Merge tag 'upstream/2014.07.11'

[youtubedl] / youtube_dl / extractor / redtube.py

diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index 1d2cf1f56df7ae932e67d4cd8253f6441818d80e..4295cf93a75188844bfe0838789e2efcb4363229 100644 (file)
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -1,37 +1,53 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 
 
 class RedTubeIE(InfoExtractor):
 import re
 
 from .common import InfoExtractor
 
 
 class RedTubeIE(InfoExtractor):

-    _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+    _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.redtube.com/66418',
-        u'file': u'66418.mp4',
-        u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
-        u'info_dict': {
-            u"title": u"Sucked on a toilet"
+        'url': 'http://www.redtube.com/66418',
+        'file': '66418.mp4',
+        # md5 varies from time to time, as in
+        # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
+        #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
+        'info_dict': {
+            "title": "Sucked on a toilet",
+            "age_limit": 18,

         }
     }
 
         }
     }
 

-    def _real_extract(self,url):
+    def _real_extract(self, url):

         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')

-        video_extension = 'mp4'        
+        video_extension = 'mp4'

         webpage = self._download_webpage(url, video_id)
 
         self.report_extraction(video_id)
 
         webpage = self._download_webpage(url, video_id)
 
         self.report_extraction(video_id)
 

-        video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
-            webpage, u'video URL')
+        video_url = self._html_search_regex(
+            r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')

 
 

-        video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+        video_title = self._html_search_regex(
+            r'<h1 class="videoTitle[^"]*">(.+?)</h1>',

             webpage, u'title')
 
             webpage, u'title')
 

-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-        }]
+        video_thumbnail = self._html_search_regex(
+            r'playerInnerHTML.+?<img\s+src="(.+?)"',
+            webpage, u'thumbnail', fatal=False)
+
+        # No self-labeling, but they describe themselves as
+        # "Home of Videos Porno"
+        age_limit = 18
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': video_extension,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'age_limit': age_limit,
+        }