release 2020.11.29

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. 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 Issues with outdated version will be REJECTED.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 2020.11.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.11.24
+ [debug] youtube-dl version 2020.11.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. 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 2020.11.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. 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 2020.11.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.29**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. 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 2020.11.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.11.24
+ [debug] youtube-dl version 2020.11.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.24. 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 2020.11.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.24**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.29**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,38 @@
+version 2020.11.29
+
+Core
+* [YoutubeDL] Write static debug to stderr and respect quiet for dynamic debug
+  (#14579, #22593)
+
+Extractors
+* [drtv] Extend URL regular expression (#27243)
+* [tiktok] Fix extraction (#20809, #22838, #22850, #25987, #26281, #26411,
+  #26639, #26776, #27237)
++ [ina] Add support for mobile URLs (#27229)
+* [pornhub] Fix like and dislike count extraction (#27227, #27234)
+* [youtube] Improve yt initial player response extraction (#27216)
+* [videa] Fix extraction (#25650, #25973, #26301)
+
+
+version 2020.11.26
+
+Core
+* [downloader/fragment] Set final file's mtime according to last fragment's
+  Last-Modified header (#11718, #18384, #27138)
+
+Extractors
++ [spreaker] Add support for spreaker.com (#13480, #13877)
+* [vlive] Improve extraction for geo-restricted videos
++ [vlive] Add support for post URLs (#27122, #27123)
+* [viki] Fix video API request (#27184)
+* [bbc] Fix BBC Three clip extraction
+* [bbc] Fix BBC News videos extraction
++ [medaltv] Add support for medal.tv (#27149)
+* [youtube] Improve music metadata and license extraction (#26013)
+* [nrk] Fix extraction
+* [cda] Fix extraction (#17803, #24458, #24518, #26381)
+
+
 version 2020.11.24
 
 Core

docs/supportedsites.md

@@ -471,6 +471,7 @@
  - **massengeschmack.tv**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
+ - **MedalTV**
  - **media.ccc.de**
  - **media.ccc.de:lists**
  - **Medialaan**
@@ -839,6 +840,10 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **Spreaker**
+ - **SpreakerPage**
+ - **SpreakerShow**
+ - **SpreakerShowPage**
  - **SpringboardPlatform**
  - **Sprout**
  - **sr:mediathek**: Saarländischer Rundfunk
@@ -907,7 +912,7 @@
  - **ThisAV**
  - **ThisOldHouse**
  - **TikTok**
- - **TikTokUser**
+ - **TikTokUser** (Currently broken)
  - **tinypic**: tinypic.com videos
  - **TMZ**
  - **TMZArticle**
@@ -1055,6 +1060,7 @@
  - **vk:wallpost**
  - **vlive**
  - **vlive:channel**
+ - **vlive:post**
  - **Vodlocker**
  - **VODPl**
  - **VODPlatform**

youtube_dl/YoutubeDL.py

@@ -1610,7 +1610,7 @@ class YoutubeDL(object):
         if req_format is None:
             req_format = self._default_format_spec(info_dict, download=download)
             if self.params.get('verbose'):
-                self.to_stdout('[debug] Default format spec: %s' % req_format)
+                self._write_string('[debug] Default format spec: %s\n' % req_format)
 
         format_selector = self.build_format_selector(req_format)
 
@@ -1871,7 +1871,7 @@ class YoutubeDL(object):
                     for ph in self._progress_hooks:
                         fd.add_progress_hook(ph)
                     if self.params.get('verbose'):
-                        self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
+                        self.to_screen('[debug] Invoking downloader on %r' % info.get('url'))
                     return fd.download(name, info)
 
                 if info_dict.get('requested_formats') is not None:

youtube_dl/extractor/drtv.py

@@ -29,7 +29,7 @@ class DRTVIE(InfoExtractor):
                     https?://
                         (?:
                             (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*|
-                            (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode)/
+                            (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
                         )
                         (?P<id>[\da-z_-]+)
                     '''
@@ -111,6 +111,9 @@ class DRTVIE(InfoExtractor):
     }, {
         'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
         'only_matching': True,
+    }, {
+        'url': 'https://www.dr.dk/drtv/program/jagten_220924',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -1082,6 +1082,12 @@ from .stitcher import StitcherIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .spreaker import (
+    SpreakerIE,
+    SpreakerPageIE,
+    SpreakerShowIE,
+    SpreakerShowPageIE,
+)
 from .springboardplatform import SpringboardPlatformIE
 from .sprout import SproutIE
 from .srgssr import (

