New upstream version 2017.02.07

[youtubedl] / youtube_dl / extractor / pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 40dbe6967fac2126b7bf6e6a1245768b3c039c8e..017f6c55219ff3db0cf9bf745f74031882f12c54 100644 (file)
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -156,7 +156,12 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 

-        video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))
+        video_urls = []
+        for quote, video_url in re.findall(
+                r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage):
+            video_urls.append(compat_urllib_parse_unquote(re.sub(
+                r'{0}\s*\+\s*{0}'.format(quote), '', video_url)))
+

         if webpage.find('"encrypted":true') != -1:
             password = compat_urllib_parse_unquote_plus(
                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
         if webpage.find('"encrypted":true') != -1:
             password = compat_urllib_parse_unquote_plus(
                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))


@@ -229,7 +234,14 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
 
 
         webpage = self._download_webpage(url, playlist_id)
 

-        entries = self._extract_entries(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)
+
+        entries = self._extract_entries(container)

 
         playlist = self._parse_json(
             self._search_regex(
 
         playlist = self._parse_json(
             self._search_regex(


@@ -243,12 +255,12 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
     _TESTS = [{
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
     _TESTS = [{

-        'url': 'http://www.pornhub.com/playlist/6201671',
+        'url': 'http://www.pornhub.com/playlist/4667351',

         'info_dict': {
         'info_dict': {

-            'id': '6201671',
-            'title': 'P0p4',
+            'id': '4667351',
+            'title': 'Nataly Hot',

         },
         },

-        'playlist_mincount': 35,
+        'playlist_mincount': 2,

     }]
 
 
     }]