release 2020.01.01

Basic authentication will be deprecated soon

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.12.25. 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 Issues with outdated version will be REJECTED.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 2020.01.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
+- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2019.12.25
+ [debug] youtube-dl version 2020.01.01
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.12.25. 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 2020.01.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
+- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.12.25. 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 2020.01.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
+- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.12.25. 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 2020.01.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
+- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2019.12.25
+ [debug] youtube-dl version 2020.01.01
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.12.25. 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 2020.01.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
+- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,24 @@
+version 2020.01.01
+
+Extractors
+* [brightcove] Invalidate policy key cache on failing requests
+* [pornhub] Improve locked videos detection (#22449, #22780)
++ [pornhub] Add support for m3u8 formats
+* [pornhub] Fix extraction (#22749, #23082)
+* [brightcove] Update policy key on failing requests
+* [spankbang] Improve removed video detection (#23423)
+* [spankbang] Fix extraction (#23307, #23423, #23444)
+* [soundcloud] Automatically update client id on failing requests
+* [prosiebensat1] Improve geo restriction handling (#23571)
+* [brightcove] Cache brightcove player policy keys
+* [teachable] Fail with error message if no video URL found
+* [teachable] Improve locked lessons detection (#23528)
++ [scrippsnetworks] Add support for Scripps Networks sites (#19857, #22981)
+* [mitele] Fix extraction (#21354, #23456)
+* [soundcloud] Update client id (#23516)
+* [mailru] Relax URL regular expressions (#23509)
+
+
 version 2019.12.25
 
 Core

devscripts/create-github-release.py

@@ -15,7 +15,6 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from youtube_dl.compat import (
     compat_basestring,
-    compat_input,
     compat_getpass,
     compat_print,
     compat_urllib_request,
@@ -40,28 +39,20 @@ class GitHubReleaser(object):
         try:
             info = netrc.netrc().authenticators(self._NETRC_MACHINE)
             if info is not None:
-                self._username = info[0]
-                self._password = info[2]
+                self._token = info[2]
                 compat_print('Using GitHub credentials found in .netrc...')
                 return
             else:
                 compat_print('No GitHub credentials found in .netrc')
         except (IOError, netrc.NetrcParseError):
             compat_print('Unable to parse .netrc')
-        self._username = compat_input(
-            'Type your GitHub username or email address and press [Return]: ')
-        self._password = compat_getpass(
-            'Type your GitHub password and press [Return]: ')
+        self._token = compat_getpass(
+            'Type your GitHub PAT (personal access token) and press [Return]: ')
 
     def _call(self, req):
         if isinstance(req, compat_basestring):
             req = sanitized_Request(req)
-        # Authorizing manually since GitHub does not response with 401 with
-        # WWW-Authenticate header set (see
-        # https://developer.github.com/v3/#basic-authentication)
-        b64 = base64.b64encode(
-            ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii')
-        req.add_header('Authorization', 'Basic %s' % b64)
+        req.add_header('Authorization', 'token %s' % self._token)
         response = self._opener.open(req).read().decode('utf-8')
         return json.loads(response)
 

docs/supportedsites.md

@@ -761,6 +761,7 @@
  - **screen.yahoo:search**: Yahoo screen search
  - **Screencast**
  - **ScreencastOMatic**
+ - **ScrippsNetworks**
  - **scrippsnetworks:watch**
  - **SCTE**
  - **SCTECourse**

youtube_dl/extractor/brightcove.py

@@ -586,45 +586,63 @@ class BrightcoveNewIE(AdobePassIE):
 
         account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups()
 
-        webpage = self._download_webpage(
-            'http://players.brightcove.net/%s/%s_%s/index.min.js'
-            % (account_id, player_id, embed), video_id)
+        policy_key_id = '%s_%s' % (account_id, player_id)
+        policy_key = self._downloader.cache.load('brightcove', policy_key_id)
+        policy_key_extracted = False
+        store_pk = lambda x: self._downloader.cache.store('brightcove', policy_key_id, x)
 
-        policy_key = None
+        def extract_policy_key():
+            webpage = self._download_webpage(
+                'http://players.brightcove.net/%s/%s_%s/index.min.js'
+                % (account_id, player_id, embed), video_id)
 
