release 2020.12.29

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.12.26
+ [debug] youtube-dl version 2020.12.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.29**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.12.26
+ [debug] youtube-dl version 2020.12.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.26**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.29**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,24 @@
+version 2020.12.29
+
+Extractors
+* [youtube] Improve yt initial data extraction (#27524)
+* [youtube:tab] Improve URL matching #27559)
+* [youtube:tab] Restore retry on browse requests (#27313, #27564)
+* [aparat] Fix extraction (#22285, #22611, #23348, #24354, #24591, #24904,
+  #25418, #26070, #26350, #26738, #27563)
+- [brightcove] Remove sonyliv specific code
+* [piksel] Improve format extraction
++ [zype] Add support for uplynk videos
++ [toggle] Add support for live.mewatch.sg (#27555)
++ [go] Add support for fxnow.fxnetworks.com (#13972, #22467, #23754, #26826)
+* [teachable] Improve embed detection (#26923)
+* [mitele] Fix free video extraction (#24624, #25827, #26757)
+* [telecinco] Fix extraction
+* [youtube] Update invidious.snopyta.org (#22667)
+* [amcnetworks] Improve auth only video detection (#27548)
++ [generic] Add support for VHX Embeds (#27546)
+
+
 version 2020.12.26
 
 Extractors

docs/supportedsites.md

@@ -317,7 +317,6 @@
  - **Funk**
  - **Fusion**
  - **Fux**
- - **FXNetworks**
  - **Gaia**
  - **GameInformer**
  - **GameSpot**

youtube_dl/extractor/aparat.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    get_element_by_id,
     int_or_none,
     merge_dicts,
     mimetype2ext,
@@ -39,23 +40,15 @@ class AparatIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id, fatal=False)
 
         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)
 
-        options = self._parse_json(
-            self._search_regex(
-                r'options\s*=\s*JSON\.parse\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1\s*\)',
-                webpage, 'options', group='value'),
-            video_id)
-
-        player = options['plugins']['sabaPlayerPlugin']
+        options = self._parse_json(self._search_regex(
+            r'options\s*=\s*({.+?})\s*;', webpage, 'options'), video_id)
 
         formats = []
-        for sources in player['multiSRC']:
+        for sources in (options.get('multiSRC') or []):
             for item in sources:
                 if not isinstance(item, dict):
                     continue
@@ -85,11 +78,12 @@ class AparatIE(InfoExtractor):
         info = self._search_json_ld(webpage, video_id, default={})
 
         if not info.get('title'):
-            info['title'] = player['title']
+            info['title'] = get_element_by_id('videoTitle', webpage) or \
+                self._html_search_meta(['og:title', 'twitter:title', 'DC.Title', 'title'], webpage, fatal=True)
 
         return merge_dicts(info, {
             'id': video_id,
             'thumbnail': url_or_none(options.get('poster')),
-            'duration': int_or_none(player.get('duration')),
+            'duration': int_or_none(options.get('duration')),
             'formats': formats,
         })

youtube_dl/extractor/brightcove.py

@@ -534,14 +534,6 @@ class BrightcoveNewIE(AdobePassIE):
                         'format_id': build_format_id('rtmp'),
                     })
                 formats.append(f)
-        if not formats:
-            # for sonyliv.com DRM protected videos
-            s3_source_url = json_data.get('custom_fields', {}).get('s3sourceurl')
-            if s3_source_url:
-                formats.append({
-                    'url': s3_source_url,
-                    'format_id': 'source',
-                })
 
         errors = json_data.get('errors')
         if not formats and errors:

youtube_dl/extractor/extractors.py

@@ -399,7 +399,6 @@ from .fujitv import FujiTVFODPlus7IE
 from .funimation import FunimationIE
 from .funk import FunkIE
 from .fusion import FusionIE
-from .fxnetworks import FXNetworksIE
 from .gaia import GaiaIE
 from .gameinformer import GameInformerIE
 from .gamespot import GameSpotIE

