+        if self._logged_in:
+            return
+
+        username, password = self._get_login_info(
+            netrc_machine=self._SITES.get(site, site))
         if username is None:
             return
 
         login_page, urlh = self._download_webpage_handle(
-            self._LOGIN_URL, None, 'Downloading login page')
+            'https://%s/sign_in' % site, None,
+            'Downloading %s login page' % site)
 
         login_url = compat_str(urlh.geturl())
 
@@ -46,18 +64,24 @@ class UpskillBaseIE(InfoExtractor):
             post_url = urljoin(login_url, post_url)
 
         response = self._download_webpage(
-            post_url, None, 'Logging in',
+            post_url, None, 'Logging in to %s' % site,
             data=urlencode_postdata(login_form),
             headers={
                 'Content-Type': 'application/x-www-form-urlencoded',
                 'Referer': login_url,
             })
 
+        if '>I accept the new Privacy Policy<' in response:
+            raise ExtractorError(
+                'Unable to login: %s asks you to accept new Privacy Policy. '
+                '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*<')):
+            self._logged_in = True
             return
 
         message = get_element_by_class('alert', response)
@@ -68,8 +92,14 @@ class UpskillBaseIE(InfoExtractor):
         raise ExtractorError('Unable to log in')
 
 
-class UpskillIE(UpskillBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P<id>\d+)'
+class TeachableIE(TeachableBaseIE):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        %shttps?://(?P<site_t>[^/]+)|
+                        https?://(?:www\.)?(?P<site>%s)
+                    )
+                    /courses/[^/]+/lectures/(?P<id>\d+)
+                    ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 
     _TESTS = [{
         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
@@ -77,7 +107,7 @@ class UpskillIE(UpskillBaseIE):
             'id': 'uzw6zw58or',
             'ext': 'mp4',
             'title': 'Welcome to the Course!',
-            'description': 'md5:8d66c13403783370af62ca97a7357bdd',
+            'description': 'md5:65edb0affa582974de4625b9cdea1107',
             'duration': 138.763,
             'timestamp': 1479846621,
             'upload_date': '20161122',
@@ -88,10 +118,38 @@ class UpskillIE(UpskillBaseIE):
     }, {
         'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
         'only_matching': True,
+    }, {
+        'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
+        'only_matching': True,
+    }, {
+        'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _is_teachable(webpage):
+        return 'teachableTracker.linker:autoLink' in webpage and re.search(
+            r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
+            webpage)
+
+    @staticmethod
+    def _extract_url(webpage, source_url):
+        if not TeachableIE._is_teachable(webpage):
+            print('NOT TEACHABLE')
+            return
+        if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
+            return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
+
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        site = mobj.group('site') or mobj.group('site_t')
+        video_id = mobj.group('id')
+
+        self._login(site)
+
+        prefixed = url.startswith(self._URL_PREFIX)
+        if prefixed:
+            url = url[len(self._URL_PREFIX):]
 
         webpage = self._download_webpage(url, video_id)
 
@@ -113,12 +171,18 @@ class UpskillIE(UpskillBaseIE):
         }
 
 
-class UpskillCourseIE(UpskillBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P<id>[^/?#&]+)'
+class TeachableCourseIE(TeachableBaseIE):
+    _VALID_URL = r'''(?x)
+                        (?:
+                            %shttps?://(?P<site_t>[^/]+)|
+                            https?://(?:www\.)?(?P<site>%s)
+                        )
+                        /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
+                    ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
     _TESTS = [{
         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
         'info_dict': {
-            'id': '119763',
+            'id': 'essential-web-developer-course',
             'title': 'The Essential Web Developer Course (Free)',
         },
         'playlist_count': 192,
@@ -128,21 +192,37 @@ class UpskillCourseIE(UpskillBaseIE):
     }, {
         'url': 'http://upskillcourses.com/courses/enrolled/119763',
         'only_matching': True,
+    }, {
+        'url': 'https://academy.gns3.com/courses/enrolled/423415',
+        'only_matching': True,
+    }, {
+        'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
+        'only_matching': True,
+    }, {
+        'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
+        'only_matching': True,
     }]
 
