X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/532a08904ffbacc5e5ccf99edb660c5f37ddb213..725f8b2d4cc43b8401946dfed69d22cfe40810fc:/youtube_dl/extractor/pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 1dcc8df..23e24d2 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -115,12 +115,13 @@ class PornHubIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        self._set_cookie('pornhub.com', 'age_verified', '1')
+
         def dl_webpage(platform):
+            self._set_cookie('pornhub.com', 'platform', platform)
             return self._download_webpage(
                 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
-                video_id, headers={
-                    'Cookie': 'age_verified=1; platform=%s' % platform,
-                })
+                video_id)
 
         webpage = dl_webpage('pc')
 
@@ -186,7 +187,7 @@ class PornHubIE(InfoExtractor):
             title, thumbnail, duration = [None] * 3
 
         video_uploader = self._html_search_regex(
-            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
 
         view_count = self._extract_count(
@@ -227,13 +228,20 @@ class PornHubIE(InfoExtractor):
 
 class PornHubPlaylistBaseIE(InfoExtractor):
     def _extract_entries(self, webpage):
+        # 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).
+        container = self._search_regex(
+            r'(?s)(<div[^>]+class=["\']container.+)', webpage,
+            'container', default=webpage)
+
         return [
             self.url_result(
                 'http://www.pornhub.com/%s' % 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="([^"]+)"',
-                webpage))
+                container))
         ]
 
     def _real_extract(self, url):
@@ -241,26 +249,22 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
 
-        # 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).
-        container = self._search_regex(
-            r'(?s)(<div[^>]+class=["\']container.+)', webpage,
-            'container', default=webpage)
-
-        entries = self._extract_entries(container)
+        entries = self._extract_entries(webpage)
 
         playlist = self._parse_json(
             self._search_regex(
-                r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
-            playlist_id)
+                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, playlist.get('title'), playlist.get('description'))
+            entries, playlist_id, title, playlist.get('description'))
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {
@@ -268,11 +272,14 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
             'title': 'Nataly Hot',
         },
         'playlist_mincount': 2,
+    }, {
+        'url': 'https://de.pornhub.com/playlist/4667351',
+        'only_matching': True,
     }]
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos'
     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {
@@ -282,6 +289,28 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
     }, {
         '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,
     }]
 
     def _real_extract(self, url):
@@ -296,6 +325,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
                     break
+                raise
             page_entries = self._extract_entries(webpage)
             if not page_entries:
                 break