Ack NMU.

[youtubedl] / youtube_dl / extractor / comedycentral.py

diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index b2453898199ed72da7df13fa90714572fad22133..5b1b99675c760a7249bcdb23ff3072af86710114 100644 (file)
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -16,11 +16,11 @@ from ..utils import (
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/

-        (video-clips|episodes|cc-studios|video-collections|full-episodes)
+        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)

         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {


@@ -29,7 +29,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
             'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
         },
             'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
         },

-    }
+    }, {
+        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
+        'only_matching': True,
+    }]

 
 
 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
 
 
 class ComedyCentralShowsIE(MTVServicesInfoExtractor):


@@ -151,12 +154,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         if mobj.group('shortname'):
         mobj = re.match(self._VALID_URL, url)
 
         if mobj.group('shortname'):

-            if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = 'http://thedailyshow.cc.com/full-episodes/'
-            else:
-                url = 'http://thecolbertreport.cc.com/full-episodes/'
-            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-            assert mobj is not None
+            return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')

 
         if mobj.group('clip'):
             if mobj.group('videotitle'):
 
         if mobj.group('clip'):
             if mobj.group('videotitle'):


@@ -197,11 +195,11 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
             if len(altMovieParams) == 0:
                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
             if len(altMovieParams) == 0:
                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:

-                mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+                mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]

 
         uri = mMovieParams[0][1]
         # Correct cc.com in uri
 
         uri = mMovieParams[0][1]
         # Correct cc.com in uri

-        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)

 
         index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
         idoc = self._download_xml(
 
         index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
         idoc = self._download_xml(


@@ -250,6 +248,8 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                 })
                 self._sort_formats(formats)
 
                 })
                 self._sort_formats(formats)
 

+            subtitles = self._extract_subtitles(cdoc, guid)
+

             virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
             entries.append({
                 'id': guid,
             virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
             entries.append({
                 'id': guid,


@@ -260,6 +260,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                 'duration': duration,
                 'thumbnail': thumbnail,
                 'description': description,
                 'duration': duration,
                 'thumbnail': thumbnail,
                 'description': description,

+                'subtitles': subtitles,

             })
 
         return {
             })
 
         return {