     @classmethod
     def suitable(cls, url):
-        return False if UpskillIE.suitable(url) else super(
-            UpskillCourseIE, cls).suitable(url)
+        return False if TeachableIE.suitable(url) else super(
+            TeachableCourseIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        course_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        site = mobj.group('site') or mobj.group('site_t')
+        course_id = mobj.group('id')
+
+        self._login(site)
+
+        prefixed = url.startswith(self._URL_PREFIX)
+        if prefixed:
+            prefix = self._URL_PREFIX
+            url = url[len(prefix):]
 
         webpage = self._download_webpage(url, course_id)
 
-        course_id = self._search_regex(
-            r'data-course-id=["\'](\d+)', webpage, 'course id',
-            default=course_id)
+        url_base = 'https://%s/' % site
 
         entries = []
 
@@ -162,10 +242,13 @@ class UpskillCourseIE(UpskillBaseIE):
             title = self._html_search_regex(
                 r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
                 'title', default=None)
+            entry_url = urljoin(url_base, lecture_url)
+            if prefixed:
+                entry_url = self._URL_PREFIX + entry_url
             entries.append(
                 self.url_result(
-                    urljoin('http://upskillcourses.com/', lecture_url),
-                    ie=UpskillIE.ie_key(), video_id=lecture_id,
+                    entry_url,
+                    ie=TeachableIE.ie_key(), video_id=lecture_id,
                     video_title=clean_html(title)))
 
         course_title = self._html_search_regex(

youtube_dl/extractor/ted.py

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

youtube_dl/extractor/theplatform.py

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

youtube_dl/extractor/tiktok.py

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

youtube_dl/extractor/tnaflix.py

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

youtube_dl/extractor/tube8.py

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

youtube_dl/extractor/tv3.py

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

youtube_dl/extractor/twitcasting.py

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

youtube_dl/extractor/twitch.py

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

youtube_dl/extractor/udemy.py

@@ -122,7 +122,9 @@ class UdemyIE(InfoExtractor):
             raise ExtractorError(error_str, expected=True)
 
     def _download_webpage_handle(self, *args, **kwargs):
-        kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
+        headers = kwargs.get('headers', {}).copy()
+        headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
+        kwargs['headers'] = headers
         return super(UdemyIE, self)._download_webpage_handle(
             *args, **compat_kwargs(kwargs))
 

youtube_dl/extractor/viewster.py

@@ -130,16 +130,16 @@ class ViewsterIE(InfoExtractor):
             def concat(suffix, sep='-'):
                 return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix
 
-            for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
-                media = self._download_json(
-                    'https://public-api.viewster.com/movies/%s/video' % entry_id,
-                    video_id, 'Downloading %s JSON' % concat(media_type, ' '), fatal=False, query={
-                        'mediaType': media_type,
-                        'language': audio,
-                        'subtitle': subtitle,
-                    })
-                if not media:
-                    continue
+            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

youtube_dl/extractor/vimeo.py

@@ -14,10 +14,13 @@ from ..compat import (
 from ..utils import (
     determine_ext,
     ExtractorError,
+    js_to_json,
     InAdvancePagedList,
     int_or_none,
     merge_dicts,
     NO_DEFAULT,
+    parse_filesize,
+    qualities,
     RegexNotFoundError,
     sanitized_Request,
     smuggle_url,
@@ -27,7 +30,6 @@ from ..utils import (
     unsmuggle_url,
     urlencode_postdata,
     unescapeHTML,
-    parse_filesize,
 )
 
 
@@ -299,10 +301,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
                 'uploader_id': 'atencio',
                 'uploader': 'Peter Atencio',
+                'channel_id': 'keypeele',
+                'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
                 'timestamp': 1380339469,
                 'upload_date': '20130928',
                 'duration': 187,
             },
+            'expected_warnings': ['Unable to download JSON metadata'],
         },
         {
             'url': 'http://vimeo.com/76979871',
@@ -355,11 +360,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'url': 'https://vimeo.com/channels/tributes/6213729',
             'info_dict': {
                 'id': '6213729',
-                'ext': 'mov',
+                'ext': 'mp4',
                 'title': 'Vimeo Tribute: The Shining',
                 'uploader': 'Casey Donahue',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
                 'uploader_id': 'caseydonahue',
+                'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
+                'channel_id': 'tributes',
                 'timestamp': 1250886430,
                 'upload_date': '20090821',
                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
@@ -465,6 +472,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
         if 'Referer' not in headers:
             headers['Referer'] = url
 
