New upstream version 2020.07.28

diff --git a/ChangeLog b/ChangeLog
index 07d6ccd69d61ee47f7130a24b65f0affbf15ef4d..bf515f784b2cfefdcd29820c5a5e22e8057cfa5e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+version 2020.07.28
+
+Extractors
+* [youtube] Fix sigfunc name extraction (#26134, #26135, #26136, #26137)
+* [youtube] Improve description extraction (#25937, #25980)
+* [wistia] Restrict embed regular expression (#25969)
+* [youtube] Prevent excess HTTP 301 (#25786)
++ [youtube:playlists] Extend URL regular expression (#25810)
++ [bellmedia] Add support for cp24.com clip URLs (#25764)
+* [brightcove] Improve embed detection (#25674)
+
+

 version 2020.06.16.1
 
 Extractors
 version 2020.06.16.1
 
 Extractors

diff --git a/youtube-dl b/youtube-dl
index a806646f03ba8a1dde4fb51acf947e7f9b692277..d0d0d2a09573e08159942e494dc6358e63b9bf2c 100755 (executable)
Binary files a/youtube-dl and b/youtube-dl differ

diff --git a/youtube_dl/extractor/bellmedia.py b/youtube_dl/extractor/bellmedia.py
index 485173774d9f9c2534f9b18f1668a8d5fb204dc9..9f9de96c61332ac405b33bfc1f5758f2c8fd6456 100644 (file)
--- a/youtube_dl/extractor/bellmedia.py
+++ b/youtube_dl/extractor/bellmedia.py
@@ -25,8 +25,8 @@ class BellMediaIE(InfoExtractor):
                 etalk|
                 marilyn
             )\.ca|
                 etalk|
                 marilyn
             )\.ca|

-            much\.com
-        )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
+            (?:much|cp24)\.com
+        )/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''

     _TESTS = [{
         'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
         'md5': '36d3ef559cfe8af8efe15922cd3ce950',
     _TESTS = [{
         'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
         'md5': '36d3ef559cfe8af8efe15922cd3ce950',


@@ -62,6 +62,9 @@ class BellMediaIE(InfoExtractor):
     }, {
         'url': 'http://www.etalk.ca/video?videoid=663455',
         'only_matching': True,
     }, {
         'url': 'http://www.etalk.ca/video?videoid=663455',
         'only_matching': True,

+    }, {
+        'url': 'https://www.cp24.com/video?clipId=1982548',
+        'only_matching': True,

     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',
     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',

diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index 5c22a730db98b77cab1db2c5503b493b162e9c9a..2aa9f4782e0dfdb2b78225c2d1fe83a8568effe3 100644 (file)
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -426,7 +426,7 @@ class BrightcoveNewIE(AdobePassIE):
         # [2] looks like:
         for video, script_tag, account_id, player_id, embed in re.findall(
                 r'''(?isx)
         # [2] looks like:
         for video, script_tag, account_id, player_id, embed in re.findall(
                 r'''(?isx)

-                    (<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
+                    (<video(?:-js)?\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)

                     (?:.*?
                         (<script[^>]+
                             src=["\'](?:https?:)?//players\.brightcove\.net/
                     (?:.*?
                         (<script[^>]+
                             src=["\'](?:https?:)?//players\.brightcove\.net/

diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py
index 168e5e90152b44d76dcbbbeb1b274db5dcbf5827..77febd2eb1b1cada3942c212739725135a36682b 100644 (file)
--- a/youtube_dl/extractor/wistia.py
+++ b/youtube_dl/extractor/wistia.py
@@ -56,7 +56,7 @@ class WistiaIE(InfoExtractor):
             urls.append(unescapeHTML(match.group('url')))
         for match in re.finditer(
                 r'''(?sx)
             urls.append(unescapeHTML(match.group('url')))
         for match in re.finditer(
                 r'''(?sx)

-                    <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
+                    <div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1

                 ''', webpage):
             urls.append('wistia:%s' % match.group('id'))
         for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
                 ''', webpage):
             urls.append('wistia:%s' % match.group('id'))
         for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 1bc79e01478445ede9a2b3a0f1d4ebea38ce7534..b35bf03aafc7c7c45b3c35735a68d00f86aed988 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -303,7 +303,7 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(

-                        'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                        'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,

                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
                         transform_source=uppercase_escape,
                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
                         transform_source=uppercase_escape,


@@ -1384,7 +1384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',

-             r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+             r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',

              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',


@@ -1930,7 +1930,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:

-            video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
+            video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage)

 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):
 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):


@@ -2776,7 +2776,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):

-            url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
+            url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)

             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(
             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(


@@ -3116,7 +3116,7 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor):
 
 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com user/channel playlists'
 
 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com user/channel playlists'

-    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
+    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'

     IE_NAME = 'youtube:playlists'
 
     _TESTS = [{
     IE_NAME = 'youtube:playlists'
 
     _TESTS = [{


@@ -3142,6 +3142,9 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
             'title': 'Chem Player',
         },
         'skip': 'Blocked',
             'title': 'Chem Player',
         },
         'skip': 'Blocked',

+    }, {
+        'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
+        'only_matching': True,

     }]
 
 
     }]
 
 


@@ -3286,7 +3289,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 break
 
             more = self._download_json(
                 break
 
             more = self._download_json(

-                'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
+                'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,

                 'Downloading page #%s' % page_num,
                 transform_source=uppercase_escape,
                 headers=self._YOUTUBE_CLIENT_HEADERS)
                 'Downloading page #%s' % page_num,
                 transform_source=uppercase_escape,
                 headers=self._YOUTUBE_CLIENT_HEADERS)

diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index 6b88eb38caeff63388f753e5afecf7320269c4a5..17101fa47501d9bae1d6f223e35d7cb4dd3f8d5e 100644 (file)
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-__version__ = '2020.06.16.1'
+__version__ = '2020.07.28'