debian/control: Update list of extractors.

[youtubedl] / youtube_dl / extractor / teamcoco.py

diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index c910110ca9775d9ad03011238aacdc3c9ef4dae1..2bf26d05682e8e2535d412c2718d78bec6077622 100644 (file)
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -11,7 +11,7 @@ class TeamcocoIE(InfoExtractor):
     _TEST = {
         u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
         u'file': u'19705.mp4',
     _TEST = {
         u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
         u'file': u'19705.mp4',

-        u'md5': u'27b6f7527da5acf534b15f21b032656e',
+        u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',

         u'info_dict': {
             u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.", 
             u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
         u'info_dict': {
             u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.", 
             u"title": u"Louis C.K. Interview Pt. 1 11/3/11"


@@ -31,16 +31,39 @@ class TeamcocoIE(InfoExtractor):
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id

-        data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+        data = self._download_xml(data_url, video_id, 'Downloading data webpage')

 
 

-        video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>',
-            data, u'video URL')

 
 

-        return [{
+        qualities = ['500k', '480p', '1000k', '720p', '1080p']
+        formats = []
+        for file in data.findall('files/file'):
+            if file.attrib.get('playmode') == 'all':
+                # it just duplicates one of the entries
+                break
+            file_url = file.text
+            m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
+            if m_format is not None:
+                format_id = m_format.group(1)
+            else:
+                format_id = file.attrib['bitrate']
+            formats.append({
+                'url': file_url,
+                'ext': 'mp4',
+                'format_id': format_id,
+            })
+        def sort_key(f):
+            try:
+                return qualities.index(f['format_id'])
+            except ValueError:
+                return -1
+        formats.sort(key=sort_key)
+        if not formats:
+            raise ExtractorError(u'Unable to extract video URL')
+
+        return {

             'id':          video_id,
             'id':          video_id,

-            'url':         video_url,
-            'ext':         'mp4',
+            'formats': formats,

             'title':       self._og_search_title(webpage),
             'thumbnail':   self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
             'title':       self._og_search_title(webpage),
             'thumbnail':   self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),

-        }]
+        }