youtube_dl/extractor/fxnetworks.py

@@ -1,77 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .adobepass import AdobePassIE
-from ..utils import (
-    extract_attributes,
-    int_or_none,
-    parse_age_limit,
-    smuggle_url,
-    update_url_query,
-)
-
-
-class FXNetworksIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'http://www.fxnetworks.com/video/1032565827847',
-        'md5': '8d99b97b4aa7a202f55b6ed47ea7e703',
-        'info_dict': {
-            'id': 'dRzwHC_MMqIv',
-            'ext': 'mp4',
-            'title': 'First Look: Better Things - Season 2',
-            'description': 'Because real life is like a fart. Watch this FIRST LOOK to see what inspired the new season of Better Things.',
-            'age_limit': 14,
-            'uploader': 'NEWA-FNG-FX',
-            'upload_date': '20170825',
-            'timestamp': 1503686274,
-            'episode_number': 0,
-            'season_number': 2,
-            'series': 'Better Things',
-        },
-        'add_ie': ['ThePlatform'],
-    }, {
-        'url': 'http://www.simpsonsworld.com/video/716094019682',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        if 'The content you are trying to access is not available in your region.' in webpage:
-            self.raise_geo_restricted()
-        video_data = extract_attributes(self._search_regex(
-            r'(<a.+?rel="https?://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
-        player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
-        release_url = video_data['rel']
-        title = video_data['data-title']
-        rating = video_data.get('data-rating')
-        query = {
-            'mbr': 'true',
-        }
-        if player_type == 'movies':
-            query.update({
-                'manifest': 'm3u',
-            })
-        else:
-            query.update({
-                'switch': 'http',
-            })
-        if video_data.get('data-req-auth') == '1':
-            resource = self._get_mvpd_resource(
-                video_data['data-channel'], title,
-                video_data.get('data-guid'), rating)
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource)
-
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'title': title,
-            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
-            'series': video_data.get('data-show-title'),
-            'episode_number': int_or_none(video_data.get('data-episode')),
-            'season_number': int_or_none(video_data.get('data-season')),
-            'thumbnail': video_data.get('data-large-thumb'),
-            'age_limit': parse_age_limit(rating),
-            'ie_key': 'ThePlatform',
-        }

youtube_dl/extractor/go.py

@@ -38,13 +38,17 @@ class GoIE(AdobePassIE):
         'disneynow': {
             'brand': '011',
             'resource_id': 'Disney',
-        }
+        },
+        'fxnow.fxnetworks': {
+            'brand': '025',
+            'requestor_id': 'dtci',
+        },
     }
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
                             (?:(?P<sub_domain>%s)\.)?go|
-                            (?P<sub_domain_2>abc|freeform|disneynow)
+                            (?P<sub_domain_2>abc|freeform|disneynow|fxnow\.fxnetworks)
                         )\.com/
                         (?:
                             (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
@@ -99,6 +103,19 @@ class GoIE(AdobePassIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
+        'info_dict': {
+            'id': 'VDKA12782841',
+            'ext': 'mp4',
+            'title': 'First Look: Better Things - Season 2',
+            'description': 'md5:fa73584a95761c605d9d54904e35b407',
+        },
+        'params': {
+            'geo_bypass_ip_block': '3.244.239.0/24',
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
         'only_matching': True,

youtube_dl/extractor/mitele.py

@@ -1,15 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .telecinco import TelecincoIE
 from ..utils import (
     int_or_none,
     parse_iso8601,
-    smuggle_url,
 )
 
 
-class MiTeleIE(InfoExtractor):
+class MiTeleIE(TelecincoIE):
     IE_DESC = 'mitele.es'
     _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
 
