Merge remote-tracking branch 'Dineshs91/f4m-2.0'

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

diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py
index a85065121f8fc7937e157ec99817cda9d436ab67..c89de5ba4a46bb261987d8dbee5f55b3d05492da 100644 (file)
--- a/youtube_dl/extractor/tudou.py
+++ b/youtube_dl/extractor/tudou.py
@@ -9,7 +9,7 @@ from .common import InfoExtractor
 
 
 class TudouIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
     _TESTS = [{
         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
         'md5': '140a49ed444bd22f93330985d8475fcb',
@@ -20,25 +20,25 @@ class TudouIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }, {
-        'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
+        'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
         'info_dict': {
-            'title': 'todo.mp4',
-        },
-        'add_ie': ['Youku'],
-        'skip': 'Only works from China'
+            'id': '117049447',
+            'ext': 'f4v',
+            'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
     }]
 
-    def _url_for_id(self, id, quality = None):
-        info_url = "http://v2.tudou.com/f?id="+str(id)
+    def _url_for_id(self, id, quality=None):
+        info_url = "http://v2.tudou.com/f?id=" + str(id)
         if quality:
             info_url += '&hd' + quality
         webpage = self._download_webpage(info_url, id, "Opening the info webpage")
-        final_url = self._html_search_regex('>(.+?)</f>',webpage, 'video url')
+        final_url = self._html_search_regex('>(.+?)</f>', webpage, 'video url')
         return final_url
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(2)
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage)
@@ -65,7 +65,7 @@ class TudouIE(InfoExtractor):
         result = []
         len_parts = len(parts)
         if len_parts > 1:
-            self.to_screen(u'%s: found %s parts' % (video_id, len_parts))
+            self.to_screen('%s: found %s parts' % (video_id, len_parts))
         for part in parts:
             part_id = part['k']
             final_url = self._url_for_id(part_id, quality)
@@ -79,4 +79,9 @@ class TudouIE(InfoExtractor):
             }
             result.append(part_info)
 
-        return result
+        return {
+            '_type': 'multi_video',
+            'entries': result,
+            'id': video_id,
+            'title': title,
+        }