+        channel_id = self._search_regex(
+            r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
+
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -543,6 +553,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 else:
                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
                 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
+                config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
                 config = self._search_regex(config_re, webpage, 'info section',
                                             flags=re.DOTALL)
                 config = json.loads(config)
@@ -563,19 +574,23 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if config.get('view') == 4:
                 config = self._verify_player_video_password(redirect_url, video_id)
 
+        vod = config.get('video', {}).get('vod', {})
+
         def is_rented():
             if '>You rented this title.<' in webpage:
                 return True
             if config.get('user', {}).get('purchased'):
                 return True
-            label = try_get(
-                config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
-            if label and label.startswith('You rented this'):
-                return True
+            for purchase_option in vod.get('purchase_options', []):
+                if purchase_option.get('purchased'):
+                    return True
+                label = purchase_option.get('label_string')
+                if label and (label.startswith('You rented this') or label.endswith(' remaining')):
+                    return True
             return False
 
-        if is_rented():
-            feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
+        if is_rented() and vod.get('is_trailer'):
+            feature_id = vod.get('feature_id')
             if feature_id and not data.get('force_feature_id', False):
                 return self.url_result(smuggle_url(
                     'https://player.vimeo.com/player/%s' % feature_id,
@@ -652,6 +667,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
                 webpage, 'license', default=None, group='license')
 
+        channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
+
         info_dict = {
             'id': video_id,
             'formats': formats,
@@ -662,6 +679,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'like_count': like_count,
             'comment_count': comment_count,
             'license': cc_license,
+            'channel_id': channel_id,
+            'channel_url': channel_url,
         }
 
         info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
@@ -1046,3 +1065,96 @@ class VimeoLikesIE(InfoExtractor):
             'description': description,
             'entries': pl,
         }
+
+
+class VHXEmbedIE(InfoExtractor):
+    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')),
+        }

youtube_dl/extractor/vk.py

@@ -293,8 +293,12 @@ class VKIE(VKBaseIE):
             # This video is no longer available, because its author has been blocked.
             'url': 'https://vk.com/video-10639516_456240611',
             'only_matching': True,
-        }
-    ]
+        },
+        {
+            # The video is not available in your region.
+            'url': 'https://vk.com/video-51812607_171445436',
+            'only_matching': True,
+        }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -354,6 +358,9 @@ class VKIE(VKBaseIE):
 
             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.',
         }
 
         for error_re, error_msg in ERRORS.items():

youtube_dl/extractor/vrv.py

@@ -90,7 +90,13 @@ class VRVIE(VRVBaseIE):
     def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang):
         if not url or stream_format not in ('hls', 'dash'):
             return []
-        stream_id = hardsub_lang or audio_lang
+        assert audio_lang or hardsub_lang
+        stream_id_list = []
+        if audio_lang:
+            stream_id_list.append('audio-%s' % audio_lang)
+        if hardsub_lang:
+            stream_id_list.append('hardsub-%s' % hardsub_lang)
+        stream_id = '-'.join(stream_id_list)
         format_id = '%s-%s' % (stream_format, stream_id)
         if stream_format == 'hls':
             adaptive_formats = self._extract_m3u8_formats(

youtube_dl/extractor/vzaar.py

@@ -4,15 +4,19 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     float_or_none,
+    unified_timestamp,
+    url_or_none,
 )
 
 
 class VzaarIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
     _TESTS = [{
+        # HTTP and HLS
         'url': 'https://vzaar.com/videos/1152805',
         'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
         'info_dict': {
@@ -40,24 +44,48 @@ class VzaarIE(InfoExtractor):
         video_id = self._match_id(url)
         video_data = self._download_json(
             'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
-        source_url = video_data['sourceUrl']
 
