]+\bhref=[^>]+>([^<]+)', div)
return {
'id': video_id,
- 'url': video_url,
'uploader': video_uploader,
+ 'upload_date': upload_date,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
@@ -219,25 +357,26 @@ class PornHubIE(InfoExtractor):
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
- # 'formats': formats,
+ 'formats': formats,
'age_limit': 18,
- 'tags': tags,
- 'categories': categories,
+ 'tags': extract_list('tags'),
+ 'categories': extract_list('categories'),
+ 'subtitles': subtitles,
}
-class PornHubPlaylistBaseIE(InfoExtractor):
- def _extract_entries(self, webpage):
+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/rg3/youtube-dl/issues/11594).
+ # 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.pornhub.com/%s' % video_url,
+ '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="([^"]+)"',
@@ -245,11 +384,13 @@ class PornHubPlaylistBaseIE(InfoExtractor):
]
def _real_extract(self, url):
- playlist_id = self._match_id(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)
+ entries = self._extract_entries(webpage, host)
playlist = self._parse_json(
self._search_regex(
@@ -263,34 +404,99 @@ class PornHubPlaylistBaseIE(InfoExtractor):
entries, playlist_id, title, playlist.get('description'))
-class PornHubPlaylistIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P\d+)'
+class PornHubUserIE(PornHubPlaylistBaseIE):
+ _VALID_URL = r'(?Phttps?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
- 'url': 'http://www.pornhub.com/playlist/4667351',
+ 'url': 'https://www.pornhub.com/model/zoe_ph',
+ 'playlist_mincount': 118,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious',
'info_dict': {
- 'id': '4667351',
- 'title': 'Nataly Hot',
+ 'id': 'liz-vicious',
},
- 'playlist_mincount': 2,
+ '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|
+