youtube_dl/extractor/ina.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class InaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ina\.fr/(?:video|audio)/(?P<id>[A-Z0-9_]+)'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?ina\.fr/(?:video|audio)/(?P<id>[A-Z0-9_]+)'
     _TESTS = [{
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
@@ -31,6 +31,9 @@ class InaIE(InfoExtractor):
     }, {
         'url': 'https://www.ina.fr/video/P16173408-video.html',
         'only_matching': True,
+    }, {
+        'url': 'http://m.ina.fr/video/I12055569',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/pornhub.py

@@ -346,9 +346,9 @@ class PornHubIE(PornHubBaseIE):
         view_count = self._extract_count(
             r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
         like_count = self._extract_count(
-            r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+            r'<span[^>]+class="votesUp"[^>]*>([\d,\.]+)</span>', webpage, 'like')
         dislike_count = self._extract_count(
-            r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+            r'<span[^>]+class="votesDown"[^>]*>([\d,\.]+)</span>', webpage, 'dislike')
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 

youtube_dl/extractor/spreaker.py

@@ -0,0 +1,176 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    str_or_none,
+    try_get,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+def _extract_episode(data, episode_id=None):
+    title = data['title']
+    download_url = data['download_url']
+
+    series = try_get(data, lambda x: x['show']['title'], compat_str)
+    uploader = try_get(data, lambda x: x['author']['fullname'], compat_str)
+
+    thumbnails = []
+    for image in ('image_original', 'image_medium', 'image'):
+        image_url = url_or_none(data.get('%s_url' % image))
+        if image_url:
+            thumbnails.append({'url': image_url})
+
+    def stats(key):
+        return int_or_none(try_get(
+            data,
+            (lambda x: x['%ss_count' % key],
+             lambda x: x['stats']['%ss' % key])))
+
+    def duration(key):
+        return float_or_none(data.get(key), scale=1000)
+
+    return {
+        'id': compat_str(episode_id or data['episode_id']),
+        'url': download_url,
+        'display_id': data.get('permalink'),
+        'title': title,
+        'description': data.get('description'),
+        'timestamp': unified_timestamp(data.get('published_at')),
+        'uploader': uploader,
+        'uploader_id': str_or_none(data.get('author_id')),
+        'creator': uploader,
+        'duration': duration('duration') or duration('length'),
+        'view_count': stats('play'),
+        'like_count': stats('like'),
+        'comment_count': stats('message'),
+        'format': 'MPEG Layer 3',
+        'format_id': 'mp3',
+        'container': 'mp3',
+        'ext': 'mp3',
+        'thumbnails': thumbnails,
+        'series': series,
+        'extractor_key': SpreakerIE.ie_key(),
+    }
+
+
+class SpreakerIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        api\.spreaker\.com/
+                        (?:
+                            (?:download/)?episode|
+                            v2/episodes
+                        )/
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [{
+        'url': 'https://api.spreaker.com/episode/12534508',
+        'info_dict': {
+            'id': '12534508',
+            'display_id': 'swm-ep15-how-to-market-your-music-part-2',
+            'ext': 'mp3',
+            'title': 'EP:15 | Music Marketing (Likes) - Part 2',
+            'description': 'md5:0588c43e27be46423e183076fa071177',
+            'timestamp': 1502250336,
+            'upload_date': '20170809',
+            'uploader': 'SWM',
+            'uploader_id': '9780658',
+            'duration': 1063.42,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'series': 'Success With Music (SWM)',
+        },
+    }, {
+        'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
+        'only_matching': True,
+    }, {
+        'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        data = self._download_json(
+            'https://api.spreaker.com/v2/episodes/%s' % episode_id,
+            episode_id)['response']['episode']
+        return _extract_episode(data, episode_id)
+
+
+class SpreakerPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        episode_id = self._search_regex(
+            (r'data-episode_id=["\'](?P<id>\d+)',
+             r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
+        return self.url_result(
+            'https://api.spreaker.com/episode/%s' % episode_id,
+            ie=SpreakerIE.ie_key(), video_id=episode_id)
+
+
+class SpreakerShowIE(InfoExtractor):
+    _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://api.spreaker.com/show/4652058',
+        'info_dict': {
+            'id': '4652058',
+        },
+        'playlist_mincount': 118,
+    }]
+
+    def _entries(self, show_id):
+        for page_num in itertools.count(1):
+            episodes = self._download_json(
+                'https://api.spreaker.com/show/%s/episodes' % show_id,
+                show_id, note='Downloading JSON page %d' % page_num, query={
+                    'page': page_num,
+                    'max_per_page': 100,
+                })
+            pager = try_get(episodes, lambda x: x['response']['pager'], dict)
+            if not pager:
+                break
+            results = pager.get('results')
+            if not results or not isinstance(results, list):
+                break
+            for result in results:
+                if not isinstance(result, dict):
+                    continue
+                yield _extract_episode(result)
+            if page_num == pager.get('last_page'):
+                break
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+
+
+class SpreakerShowPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.spreaker.com/show/success-with-music',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        show_id = self._search_regex(
+            r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
+        return self.url_result(
+            'https://api.spreaker.com/show/%s' % show_id,
+            ie=SpreakerShowIE.ie_key(), video_id=show_id)

youtube_dl/extractor/tiktok.py

@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_str,
     ExtractorError,
+    float_or_none,
     int_or_none,
     str_or_none,
     try_get,
@@ -13,7 +14,7 @@ from ..utils import (
 
 
 class TikTokBaseIE(InfoExtractor):
-    def _extract_aweme(self, data):
+    def _extract_video(self, data, video_id=None):
         video = data['video']
         description = str_or_none(try_get(data, lambda x: x['desc']))
         width = int_or_none(try_get(data, lambda x: video['width']))
@@ -21,43 +22,54 @@ class TikTokBaseIE(InfoExtractor):
 
         format_urls = set()
         formats = []
-        for format_id in (
-                'play_addr_lowbr', 'play_addr', 'play_addr_h264',
-                'download_addr'):
-            for format in try_get(
-                    video, lambda x: x[format_id]['url_list'], list) or []:
-                format_url = url_or_none(format)
-                if not format_url:
-                    continue
-                if format_url in format_urls:
-                    continue
-                format_urls.add(format_url)
-                formats.append({
-                    'url': format_url,
-                    'ext': 'mp4',
-                    'height': height,
-                    'width': width,
-                })
+        for format_id in ('download', 'play'):
+            format_url = url_or_none(video.get('%sAddr' % format_id))
+            if not format_url:
+                continue
+            if format_url in format_urls:
+                continue
+            format_urls.add(format_url)
+            formats.append({
+                'url': format_url,
+                'ext': 'mp4',
+                'height': height,
+                'width': width,
+                'http_headers': {
+                    'Referer': 'https://www.tiktok.com/',
+                }
+            })
         self._sort_formats(formats)
 
-        thumbnail = url_or_none(try_get(
-            video, lambda x: x['cover']['url_list'][0], compat_str))
-        uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
-        timestamp = int_or_none(data.get('create_time'))
-        comment_count = int_or_none(data.get('comment_count')) or int_or_none(
-            try_get(data, lambda x: x['statistics']['comment_count']))
-        repost_count = int_or_none(try_get(
-            data, lambda x: x['statistics']['share_count']))
+        thumbnail = url_or_none(video.get('cover'))
+        duration = float_or_none(video.get('duration'))
 
-        aweme_id = data['aweme_id']
+        uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
+        uploader_id = try_get(data, lambda x: x['author']['id'], compat_str)
+
+        timestamp = int_or_none(data.get('createTime'))
+
+        def stats(key):
+            return int_or_none(try_get(
+                data, lambda x: x['stats']['%sCount' % key]))
+
+        view_count = stats('play')
+        like_count = stats('digg')
+        comment_count = stats('comment')
+        repost_count = stats('share')
+
+        aweme_id = data.get('id') or video_id
 
         return {
             'id': aweme_id,
             'title': uploader or aweme_id,
             'description': description,
             'thumbnail': thumbnail,
+            'duration': duration,
             'uploader': uploader,
+            'uploader_id': uploader_id,
             'timestamp': timestamp,
+            'view_count': view_count,
+            'like_count': like_count,
             'comment_count': comment_count,
             'repost_count': repost_count,
             'formats': formats,
@@ -65,62 +77,56 @@ class TikTokBaseIE(InfoExtractor):
 
