]+\bhref=[^>]+>([^<]+)', div)
info = self._search_json_ld(webpage, video_id, default={})
# description provided in JSON-LD is irrelevant
info['description'] = None
return merge_dicts({
'id': video_id,
'uploader': video_uploader,
'upload_date': upload_date,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
'tags': extract_list('tags'),
'categories': extract_list('categories'),
'subtitles': subtitles,
}, info)
class PornHubPlaylistBaseIE(PornHubBaseIE):
def _extract_entries(self, webpage, host):
# Only process container div with main playlist content skipping
# drop-down menu that uses similar pattern for videos (see
# https://github.com/ytdl-org/youtube-dl/issues/11594).
container = self._search_regex(
r'(?s)(]+class=["\']container.+)', webpage,
'container', default=webpage)
return [
self.url_result(
'http://www.%s/%s' % (host, video_url),
PornHubIE.ie_key(), video_title=title)
for video_url, title in orderedSet(re.findall(
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
container))
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
playlist_id = mobj.group('id')
webpage = self._download_webpage(url, playlist_id)
entries = self._extract_entries(webpage, host)
playlist = self._parse_json(
self._search_regex(
r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
'playlist', default='{}'),
playlist_id, fatal=False)
title = playlist.get('title') or self._search_regex(
r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
return self.playlist_result(
entries, playlist_id, title, playlist.get('description'))
class PornHubUserIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?Phttps?://(?:[^/]+\.)?(?Ppornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
}, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious',
'info_dict': {
'id': 'liz-vicious',
},
'playlist_mincount': 118,
}, {
'url': 'https://www.pornhub.com/users/russianveet69',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/channels/povd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('id')
return self.url_result(
'%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
video_id=user_id)
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
@staticmethod
def _has_more(webpage):
return re.search(
r'''(?x)
]+\bclass=["\']page_next|
]+\brel=["\']next|