Skip to content

Commit

Permalink
[redtube] Fix metadata extraction (closes #15472)
Browse files Browse the repository at this point in the history
  • Loading branch information
dstftw committed Feb 2, 2018
1 parent 9a340af commit 1367c79
Showing 1 changed file with 7 additions and 5 deletions.
12 changes: 7 additions & 5 deletions youtube_dl/extractor/redtube.py
Original file line number Diff line number Diff line change
Expand Up @@ -46,9 +46,10 @@ def _real_extract(self, url):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)

title = self._html_search_regex(
(r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>',
r'videoTitle\s*:\s*(["\'])(?P<title>)\1'),
webpage, 'title', group='title')
(r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
webpage, 'title', group='title',
default=None) or self._og_search_title(webpage)

formats = []
sources = self._parse_json(
Expand Down Expand Up @@ -87,12 +88,13 @@ def _real_extract(self, url):

thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
r'<span[^>]+>ADDED ([^<]+)<',
webpage, 'upload date', fatal=False))
duration = int_or_none(self._search_regex(
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
view_count = str_to_int(self._search_regex(
r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
(r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'),
webpage, 'view count', fatal=False))

# No self-labeling, but they describe themselves as
Expand Down

0 comments on commit 1367c79

Please sign in to comment.