-        info = {
+        title = video_data['videoTitle']
+
+        formats = []
+
+        source_url = url_or_none(video_data.get('sourceUrl'))
+        if source_url:
+            f = {
+                'url': source_url,
+                'format_id': 'http',
+            }
+            if 'audio' in source_url:
+                f.update({
+                    'vcodec': 'none',
+                    'ext': 'mp3',
+                })
+            else:
+                f.update({
+                    'width': int_or_none(video_data.get('width')),
+                    'height': int_or_none(video_data.get('height')),
+                    'ext': 'mp4',
+                    'fps': float_or_none(video_data.get('fps')),
+                })
+            formats.append(f)
+
+        video_guid = video_data.get('guid')
+        usp = video_data.get('usp')
+        if isinstance(video_guid, compat_str) and isinstance(usp, dict):
+            m3u8_url = ('http://fable.vzaar.com/v4/usp/%s/%s.ism/.m3u8?'
+                        % (video_guid, video_id)) + '&'.join(
+                '%s=%s' % (k, v) for k, v in usp.items())
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        self._sort_formats(formats)
+
+        return {
             'id': video_id,
-            'title': video_data['videoTitle'],
-            'url': source_url,
+            'title': title,
             'thumbnail': self._proto_relative_url(video_data.get('poster')),
             'duration': float_or_none(video_data.get('videoDuration')),
+            'timestamp': unified_timestamp(video_data.get('ts')),
+            'formats': formats,
         }
-        if 'audio' in source_url:
-            info.update({
-                'vcodec': 'none',
-                'ext': 'mp3',
-            })
-        else:
-            info.update({
-                'width': int_or_none(video_data.get('width')),
-                'height': int_or_none(video_data.get('height')),
-                'ext': 'mp4',
-            })
-        return info

youtube_dl/extractor/wistia.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class WistiaIE(InfoExtractor):
-    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.net/embed/iframe/)(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)'
     _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
     _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
 
@@ -35,12 +35,15 @@ class WistiaIE(InfoExtractor):
         # with hls video
         'url': 'wistia:807fafadvk',
         'only_matching': True,
+    }, {
+        'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_url(webpage):
         match = re.search(
-            r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+            r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage)
         if match:
             return unescapeHTML(match.group('url'))
 

youtube_dl/extractor/wwe.py

@@ -0,0 +1,140 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    try_get,
+    unescapeHTML,
+    url_or_none,
+    urljoin,
+)
+
+
+class WWEBaseIE(InfoExtractor):
+    _SUBTITLE_LANGS = {
+        'English': 'en',
+        'Deutsch': 'de',
+    }
+
+    def _extract_entry(self, data, url, video_id=None):
+        video_id = compat_str(video_id or data['nid'])
+        title = data['title']
+
+        formats = self._extract_m3u8_formats(
+            data['file'], video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        description = data.get('description')
+        thumbnail = urljoin(url, data.get('image'))
+        series = data.get('show_name')
+        episode = data.get('episode_name')
+
+        subtitles = {}
+        tracks = data.get('tracks')
+        if isinstance(tracks, list):
+            for track in tracks:
+                if not isinstance(track, dict):
+                    continue
+                if track.get('kind') != 'captions':
+                    continue
+                track_file = url_or_none(track.get('file'))
+                if not track_file:
+                    continue
+                label = track.get('label')
+                lang = self._SUBTITLE_LANGS.get(label, label) or 'en'
+                subtitles.setdefault(lang, []).append({
+                    'url': track_file,
+                })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'series': series,
+            'episode': episode,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class WWEIE(WWEBaseIE):
+    _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018',
+        'md5': '92811c6a14bfc206f7a6a9c5d9140184',
+        'info_dict': {
+            'id': '40048199',
+            'ext': 'mp4',
+            'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018',
+            'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'https://de.wwe.com/videos/gran-metalik-vs-tony-nese-wwe-205-live-sept-4-2018',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        landing = self._parse_json(
+            self._html_search_regex(
+                r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;',
+                webpage, 'drupal settings'),
+            display_id)['WWEVideoLanding']
+
+        data = landing['initialVideo']['playlist'][0]
+        video_id = landing.get('initialVideoId')
+
+        info = self._extract_entry(data, url, video_id)
+        info['display_id'] = display_id
+        return info
+
+
+class WWEPlaylistIE(WWEBaseIE):
+    _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.wwe.com/shows/raw/2018-11-12',
+        'info_dict': {
+            'id': '2018-11-12',
+        },
+        'playlist_mincount': 11,
+    }, {
+        'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        entries = []
+        for mobj in re.finditer(
+                r'data-video\s*=\s*(["\'])(?P<data>{.+?})\1', webpage):
+            video = self._parse_json(
+                mobj.group('data'), display_id, transform_source=unescapeHTML,
+                fatal=False)
+            if not video:
+                continue
+            data = try_get(video, lambda x: x['playlist'][0], dict)
+            if not data:
+                continue
+            try:
+                entry = self._extract_entry(data, url)
+            except Exception:
+                continue
+            entry['extractor_key'] = WWEIE.ie_key()
+            entries.append(entry)
+
+        return self.playlist_result(entries, display_id)

