diff options
| author | Sergey M․ <dstftw@gmail.com> | 2019-01-09 00:37:01 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2019-01-09 00:37:01 +0700 |
| commit | 6089ff40e7cc7710e399db1be87fea103a190ee6 (patch) | |
| tree | 71f9b9a81d89ac11588abe38c2ecf9dd1650a002 | |
| parent | 2543938bbe393ceef8dca6a69b441d54df099107 (diff) | |
[youporn] Fix title and description extraction (closes #18748)
| -rw-r--r-- | youtube_dl/extractor/youporn.py | 14 |
1 files changed, 8 insertions, 6 deletions
diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index ea0bce784..d4eccb4b2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor): request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) - title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], - webpage, 'title', group='title', - default=None) or self._og_search_title( + title = self._html_search_regex( + r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', + webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or self._html_search_meta( 'title', webpage, fatal=True) @@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>', + webpage, 'description', + default=None) or self._og_search_description( + webpage, default=None) thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail') |