release 2020.12.12

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.12. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.12.09
+ [debug] youtube-dl version 2020.12.12
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.12. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.12. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.12. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.12.09
+ [debug] youtube-dl version 2020.12.12
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.12. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
+- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,36 @@
+version 2020.12.12
+
+Core
+* [YoutubeDL] Improve thumbnail filename deducing (#26010, #27244)
+
+Extractors
++ [ruutu] Extract more metadata
++ [ruutu] Detect non-free videos (#21154)
+* [ruutu] Authenticate format URLs (#21031, #26782)
++ [ruutu] Add support for static.nelonenmedia.fi (#25412)
++ [ruutu] Extend URL regular expression (#24839)
++ [facebook] Add support archived live video URLs (#15859)
+* [wdr] Improve overall extraction
++ [wdr] Extend subtitles extraction (#22672, #22723)
++ [facebook] Add support for videos attached to Relay based story pages
+  (#10795)
++ [wdr:page] Add support for kinder.wdr.de (#27350)
++ [facebook] Add another regular expression for handleServerJS
+* [facebook] Fix embed page extraction
++ [facebook] Add support for Relay post pages (#26935)
++ [facebook] Add support for watch videos (#22795, #27062)
++ [facebook] Add support for group posts with multiple videos (#19131)
+* [itv] Fix series metadata extraction (#26897)
+- [itv] Remove old extraction method (#23177)
+* [facebook] Redirect mobile URLs to desktop URLs (#24831, #25624)
++ [facebook] Add support for Relay based pages (#26823)
+* [facebook] Try to reduce unnecessary tahoe requests
+- [facebook] Remove hardcoded Chrome User-Agent (#18974, #25411, #26958,
+  #27329)
+- [smotri] Remove extractor (#27358)
+- [beampro] Remove extractor (#17290, #22871, #23020, #23061, #26099)
+
+
 version 2020.12.09
 
 Core

README.md

@@ -371,7 +371,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      out, youtube-dl will ask interactively.
     -2, --twofactor TWOFACTOR        Two-factor authentication code
     -n, --netrc                      Use .netrc authentication data
-    --video-password PASSWORD        Video password (vimeo, smotri, youku)
+    --video-password PASSWORD        Video password (vimeo, youku)
 
 ## Adobe Pass Options:
     --ap-mso MSO                     Adobe Pass multiple-system operator (TV

docs/supportedsites.md

@@ -501,8 +501,6 @@
  - **mixcloud**
  - **mixcloud:playlist**
  - **mixcloud:user**
- - **Mixer:live**
- - **Mixer:vod**
  - **MLB**
  - **Mnet**
  - **MNetTV**
@@ -817,10 +815,6 @@
  - **Slideshare**
  - **SlidesLive**
  - **Slutload**
- - **smotri**: Smotri.com
- - **smotri:broadcast**: Smotri.com broadcasts
- - **smotri:community**: Smotri.com community videos
- - **smotri:user**: Smotri.com user videos
  - **Snotr**
  - **Sohu**
  - **SonyLIV**

youtube_dl/YoutubeDL.py

@@ -2410,7 +2410,7 @@ class YoutubeDL(object):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+            t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
 
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %

youtube_dl/extractor/facebook.py

@@ -43,7 +43,7 @@ class FacebookIE(InfoExtractor):
                                 video\.php|
                                 video/embed|
                                 story\.php|
-                                watch/?
+                                watch(?:/live)?/?
                             )\?(?:.*?)(?:v|video_id|story_fbid)=|
                             [^/]+/videos/(?:[^/]+/)?|
                             [^/]+/posts/|
@@ -265,6 +265,21 @@ class FacebookIE(InfoExtractor):
             'timestamp': 1606162592,
         },
         'skip': 'Requires logging in',
+    }, {
+        # node.comet_sections.content.story.attached_story.attachments.style_type_renderer.attachment.media
+        'url': 'https://www.facebook.com/groups/ateistiskselskab/permalink/10154930137678856/',
+        'info_dict': {
+            'id': '211567722618337',
+            'ext': 'mp4',
+            'title': 'Facebook video #211567722618337',
+            'uploader_id': '127875227654254',
+            'upload_date': '20161122',
+            'timestamp': 1479793574,
+        },
+    }, {
+        # data.video.creation_story.attachments[].media
+        'url': 'https://www.facebook.com/watch/live/?v=1823658634322275',
+        'only_matching': True,
     }]
     _SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
 