 
 class TikTokIE(TikTokBaseIE):
-    _VALID_URL = r'''(?x)
-                        https?://
-                            (?:
-                                (?:m\.)?tiktok\.com/v|
-                                (?:www\.)?tiktok\.com/share/video
-                            )
-                            /(?P<id>\d+)
-                    '''
+    _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@[^/]+/video/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://m.tiktok.com/v/6606727368545406213.html',
-        'md5': 'd584b572e92fcd48888051f238022420',
+        'url': 'https://www.tiktok.com/@zureeal/video/6606727368545406213',
+        'md5': '163ceff303bb52de60e6887fe399e6cd',
         'info_dict': {
             'id': '6606727368545406213',
             'ext': 'mp4',
             'title': 'Zureeal',
             'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
-            'thumbnail': r're:^https?://.*~noop.image',
+            'thumbnail': r're:^https?://.*',
+            'duration': 15,
             'uploader': 'Zureeal',
+            'uploader_id': '188294915489964032',
             'timestamp': 1538248586,
             'upload_date': '20180929',
+            'view_count': int,
+            'like_count': int,
             'comment_count': int,
             'repost_count': int,
         }
-    }, {
-        'url': 'https://www.tiktok.com/share/video/6606727368545406213',
-        'only_matching': True,
     }]
 
+    def _real_initialize(self):
+        # Setup session (will set necessary cookies)
+        self._request_webpage(
+            'https://www.tiktok.com/', None, note='Setting up session')
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            'https://m.tiktok.com/v/%s.html' % video_id, video_id)
+        webpage = self._download_webpage(url, video_id)
         data = self._parse_json(self._search_regex(
-            r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id)
-        return self._extract_aweme(data)
+            r'<script[^>]+\bid=["\']__NEXT_DATA__[^>]+>\s*({.+?})\s*</script',
+            webpage, 'data'), video_id)['props']['pageProps']['itemInfo']['itemStruct']
+        return self._extract_video(data, video_id)
 
 
 class TikTokUserIE(TikTokBaseIE):
-    _VALID_URL = r'''(?x)
-                        https?://
-                            (?:
-                                (?:m\.)?tiktok\.com/h5/share/usr|
-                                (?:www\.)?tiktok\.com/share/user
-                            )
-                            /(?P<id>\d+)
-                    '''
+    _VALID_URL = r'https://(?:www\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
     _TESTS = [{
-        'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html',
+        'url': 'https://www.tiktok.com/@zureeal',
         'info_dict': {
             'id': '188294915489964032',
         },
         'playlist_mincount': 24,
-    }, {
-        'url': 'https://www.tiktok.com/share/user/188294915489964032',
-        'only_matching': True,
     }]
+    _WORKING = False
+
+    @classmethod
+    def suitable(cls, url):
+        return False if TikTokIE.suitable(url) else super(TikTokUserIE, cls).suitable(url)
 
     def _real_extract(self, url):
         user_id = self._match_id(url)
@@ -130,7 +136,7 @@ class TikTokUserIE(TikTokBaseIE):
         entries = []
         for aweme in data['aweme_list']:
             try:
-                entry = self._extract_aweme(aweme)
+                entry = self._extract_video(aweme)
             except ExtractorError:
                 continue
             entry['extractor_key'] = TikTokIE.ie_key()

youtube_dl/extractor/videa.py

@@ -1,16 +1,25 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
 import re
+import string
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
     mimetype2ext,
     parse_codecs,
+    update_url_query,
     xpath_element,
     xpath_text,
 )
+from ..compat import (
+    compat_b64decode,
+    compat_ord,
+    compat_struct_pack,
+)
 
 
 class VideaIE(InfoExtractor):
@@ -19,7 +28,7 @@ class VideaIE(InfoExtractor):
                         videa(?:kid)?\.hu/
                         (?:
                             videok/(?:[^/]+/)*[^?#&]+-|
-                            player\?.*?\bv=|
+                            (?:videojs_)?player\?.*?\bv=|
                             player/v/
                         )
                         (?P<id>[^?#&]+)
@@ -53,6 +62,7 @@ class VideaIE(InfoExtractor):
         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
         'only_matching': True,
     }]
+    _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
 
     @staticmethod
     def _extract_urls(webpage):
@@ -60,26 +70,84 @@ class VideaIE(InfoExtractor):
             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
             webpage)]
 
