github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[cracked] Fix extraction

Browse source
This commit is contained in:
Sergey M․ 2015-04-23 21:44:51 +06:00
parent cd9fdccde0
commit b46ed49996
1 changed files with 13 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/cracked.py
View file

@ -33,17 +33,25 @@ def _real_extract(self, url):
video_url = self._html_search_regex( video_url = self._html_search_regex(
[r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL') [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
title = self._og_search_title(webpage) title = self._search_regex(
description = self._og_search_description(webpage) [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
webpage, 'title')
timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False) description = self._search_regex(
r'name="?(?:og:)?description"?\s+content="([^"]+)"',
webpage, 'description', default=None)
timestamp = self._html_search_regex(
r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
if timestamp: if timestamp:
timestamp = parse_iso8601(timestamp[:-6]) timestamp = parse_iso8601(timestamp[:-6])
view_count = str_to_int(self._html_search_regex( view_count = str_to_int(self._html_search_regex(
r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False)) r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex( comment_count = str_to_int(self._html_search_regex(
r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False)) r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url) m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
if m: if m: