midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[xhamster] Improve title extraction

Browse source
This commit is contained in:
Sergey M․ 2016-01-09 00:19:36 +06:00
parent 7e182627d9
commit 6609b3ce37
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/xhamster.py
View file

@ -64,8 +64,9 @@ class XHamsterIE(InfoExtractor):
webpage = self._download_webpage(mrss_url, video_id) webpage = self._download_webpage(mrss_url, video_id)
title = self._html_search_regex( title = self._html_search_regex(
[r'<title>(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)</title>', [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>',
r'<h1(?: itemprop="name")?>([^<]+)</h1>'], webpage, 'title') r'<h1[^>]*>([^<]+)</h1>',
r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title')
# Only a few videos have an description # Only a few videos have an description
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage) mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)