youtube_dl/extractor/xvideos.py

@@ -45,7 +45,7 @@ class XVideosIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'http://www.xvideos.com/video%s/' % video_id, video_id)
+            'https://www.xvideos.com/video%s/' % video_id, video_id)
 
         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
         if mobj:

youtube_dl/extractor/yourporn.py

@@ -26,7 +26,7 @@ class YourPornIE(InfoExtractor):
             self._search_regex(
                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
                 group='data'),
-            video_id)[video_id])
+            video_id)[video_id]).replace('/cdn/', '/cdn2/')
 
         title = (self._search_regex(
             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',

youtube_dl/extractor/youtube.py

@@ -41,6 +41,7 @@ from ..utils import (
     remove_quotes,
     remove_start,
     smuggle_url,
+    str_or_none,
     str_to_int,
     try_get,
     unescapeHTML,
@@ -259,7 +260,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         return True
 
     def _download_webpage_handle(self, *args, **kwargs):
-        kwargs.setdefault('query', {})['disable_polymer'] = 'true'
+        query = kwargs.get('query', {}).copy()
+        query['disable_polymer'] = 'true'
+        kwargs['query'] = query
         return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
             *args, **compat_kwargs(kwargs))
 
@@ -347,6 +350,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?hooktube\.com/|
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
+                            (?:www\.)?invidio\.us/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
@@ -490,12 +494,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Philipp Hagemeister',
                 'uploader_id': 'phihag',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
+                'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
+                'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
                 'upload_date': '20121002',
                 'license': 'Standard YouTube License',
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
                 'duration': 10,
+                'view_count': int,
                 'like_count': int,
                 'dislike_count': int,
                 'start_time': 1,
@@ -578,6 +585,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
                 'duration': 10,
+                'view_count': int,
                 'like_count': int,
                 'dislike_count': int,
             },
@@ -1064,6 +1072,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
             'only_matching': True,
         },
+        {
+            'url': 'https://invidio.us/watch?v=BaW_jenozKc',
+            'only_matching': True,
+        },
     ]
 
     def __init__(self, *args, **kwargs):
@@ -1180,7 +1192,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
              r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\('),
+             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
             jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
@@ -1529,6 +1542,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         def extract_view_count(v_info):
             return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
 
+        player_response = {}
+
         # Get video info
         embed_webpage = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
@@ -1571,6 +1586,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 if args.get('livestream') == '1' or args.get('live_playback') == 1:
                     is_live = True
                 sts = ytplayer_config.get('sts')
+                if not player_response:
+                    pl_response = str_or_none(args.get('player_response'))
+                    if pl_response:
+                        pl_response = self._parse_json(pl_response, video_id, fatal=False)
+                        if isinstance(pl_response, dict):
+                            player_response = pl_response
             if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
                 # We also try looking in get_video_info since it may contain different dashmpd
                 # URL that points to a DASH manifest with possibly different itag set (some itags
@@ -1599,6 +1620,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     if not video_info_webpage:
                         continue
                     get_video_info = compat_parse_qs(video_info_webpage)
+                    if not player_response:
+                        pl_response = get_video_info.get('player_response', [None])[0]
+                        if isinstance(pl_response, dict):
+                            player_response = pl_response
                     add_dash_mpd(get_video_info)
                     if view_count is None:
                         view_count = extract_view_count(get_video_info)
@@ -1644,9 +1669,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     '"token" parameter not in video info for unknown reason',
                     video_id=video_id)
 
