Merge branch 'master' into FixBilibili

.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 2020.03.06. 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 Issues with outdated version will be REJECTED.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 2020.03.24. 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 Issues with outdated version will be REJECTED.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 **2020.03.06**
+- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
 - [ ] 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 2020.03.06
+ [debug] youtube-dl version 2020.03.24
  [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 2020.03.06. 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 2020.03.24. 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 **2020.03.06**
+- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
 - [ ] 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 2020.03.06. 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 2020.03.24. 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 **2020.03.06**
+- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
 - [ ] 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 2020.03.06. 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 2020.03.24. 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 **2020.03.06**
+- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
 - [ ] 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 2020.03.06
+ [debug] youtube-dl version 2020.03.24
  [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 2020.03.06. 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 2020.03.24. 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 **2020.03.06**
+- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,38 @@
+version 2020.03.24
+
+Core
+- [utils] Revert support for cookie files with spaces used instead of tabs
+
+Extractors
+* [teachable] Update upskillcourses and gns3 domains
+* [generic] Look for teachable embeds before wistia
++ [teachable] Extract chapter metadata (#24421)
++ [bilibili] Add support for player.bilibili.com (#24402)
++ [bilibili] Add support for new URL schema with BV ids (#24439, #24442)
+* [limelight] Remove disabled API requests (#24255)
+* [soundcloud] Fix download URL extraction (#24394)
++ [cbc:watch] Add support for authentication (#19160)
+* [hellporno] Fix extraction (#24399)
+* [xtube] Fix formats extraction (#24348)
+* [ndr] Fix extraction (#24326)
+* [nhk] Update m3u8 URL and use native HLS downloader (#24329)
+- [nhk] Remove obsolete rtmp formats (#24329)
+* [nhk] Relax URL regular expression (#24329)
+- [vimeo] Revert fix showcase password protected video extraction (#24224)
+
+
+version 2020.03.08
+
+Core
++ [utils] Add support for cookie files with spaces used instead of tabs
+
+Extractors
++ [pornhub] Add support for pornhubpremium.com (#24288)
+- [youtube] Remove outdated code and unnecessary requests
+* [youtube] Improve extraction in 429 HTTP error conditions (#24283)
+* [nhk] Update API version (#24270)
+
+
 version 2020.03.06
 
 Extractors

README.md

@@ -835,7 +835,9 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 ### HTTP Error 429: Too Many Requests or 402: Payment Required
 
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds).
+
+If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
 ### SyntaxError: Non-ASCII character
 

docs/supportedsites.md

@@ -98,6 +98,7 @@
  - **BiliBili**
  - **BilibiliAudio**
  - **BilibiliAudioAlbum**
+ - **BiliBiliPlayer**
  - **BioBioChileTV**
  - **BIQLE**
  - **BitChute**

youtube_dl/extractor/bilibili.py

@@ -27,7 +27,18 @@ md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P<anime_id>\d+)/play#)(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:(?:www|bangumi)\.)?
+                        bilibili\.(?:tv|com)/
+                        (?:
+                            (?:
+                                video/[aA][vV]|
+                                anime/(?P<anime_id>\d+)/play\#
+                            )(?P<id_bv>\d+)|
+                            video/[bB][vV](?P<id>[^/?#&]+)
+                        )
+                    '''
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
@@ -95,6 +106,10 @@ class BiliBiliIE(InfoExtractor):
                 'skip_download': True,  # Test metadata only
             },
         }]
+    }, {
+        # new BV video id format
+        'url': 'https://www.bilibili.com/video/BV1JE411F741',
+        'only_matching': True,
     }]
 
     _APP_KEY = 'iVGUTjsxvpLeuDCf'
@@ -112,7 +127,7 @@ class BiliBiliIE(InfoExtractor):
         url, smuggled_data = unsmuggle_url(url, {})
 
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = mobj.group('id') or mobj.group('id_bv')
         anime_id = mobj.group('anime_id')
         webpage = self._download_webpage(url, video_id)
 
@@ -488,3 +503,16 @@ class BilibiliNewBangumiIE(InfoExtractor):
                 'Referer': url,
             }
         }
+
+class BiliBiliPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            'http://www.bilibili.tv/video/av%s/' % video_id,
+            ie=BiliBiliIE.ie_key(), video_id=video_id)

youtube_dl/extractor/cbc.py

@@ -1,8 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import hashlib
 import json
 import re
+from xml.sax.saxutils import escape
 
 from .common import InfoExtractor
 from ..compat import (
@@ -216,6 +218,29 @@ class CBCWatchBaseIE(InfoExtractor):
         'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
     }
     _GEO_COUNTRIES = ['CA']
+    _LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login'
+    _TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token'
+    _API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37'
+    _NETRC_MACHINE = 'cbcwatch'
+
+    def _signature(self, email, password):
+        data = json.dumps({
+            'email': email,
+            'password': password,
+        }).encode()
+        headers = {'content-type': 'application/json'}
+        query = {'apikey': self._API_KEY}
+        resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query)
+        access_token = resp['access_token']
+
+        # token
+        query = {
+            'access_token': access_token,
+            'apikey': self._API_KEY,
+            'jwtapp': 'jwt',
+        }
+        resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query)
+        return resp['signature']
 