+    @staticmethod
+    def rc4(cipher_text, key):
+        res = b''
+
+        key_len = len(key)
+        S = list(range(256))
+
+        j = 0
+        for i in range(256):
+            j = (j + S[i] + ord(key[i % key_len])) % 256
+            S[i], S[j] = S[j], S[i]
+
+        i = 0
+        j = 0
+        for m in range(len(cipher_text)):
+            i = (i + 1) % 256
+            j = (j + S[i]) % 256
+            S[i], S[j] = S[j], S[i]
+            k = S[(S[i] + S[j]) % 256]
+            res += compat_struct_pack('B', k ^ compat_ord(cipher_text[m]))
+
+        return res.decode()
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        query = {'v': video_id}
+        player_page = self._download_webpage(
+            'https://videa.hu/player', video_id, query=query)
 
-        info = self._download_xml(
-            'http://videa.hu/videaplayer_get_xml.php', video_id,
-            query={'v': video_id})
+        nonce = self._search_regex(
+            r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
+        l = nonce[:32]
+        s = nonce[32:]
+        result = ''
+        for i in range(0, 32):
+            result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 
-        video = xpath_element(info, './/video', 'video', fatal=True)
-        sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
+        random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
+        query['_s'] = random_seed
+        query['_t'] = result[:16]
+
+        b64_info, handle = self._download_webpage_handle(
+            'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
+        if b64_info.startswith('<?xml'):
+            info = self._parse_xml(b64_info, video_id)
+        else:
+            key = result[16:] + random_seed + handle.headers['x-videa-xs']
+            info = self._parse_xml(self.rc4(
+                compat_b64decode(b64_info), key), video_id)
+
+        video = xpath_element(info, './video', 'video')
+        if not video:
+            raise ExtractorError(xpath_element(
+                info, './error', fatal=True), expected=True)
+        sources = xpath_element(
+            info, './video_sources', 'sources', fatal=True)
+        hash_values = xpath_element(
+            info, './hash_values', 'hash values', fatal=True)
 
         title = xpath_text(video, './title', fatal=True)
 
         formats = []
         for source in sources.findall('./video_source'):
             source_url = source.text
-            if not source_url:
+            source_name = source.get('name')
+            source_exp = source.get('exp')
+            if not (source_url and source_name and source_exp):
                 continue
+            hash_value = xpath_text(hash_values, 'hash_value_' + source_name)
+            if not hash_value:
+                continue
+            source_url = update_url_query(source_url, {
+                'md5': hash_value,
+                'expires': source_exp,
+            })
             f = parse_codecs(source.get('codecs'))
             f.update({
-                'url': source_url,
+                'url': self._proto_relative_url(source_url),
                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
                 'format_id': source.get('name'),
                 'width': int_or_none(source.get('width')),
@@ -88,8 +156,7 @@ class VideaIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        thumbnail = xpath_text(video, './poster_src')
-        duration = int_or_none(xpath_text(video, './duration'))
+        thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 
         age_limit = None
         is_adult = xpath_text(video, './is_adult_content', default=None)
@@ -100,7 +167,7 @@ class VideaIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
-            'duration': duration,
+            'duration': int_or_none(xpath_text(video, './duration')),
             'age_limit': age_limit,
             'formats': formats,
         }

youtube_dl/extractor/youtube.py

@@ -283,6 +283,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     }
 
     _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
+    _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
 
     def _call_api(self, ep, query, video_id):
         data = self._DEFAULT_API_DATA.copy()
@@ -1068,7 +1069,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             },
         },
         {
-            # with '};' inside yt initial data (see https://github.com/ytdl-org/youtube-dl/issues/27093)
+            # with '};' inside yt initial data (see [1])
+            # see [2] for an example with '};' inside ytInitialPlayerResponse
+            # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
+            # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
             'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
             'info_dict': {
                 'id': 'CHqg6qOn4no',
@@ -1686,7 +1690,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not video_info and not player_response:
             player_response = extract_player_response(
                 self._search_regex(
-                    r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;', video_webpage,
+                    (r'%s\s*(?:var\s+meta|</script|\n)' % self._YT_INITIAL_PLAYER_RESPONSE_RE,
+                     self._YT_INITIAL_PLAYER_RESPONSE_RE), video_webpage,
                     'initial player response', default='{}'),
                 video_id)
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.11.24'
+__version__ = '2020.11.29'