+        video_details = try_get(
+            player_response, lambda x: x['videoDetails'], dict) or {}
+
         # title
         if 'title' in video_info:
             video_title = video_info['title'][0]
+        elif 'title' in player_response:
+            video_title = video_details['title']
         else:
             self._downloader.report_warning('Unable to extract video title')
             video_title = '_'
@@ -1709,6 +1739,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         if view_count is None:
             view_count = extract_view_count(video_info)
+        if view_count is None and video_details:
+            view_count = int_or_none(video_details.get('viewCount'))
 
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
@@ -1889,7 +1921,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
         # uploader
-        video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
+        video_uploader = try_get(
+            video_info, lambda x: x['author'][0],
+            compat_str) or str_or_none(video_details.get('author'))
         if video_uploader:
             video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
         else:
@@ -1907,6 +1941,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             self._downloader.report_warning('unable to extract uploader nickname')
 
+        channel_id = self._html_search_meta(
+            'channelId', video_webpage, 'channel id')
+        channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
+
         # thumbnail image
         # We try first to get a high quality image:
         m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
@@ -1998,12 +2036,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         like_count = _extract_count('like')
         dislike_count = _extract_count('dislike')
 
+        if view_count is None:
+            view_count = str_to_int(self._search_regex(
+                r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
+                'view count', default=None))
+
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, video_webpage)
         automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
 
         video_duration = try_get(
             video_info, lambda x: int_or_none(x['length_seconds'][0]))
+        if not video_duration:
+            video_duration = int_or_none(video_details.get('lengthSeconds'))
         if not video_duration:
             video_duration = parse_duration(self._html_search_meta(
                 'duration', video_webpage, 'video duration'))
@@ -2078,6 +2123,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'uploader': video_uploader,
             'uploader_id': video_uploader_id,
             'uploader_url': video_uploader_url,
+            'channel_id': channel_id,
+            'channel_url': channel_url,
             'upload_date': upload_date,
             'license': video_license,
             'creator': video_creator or artist,
@@ -2116,7 +2163,11 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                         (?:https?://)?
                         (?:\w+\.)?
                         (?:
-                            youtube\.com/
+                            (?:
+                                youtube\.com|
+                                invidio\.us
+                            )
+                            /
                             (?:
                                (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
                                \? (?:.*?[&;])*? (?:p|a|list)=
@@ -2229,6 +2280,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
             'categories': ['People & Blogs'],
             'tags': list,
+            'view_count': int,
             'like_count': int,
             'dislike_count': int,
         },
@@ -2267,6 +2319,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         # music album playlist
         'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
         'only_matching': True,
+    }, {
+        'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
+        'only_matching': True,
     }]
 
     def _real_initialize(self):
@@ -2409,7 +2464,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
 
 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
     IE_DESC = 'YouTube.com channels'
-    _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
+    _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
     _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
     _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
     IE_NAME = 'youtube:channel'
@@ -2430,6 +2485,9 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
             'id': 'UUs0ifCMCm1icqRbqhUINa0w',
             'title': 'Uploads from Deus Ex',
         },
+    }, {
+        'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/extractor/zattoo.py

@@ -18,12 +18,12 @@ from ..utils import (
 )
 
 
-class ZattooBaseIE(InfoExtractor):
-    _NETRC_MACHINE = 'zattoo'
-    _HOST_URL = 'https://zattoo.com'
-
+class ZattooPlatformBaseIE(InfoExtractor):
     _power_guide_hash = None
 
+    def _host_url(self):
+        return 'https://%s' % (self._API_HOST if hasattr(self, '_API_HOST') else self._HOST)
+
     def _login(self):
         username, password = self._get_login_info()
         if not username or not password:
@@ -33,13 +33,13 @@ class ZattooBaseIE(InfoExtractor):
 
         try:
             data = self._download_json(
-                '%s/zapi/v2/account/login' % self._HOST_URL, None, 'Logging in',
+                '%s/zapi/v2/account/login' % self._host_url(), None, 'Logging in',
                 data=urlencode_postdata({
                     'login': username,
                     'password': password,
                     'remember': 'true',
                 }), headers={
-                    'Referer': '%s/login' % self._HOST_URL,
+                    'Referer': '%s/login' % self._host_url(),
                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
                 })
         except ExtractorError as e:
@@ -53,7 +53,7 @@ class ZattooBaseIE(InfoExtractor):
 