     def _call_api(self, path, video_id):
         url = path if path.startswith('http') else self._API_BASE_URL + path
@@ -239,7 +264,8 @@ class CBCWatchBaseIE(InfoExtractor):
     def _real_initialize(self):
         if self._valid_device_token():
             return
-        device = self._downloader.cache.load('cbcwatch', 'device') or {}
+        device = self._downloader.cache.load(
+            'cbcwatch', self._cache_device_key()) or {}
         self._device_id, self._device_token = device.get('id'), device.get('token')
         if self._valid_device_token():
             return
@@ -248,16 +274,30 @@ class CBCWatchBaseIE(InfoExtractor):
     def _valid_device_token(self):
         return self._device_id and self._device_token
 
+    def _cache_device_key(self):
+        email, _ = self._get_login_info()
+        return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device'
+
     def _register_device(self):
-        self._device_id = self._device_token = None
         result = self._download_xml(
             self._API_BASE_URL + 'device/register',
             None, 'Acquiring device token',
             data=b'<device><type>web</type></device>')
         self._device_id = xpath_text(result, 'deviceId', fatal=True)
-        self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+        email, password = self._get_login_info()
+        if email and password:
+            signature = self._signature(email, password)
+            data = '<login><token>{0}</token><device><deviceId>{1}</deviceId><type>web</type></device></login>'.format(
+                escape(signature), escape(self._device_id)).encode()
+            url = self._API_BASE_URL + 'device/login'
+            result = self._download_xml(
+                url, None, data=data,
+                headers={'content-type': 'application/xml'})
+            self._device_token = xpath_text(result, 'token', fatal=True)
+        else:
+            self._device_token = xpath_text(result, 'deviceToken', fatal=True)
         self._downloader.cache.store(
-            'cbcwatch', 'device', {
+            'cbcwatch', self._cache_device_key(), {
                 'id': self._device_id,
                 'token': self._device_token,
             })

youtube_dl/extractor/extractors.py

@@ -106,6 +106,7 @@ from .bilibili import (
     BilibiliAudioIE,
     BilibiliAudioAlbumIE,
     BilibiliNewBangumiIE,
+    BiliBiliPlayerIE,
 )
 from .biobiochiletv import BioBioChileTVIE
 from .bitchute import (

youtube_dl/extractor/generic.py

@@ -2536,6 +2536,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
 
+        # Look for Teachable embeds, must be before Wistia
+        teachable_url = TeachableIE._extract_url(webpage, url)
+        if teachable_url:
+            return self.url_result(teachable_url)
+
         # Look for embedded Wistia player
         wistia_urls = WistiaIE._extract_urls(webpage)
         if wistia_urls:
@@ -3141,10 +3146,6 @@ 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(

youtube_dl/extractor/hellporno.py

@@ -1,12 +1,11 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    js_to_json,
+    int_or_none,
+    merge_dicts,
     remove_end,
-    determine_ext,
+    unified_timestamp,
 )
 
 
@@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
-        'md5': '1fee339c610d2049699ef2aa699439f1',
+        'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
         'info_dict': {
             'id': '149116',
             'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
             'ext': 'mp4',
             'title': 'Dixie is posing with naked ass very erotic',
+            'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
+            'categories': list,
             'thumbnail': r're:https?://.*\.jpg$',
+            'duration': 240,
+            'timestamp': 1398762720,
+            'upload_date': '20140429',
+            'view_count': int,
             'age_limit': 18,
-        }
+        },
     }, {
         'url': 'http://hellporno.net/v/186271/',
         'only_matching': True,
@@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor):
         title = remove_end(self._html_search_regex(
             r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
 
-        flashvars = self._parse_json(self._search_regex(
+        info = self._parse_html5_media_entries(url, webpage, display_id)[0]
-            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+        self._sort_formats(info['formats'])
-            display_id, transform_source=js_to_json)
 
-        video_id = flashvars.get('video_id')
+        video_id = self._search_regex(
-        thumbnail = flashvars.get('preview_url')
+            (r'chs_object\s*=\s*["\'](\d+)',
-        ext = determine_ext(flashvars.get('postfix'), 'mp4')
+             r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
+            default=display_id)
+        description = self._search_regex(
+            r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
+            'description', fatal=False)
+        categories = [
+            c.strip()
+            for c in self._html_search_meta(
+                'keywords', webpage, 'categories', default='').split(',')
+            if c.strip()]
+        duration = int_or_none(self._og_search_property(
+            'video:duration', webpage, fatal=False))
+        timestamp = unified_timestamp(self._og_search_property(
+            'video:release_date', webpage, fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
 
