[youporn] Fix metadata extraction

pull/8/head
Sergey M․ 9 years ago
parent 80ae228b34
commit 2c3322e36e
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

@ -17,7 +17,7 @@ class YouPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '71ec5fcfddacf80f495efa8b6a8d9a89', 'md5': '3744d24c50438cf5b6f6d59feb5055c2',
'info_dict': { 'info_dict': {
'id': '505835', 'id': '505835',
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily', 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
@ -121,21 +121,21 @@ class YouPornIE(InfoExtractor):
webpage, 'thumbnail', fatal=False, group='thumbnail') webpage, 'thumbnail', fatal=False, group='thumbnail')
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoBy(?:\s+[^"\']+)?["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>', r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex( upload_date = unified_strdate(self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>', r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
webpage, 'upload date', fatal=False)) webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
average_rating = int_or_none(self._search_regex( average_rating = int_or_none(self._search_regex(
r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>', r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
webpage, 'average rating', fatal=False)) webpage, 'average rating', fatal=False))
view_count = str_to_int(self._search_regex( view_count = str_to_int(self._search_regex(
r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>', r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False, group='count'))
comment_count = str_to_int(self._search_regex( comment_count = str_to_int(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)', r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', fatal=False)) webpage, 'comment count', fatal=False))

Loading…
Cancel
Save