Merge tag 'upstream/2015.05.15'

[youtubedl] / youtube_dl / extractor / redtube.py

diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index c2254ae8abdca2ab9dde2388fb2182b056ffd0e2..d6054d7175fd49a22117dd357bea7905f6e739be 100644 (file)
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -1,46 +1,45 @@
-import re
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

+from ..utils import ExtractorError

 
 
 class RedTubeIE(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',
-        # md5 varies from time to time, as in
-        # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
-        #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
-        u'info_dict': {
-            u"title": u"Sucked on a toilet",
-            u"age_limit": 18,
+        'url': 'http://www.redtube.com/66418',
+        'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
+        'info_dict': {
+            'id': '66418',
+            'ext': 'mp4',
+            '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')
-        video_extension = 'mp4'
+        video_id = self._match_id(url)

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

-        self.report_extraction(video_id)
+        if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
+            raise ExtractorError('Video %s has been removed' % video_id, expected=True)

 
         video_url = self._html_search_regex(
 
         video_url = self._html_search_regex(

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

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

-            webpage, u'title')
+            webpage, 'title')
+        video_thumbnail = self._og_search_thumbnail(webpage)

 
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"
         age_limit = 18
 
         return {
 
         # 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,
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': video_title,
+            'thumbnail': video_thumbnail,

             'age_limit': age_limit,
         }
             'age_limit': age_limit,
         }