-        formats = []
+        return merge_dicts(info, {
-        for video_url_key in ['video_url', 'video_alt_url']:
-            video_url = flashvars.get(video_url_key)
-            if not video_url:
-                continue
-            video_text = flashvars.get('%s_text' % video_url_key)
-            fmt = {
-                'url': video_url,
-                'ext': ext,
-                'format_id': video_text,
-            }
-            m = re.search(r'^(?P<height>\d+)[pP]', video_text)
-            if m:
-                fmt['height'] = int(m.group('height'))
-            formats.append(fmt)
-        self._sort_formats(formats)
-
-        categories = self._html_search_meta(
-            'keywords', webpage, 'categories', default='').split(',')
-
-        return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'thumbnail': thumbnail,
+            'description': description,
             'categories': categories,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
             'age_limit': 18,
-            'formats': formats,
+        })
-        }

youtube_dl/extractor/limelight.py

@@ -18,7 +18,6 @@ from ..utils import (
 
 class LimelightBaseIE(InfoExtractor):
     _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
-    _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
 
     @classmethod
     def _extract_urls(cls, webpage, source_url):
@@ -70,7 +69,8 @@ class LimelightBaseIE(InfoExtractor):
         try:
             return self._download_json(
                 self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
-                item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
+                item_id, 'Downloading PlaylistService %s JSON' % method,
+                fatal=fatal, headers=headers)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                 error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
@@ -79,22 +79,22 @@ class LimelightBaseIE(InfoExtractor):
                 raise ExtractorError(error, expected=True)
             raise
 
-    def _call_api(self, organization_id, item_id, method):
+    def _extract(self, item_id, pc_method, mobile_method, referer=None):
-        return self._download_json(
-            self._API_URL % (organization_id, self._API_PATH, item_id, method),
-            item_id, 'Downloading API %s JSON' % method)
-
-    def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
         pc = self._call_playlist_service(item_id, pc_method, referer=referer)
-        metadata = self._call_api(pc['orgId'], item_id, meta_method)
+        mobile = self._call_playlist_service(
-        mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer)
+            item_id, mobile_method, fatal=False, referer=referer)
-        return pc, mobile, metadata
+        return pc, mobile
+
+    def _extract_info(self, pc, mobile, i, referer):
+        get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
+        pc_item = get_item(pc, 'playlistItems')
+        mobile_item = get_item(mobile, 'mediaList')
+        video_id = pc_item.get('mediaId') or mobile_item['mediaId']
+        title = pc_item.get('title') or mobile_item['title']
 
-    def _extract_info(self, streams, mobile_urls, properties):
-        video_id = properties['media_id']
         formats = []
         urls = []
-        for stream in streams:
+        for stream in pc_item.get('streams', []):
             stream_url = stream.get('url')
             if not stream_url or stream.get('drmProtected') or stream_url in urls:
                 continue
@@ -155,7 +155,7 @@ class LimelightBaseIE(InfoExtractor):
                     })
                 formats.append(fmt)
 
-        for mobile_url in mobile_urls:
+        for mobile_url in mobile_item.get('mobileUrls', []):
             media_url = mobile_url.get('mobileUrl')
             format_id = mobile_url.get('targetMediaPlatform')
             if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
@@ -179,54 +179,34 @@ class LimelightBaseIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        title = properties['title']
-        description = properties.get('description')
-        timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date'))
-        duration = float_or_none(properties.get('duration_in_milliseconds'), 1000)
-        filesize = int_or_none(properties.get('total_storage_in_bytes'))
-        categories = [properties.get('category')]
-        tags = properties.get('tags', [])
-        thumbnails = [{
-            'url': thumbnail['url'],
-            'width': int_or_none(thumbnail.get('width')),
-            'height': int_or_none(thumbnail.get('height')),
-        } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
-
         subtitles = {}
-        for caption in properties.get('captions', []):
+        for flag in mobile_item.get('flags'):
-            lang = caption.get('language_code')
+            if flag == 'ClosedCaptions':
-            subtitles_url = caption.get('url')
+                closed_captions = self._call_playlist_service(
-            if lang and subtitles_url:
+                    video_id, 'getClosedCaptionsDetailsByMediaId',
-                subtitles.setdefault(lang, []).append({
+                    False, referer) or []
-                    'url': subtitles_url,
+                for cc in closed_captions:
-                })
+                    cc_url = cc.get('webvttFileUrl')
-        closed_captions_url = properties.get('closed_captions_url')
+                    if not cc_url:
-        if closed_captions_url:
+                        continue
-            subtitles.setdefault('en', []).append({
+                    lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en')
-                'url': closed_captions_url,
+                    subtitles.setdefault(lang, []).append({
-                'ext': 'ttml',
+                        'url': cc_url,
-            })
+                    })
+                break
+
+        get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': get_meta('description'),
             'formats': formats,
-            'timestamp': timestamp,
+            'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
-            'duration': duration,
+            'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
-            'filesize': filesize,
-            'categories': categories,
-            'tags': tags,
-            'thumbnails': thumbnails,
             'subtitles': subtitles,
         }
 