-        catalog = self._search_regex(
-            r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
-        if catalog:
-            catalog = self._parse_json(
-                js_to_json(catalog), video_id, fatal=False)
+            policy_key = None
+
+            catalog = self._search_regex(
+                r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
             if catalog:
-                policy_key = catalog.get('policyKey')
+                catalog = self._parse_json(
+                    js_to_json(catalog), video_id, fatal=False)
+                if catalog:
+                    policy_key = catalog.get('policyKey')
 
-        if not policy_key:
-            policy_key = self._search_regex(
-                r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
-                webpage, 'policy key', group='pk')
+            if not policy_key:
+                policy_key = self._search_regex(
+                    r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
+                    webpage, 'policy key', group='pk')
+
+            store_pk(policy_key)
+            return policy_key
 
         api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id)
-        headers = {
-            'Accept': 'application/json;pk=%s' % policy_key,
-        }
+        headers = {}
         referrer = smuggled_data.get('referrer')
         if referrer:
             headers.update({
                 'Referer': referrer,
                 'Origin': re.search(r'https?://[^/]+', referrer).group(0),
             })
-        try:
-            json_data = self._download_json(api_url, video_id, headers=headers)
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
-                message = json_data.get('message') or json_data['error_code']
-                if json_data.get('error_subcode') == 'CLIENT_GEO':
-                    self.raise_geo_restricted(msg=message)
-                raise ExtractorError(message, expected=True)
-            raise
+
+        for _ in range(2):
+            if not policy_key:
+                policy_key = extract_policy_key()
+                policy_key_extracted = True
+            headers['Accept'] = 'application/json;pk=%s' % policy_key
+            try:
+                json_data = self._download_json(api_url, video_id, headers=headers)
+                break
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
+                    json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
+                    message = json_data.get('message') or json_data['error_code']
+                    if json_data.get('error_subcode') == 'CLIENT_GEO':
+                        self.raise_geo_restricted(msg=message)
+                    elif json_data.get('error_code') == 'INVALID_POLICY_KEY' and not policy_key_extracted:
+                        policy_key = None
+                        store_pk(None)
+                        continue
+                    raise ExtractorError(message, expected=True)
+                raise
 
         errors = json_data.get('errors')
         if errors and errors[0].get('error_subcode') == 'TVE_AUTH':

youtube_dl/extractor/extractors.py

@@ -963,7 +963,10 @@ from .savefrom import SaveFromIE
 from .sbs import SBSIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
-from .scrippsnetworks import ScrippsNetworksWatchIE
+from .scrippsnetworks import (
+    ScrippsNetworksWatchIE,
+    ScrippsNetworksIE,
+)
 from .scte import (
     SCTEIE,
     SCTECourseIE,

youtube_dl/extractor/mailru.py

@@ -20,10 +20,10 @@ class MailRuIE(InfoExtractor):
     IE_DESC = 'Видео@Mail.Ru'
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:(?:www|m)\.)?my\.mail\.ru/
+                        (?:(?:www|m)\.)?my\.mail\.ru/+
                         (?:
                             video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
-                            (?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
+                            (?:(?P<idv2prefix>(?:[^/]+/+){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
                             (?:video/embed|\+/video/meta)/(?P<metaid>\d+)
                         )
                     '''
@@ -85,6 +85,14 @@ class MailRuIE(InfoExtractor):
         {
             'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
             'only_matching': True,
+        },
+        {
+            'url': 'https://my.mail.ru//list/sinyutin10/video/_myvideo/4.html',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html',
+            'only_matching': True,
         }
     ]
 
@@ -237,7 +245,7 @@ class MailRuMusicSearchBaseIE(InfoExtractor):
 class MailRuMusicIE(MailRuMusicSearchBaseIE):
     IE_NAME = 'mailru:music'
     IE_DESC = 'Музыка@Mail.Ru'
-    _VALID_URL = r'https?://my\.mail\.ru/music/songs/[^/?#&]+-(?P<id>[\da-f]+)'
+    _VALID_URL = r'https?://my\.mail\.ru/+music/+songs/+[^/?#&]+-(?P<id>[\da-f]+)'
     _TESTS = [{
         'url': 'https://my.mail.ru/music/songs/%D0%BC8%D0%BB8%D1%82%D1%85-l-a-h-luciferian-aesthetics-of-herrschaft-single-2017-4e31f7125d0dfaef505d947642366893',
         'md5': '0f8c22ef8c5d665b13ac709e63025610',
@@ -273,7 +281,7 @@ class MailRuMusicIE(MailRuMusicSearchBaseIE):
 class MailRuMusicSearchIE(MailRuMusicSearchBaseIE):
     IE_NAME = 'mailru:music:search'
     IE_DESC = 'Музыка@Mail.Ru'
-    _VALID_URL = r'https?://my\.mail\.ru/music/search/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://my\.mail\.ru/+music/+search/+(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://my.mail.ru/music/search/black%20shadow',
         'info_dict': {

youtube_dl/extractor/mitele.py

@@ -4,8 +4,8 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    parse_iso8601,
     smuggle_url,
-    parse_duration,
 )
 
