From: Sergey M․ Date: Fri, 8 Jan 2016 18:19:36 +0000 (+0600) Subject: [xhamster] Improve title extraction X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=commitdiff_plain;h=6609b3ce371d08c0464a3caa30c21b61de221508 [xhamster] Improve title extraction --- diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 261d323a7..97355d17f 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -64,8 +64,9 @@ class XHamsterIE(InfoExtractor): webpage = self._download_webpage(mrss_url, video_id) title = self._html_search_regex( - [r'(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)', - r'([^<]+)'], webpage, 'title') + [r']*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)', + r']*>([^<]+)', + r']+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title') # Only a few videos have an description mobj = re.search(r'Description: ([^<]+)', webpage)