-    def _extract_info_helper(self, pc, mobile, i, metadata):
-        return self._extract_info(
-            try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
-            try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
-            metadata)
-
 
 class LimelightMediaIE(LimelightBaseIE):
     IE_NAME = 'limelight'
@@ -251,8 +231,6 @@ class LimelightMediaIE(LimelightBaseIE):
             'description': 'md5:8005b944181778e313d95c1237ddb640',
             'thumbnail': r're:^https?://.*\.jpeg$',
             'duration': 144.23,
-            'timestamp': 1244136834,
-            'upload_date': '20090604',
         },
         'params': {
             # m3u8 download
@@ -268,30 +246,29 @@ class LimelightMediaIE(LimelightBaseIE):
             'title': '3Play Media Overview Video',
             'thumbnail': r're:^https?://.*\.jpeg$',
             'duration': 78.101,
-            'timestamp': 1338929955,
+            # TODO: extract all languages that were accessible via API
-            'upload_date': '20120605',
+            # 'subtitles': 'mincount:9',
-            'subtitles': 'mincount:9',
+            'subtitles': 'mincount:1',
         },
     }, {
         'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
         'only_matching': True,
     }]
     _PLAYLIST_SERVICE_PATH = 'media'
-    _API_PATH = 'media'
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
         video_id = self._match_id(url)
+        source_url = smuggled_data.get('source_url')
         self._initialize_geo_bypass({
             'countries': smuggled_data.get('geo_countries'),
         })
 
-        pc, mobile, metadata = self._extract(
+        pc, mobile = self._extract(
             video_id, 'getPlaylistByMediaId',
-            'getMobilePlaylistByMediaId', 'properties',
+            'getMobilePlaylistByMediaId', source_url)
-            smuggled_data.get('source_url'))
 
-        return self._extract_info_helper(pc, mobile, 0, metadata)
+        return self._extract_info(pc, mobile, 0, source_url)
 
 
 class LimelightChannelIE(LimelightBaseIE):
@@ -313,6 +290,7 @@ class LimelightChannelIE(LimelightBaseIE):
         'info_dict': {
             'id': 'ab6a524c379342f9b23642917020c082',
             'title': 'Javascript Sample Code',
+            'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
         },
         'playlist_mincount': 3,
     }, {
@@ -320,22 +298,23 @@ class LimelightChannelIE(LimelightBaseIE):
         'only_matching': True,
     }]
     _PLAYLIST_SERVICE_PATH = 'channel'
-    _API_PATH = 'channels'
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
         channel_id = self._match_id(url)
+        source_url = smuggled_data.get('source_url')
 
-        pc, mobile, medias = self._extract(
+        pc, mobile = self._extract(
             channel_id, 'getPlaylistByChannelId',
             'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
-            'media', smuggled_data.get('source_url'))
+            source_url)
 
         entries = [
-            self._extract_info_helper(pc, mobile, i, medias['media_list'][i])
+            self._extract_info(pc, mobile, i, source_url)
-            for i in range(len(medias['media_list']))]
+            for i in range(len(pc['playlistItems']))]
 
-        return self.playlist_result(entries, channel_id, pc['title'])
+        return self.playlist_result(
+            entries, channel_id, pc.get('title'), mobile.get('description'))
 
 
 class LimelightChannelListIE(LimelightBaseIE):
@@ -368,10 +347,12 @@ class LimelightChannelListIE(LimelightBaseIE):
     def _real_extract(self, url):
         channel_list_id = self._match_id(url)
 
-        channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById')
+        channel_list = self._call_playlist_service(
+            channel_list_id, 'getMobileChannelListById')
 
         entries = [
             self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel')
             for channel in channel_list['channelList']]
 
-        return self.playlist_result(entries, channel_list_id, channel_list['title'])
+        return self.playlist_result(
+            entries, channel_list_id, channel_list['title'])

youtube_dl/extractor/ndr.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     int_or_none,
+    merge_dicts,
     parse_iso8601,
     qualities,
     try_get,
@@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE):
 
     def _extract_embed(self, webpage, display_id):
         embed_url = self._html_search_meta(
-            'embedURL', webpage, 'embed URL', fatal=True)
+            'embedURL', webpage, 'embed URL',
+            default=None) or self._search_regex(
+            r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'embed URL', group='url')
         description = self._search_regex(
             r'<p[^>]+itemprop="description">([^<]+)</p>',
             webpage, 'description', default=None) or self._og_search_description(webpage)
         timestamp = parse_iso8601(
             self._search_regex(
                 r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
-                webpage, 'upload date', fatal=False))
+                webpage, 'upload date', default=None))
-        return {
+        info = self._search_json_ld(webpage, display_id, default={})
+        return merge_dicts({
             '_type': 'url_transparent',
             'url': embed_url,
             'display_id': display_id,
             'description': description,
             'timestamp': timestamp,
-        }
+        }, info)
 
 
 class NJoyIE(NDRBaseIE):

youtube_dl/extractor/nhk.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)'
     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{
@@ -30,8 +30,11 @@ class NhkVodIE(InfoExtractor):
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
         'only_matching': True,
+    }, {
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
+        'only_matching': True,
     }]
-    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
+    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json'
 
     def _real_extract(self, url):
         lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
@@ -82,15 +85,9 @@ class NhkVodIE(InfoExtractor):
             audio = episode['audio']
             audio_path = audio['audio']
             info['formats'] = self._extract_m3u8_formats(
-                'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
+                'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
-                episode_id, 'm4a', m3u8_id='hls', fatal=False)
+                episode_id, 'm4a', entry_protocol='m3u8_native',
-            for proto in ('rtmpt', 'rtmp'):
+                m3u8_id='hls', fatal=False)
-                info['formats'].append({
-                    'ext': 'flv',
-                    'format_id': proto,
-                    'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
-                    'vcodec': 'none',
-                })
             for f in info['formats']:
                 f['language'] = lang
         return info