 
@@ -18,16 +18,18 @@ class MiTeleIE(InfoExtractor):
         'info_dict': {
             'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
             'ext': 'mp4',
-            'title': 'Tor, la web invisible',
-            'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+            'title': 'Diario de La redacción Programa 144',
+            'description': 'md5:07c35a7b11abb05876a6a79185b58d27',
             'series': 'Diario de',
-            'season': 'La redacción',
+            'season': 'Season 14',
             'season_number': 14,
-            'season_id': 'diario_de_t14_11981',
-            'episode': 'Programa 144',
+            'episode': 'Tor, la web invisible',
             'episode_number': 3,
             'thumbnail': r're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
+            'age_limit': 16,
+            'timestamp': 1471209401,
+            'upload_date': '20160814',
         },
         'add_ie': ['Ooyala'],
     }, {
@@ -39,13 +41,15 @@ class MiTeleIE(InfoExtractor):
             'title': 'Cuarto Milenio Temporada 6 Programa 226',
             'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
             'series': 'Cuarto Milenio',
-            'season': 'Temporada 6',
+            'season': 'Season 6',
             'season_number': 6,
-            'season_id': 'cuarto_milenio_t06_12715',
-            'episode': 'Programa 226',
+            'episode': 'Episode 24',
             'episode_number': 24,
             'thumbnail': r're:(?i)^https?://.*\.jpg$',
             'duration': 7313,
+            'age_limit': 12,
+            'timestamp': 1471209021,
+            'upload_date': '20160814',
         },
         'params': {
             'skip_download': True,
@@ -54,67 +58,36 @@ class MiTeleIE(InfoExtractor):
     }, {
         'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
         'only_matching': True,
+    }, {
+        'url': 'https://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144-40_1006364575251/player/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        paths = self._download_json(
-            'https://www.mitele.es/amd/agp/web/metadata/general_configuration',
-            video_id, 'Downloading paths JSON')
-
-        ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
-        base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com')
-        full_path = ooyala_s.get('full_path', '/search/v1/full/providers/')
-        source = self._download_json(
-            '%s://%s%s%s/docs/%s' % (
-                ooyala_s.get('protocol', 'https'), base_url, full_path,
-                ooyala_s.get('provider_id', '104951'), video_id),
-            video_id, 'Downloading data JSON', query={
-                'include_titles': 'Series,Season',
-                'product_name': ooyala_s.get('product_name', 'test'),
-                'format': 'full',
-            })['hits']['hits'][0]['_source']
-
-        embedCode = source['offers'][0]['embed_codes'][0]
-        titles = source['localizable_titles'][0]
-
-        title = titles.get('title_medium') or titles['title_long']
-
-        description = titles.get('summary_long') or titles.get('summary_medium')
-
-        def get(key1, key2):
-            value1 = source.get(key1)
-            if not value1 or not isinstance(value1, list):
-                return
-            if not isinstance(value1[0], dict):
-                return
-            return value1[0].get(key2)
-
-        series = get('localizable_titles_series', 'title_medium')
-
-        season = get('localizable_titles_season', 'title_medium')
-        season_number = int_or_none(source.get('season_number'))
-        season_id = source.get('season_id')
-
-        episode = titles.get('title_sort_name')
-        episode_number = int_or_none(source.get('episode_number'))
-
-        duration = parse_duration(get('videos', 'duration'))
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        pre_player = self._parse_json(self._search_regex(
+            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']
+        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:' + embedCode, {'supportedformats': 'm3u8,dash'}),
+            'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
             'id': video_id,
             'title': title,
-            'description': description,
-            'series': series,
-            'season': season,
-            'season_number': season_number,
-            'season_id': season_id,
-            'episode': episode,
-            'episode_number': episode_number,
-            'duration': duration,
-            'thumbnail': get('images', 'url'),
+            'description': info.get('synopsis'),
+            'series': content.get('title'),
+            'season_number': int_or_none(info.get('season_number')),
+            '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')),
         }

youtube_dl/extractor/pornhub.py

@@ -17,6 +17,7 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
+    NO_DEFAULT,
     orderedSet,
     remove_quotes,
     str_to_int,
@@ -227,12 +228,13 @@ class PornHubIE(PornHubBaseIE):
         else:
             thumbnail, duration = [None] * 2
 