     def _real_initialize(self):
         webpage = self._download_webpage(
-            self._HOST_URL, None, 'Downloading app token')
+            self._host_url(), None, 'Downloading app token')
         app_token = self._html_search_regex(
             r'appToken\s*=\s*(["\'])(?P<token>(?:(?!\1).)+?)\1',
             webpage, 'app token', group='token')
@@ -62,7 +62,7 @@ class ZattooBaseIE(InfoExtractor):
 
         # Will setup appropriate cookies
         self._request_webpage(
-            '%s/zapi/v2/session/hello' % self._HOST_URL, None,
+            '%s/zapi/v2/session/hello' % self._host_url(), None,
             'Opening session', data=urlencode_postdata({
                 'client_app_token': app_token,
                 'uuid': compat_str(uuid4()),
@@ -75,7 +75,7 @@ class ZattooBaseIE(InfoExtractor):
 
     def _extract_cid(self, video_id, channel_name):
         channel_groups = self._download_json(
-            '%s/zapi/v2/cached/channels/%s' % (self._HOST_URL,
+            '%s/zapi/v2/cached/channels/%s' % (self._host_url(),
                                                self._power_guide_hash),
             video_id, 'Downloading channel list',
             query={'details': False})['channel_groups']
@@ -93,28 +93,30 @@ class ZattooBaseIE(InfoExtractor):
 
     def _extract_cid_and_video_info(self, video_id):
         data = self._download_json(
-            '%s/zapi/program/details' % self._HOST_URL,
+            '%s/zapi/v2/cached/program/power_details/%s' % (
+                self._host_url(), self._power_guide_hash),
             video_id,
             'Downloading video information',
             query={
-                'program_id': video_id,
-                'complete': True
+                'program_ids': video_id,
+                'complete': True,
             })
 
-        p = data['program']
+        p = data['programs'][0]
         cid = p['cid']
 
         info_dict = {
             'id': video_id,
-            'title': p.get('title') or p['episode_title'],
-            'description': p.get('description'),
-            'thumbnail': p.get('image_url'),
+            'title': p.get('t') or p['et'],
+            'description': p.get('d'),
+            'thumbnail': p.get('i_url'),
             'creator': p.get('channel_name'),
-            'episode': p.get('episode_title'),
-            'episode_number': int_or_none(p.get('episode_number')),
-            'season_number': int_or_none(p.get('season_number')),
+            'episode': p.get('et'),
+            'episode_number': int_or_none(p.get('e_no')),
+            'season_number': int_or_none(p.get('s_no')),
             'release_year': int_or_none(p.get('year')),
-            'categories': try_get(p, lambda x: x['categories'], list),
+            'categories': try_get(p, lambda x: x['c'], list),
+            'tags': try_get(p, lambda x: x['g'], list)
         }
 
         return cid, info_dict
@@ -126,11 +128,11 @@ class ZattooBaseIE(InfoExtractor):
 
         if is_live:
             postdata_common.update({'timeshift': 10800})
-            url = '%s/zapi/watch/live/%s' % (self._HOST_URL, cid)
+            url = '%s/zapi/watch/live/%s' % (self._host_url(), cid)
         elif record_id:
-            url = '%s/zapi/watch/recording/%s' % (self._HOST_URL, record_id)
+            url = '%s/zapi/watch/recording/%s' % (self._host_url(), record_id)
         else:
-            url = '%s/zapi/watch/recall/%s/%s' % (self._HOST_URL, cid, video_id)
+            url = '%s/zapi/watch/recall/%s/%s' % (self._host_url(), cid, video_id)
 
         formats = []
         for stream_type in ('dash', 'hls', 'hls5', 'hds'):
@@ -201,13 +203,13 @@ class ZattooBaseIE(InfoExtractor):
         return info_dict
 