youtube_dl/extractor/pokemon.py

@@ -20,20 +20,16 @@ class PokemonIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'The Ol’ Raise and Switch!',
             'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
-            'timestamp': 1511824728,
-            'upload_date': '20171127',
         },
         'add_id': ['LimelightMedia'],
     }, {
         # no data-video-title
-        'url': 'https://www.pokemon.com/us/pokemon-episodes/pokemon-movies/pokemon-the-rise-of-darkrai-2008',
+        'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
         'info_dict': {
-            'id': '99f3bae270bf4e5097274817239ce9c8',
+            'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
             'ext': 'mp4',
-            'title': 'Pokémon: The Rise of Darkrai',
+            'title': "Pokémon : L'ascension de Darkrai",
-            'description': 'md5:ea8fbbf942e1e497d54b19025dd57d9d',
+            'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
-            'timestamp': 1417778347,
-            'upload_date': '20141205',
         },
         'add_id': ['LimelightMedia'],
         'params': {

youtube_dl/extractor/pornhub.py

@@ -52,7 +52,7 @@ class PornHubIE(PornHubBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -149,6 +149,9 @@ class PornHubIE(PornHubBaseIE):
     }, {
         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
         'only_matching': True,
+    }, {
+        'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -166,6 +169,13 @@ class PornHubIE(PornHubBaseIE):
         host = mobj.group('host') or 'pornhub.com'
         video_id = mobj.group('id')
 
+        if 'premium' in host:
+            if not self._downloader.params.get('cookiefile'):
+                raise ExtractorError(
+                    'PornHub Premium requires authentication.'
+                    ' You may want to use --cookies.',
+                    expected=True)
+
         self._set_cookie(host, 'age_verified', '1')
 
         def dl_webpage(platform):
@@ -405,7 +415,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
 
 
 class PornHubUserIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/model/zoe_ph',
         'playlist_mincount': 118,
@@ -473,7 +483,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
 
 
 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
         'only_matching': True,
@@ -588,7 +598,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
 
 
 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
     _TESTS = [{
         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
         'info_dict': {

youtube_dl/extractor/soundcloud.py

@@ -27,6 +27,7 @@ from ..utils import (
     unified_timestamp,
     update_url_query,
     url_or_none,
+    urlhandle_detect_ext,
 )
 
 
@@ -96,7 +97,7 @@ class SoundcloudIE(InfoExtractor):
                 'repost_count': int,
             }
         },
-        # not streamable song, preview
+        # geo-restricted
         {
             'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
             'info_dict': {
@@ -108,17 +109,13 @@ class SoundcloudIE(InfoExtractor):
                 'uploader_id': '9615865',
                 'timestamp': 1337635207,
                 'upload_date': '20120521',
-                'duration': 30,
+                'duration': 227.155,
                 'license': 'all-rights-reserved',
                 'view_count': int,
                 'like_count': int,
                 'comment_count': int,
                 'repost_count': int,
             },
-            'params': {
-                # rtmp
-                'skip_download': True,
-            },
         },
         # private link
         {
@@ -229,7 +226,6 @@ class SoundcloudIE(InfoExtractor):
                 'skip_download': True,
             },
         },
-        # not available via api.soundcloud.com/i1/tracks/id/streams
         {
             'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
             'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
@@ -250,11 +246,9 @@ class SoundcloudIE(InfoExtractor):
                 'comment_count': int,
                 'repost_count': int,
             },
-            'expected_warnings': ['Unable to download JSON metadata'],
         }
     ]
 
-    _API_BASE = 'https://api.soundcloud.com/'
     _API_V2_BASE = 'https://api-v2.soundcloud.com/'
     _BASE_URL = 'https://soundcloud.com/'
     _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
@@ -316,10 +310,9 @@ class SoundcloudIE(InfoExtractor):
     def _resolv_url(cls, url):
         return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url
 
-    def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2):
+    def _extract_info_dict(self, info, full_title=None, secret_token=None):
         track_id = compat_str(info['id'])
         title = info['title']
-        track_base_url = self._API_BASE + 'tracks/%s' % track_id
 
         format_urls = set()
         formats = []
@@ -328,21 +321,22 @@ class SoundcloudIE(InfoExtractor):
             query['secret_token'] = secret_token
 
