diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 30 |
2 files changed, 34 insertions, 1 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c2424ed48..9b5855768 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -353,7 +353,10 @@ from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE -from .pornhub import PornHubIE +from .pornhub import ( + PornHubIE, + PornHubPlaylistIE, +) from .pornotube import PornotubeIE from .pornoxo import PornoXOIE from .promptfile import PromptFileIE diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index fb2032832..913995044 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -110,3 +110,33 @@ class PornHubIE(InfoExtractor): 'formats': formats, 'age_limit': 18, } + + +class PornHubPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.pornhub.com/playlist/6201671', + 'info_dict': { + 'id': '6201671', + 'title': 'P0p4', + }, + 'playlist_mincount': 35, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') + for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage)) + ] + + playlist = self._parse_json( + self._search_regex( + r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'), + playlist_id) + + return self.playlist_result( + entries, playlist_id, playlist.get('title'), playlist.get('description')) |