0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00

[vporn] More metadata extraction fixes and tests update (#5560)

This commit is contained in:
Sergey M․ 2015-04-30 21:31:38 +06:00
parent cd298882cd
commit 7a03280df4

View file

@ -27,9 +27,6 @@ class VpornIE(InfoExtractor):
'duration': 393, 'duration': 393,
'age_limit': 18, 'age_limit': 18,
'view_count': int, 'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
} }
}, },
{ {
@ -47,9 +44,6 @@ class VpornIE(InfoExtractor):
'duration': 588, 'duration': 588,
'age_limit': 18, 'age_limit': 18,
'view_count': int, 'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
} }
}, },
] ]
@ -72,10 +66,10 @@ def _real_extract(self, url):
thumbnail = 'http://www.vporn.com' + thumbnail thumbnail = 'http://www.vporn.com' + thumbnail
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'(?s)Uploaded by:.*?<a href="/user/[^"]+">([^<]+)</a>', r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'Runtime:\s*</span>\s*(\d+ min \d+ sec)', r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',