         if info.get('downloadable') and info.get('has_downloads_left'):
-            format_url = update_url_query(
+            download_url = update_url_query(
-                info.get('download_url') or track_base_url + '/download', query)
+                self._API_V2_BASE + 'tracks/' + track_id + '/download', query)
-            format_urls.add(format_url)
+            redirect_url = (self._download_json(download_url, track_id, fatal=False) or {}).get('redirectUri')
-            if version == 2:
+            if redirect_url:
-                v1_info = self._download_json(
+                urlh = self._request_webpage(
-                    track_base_url, track_id, query=query, fatal=False) or {}
+                    HEADRequest(redirect_url), track_id, fatal=False)
-            else:
+                if urlh:
-                v1_info = info
+                    format_url = urlh.geturl()
-            formats.append({
+                    format_urls.add(format_url)
-                'format_id': 'download',
+                    formats.append({
-                'ext': v1_info.get('original_format') or 'mp3',
+                        'format_id': 'download',
-                'filesize': int_or_none(v1_info.get('original_content_size')),
+                        'ext': urlhandle_detect_ext(urlh) or 'mp3',
-                'url': format_url,
+                        'filesize': int_or_none(urlh.headers.get('Content-Length')),
-                'preference': 10,
+                        'url': format_url,
-            })
+                        'preference': 10,
+                    })
 
         def invalid_url(url):
             return not url or url in format_urls
@@ -406,42 +400,11 @@ class SoundcloudIE(InfoExtractor):
             }, 'http' if protocol == 'progressive' else protocol,
                 t.get('snipped') or '/preview/' in format_url)
 
-        if not formats:
-            # Old API, does not work for some tracks (e.g.
-            # https://soundcloud.com/giovannisarani/mezzo-valzer)
-            # and might serve preview URLs (e.g.
-            # http://www.soundcloud.com/snbrn/ele)
-            format_dict = self._download_json(
-                track_base_url + '/streams', track_id,
-                'Downloading track url', query=query, fatal=False) or {}
-
-            for key, stream_url in format_dict.items():
-                if invalid_url(stream_url):
-                    continue
-                format_urls.add(stream_url)
-                mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key)
-                if mobj:
-                    protocol, ext, abr = mobj.groups()
-                    add_format({
-                        'abr': abr,
-                        'ext': ext,
-                        'url': stream_url,
-                    }, protocol)
-
-        if not formats:
-            # We fallback to the stream_url in the original info, this
-            # cannot be always used, sometimes it can give an HTTP 404 error
-            urlh = self._request_webpage(
-                HEADRequest(info.get('stream_url') or track_base_url + '/stream'),
-                track_id, query=query, fatal=False)
-            if urlh:
-                stream_url = urlh.geturl()
-                if not invalid_url(stream_url):
-                    add_format({'url': stream_url}, 'http')
-
         for f in formats:
             f['vcodec'] = 'none'
 
+        if not formats and info.get('policy') == 'BLOCK':
+            self.raise_geo_restricted()
         self._sort_formats(formats)
 
         user = info.get('user') or {}
@@ -511,16 +474,10 @@ class SoundcloudIE(InfoExtractor):
                 resolve_title += '/%s' % token
             info_json_url = self._resolv_url(self._BASE_URL + resolve_title)
 
-        version = 2
         info = self._download_json(
-            info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False)
+            info_json_url, full_title, 'Downloading info JSON', query=query)
-        if not info:
-            info = self._download_json(
-                info_json_url.replace(self._API_V2_BASE, self._API_BASE),
-                full_title, 'Downloading info JSON', query=query)
-            version = 1
 
-        return self._extract_info_dict(info, full_title, token, version)
+        return self._extract_info_dict(info, full_title, token)
 
 
 class SoundcloudPlaylistBaseIE(SoundcloudIE):

youtube_dl/extractor/teachable.py

@@ -7,7 +7,9 @@ from .wistia import WistiaIE
 from ..utils import (
     clean_html,
     ExtractorError,
+    int_or_none,
     get_element_by_class,
+    strip_or_none,
     urlencode_postdata,
     urljoin,
 )
@@ -19,8 +21,8 @@ class TeachableBaseIE(InfoExtractor):
 
     _SITES = {
         # Only notable ones here
-        'upskillcourses.com': 'upskill',
+        'v1.upskillcourses.com': 'upskill',
-        'academy.gns3.com': 'gns3',
+        'gns3.teachable.com': 'gns3',
         'academyhacker.com': 'academyhacker',
         'stackskills.com': 'stackskills',
         'market.saleshacker.com': 'saleshacker',
@@ -109,27 +111,29 @@ class TeachableIE(TeachableBaseIE):
                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 
     _TESTS = [{
-        'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
+        'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
         'info_dict': {
-            'id': 'uzw6zw58or',
+            'id': 'untlgzk1v7',
-            'ext': 'mp4',
+            'ext': 'bin',
-            'title': 'Welcome to the Course!',
+            'title': 'Overview',
-            'description': 'md5:65edb0affa582974de4625b9cdea1107',
+            'description': 'md5:071463ff08b86c208811130ea1c2464c',
-            'duration': 138.763,
+            'duration': 736.4,
-            'timestamp': 1479846621,
+            'timestamp': 1542315762,
-            'upload_date': '20161122',
+            'upload_date': '20181115',
+            'chapter': 'Welcome',
+            'chapter_number': 1,
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
+        'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
         'only_matching': True,
     }, {
-        'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
+        'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
         'only_matching': True,
     }, {
-        'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
+        'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
         'only_matching': True,
     }]
 
@@ -173,11 +177,34 @@ class TeachableIE(TeachableBaseIE):
 
         title = self._og_search_title(webpage, default=None)
 