@@ -31,7 +30,6 @@ class MiTeleIE(InfoExtractor):
             'timestamp': 1471209401,
             'upload_date': '20160814',
         },
-        'add_ie': ['Ooyala'],
     }, {
         # no explicit title
         'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
@@ -54,7 +52,6 @@ class MiTeleIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['Ooyala'],
     }, {
         'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
         'only_matching': True,
@@ -70,16 +67,11 @@ class MiTeleIE(InfoExtractor):
             r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})',
             webpage, 'Pre Player'), display_id)['prePlayer']
         title = pre_player['title']
-        video = pre_player['video']
-        video_id = video['dataMediaId']
+        video_info = self._parse_content(pre_player['video'], url)
         content = pre_player.get('content') or {}
         info = content.get('info') or {}
 
-        return {
-            '_type': 'url_transparent',
-            # for some reason only HLS is supported
-            'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
-            'id': video_id,
+        video_info.update({
             'title': title,
             'description': info.get('synopsis'),
             'series': content.get('title'),
@@ -87,7 +79,7 @@ class MiTeleIE(InfoExtractor):
             'episode': content.get('subtitle'),
             'episode_number': int_or_none(info.get('episode_number')),
             'duration': int_or_none(info.get('duration')),
-            'thumbnail': video.get('dataPoster'),
             'age_limit': int_or_none(info.get('rating')),
             'timestamp': parse_iso8601(pre_player.get('publishedTime')),
-        }
+        })
+        return video_info

youtube_dl/extractor/nhk.py

@@ -90,7 +90,7 @@ class NhkVodIE(NhkBaseIE):
     _TESTS = [{
         # video clip
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
-        'md5': '256a1be14f48d960a7e61e2532d95ec3',
+        'md5': '7a90abcfe610ec22a6bfe15bd46b30ca',
         'info_dict': {
             'id': 'a95j5iza',
             'ext': 'mp4',

youtube_dl/extractor/piksel.py

@@ -6,16 +6,33 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
     dict_get,
+    ExtractorError,
     int_or_none,
-    unescapeHTML,
     parse_iso8601,
+    try_get,
+    unescapeHTML,
 )
 
 
 class PikselIE(InfoExtractor):
-    _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P<id>[a-z0-9_]+)'
+    _VALID_URL = r'''(?x)https?://
+        (?:
+            (?:
+                player\.
+                    (?:
+                        olympusattelecom|
+                        vibebyvista
+                    )|
+                (?:api|player)\.multicastmedia|
+                (?:api-ovp|player)\.piksel
+            )\.com|
+            (?:
+                mz-edge\.stream\.co|
+                movie-s\.nhk\.or
+            )\.jp|
+            vidego\.baltimorecity\.gov
+        )/v/(?:refid/(?P<refid>[^/]+)/prefid/)?(?P<id>[\w-]+)'''
     _TESTS = [
         {
             'url': 'http://player.piksel.com/v/ums2867l',
@@ -56,46 +73,41 @@ class PikselIE(InfoExtractor):
         if mobj:
             return mobj.group('url')
 
+    def _call_api(self, app_token, resource, display_id, query, fatal=True):
+        response = (self._download_json(
+            'http://player.piksel.com/ws/ws_%s/api/%s/mode/json/apiv/5' % (resource, app_token),
+            display_id, query=query, fatal=fatal) or {}).get('response')
+        failure = try_get(response, lambda x: x['failure']['reason'])
+        if failure:
+            if fatal:
+                raise ExtractorError(failure, expected=True)
+            self.report_warning(failure)
+        return response
+
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        ref_id, display_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(
-            r'data-de-program-uuid=[\'"]([a-z0-9]+)',
-            webpage, 'program uuid', default=display_id)
         app_token = self._search_regex([
             r'clientAPI\s*:\s*"([^"]+)"',
             r'data-de-api-key\s*=\s*"([^"]+)"'
         ], webpage, 'app token')
-        response = self._download_json(
-            'http://player.piksel.com/ws/ws_program/api/%s/mode/json/apiv/5' % app_token,
-            video_id, query={
-                'v': video_id
-            })['response']
-        failure = response.get('failure')
-        if failure:
-            raise ExtractorError(response['failure']['reason'], expected=True)
-        video_data = response['WsProgramResponse']['program']['asset']
+        query = {'refid': ref_id, 'prefid': display_id} if ref_id else {'v': display_id}
+        program = self._call_api(
+            app_token, 'program', display_id, query)['WsProgramResponse']['program']
+        video_id = program['uuid']
+        video_data = program['asset']
         title = video_data['title']
+        asset_type = dict_get(video_data, ['assetType', 'asset_type'])
 
         formats = []
 