-        if not video_urls:
-            tv_webpage = dl_webpage('tv')
-
+        def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
             assignments = self._search_regex(
-                r'(var.+?mediastring.+?)</script>', tv_webpage,
-                'encoded url').split(';')
+                pattern, webpage, 'encoded url', default=default)
+            if not assignments:
+                return {}
+
+            assignments = assignments.split(';')
 
             js_vars = {}
 
@@ -254,11 +256,35 @@ class PornHubIE(PornHubBaseIE):
                 assn = re.sub(r'var\s+', '', assn)
                 vname, value = assn.split('=', 1)
                 js_vars[vname] = parse_js_value(value)
+            return js_vars
 
-            video_url = js_vars['mediastring']
-            if video_url not in video_urls_set:
-                video_urls.append((video_url, None))
-                video_urls_set.add(video_url)
+        def add_video_url(video_url):
+            v_url = url_or_none(video_url)
+            if not v_url:
+                return
+            if v_url in video_urls_set:
+                return
+            video_urls.append((v_url, None))
+            video_urls_set.add(v_url)
+
+        if not video_urls:
+            FORMAT_PREFIXES = ('media', 'quality')
+            js_vars = extract_js_vars(
+                webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
+                default=None)
+            if js_vars:
+                for key, format_url in js_vars.items():
+                    if any(key.startswith(p) for p in FORMAT_PREFIXES):
+                        add_video_url(format_url)
+            if not video_urls and re.search(
+                    r'<[^>]+\bid=["\']lockedPlayer', webpage):
+                raise ExtractorError(
+                    'Video %s is locked' % video_id, expected=True)
+
+        if not video_urls:
+            js_vars = extract_js_vars(
+                dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
+            add_video_url(js_vars['mediastring'])
 
         for mobj in re.finditer(
                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
@@ -276,10 +302,16 @@ class PornHubIE(PornHubBaseIE):
                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                 if upload_date:
                     upload_date = upload_date.replace('/', '')
-            if determine_ext(video_url) == 'mpd':
+            ext = determine_ext(video_url)
+            if ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
                     video_url, video_id, mpd_id='dash', fatal=False))
                 continue
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:

youtube_dl/extractor/prosiebensat1.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class ProSiebenSat1BaseIE(InfoExtractor):
-    _GEO_COUNTRIES = ['DE']
+    _GEO_BYPASS = False
     _ACCESS_ID = None
     _SUPPORTED_PROTOCOLS = 'dash:clear,hls:clear,progressive:clear'
     _V4_BASE_URL = 'https://vas-v4.p7s1video.net/4.0/get'
@@ -39,14 +39,18 @@ class ProSiebenSat1BaseIE(InfoExtractor):
         formats = []
         if self._ACCESS_ID:
             raw_ct = self._ENCRYPTION_KEY + clip_id + self._IV + self._ACCESS_ID
-            server_token = (self._download_json(
+            protocols = self._download_json(
                 self._V4_BASE_URL + 'protocols', clip_id,
                 'Downloading protocols JSON',
                 headers=self.geo_verification_headers(), query={
                     'access_id': self._ACCESS_ID,
                     'client_token': sha1((raw_ct).encode()).hexdigest(),
                     'video_id': clip_id,
-                }, fatal=False) or {}).get('server_token')
+                }, fatal=False, expected_status=(403,)) or {}
+            error = protocols.get('error') or {}
+            if error.get('title') == 'Geo check failed':
+                self.raise_geo_restricted(countries=['AT', 'CH', 'DE'])
+            server_token = protocols.get('server_token')
             if server_token:
                 urls = (self._download_json(
                     self._V4_BASE_URL + 'urls', clip_id, 'Downloading urls JSON', query={

