[youtube] Force old layout for each webpage (closes #14083)

[youtube-dl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 4597ccb3ac94d75fb90028a6da92b6cbf80c4cdb..953e38227e60e6fa08bac62b6ab56cb3f3be8b6e 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
 from ..swfinterp import SWFInterpreter
 from ..compat import (
     compat_chr,
+    compat_kwargs,
     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
@@ -245,6 +246,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         return True
 
+    def _download_webpage(self, *args, **kwargs):
+        kwargs.setdefault('query', {})['disable_polymer'] = 'true'
+        return super(YoutubeBaseInfoExtractor, self)._download_webpage(
+            *args, **compat_kwargs(kwargs))
+
     def _real_initialize(self):
         if self._downloader is None:
             return
@@ -1003,6 +1009,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'Skipping DASH manifest',
             ],
         },
+        {
+            # The following content has been identified by the YouTube community
+            # as inappropriate or offensive to some audiences.
+            'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
+            'info_dict': {
+                'id': '6SJNVb0GnPI',
+                'ext': 'mp4',
+                'title': 'Race Differences in Intelligence',
+                'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
+                'duration': 965,
+                'upload_date': '20140124',
+                'uploader': 'New Century Foundation',
+                'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
+                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
+                'license': 'Standard YouTube License',
+                'view_count': int,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # itag 212
             'url': '1t24XAntNCY',
@@ -1437,9 +1464,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if dash_mpd and dash_mpd[0] not in dash_mpds:
                 dash_mpds.append(dash_mpd[0])
 
+        is_live = None
+        view_count = None
+
+        def extract_view_count(v_info):
+            return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
+
         # Get video info
         embed_webpage = None
-        is_live = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
@@ -1509,6 +1541,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         continue
                     get_video_info = compat_parse_qs(video_info_webpage)
                     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
                     if 'token' in get_video_info:
@@ -1592,10 +1626,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 return self.playlist_result(entries, video_id, video_title, video_description)
             self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
 
-        if 'view_count' in video_info:
-            view_count = int(video_info['view_count'][0])
-        else:
-            view_count = None
+        if view_count is None:
+            view_count = extract_view_count(video_info)
 
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
@@ -1639,10 +1671,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not upload_date:
             upload_date = self._search_regex(
                 [r'(?s)id="eow-date.*?>(.*?)</span>',
-                 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
                 video_webpage, 'upload date', default=None)
-            if upload_date:
-                upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
         upload_date = unified_strdate(upload_date)
 
         video_license = self._html_search_regex(
@@ -1660,7 +1690,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     <a[^>]*
                         (?:
                             \bhref=["\']/red[^>]*>|             # drop possible
-                            >\s*Listen ad-free with YouTube Red # YouTube Red ad 
+                            >\s*Listen ad-free with YouTube Red # YouTube Red ad
                         )
                     .*?
                 )?</li
@@ -2028,7 +2058,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                      |
                         (%(playlist_id)s)
                      )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
-    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
+    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
     IE_NAME = 'youtube:playlist'
     _TESTS = [{