-        m3u8_url = dict_get(video_data, [
-            'm3u8iPadURL',
-            'ipadM3u8Url',
-            'm3u8AndroidURL',
-            'm3u8iPhoneURL',
-            'iphoneM3u8Url'])
-        if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', 'm3u8_native',
-                m3u8_id='hls', fatal=False))
-
-        asset_type = dict_get(video_data, ['assetType', 'asset_type'])
-        for asset_file in video_data.get('assetFiles', []):
+        def process_asset_file(asset_file):
+            if not asset_file:
+                return
             # TODO: extract rtmp formats
             http_url = asset_file.get('http_url')
             if not http_url:
-                continue
+                return
             tbr = None
             vbr = int_or_none(asset_file.get('videoBitrate'), 1024)
             abr = int_or_none(asset_file.get('audioBitrate'), 1024)
@@ -118,6 +130,43 @@ class PikselIE(InfoExtractor):
                 'filesize': int_or_none(asset_file.get('filesize')),
                 'tbr': tbr,
             })
+
+        def process_asset_files(asset_files):
+            for asset_file in (asset_files or []):
+                process_asset_file(asset_file)
+
+        process_asset_files(video_data.get('assetFiles'))
+        process_asset_file(video_data.get('referenceFile'))
+        if not formats:
+            asset_id = video_data.get('assetid') or program.get('assetid')
+            if asset_id:
+                process_asset_files(try_get(self._call_api(
+                    app_token, 'asset_file', display_id, {
+                        'assetid': asset_id,
+                    }, False), lambda x: x['WsAssetFileResponse']['AssetFiles']))
+
+        m3u8_url = dict_get(video_data, [
+            'm3u8iPadURL',
+            'ipadM3u8Url',
+            'm3u8AndroidURL',
+            'm3u8iPhoneURL',
+            'iphoneM3u8Url'])
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        smil_url = dict_get(video_data, ['httpSmil', 'hdSmil', 'rtmpSmil'])
+        if smil_url:
+            transform_source = None
+            if ref_id == 'nhkworld':
+                # TODO: figure out if this is something to be fixed in urljoin,
+                # _parse_smil_formats or keep it here
+                transform_source = lambda x: x.replace('src="/', 'src="').replace('/media"', '/media/"')
+            formats.extend(self._extract_smil_formats(
+                re.sub(r'/od/[^/]+/', '/od/http/', smil_url), video_id,
+                transform_source=transform_source, fatal=False))
+
         self._sort_formats(formats)
 
         subtitles = {}

youtube_dl/extractor/teachable.py

@@ -140,7 +140,7 @@ class TeachableIE(TeachableBaseIE):
     @staticmethod
     def _is_teachable(webpage):
         return 'teachableTracker.linker:autoLink' in webpage and re.search(
-            r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
+            r'<link[^>]+href=["\']https?://(?:process\.fs|assets)\.teachablecdn\.com',
             webpage)
 
     @staticmethod

youtube_dl/extractor/telecinco.py

@@ -5,14 +5,11 @@ import json
 import re
 
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
 from ..utils import (
     clean_html,
-    determine_ext,
     int_or_none,
     str_or_none,
     try_get,
-    urljoin,
 )
 