youtube_dl/extractor/scrippsnetworks.py

@@ -7,6 +7,7 @@ import re
 
 from .aws import AWSIE
 from .anvato import AnvatoIE
+from .common import InfoExtractor
 from ..utils import (
     smuggle_url,
     urlencode_postdata,
@@ -102,3 +103,46 @@ class ScrippsNetworksWatchIE(AWSIE):
                 'anvato:anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a:%s' % mcp_id,
                 {'geo_countries': ['US']}),
             AnvatoIE.ie_key(), video_id=mcp_id)
+
+
+class ScrippsNetworksIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>cookingchanneltv|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.cookingchanneltv.com/videos/the-best-of-the-best-0260338',
+        'info_dict': {
+            'id': '0260338',
+            'ext': 'mp4',
+            'title': 'The Best of the Best',
+            'description': 'Catch a new episode of MasterChef Canada Tuedsay at 9/8c.',
+            'timestamp': 1475678834,
+            'upload_date': '20161005',
+            'uploader': 'SCNI-SCND',
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'https://www.diynetwork.com/videos/diy-barnwood-tablet-stand-0265790',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.foodnetwork.com/videos/chocolate-strawberry-cake-roll-7524591',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.hgtv.com/videos/cookie-decorating-101-0301929',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.travelchannel.com/videos/two-climates-one-bag-5302184',
+        'only_matching': True,
+    }]
+    _ACCOUNT_MAP = {
+        'cookingchanneltv': 2433005105,
+        'diynetwork': 2433004575,
+        'foodnetwork': 2433005105,
+        'hgtv': 2433004575,
+        'travelchannel': 2433005739,
+    }
+    _TP_TEMPL = 'https://link.theplatform.com/s/ip77QC/media/guid/%d/%s?mbr=true'
+
+    def _real_extract(self, url):
+        site, guid = re.match(self._VALID_URL, url).groups()
+        return self.url_result(smuggle_url(
+            self._TP_TEMPL % (self._ACCOUNT_MAP[site], guid),
+            {'force_smil_url': True}), 'ThePlatform', guid)

youtube_dl/extractor/soundcloud.py

@@ -9,10 +9,13 @@ from .common import (
     SearchInfoExtractor
 )
 from ..compat import (
+    compat_HTTPError,
+    compat_kwargs,
     compat_str,
     compat_urlparse,
 )
 from ..utils import (
+    error_to_compat_str,
     ExtractorError,
     float_or_none,
     HEADRequest,
@@ -255,7 +258,6 @@ class SoundcloudIE(InfoExtractor):
     _API_BASE = 'https://api.soundcloud.com/'
     _API_V2_BASE = 'https://api-v2.soundcloud.com/'
     _BASE_URL = 'https://soundcloud.com/'
-    _CLIENT_ID = 'UW9ajvMgVdMMW3cdeBi8lPfN6dvOVGji'
     _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
 
     _ARTWORK_MAP = {
@@ -271,9 +273,49 @@ class SoundcloudIE(InfoExtractor):
         'original': 0,
     }
 
+    def _store_client_id(self, client_id):
+        self._downloader.cache.store('soundcloud', 'client_id', client_id)
+
+    def _update_client_id(self):
+        webpage = self._download_webpage('https://soundcloud.com/', None)
+        for src in reversed(re.findall(r'<script[^>]+src="([^"]+)"', webpage)):
+            script = self._download_webpage(src, None, fatal=False)
+            if script:
+                client_id = self._search_regex(
+                    r'client_id\s*:\s*"([0-9a-zA-Z]{32})"',
+                    script, 'client id', default=None)
+                if client_id:
+                    self._CLIENT_ID = client_id
+                    self._store_client_id(client_id)
+                    return
+        raise ExtractorError('Unable to extract client id')
+
+    def _download_json(self, *args, **kwargs):
+        non_fatal = kwargs.get('fatal') is False
+        if non_fatal:
+            del kwargs['fatal']
+        query = kwargs.get('query', {}).copy()
+        for _ in range(2):
+            query['client_id'] = self._CLIENT_ID
+            kwargs['query'] = query
+            try:
+                return super(SoundcloudIE, self)._download_json(*args, **compat_kwargs(kwargs))
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                    self._store_client_id(None)
+                    self._update_client_id()
+                    continue
+                elif non_fatal:
+                    self._downloader.report_warning(error_to_compat_str(e))
+                    return False
+                raise
+
+    def _real_initialize(self):
+        self._CLIENT_ID = self._downloader.cache.load('soundcloud', 'client_id') or 'YUKXoArFcqrlQn9tfNHvvyfnDISj04zk'
+
     @classmethod
     def _resolv_url(cls, url):
-        return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url + '&client_id=' + cls._CLIENT_ID
+        return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url
 
     def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2):
         track_id = compat_str(info['id'])
@@ -451,9 +493,7 @@ class SoundcloudIE(InfoExtractor):
 
         track_id = mobj.group('track_id')
 
