diff options
| author | Sergey M․ <dstftw@gmail.com> | 2016-01-09 00:19:36 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-01-09 00:19:36 +0600 |
| commit | 6609b3ce371d08c0464a3caa30c21b61de221508 (patch) | |
| tree | bcbe1daf45e279a90f34d7004f899a96a8de8e6d | |
| parent | 7e182627d9963b8c95faab2f2c6213d17a8db745 (diff) | |
| download | youtube-dl-6609b3ce371d08c0464a3caa30c21b61de221508.tar.gz youtube-dl-6609b3ce371d08c0464a3caa30c21b61de221508.tar.xz youtube-dl-6609b3ce371d08c0464a3caa30c21b61de221508.zip | |
[xhamster] Improve title extraction
| -rw-r--r-- | youtube_dl/extractor/xhamster.py | 5 |
1 files changed, 3 insertions, 2 deletions
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'<title>(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)</title>', - r'<h1(?: itemprop="name")?>([^<]+)</h1>'], webpage, 'title') + [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>', + r'<h1[^>]*>([^<]+)</h1>', + r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title') # Only a few videos have an description mobj = re.search(r'<span>Description: </span>([^<]+)', webpage) |