 
@@ -28,7 +25,7 @@ class TelecincoIE(InfoExtractor):
             'description': 'md5:716caf5601e25c3c5ab6605b1ae71529',
         },
         'playlist': [{
-            'md5': 'adb28c37238b675dad0f042292f209a7',
+            'md5': '7ee56d665cfd241c0e6d80fd175068b0',
             'info_dict': {
                 'id': 'JEA5ijCnF6p5W08A1rNKn7',
                 'ext': 'mp4',
@@ -38,7 +35,7 @@ class TelecincoIE(InfoExtractor):
         }]
     }, {
         'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
-        'md5': '9468140ebc300fbb8b9d65dc6e5c4b43',
+        'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
         'info_dict': {
             'id': 'jn24Od1zGLG4XUZcnUnZB6',
             'ext': 'mp4',
@@ -48,7 +45,7 @@ class TelecincoIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
-        'md5': 'ae2dc6b7b50b2392076a51c0f70e01f6',
+        'md5': 'eddb50291df704ce23c74821b995bcac',
         'info_dict': {
             'id': 'aywerkD2Sv1vGNqq9b85Q2',
             'ext': 'mp4',
@@ -90,58 +87,24 @@ class TelecincoIE(InfoExtractor):
 
     def _parse_content(self, content, url):
         video_id = content['dataMediaId']
-        if content.get('dataCmsId') == 'ooyala':
-            return self.url_result(
-                'ooyala:%s' % video_id, OoyalaIE.ie_key(), video_id)
-        config_url = urljoin(url, content['dataConfig'])
         config = self._download_json(
-            config_url, video_id, 'Downloading config JSON')
+            content['dataConfig'], video_id, 'Downloading config JSON')
         title = config['info']['title']
-
-        def mmc_url(mmc_type):
-            return re.sub(
-                r'/(?:flash|html5)\.json', '/%s.json' % mmc_type,
-                config['services']['mmc'])
-
-        duration = None
-        formats = []
-        for mmc_type in ('flash', 'html5'):
-            mmc = self._download_json(
-                mmc_url(mmc_type), video_id,
-                'Downloading %s mmc JSON' % mmc_type, fatal=False)
-            if not mmc:
-                continue
-            if not duration:
-                duration = int_or_none(mmc.get('duration'))
-            for location in mmc['locations']:
-                gat = self._proto_relative_url(location.get('gat'), 'http:')
-                gcp = location.get('gcp')
-                ogn = location.get('ogn')
-                if None in (gat, gcp, ogn):
-                    continue
-                token_data = {
-                    'gcp': gcp,
-                    'ogn': ogn,
-                    'sta': 0,
-                }
-                media = self._download_json(
-                    gat, video_id, data=json.dumps(token_data).encode('utf-8'),
-                    headers={
-                        'Content-Type': 'application/json;charset=utf-8',
-                        'Referer': url,
-                    }, fatal=False) or {}
-                stream = media.get('stream') or media.get('file')
-                if not stream:
-                    continue
-                ext = determine_ext(stream)
-                if ext == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
-                        video_id, f4m_id='hds', fatal=False))
-                elif ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        stream, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
+        services = config['services']
+        caronte = self._download_json(services['caronte'], video_id)
+        stream = caronte['dls'][0]['stream']
+        headers = self.geo_verification_headers()
+        headers.update({
+            'Content-Type': 'application/json;charset=UTF-8',
+            'Origin': re.match(r'https?://[^/]+', url).group(0),
+        })
+        cdn = self._download_json(
+            caronte['cerbero'], video_id, data=json.dumps({
+                'bbx': caronte['bbx'],
+                'gbx': self._download_json(services['gbx'], video_id)['gbx'],
+            }).encode(), headers=headers)['tokens']['1']['cdn']
+        formats = self._extract_m3u8_formats(
+            stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
         self._sort_formats(formats)
 
         return {
@@ -149,7 +112,7 @@ class TelecincoIE(InfoExtractor):
             'title': title,
             'formats': formats,
             'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
-            'duration': duration,
+            'duration': int_or_none(content.get('dataDuration')),
         }
 
     def _real_extract(self, url):

youtube_dl/extractor/toggle.py

@@ -200,7 +200,7 @@ class ToggleIE(InfoExtractor):
 
 class MeWatchIE(InfoExtractor):
     IE_NAME = 'mewatch'
-    _VALID_URL = r'https?://(?:www\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
         'info_dict': {
@@ -220,6 +220,9 @@ class MeWatchIE(InfoExtractor):
     }, {
         'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
         'only_matching': True,
+    }, {
+        'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/youtube.py

