identifying multiple assets in a webpage for html5

youtube_dl/extractor/common.py

@@ -312,6 +312,18 @@ class InfoExtractor(object):
         if video_id is not None:
             video_info['id'] = video_id
         return video_info
+
+    @staticmethod
+    def video_result(video_url=None, video_id=None, uploader=None, video_title=None):
+        """Returns a url that points to a page that should be processed"""
+        #TODO: ie should be the class used for getting the info
+        video_info = {'_type': 'video',
+                      'url': video_url,
+                      'id': video_id,
+                      'uploader': uploader,
+                       'title': video_title}
+        return video_info
+
     @staticmethod
     def playlist_result(entries, playlist_id=None, playlist_title=None):
         """Returns a playlist"""

youtube_dl/extractor/generic.py

@@ -348,7 +348,13 @@ class GenericIE(InfoExtractor):
                 mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
         if mobj is None:
             # HTML5 video
-            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
+            matches = re.findall(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
+            if matches:
+                urlrs = [self.video_result(unescapeHTML(tuppl), video_id, video_uploader,video_title)
+                for tuppl in matches]
+                return self.playlist_result(
+                    urlrs, playlist_id=video_id, playlist_title=video_title)
+
         if mobj is None:
             raise ExtractorError('Unsupported URL: %s' % url)