-        query = {
-            'client_id': self._CLIENT_ID,
-        }
+        query = {}
         if track_id:
             info_json_url = self._API_V2_BASE + 'tracks/' + track_id
             full_title = track_id
@@ -536,7 +576,6 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
         COMMON_QUERY = {
             'limit': 2000000000,
-            'client_id': self._CLIENT_ID,
             'linked_partitioning': '1',
         }
 
@@ -722,9 +761,7 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
         mobj = re.match(self._VALID_URL, url)
         playlist_id = mobj.group('id')
 
-        query = {
-            'client_id': self._CLIENT_ID,
-        }
+        query = {}
         token = mobj.group('token')
         if token:
             query['secret_token'] = token
@@ -761,7 +798,6 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
             self._MAX_RESULTS_PER_PAGE)
         query.update({
             'limit': limit,
-            'client_id': self._CLIENT_ID,
             'linked_partitioning': 1,
             'offset': 0,
         })

youtube_dl/extractor/spankbang.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     merge_dicts,
     orderedSet,
@@ -64,7 +65,7 @@ class SpankBangIE(InfoExtractor):
             url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
             video_id, headers={'Cookie': 'country=US'})
 
-        if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+        if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
@@ -75,11 +76,20 @@ class SpankBangIE(InfoExtractor):
             if not f_url:
                 return
             f = parse_resolution(format_id)
-            f.update({
-                'url': f_url,
-                'format_id': format_id,
-            })
-            formats.append(f)
+            ext = determine_ext(f_url)
+            if format_id.startswith('m3u8') or ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    f_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif format_id.startswith('mpd') or ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    f_url, video_id, mpd_id='dash', fatal=False))
+            elif ext == 'mp4' or f.get('width') or f.get('height'):
+                f.update({
+                    'url': f_url,
+                    'format_id': format_id,
+                })
+                formats.append(f)
 
         STREAM_URL_PREFIX = 'stream_url_'
 
@@ -93,28 +103,22 @@ class SpankBangIE(InfoExtractor):
                 r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
                 webpage, 'stream key', group='value')
 
-            sb_csrf_session = self._get_cookies(
-                'https://spankbang.com')['sb_csrf_session'].value
-
             stream = self._download_json(
                 'https://spankbang.com/api/videos/stream', video_id,
                 'Downloading stream JSON', data=urlencode_postdata({
                     'id': stream_key,
                     'data': 0,
-                    'sb_csrf_session': sb_csrf_session,
                 }), headers={
                     'Referer': url,
-                    'X-CSRFToken': sb_csrf_session,
+                    'X-Requested-With': 'XMLHttpRequest',
                 })
 
             for format_id, format_url in stream.items():
-                if format_id.startswith(STREAM_URL_PREFIX):
-                    if format_url and isinstance(format_url, list):
-                        format_url = format_url[0]
-                    extract_format(
-                        format_id[len(STREAM_URL_PREFIX):], format_url)
+                if format_url and isinstance(format_url, list):
+                    format_url = format_url[0]
+                extract_format(format_id, format_url)
 
-        self._sort_formats(formats)
+        self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
 
         info = self._search_json_ld(webpage, video_id, default={})
 

youtube_dl/extractor/teachable.py

@@ -165,8 +165,12 @@ class TeachableIE(TeachableBaseIE):
             if any(re.search(p, webpage) for p in (
                     r'class=["\']lecture-contents-locked',
                     r'>\s*Lecture contents locked',
-                    r'id=["\']lecture-locked')):
+                    r'id=["\']lecture-locked',
+                    # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
+                    r'class=["\'](?:inner-)?lesson-locked',
+                    r'>LESSON LOCKED<')):
                 self.raise_login_required('Lecture contents locked')
+            raise ExtractorError('Unable to find video URL')
 
         title = self._og_search_title(webpage, default=None)
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2019.12.25'
+__version__ = '2020.01.01'