Imported Upstream version 2015.06.04.1

[youtubedl] / youtube_dl / extractor / tudou.py

diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py
index 161e47624b383dfe76ea1e2ea6ec73395a97db53..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):
 
 
 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',
     _TESTS = [{
         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
         'md5': '140a49ed444bd22f93330985d8475fcb',


@@ -27,13 +27,6 @@ class TudouIE(InfoExtractor):
             'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
             'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
             'thumbnail': 're:^https?://.*\.jpg$',
         }

-    }, {
-        'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
-        'info_dict': {
-            'title': 'todo.mp4',
-        },
-        'add_ie': ['Youku'],
-        'skip': 'Only works from China'

     }]
 
     def _url_for_id(self, id, quality=None):
     }]
 
     def _url_for_id(self, id, quality=None):


@@ -45,8 +38,7 @@ class TudouIE(InfoExtractor):
         return final_url
 
     def _real_extract(self, 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)
         webpage = self._download_webpage(url, video_id)
 
         m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage)


@@ -87,4 +79,9 @@ class TudouIE(InfoExtractor):
             }
             result.append(part_info)
 
             }
             result.append(part_info)
 

-        return result
+        return {
+            '_type': 'multi_video',
+            'entries': result,
+            'id': video_id,
+            'title': title,
+        }