@@ -358,15 +373,15 @@ class FacebookIE(InfoExtractor):
         def extract_video_data(instances):
             video_data = []
             for item in instances:
-                if item[1][0] == 'VideoConfig':
+                if try_get(item, lambda x: x[1][0]) == 'VideoConfig':
                     video_item = item[2][0]
                     if video_item.get('video_id'):
                         video_data.append(video_item['videoData'])
             return video_data
 
         server_js_data = self._parse_json(self._search_regex(
-            r'handleServerJS\(({.+})(?:\);|,")', webpage,
+            [r'handleServerJS\(({.+})(?:\);|,")', r'\bs\.handle\(({.+?})\);'],
-            'server js data', default='{}'), video_id, fatal=False)
+            webpage, 'server js data', default='{}'), video_id, fatal=False)
 
         if server_js_data:
             video_data = extract_video_data(server_js_data.get('instances', []))
@@ -451,7 +466,11 @@ class FacebookIE(InfoExtractor):
                     if not nodes and node:
                         nodes.append(node)
                     for node in nodes:
-                        attachments = try_get(node, lambda x: x['comet_sections']['content']['story']['attachments'], list) or []
+                        story = try_get(node, lambda x: x['comet_sections']['content']['story'], dict) or {}
+                        attachments = try_get(story, [
+                            lambda x: x['attached_story']['attachments'],
+                            lambda x: x['attachments']
+                        ], list) or []
                         for attachment in attachments:
                             attachment = try_get(attachment, lambda x: x['style_type_renderer']['attachment'], dict)
                             ns = try_get(attachment, lambda x: x['all_subattachments']['nodes'], list) or []

youtube_dl/extractor/ruutu.py

@@ -6,14 +6,24 @@ from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     determine_ext,
     ExtractorError,
+    find_xpath_attr,
     int_or_none,
+    unified_strdate,
+    url_or_none,
     xpath_attr,
     xpath_text,
 )
 
 
 class RuutuIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
+                            static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
+                        )
+                        (?P<id>\d+)
+                    '''
     _TESTS = [
         {
             'url': 'http://www.ruutu.fi/video/2058907',
@@ -71,15 +81,53 @@ class RuutuIE(InfoExtractor):
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'age_limit': 0,
             },
-            'expected_warnings': ['HTTP Error 502: Bad Gateway'],
+            'expected_warnings': [
-        }
+                'HTTP Error 502: Bad Gateway',
+                'Failed to download m3u8 information',
+            ],
+        },
+        {
+            'url': 'http://www.supla.fi/audio/2231370',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
+            'only_matching': True,
+        },
+        {
+            # episode
+            'url': 'https://www.ruutu.fi/video/3401964',
+            'info_dict': {
+                'id': '3401964',
+                'ext': 'mp4',
+                'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
+                'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 2582,
+                'age_limit': 12,
+                'upload_date': '20190508',
+                'series': 'Temptation Island Suomi',
+                'season_number': 5,
+                'episode_number': 17,
+                'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # premium
+            'url': 'https://www.ruutu.fi/video/3618715',
+            'only_matching': True,
+        },
     ]
+    _API_BASE = 'https://gatling.nelonenmedia.fi'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         video_xml = self._download_xml(
-            'https://gatling.nelonenmedia.fi/media-xml-cache', video_id,
+            '%s/media-xml-cache' % self._API_BASE, video_id,
             query={'id': video_id})
 