@@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
 from ..swfinterp import SWFInterpreter
 from ..compat import (
     compat_chr,
+    compat_HTTPError,
     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
@@ -279,6 +280,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
     _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
+    _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
 
     def _call_api(self, ep, query, video_id):
         data = self._DEFAULT_API_DATA.copy()
@@ -296,7 +298,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     def _extract_yt_initial_data(self, video_id, webpage):
         return self._parse_json(
             self._search_regex(
-                (r'%s\s*\n' % self._YT_INITIAL_DATA_RE,
+                (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
                  self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
             video_id)
 
@@ -321,7 +323,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
                             (?:(?:www|dev)\.)?invidio\.us/|
                             (?:(?:www|no)\.)?invidiou\.sh/|
-                            (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
+                            (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
                             (?:www\.)?invidious\.kabi\.tk/|
                             (?:www\.)?invidious\.13ad\.de/|
                             (?:www\.)?invidious\.mastodon\.host/|
@@ -1102,6 +1104,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # another example of '};' in ytInitialData
+            'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
+            'only_matching': True,
+        },
     ]
 
     def __init__(self, *args, **kwargs):
@@ -1701,7 +1712,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not video_info and not player_response:
             player_response = extract_player_response(
                 self._search_regex(
-                    (r'%s\s*(?:var\s+meta|</script|\n)' % self._YT_INITIAL_PLAYER_RESPONSE_RE,
+                    (r'%s\s*%s' % (self._YT_INITIAL_PLAYER_RESPONSE_RE, self._YT_INITIAL_BOUNDARY_RE),
                      self._YT_INITIAL_PLAYER_RESPONSE_RE), video_webpage,
                     'initial player response', default='{}'),
                 video_id)
@@ -2729,6 +2740,11 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if YoutubeIE.suitable(url) else super(
+            YoutubeTabIE, cls).suitable(url)
+
     def _extract_channel_id(self, webpage):
         channel_id = self._html_search_meta(
             'channelId', webpage, 'channel id', default=None)
@@ -3009,10 +3025,24 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         for page_num in itertools.count(1):
             if not continuation:
                 break
-            browse = self._download_json(
-                'https://www.youtube.com/browse_ajax', None,
-                'Downloading page %d' % page_num,
-                headers=headers, query=continuation, fatal=False)
+            count = 0
+            retries = 3
+            while count <= retries:
+                try:
+                    # Downloading page may result in intermittent 5xx HTTP error
+                    # that is usually worked around with a retry
+                    browse = self._download_json(
+                        'https://www.youtube.com/browse_ajax', None,
+                        'Downloading page %d%s'
+                        % (page_num, ' (retry #%d)' % count if count else ''),
+                        headers=headers, query=continuation)
+                    break
+                except ExtractorError as e:
+                    if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
+                        count += 1
+                        if count <= retries:
+                            continue
+                    raise
             if not browse:
                 break
             response = try_get(browse, lambda x: x[1]['response'], dict)

youtube_dl/extractor/zype.py

@@ -85,7 +85,13 @@ class ZypeIE(InfoExtractor):
         else:
             m3u8_url = self._search_regex(
                 r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
-                body, 'm3u8 url', group='url')
+                body, 'm3u8 url', group='url', default=None)
+            if not m3u8_url:
+                source = self._parse_json(self._search_regex(
+                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body,
+                    'source'), video_id, js_to_json)
+                if source.get('integration') == 'verizon-media':
+                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % source['id']
             formats = self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
             text_tracks = self._search_regex(

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.12.26'
+__version__ = '2020.12.29'