diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-12-05 22:42:02 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-12-05 22:42:02 +0700 |
| commit | 61d18c8a4bc91602738bfd2e506c3cbbc3a3788b (patch) | |
| tree | 0fb3dbdd34346ecf536591b801f6044229583d44 | |
| parent | c94427dd60f9836e3752077977cae3b4d0da47d1 (diff) | |
[porncom] Fix metadata extraction (closes #14911)
| -rw-r--r-- | youtube_dl/extractor/porncom.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/youtube_dl/extractor/porncom.py b/youtube_dl/extractor/porncom.py index 8218c7d3b..60ade06da 100644 --- a/youtube_dl/extractor/porncom.py +++ b/youtube_dl/extractor/porncom.py @@ -77,12 +77,14 @@ class PornComIE(InfoExtractor): self._sort_formats(formats) view_count = str_to_int(self._search_regex( - r'class=["\']views["\'][^>]*><p>([\d,.]+)', webpage, + (r'Views:\s*</span>\s*<span>\s*([\d,.]+)', + r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage, 'view count', fatal=False)) def extract_list(kind): s = self._search_regex( - r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize(), + (r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(), + r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()), webpage, kind, fatal=False) return re.findall(r'<a[^>]+>([^<]+)</a>', s or '') |