comedycentral: 1 seems to be the constant correct offset

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index a1245a8..1b2ccae 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -15,7 +15,7 @@ __author__  = (
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.06-phihag'
+__version__ = '2011.09.09-phihag'
 
 UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
 
@@ -3074,13 +3074,22 @@ class ComedyCentralIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
                        return
 
-               mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:.*?:)(.*?))"/>', html)
+               mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
                if len(mMovieParams) == 0:
                        self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
                        return
-               ACT_COUNT = 4
+               show_id = mMovieParams[0][2]
+               ACT_COUNT = { # TODO: Detect this dynamically
+                       'thedailyshow.com': 4,
+                       'colbertnation.com': 3,
+               }.get(show_id, 4)
+               OFFSET = {
+                       'thedailyshow.com': 1,
+                       'colbertnation.com': 1,
+               }.get(show_id, 1)
+
                first_player_url = mMovieParams[0][0]
-               mediaNum = int(mMovieParams[0][2]) - ACT_COUNT
+               startMediaNum = int(mMovieParams[0][3]) + OFFSET
                movieId = mMovieParams[0][1]
 
                playerReq = urllib2.Request(first_player_url)
@@ -3093,7 +3102,8 @@ class ComedyCentralIE(InfoExtractor):
                player_url = playerResponse.geturl()
 
                for actNum in range(ACT_COUNT):
-                       mediaId = movieId + str(mediaNum + actNum)
+                       mediaNum = startMediaNum + actNum
+                       mediaId = movieId + str(mediaNum)
                        configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                                                urllib.urlencode({'uri': mediaId}))
                        configReq = urllib2.Request(configUrl)
@@ -3103,36 +3113,42 @@ class ComedyCentralIE(InfoExtractor):
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
                                return
-       
+
                        cdoc = xml.etree.ElementTree.fromstring(configXml)
                        turls = []
                        for rendition in cdoc.findall('.//rendition'):
                                finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
                                turls.append(finfo)
 
+                       if len(turls) == 0:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+                               continue
+
                        # For now, just pick the highest bitrate
                        format,video_url = turls[-1]
 
                        self._downloader.increment_downloads()
-                       actTitle = 'act' + str(actNum+1)
+
+                       effTitle = show_id.replace('.com', '') + '-' + epTitle
                        info = {
-                               'id': epTitle,
+                               'id': str(mediaNum),
                                'url': video_url,
-                               'uploader': 'NA',
+                               'uploader': show_id,
                                'upload_date': 'NA',
-                               'title': actTitle,
-                               'stitle': self._simplify_title(actTitle),
+                               'title': effTitle,
+                               'stitle': self._simplify_title(effTitle),
                                'ext': 'mp4',
                                'format': format,
                                'thumbnail': None,
                                'description': 'TODO: Not yet supported',
                                'player_url': player_url
                        }
-       
+
                        try:
                                self._downloader.process_info(info)
                        except UnavailableVideoError, err:
-                               self._downloader.trouble(u'\nERROR: unable to download video')
+                               self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+                               continue
 
 
 class PostProcessor(object):