diff options
| author | Sergey M․ <dstftw@gmail.com> | 2020-03-03 06:23:39 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2020-03-03 06:23:39 +0700 |
| commit | 46cc54ca8f13c7b823c1a12446cdd76d060c74b6 (patch) | |
| tree | 4405aa44fd49cf2fbdf1e518a7682c29a3a0b146 | |
| parent | 1e1c1960aa154a6e257e83e94e86ee6dc8b0b362 (diff) | |
| download | youtube-dl-46cc54ca8f13c7b823c1a12446cdd76d060c74b6.tar.gz youtube-dl-46cc54ca8f13c7b823c1a12446cdd76d060c74b6.tar.xz youtube-dl-46cc54ca8f13c7b823c1a12446cdd76d060c74b6.zip | |
[pornhub] Improve title extraction (closes #24184)
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index b3251ccd9..b8f65af7c 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -189,10 +189,10 @@ class PornHubIE(PornHubBaseIE): # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. title = self._html_search_meta( - 'twitter:title', webpage, default=None) or self._search_regex( - (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', - r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', - r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), + 'twitter:title', webpage, default=None) or self._html_search_regex( + (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', + r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), webpage, 'title', group='title') video_urls = [] |