         formats = []
@@ -96,9 +144,18 @@ class RuutuIE(InfoExtractor):
                         continue
                     processed_urls.append(video_url)
                     ext = determine_ext(video_url)
+                    auth_video_url = url_or_none(self._download_webpage(
+                        '%s/auth/access/v2' % self._API_BASE, video_id,
+                        note='Downloading authenticated %s stream URL' % ext,
+                        fatal=False, query={'stream': video_url}))
+                    if auth_video_url:
+                        processed_urls.append(auth_video_url)
+                        video_url = auth_video_url
                     if ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                            video_url, video_id, 'mp4',
+                            entry_protocol='m3u8_native', m3u8_id='hls',
+                            fatal=False))
                     elif ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             video_url, video_id, f4m_id='hds', fatal=False))
@@ -136,18 +193,35 @@ class RuutuIE(InfoExtractor):
 
         extract_formats(video_xml.find('./Clip'))
 
+        def pv(name):
+            node = find_xpath_attr(
+                video_xml, './Clip/PassthroughVariables/variable', 'name', name)
+            if node is not None:
+                return node.get('value')
+
+        if not formats:
             drm = xpath_text(video_xml, './Clip/DRM', default=None)
-        if not formats and drm:
+            if drm:
                 raise ExtractorError('This video is DRM protected.', expected=True)
+            ns_st_cds = pv('ns_st_cds')
+            if ns_st_cds != 'free':
+                raise ExtractorError('This video is %s.' % ns_st_cds, expected=True)
 
         self._sort_formats(formats)
 
+        themes = pv('themes')
+
         return {
             'id': video_id,
             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
-            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
+            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
+            'upload_date': unified_strdate(pv('date_start')),
+            'series': pv('series_name'),
+            'season_number': int_or_none(pv('season_number')),
+            'episode_number': int_or_none(pv('episode_number')),
+            'categories': themes.split(',') if themes else [],
             'formats': formats,
         }

youtube_dl/extractor/wdr.py

@@ -17,6 +17,7 @@ from ..utils import (
     unified_strdate,
     update_url_query,
     urlhandle_detect_ext,
+    url_or_none,
 )
 
 
@@ -42,16 +43,20 @@ class WDRIE(InfoExtractor):
         is_live = metadata.get('mediaType') == 'live'
 
         tracker_data = metadata['trackerData']
+        title = tracker_data['trackerClipTitle']
+
         media_resource = metadata['mediaResource']
 
         formats = []
 
         # check if the metadata contains a direct URL to a file
-        for kind, media_resource in media_resource.items():
+        for kind, media in media_resource.items():
+            if not isinstance(media, dict):
+                continue
             if kind not in ('dflt', 'alt'):
                 continue
 
-            for tag_name, medium_url in media_resource.items():
+            for tag_name, medium_url in media.items():
                 if tag_name not in ('videoURL', 'audioURL'):
                     continue
 
@@ -88,8 +93,16 @@ class WDRIE(InfoExtractor):
                 'url': caption_url,
                 'ext': 'ttml',
             }]
-
+        captions_hash = media_resource.get('captionsHash')
-        title = tracker_data['trackerClipTitle']
+        if isinstance(captions_hash, dict):
+            for ext, format_url in captions_hash.items():
+                format_url = url_or_none(format_url)
+                if not format_url:
+                    continue
+                subtitles.setdefault('de', []).append({
+                    'url': format_url,
+                    'ext': determine_ext(format_url, None) or ext,
+                })
 
         return {
             'id': tracker_data.get('trackerClipId', video_id),
@@ -105,7 +118,7 @@ class WDRIE(InfoExtractor):
 class WDRPageIE(InfoExtractor):
     _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
     _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
-    _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
+    _VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
 
     _TESTS = [
         {
@@ -212,7 +225,11 @@ class WDRPageIE(InfoExtractor):
         {
             'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
             'only_matching': True,
-        }
+        },
+        {
+            'url': 'https://kinder.wdr.de/tv/die-sendung-mit-dem-elefanten/av/video-folge---astronaut-100.html',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.12.09'
+__version__ = '2020.12.12'