+
+
+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)(<div[^>]+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 PornHubPlaylistIE(PornHubPlaylistBaseIE):
+ _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://www.pornhub.com/playlist/4667351',
+ 'info_dict': {
+ 'id': '4667351',
+ 'title': 'Nataly Hot',
+ },
+ 'playlist_mincount': 2,
+ }, {
+ 'url': 'https://de.pornhub.com/playlist/4667351',
+ 'only_matching': True,
+ }]
+
+
+class PornHubUserVideosIE(PornHubPlaylistBaseIE):
+ _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
+ _TESTS = [{
+ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
+ 'info_dict': {
+ 'id': 'zoe_ph',
+ },
+ 'playlist_mincount': 171,
+ }, {
+ 'url': 'http://www.pornhub.com/users/rushandlia/videos',
+ 'only_matching': True,
+ }, {
+ # default sorting as Top Rated Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos',
+ 'info_dict': {
+ 'id': 'povd',
+ },
+ 'playlist_mincount': 293,
+ }, {
+ # Top Rated Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
+ 'only_matching': True,
+ }, {
+ # Most Recent Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
+ 'only_matching': True,
+ }, {
+ # Most Viewed Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host')
+ user_id = mobj.group('id')
+
+ entries = []
+ for page_num in itertools.count(1):
+ try:
+ webpage = self._download_webpage(
+ url, user_id, 'Downloading page %d' % page_num,
+ query={'page': page_num})
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+ break
+ raise
+ page_entries = self._extract_entries(webpage, host)
+ if not page_entries:
+ break
+ entries.extend(page_entries)
+
+ return self.playlist_result(entries, user_id)