+        chapter = None
+        chapter_number = None
+        section_item = self._search_regex(
+            r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
+            webpage, 'section item', default=None, group='li')
+        if section_item:
+            chapter_number = int_or_none(self._search_regex(
+                r'data-ss-position=["\'](\d+)', section_item, 'section id',
+                default=None))
+            if chapter_number is not None:
+                sections = []
+                for s in re.findall(
+                        r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
+                    section = strip_or_none(clean_html(s))
+                    if not section:
+                        sections = []
+                        break
+                    sections.append(section)
+                if chapter_number <= len(sections):
+                    chapter = sections[chapter_number - 1]
+
         entries = [{
             '_type': 'url_transparent',
             'url': wistia_url,
             'ie_key': WistiaIE.ie_key(),
             'title': title,
+            'chapter': chapter,
+            'chapter_number': chapter_number,
         } for wistia_url in wistia_urls]
 
         return self.playlist_result(entries, video_id, title)
@@ -192,20 +219,20 @@ class TeachableCourseIE(TeachableBaseIE):
                         /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
     _TESTS = [{
-        'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
+        'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
         'info_dict': {
             'id': 'essential-web-developer-course',
             'title': 'The Essential Web Developer Course (Free)',
         },
         'playlist_count': 192,
     }, {
-        'url': 'http://upskillcourses.com/courses/119763/',
+        'url': 'http://v1.upskillcourses.com/courses/119763/',
         'only_matching': True,
     }, {
-        'url': 'http://upskillcourses.com/courses/enrolled/119763',
+        'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
         'only_matching': True,
     }, {
-        'url': 'https://academy.gns3.com/courses/enrolled/423415',
+        'url': 'https://gns3.teachable.com/courses/enrolled/423415',
         'only_matching': True,
     }, {
         'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',

youtube_dl/extractor/telequebec.py

@@ -38,8 +38,6 @@ class TeleQuebecIE(TeleQuebecBaseIE):
             'ext': 'mp4',
             'title': 'Un petit choc et puis repart!',
             'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
-            'upload_date': '20180222',
-            'timestamp': 1519326631,
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/tfo.py

@@ -17,14 +17,12 @@ class TFOIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
-        'md5': '47c987d0515561114cf03d1226a9d4c7',
+        'md5': 'cafbe4f47a8dae0ca0159937878100d6',
         'info_dict': {
-            'id': '100463871',
+            'id': '7da3d50e495c406b8fc0b997659cc075',
             'ext': 'mp4',
             'title': 'Video Game Hackathon',
             'description': 'md5:558afeba217c6c8d96c60e5421795c07',
-            'upload_date': '20160212',
-            'timestamp': 1455310233,
         }
     }
 

youtube_dl/extractor/vimeo.py

@@ -585,7 +585,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 url = 'https://vimeo.com/' + video_id
         elif is_player:
             url = 'https://player.vimeo.com/video/' + video_id
-        elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf', '/album/', '/showcase/')):
+        elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id
 
         try:

youtube_dl/extractor/xtube.py

@@ -98,9 +98,9 @@ class XTubeIE(InfoExtractor):
                 title = config.get('title')
                 thumbnail = config.get('poster')
                 duration = int_or_none(config.get('duration'))
-                sources = config.get('sources')
+                sources = config.get('sources') or config.get('format')
 
-        if isinstance(sources, dict):
+        if not isinstance(sources, dict):
             sources = self._parse_json(self._search_regex(
                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
                 webpage, 'sources', group='sources'), video_id,

youtube_dl/extractor/youtube.py

@@ -29,7 +29,6 @@ from ..compat import (
 from ..utils import (
     bool_or_none,
     clean_html,
-    dict_get,
     error_to_compat_str,
     extract_attributes,
     ExtractorError,
@@ -1708,9 +1707,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         def extract_view_count(v_info):
             return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
 
-        def extract_token(v_info):
-            return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
-
         def extract_player_response(player_response, video_id):
             pl_response = str_or_none(player_response)
             if not pl_response:
@@ -1723,6 +1719,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         player_response = {}
 
