justin.tv tweaks

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index f811af5d17260d7f0a2f10b51884e0d365c46551..4f87eeb3927ef72be525e616e4ac0cd8082aa96b 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -2333,7 +2333,6 @@ class ComedyCentralIE(InfoExtractor):
                               (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
                      $"""
-    IE_NAME = u'comedycentral'
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
@@ -2405,6 +2404,7 @@ class ComedyCentralIE(InfoExtractor):
         try:
             htmlHandle = compat_urllib_request.urlopen(req)
             html = htmlHandle.read()
+            webpage = html.decode('utf-8')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
             return
@@ -2419,14 +2419,14 @@ class ComedyCentralIE(InfoExtractor):
                 return
             epTitle = mobj.group('episode')
 
-        mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html)
+        mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
 
         if len(mMovieParams) == 0:
             # The Colbert Report embeds the information in a without
             # a URL prefix; so extract the alternate reference
             # and then add the URL prefix manually.
 
-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html)
+            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
                 self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
                 return
@@ -2446,7 +2446,7 @@ class ComedyCentralIE(InfoExtractor):
 
         idoc = xml.etree.ElementTree.fromstring(indexXml)
         itemEls = idoc.findall('.//item')
-        for itemEl in itemEls:
+        for partNum,itemEl in enumerate(itemEls):
             mediaId = itemEl.findall('./guid')[0].text
             shortMediaId = mediaId.split(':')[-1]
             showId = mediaId.split(':')[-2].replace('.com', '')
@@ -2495,7 +2495,7 @@ class ComedyCentralIE(InfoExtractor):
             base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
             video_url = base + m.group('finalid')
 
-            effTitle = showId + u'-' + epTitle
+            effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
             info = {
                 'id': shortMediaId,
                 'url': video_url,
@@ -3524,17 +3524,23 @@ class JustinTVIE(InfoExtractor):
             return
 
         response = json.loads(webpage)
+        if type(response) != list:
+            error_text = response.get('error', 'unknown error')
+            self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
+            return
         info = []
         for clip in response:
             video_url = clip['video_file_url']
             if video_url:
                 video_extension = os.path.splitext(video_url)[1][1:]
-                video_date = re.sub('-', '', clip['created_on'][:10])
+                video_date = re.sub('-', '', clip['start_time'][:10])
+                video_uploader_id = clip.get('user_id', clip.get('channel_id'))
                 info.append({
                     'id': clip['id'],
                     'url': video_url,
                     'title': clip['title'],
-                    'uploader': clip.get('user_id', clip.get('channel_id')),
+                    'uploader': clip.get('channel_name', video_uploader_id),
+                    'uploader_id': video_uploader_id,
                     'upload_date': video_date,
                     'ext': video_extension,
                 })
@@ -3553,7 +3559,7 @@ class JustinTVIE(InfoExtractor):
             paged = True
             api += '/channel/archives/%s.json'
         else:
-            api += '/clip/show/%s.json'
+            api += '/broadcast/by_archive/%s.json'
         api = api % (video_id,)
 
         self.report_extraction(video_id)