aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-02-19 22:15:19 +0600
committerSergey M․ <dstftw@gmail.com>2015-02-19 22:15:19 +0600
commite66e1a0046ca804461c4c9c3e890165ec9d865e1 (patch)
treee5b3c3cec76f69357c2caed143af443b5c0d3b24 /youtube_dl/extractor
parentd5c69f1da41f3e370c500482303196ae845472ed (diff)
[pornhub] Add support for playlists (Closes #4995)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py5
-rw-r--r--youtube_dl/extractor/pornhub.py30
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'))