 
-class QuicklineBaseIE(ZattooBaseIE):
+class QuicklineBaseIE(ZattooPlatformBaseIE):
     _NETRC_MACHINE = 'quickline'
-    _HOST_URL = 'https://mobiltv.quickline.com'
+    _HOST = 'mobiltv.quickline.com'
 
 
 class QuicklineIE(QuicklineBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)' % re.escape(QuicklineBaseIE._HOST)
 
     _TEST = {
         'url': 'https://mobiltv.quickline.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste',
@@ -220,7 +222,7 @@ class QuicklineIE(QuicklineBaseIE):
 
 
 class QuicklineLiveIE(QuicklineBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<id>[^/]+)' % re.escape(QuicklineBaseIE._HOST)
 
     _TEST = {
         'url': 'https://mobiltv.quickline.com/watch/srf1',
@@ -236,8 +238,18 @@ class QuicklineLiveIE(QuicklineBaseIE):
         return self._extract_video(channel_name, video_id, is_live=True)
 
 
+class ZattooBaseIE(ZattooPlatformBaseIE):
+    _NETRC_MACHINE = 'zattoo'
+    _HOST = 'zattoo.com'
+
+
+def _make_valid_url(tmpl, host):
+    return tmpl % re.escape(host)
+
+
 class ZattooIE(ZattooBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?'
+    _VALID_URL_TEMPLATE = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?'
+    _VALID_URL = _make_valid_url(_VALID_URL_TEMPLATE, ZattooBaseIE._HOST)
 
     # Since regular videos are only available for 7 days and recorded videos
     # are only available for a specific user, we cannot have detailed tests.
@@ -269,3 +281,142 @@ class ZattooLiveIE(ZattooBaseIE):
     def _real_extract(self, url):
         channel_name = video_id = self._match_id(url)
         return self._extract_video(channel_name, video_id, is_live=True)
+
+
+class NetPlusIE(ZattooIE):
+    _NETRC_MACHINE = 'netplus'
+    _HOST = 'netplus.tv'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.netplus.tv/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class MNetTVIE(ZattooIE):
+    _NETRC_MACHINE = 'mnettv'
+    _HOST = 'tvplus.m-net.de'
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://tvplus.m-net.de/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class WalyTVIE(ZattooIE):
+    _NETRC_MACHINE = 'walytv'
+    _HOST = 'player.waly.tv'
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://player.waly.tv/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class BBVTVIE(ZattooIE):
+    _NETRC_MACHINE = 'bbvtv'
+    _HOST = 'bbv-tv.net'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.bbv-tv.net/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class VTXTVIE(ZattooIE):
+    _NETRC_MACHINE = 'vtxtv'
+    _HOST = 'vtxtv.ch'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.vtxtv.ch/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class MyVisionTVIE(ZattooIE):
+    _NETRC_MACHINE = 'myvisiontv'
+    _HOST = 'myvisiontv.ch'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.myvisiontv.ch/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class GlattvisionTVIE(ZattooIE):
+    _NETRC_MACHINE = 'glattvisiontv'
+    _HOST = 'iptv.glattvision.ch'
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://iptv.glattvision.ch/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class SAKTVIE(ZattooIE):
+    _NETRC_MACHINE = 'saktv'
+    _HOST = 'saktv.ch'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.saktv.ch/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class EWETVIE(ZattooIE):
+    _NETRC_MACHINE = 'ewetv'
+    _HOST = 'tvonline.ewe.de'
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://tvonline.ewe.de/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class QuantumTVIE(ZattooIE):
+    _NETRC_MACHINE = 'quantumtv'
+    _HOST = 'quantum-tv.com'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.quantum-tv.com/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class OsnatelTVIE(ZattooIE):
+    _NETRC_MACHINE = 'osnateltv'
+    _HOST = 'tvonline.osnatel.de'
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://tvonline.osnatel.de/watch/abc/123-abc',
+        'only_matching': True,
+    }]
+
+
+class EinsUndEinsTVIE(ZattooIE):
+    _NETRC_MACHINE = '1und1tv'
+    _HOST = '1und1.tv'
+    _API_HOST = 'www.%s' % _HOST
+    _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
+
+    _TESTS = [{
+        'url': 'https://www.1und1.tv/watch/abc/123-abc',
+        'only_matching': True,
+    }]