         # Get video info
+        video_info = {}
         embed_webpage = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
@@ -1737,19 +1734,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
             })
             video_info_url = proto + '://www.youtube.com/get_video_info?' + data
-            video_info_webpage = self._download_webpage(
+            try:
-                video_info_url, video_id,
+                video_info_webpage = self._download_webpage(
-                note='Refetching age-gated info webpage',
+                    video_info_url, video_id,
-                errnote='unable to download video info webpage')
+                    note='Refetching age-gated info webpage',
-            video_info = compat_parse_qs(video_info_webpage)
+                    errnote='unable to download video info webpage')
-            pl_response = video_info.get('player_response', [None])[0]
+            except ExtractorError:
-            player_response = extract_player_response(pl_response, video_id)
+                video_info_webpage = None
-            add_dash_mpd(video_info)
+            if video_info_webpage:
-            view_count = extract_view_count(video_info)
+                video_info = compat_parse_qs(video_info_webpage)
+                pl_response = video_info.get('player_response', [None])[0]
+                player_response = extract_player_response(pl_response, video_id)
+                add_dash_mpd(video_info)
+                view_count = extract_view_count(video_info)
         else:
             age_gate = False
-            video_info = None
-            sts = None
             # Try looking directly into the video webpage
             ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
             if ytplayer_config:
@@ -1766,61 +1765,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
                 if args.get('livestream') == '1' or args.get('live_playback') == 1:
                     is_live = True
-                sts = ytplayer_config.get('sts')
                 if not player_response:
                     player_response = extract_player_response(args.get('player_response'), video_id)
             if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
                 add_dash_mpd_pr(player_response)
-                # 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
-                # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
-                # manifest pointed by get_video_info's dashmpd).
-                # The general idea is to take a union of itags of both DASH manifests (for example
-                # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
-                self.report_video_info_webpage_download(video_id)
-                for el in ('embedded', 'detailpage', 'vevo', ''):
-                    query = {
-                        'video_id': video_id,
-                        'ps': 'default',
-                        'eurl': '',
-                        'gl': 'US',
-                        'hl': 'en',
-                    }
-                    if el:
-                        query['el'] = el
-                    if sts:
-                        query['sts'] = sts
-                    video_info_webpage = self._download_webpage(
-                        '%s://www.youtube.com/get_video_info' % proto,
-                        video_id, note=False,
-                        errnote='unable to download video info webpage',
-                        fatal=False, query=query)
-                    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]
-                        player_response = extract_player_response(pl_response, video_id)
-                    add_dash_mpd(get_video_info)
-                    if view_count is None:
-                        view_count = extract_view_count(get_video_info)
-                    if not video_info:
-                        video_info = get_video_info
-                    get_token = extract_token(get_video_info)
-                    if get_token:
-                        # Different get_video_info requests may report different results, e.g.
-                        # some may report video unavailability, but some may serve it without
-                        # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
-                        # the original webpage as well as el=info and el=embedded get_video_info
-                        # requests report video unavailability due to geo restriction while
-                        # el=detailpage succeeds and returns valid data). This is probably
-                        # due to YouTube measures against IP ranges of hosting providers.
-                        # Working around by preferring the first succeeded video_info containing
-                        # the token if no such video_info yet was found.
-                        token = extract_token(video_info)
-                        if not token:
-                            video_info = get_video_info
-                        break
 
         def extract_unavailable_message():
             messages = []
@@ -1833,13 +1781,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if messages:
                 return '\n'.join(messages)
 
-        if not video_info:
+        if not video_info and not player_response:
             unavailable_message = extract_unavailable_message()
             if not unavailable_message:
                 unavailable_message = 'Unable to extract video data'
             raise ExtractorError(
                 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
 
+        if not isinstance(video_info, dict):
+            video_info = {}
+
         video_details = try_get(
             player_response, lambda x: x['videoDetails'], dict) or {}
 
@@ -2392,30 +2343,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         f['stretched_ratio'] = ratio
 
         if not formats:
-            token = extract_token(video_info)
+            if 'reason' in video_info:
-            if not token:
+                if 'The uploader has not made this video available in your country.' in video_info['reason']:
-                if 'reason' in video_info:
+                    regions_allowed = self._html_search_meta(
-                    if 'The uploader has not made this video available in your country.' in video_info['reason']:
+                        'regionsAllowed', video_webpage, default=None)
-                        regions_allowed = self._html_search_meta(
+                    countries = regions_allowed.split(',') if regions_allowed else None
-                            'regionsAllowed', video_webpage, default=None)
+                    self.raise_geo_restricted(
-                        countries = regions_allowed.split(',') if regions_allowed else None
+                        msg=video_info['reason'][0], countries=countries)
-                        self.raise_geo_restricted(
+                reason = video_info['reason'][0]
-                            msg=video_info['reason'][0], countries=countries)
+                if 'Invalid parameters' in reason:
-                    reason = video_info['reason'][0]
+                    unavailable_message = extract_unavailable_message()
-                    if 'Invalid parameters' in reason:
+                    if unavailable_message:
-                        unavailable_message = extract_unavailable_message()
+                        reason = unavailable_message
-                        if unavailable_message:
+                raise ExtractorError(
-                            reason = unavailable_message
+                    'YouTube said: %s' % reason,
-                    raise ExtractorError(
+                    expected=True, video_id=video_id)
-                        'YouTube said: %s' % reason,
+            if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
-                        expected=True, video_id=video_id)
+                raise ExtractorError('This video is DRM protected.', expected=True)
-                else:
-                    raise ExtractorError(
-                        '"token" parameter not in video info for unknown reason',
-                        video_id=video_id)
-
-        if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
-            raise ExtractorError('This video is DRM protected.', expected=True)
 
         self._sort_formats(formats)
 

youtube_dl/utils.py

@@ -2729,6 +2729,11 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
 
 
 class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
+    """
+    See [1] for cookie file format.
+
+    1. https://curl.haxx.se/docs/http-cookies.html
+    """
     _HTTPONLY_PREFIX = '#HttpOnly_'
 
     def save(self, filename=None, ignore_discard=False, ignore_expires=False):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.03.06'
+__version__ = '2020.03.24'