Upstream/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-13 04:37:52 +01:00
Code Issues Projects Releases Wiki Activity

[redtube] Fix metadata extraction (closes #15472)

Browse Source
This commit is contained in:
Sergey M․ 2018-02-02 22:32:53 +07:00
parent 9a340af37e
commit 1367c798e3
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
youtube_dl/extractor/redtube.py
View File

@ -46,9 +46,10 @@ class RedTubeIE(InfoExtractor):
raise ExtractorError('Video %s has been removed' % video_id, expected=True) raise ExtractorError('Video %s has been removed' % video_id, expected=True)
title = self._html_search_regex( title = self._html_search_regex(
(r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>', (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
r'videoTitle\s*:\s*(["\'])(?P<title>)\1'), r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
webpage, 'title', group='title') webpage, 'title', group='title',
default=None) or self._og_search_title(webpage)
formats = [] formats = []
sources = self._parse_json( sources = self._parse_json(
@ -87,12 +88,13 @@ class RedTubeIE(InfoExtractor):
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex( upload_date = unified_strdate(self._search_regex(
r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<', r'<span[^>]+>ADDED ([^<]+)<',
webpage, 'upload date', fatal=False)) webpage, 'upload date', fatal=False))
duration = int_or_none(self._search_regex( duration = int_or_none(self._search_regex(
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None)) r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
view_count = str_to_int(self._search_regex( 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)) webpage, 'view count', fatal=False))
# No self-labeling, but they describe themselves as # No self-labeling, but they describe themselves as