Merge remote-tracking branch 'AGSPhoenix/teamcoco-fix'

[youtube-dl] / youtube_dl / extractor / comedycentral.py

diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 1c29ddeb29321b2aa60dcd98e55ea52be49b3101..0c99887a2e4ef7f3d1b2a75f605553119da16b3b 100644 (file)
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -8,7 +8,7 @@ from ..utils import (
     compat_str,
     compat_urllib_parse,
     ExtractorError,
-    int_or_none,
+    float_or_none,
     unified_strdate,
 )
 
@@ -41,13 +41,15 @@ class ComedyCentralShowsIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
                       |https?://(:www\.)?
                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
-                         (full-episodes/(?P<episode>.*)|
+                         (full-episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                              (?:(?:guests/[^/]+|videos)/[^/]+/(?P<videotitle>[^/?#]+))
+                              |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
+                          )|
                           (?P<interview>
-                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
-                     $'''
+                              extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+                     (?:[?#].*|$)'''
     _TEST = {
         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
@@ -57,7 +59,7 @@ class ComedyCentralShowsIE(InfoExtractor):
             'upload_date': '20121213',
             'description': 'Kristen Stewart learns to let loose in "On the Road."',
             'uploader': 'thedailyshow',
-            'title': 'thedailyshow-kristen-stewart part 1',
+            'title': 'thedailyshow kristen-stewart part 1',
         }
     }
 
@@ -102,7 +104,9 @@ class ComedyCentralShowsIE(InfoExtractor):
             assert mobj is not None
 
         if mobj.group('clip'):
-            if mobj.group('showname') == 'thedailyshow':
+            if mobj.group('videotitle'):
+                epTitle = mobj.group('videotitle')
+            elif mobj.group('showname') == 'thedailyshow':
                 epTitle = mobj.group('tdstitle')
             else:
                 epTitle = mobj.group('cntitle')
@@ -134,13 +138,16 @@ class ComedyCentralShowsIE(InfoExtractor):
             # a URL prefix; so extract the alternate reference
             # and then add the URL prefix manually.
 
-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
+            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
+        # Correct cc.com in uri
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.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, epTitle,
@@ -156,9 +163,9 @@ class ComedyCentralShowsIE(InfoExtractor):
             thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
 
             content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
-            duration = int_or_none(content.attrib.get('duration'))
+            duration = float_or_none(content.attrib.get('duration'))
             mediagen_url = content.attrib['url']
-            guid = itemEl.find('.//guid').text.rpartition(':')[-1]
+            guid = itemEl.find('./guid').text.rpartition(':')[-1]
 
             cdoc = self._download_xml(
                 mediagen_url, epTitle,
@@ -188,7 +195,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 })
                 self._sort_formats(formats)
 
-            virtual_id = show_name + '-' + epTitle + ' part ' + compat_str(part_num + 1)
+            virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
             entries.append({
                 'id': guid,
                 'title': virtual_id,
@@ -203,6 +210,6 @@ class ComedyCentralShowsIE(InfoExtractor):
         return {
             '_type': 'playlist',
             'entries': entries,
-            'title': title,
+            'title': show_name + ' ' + title,
             'description': description,
         }