Merge remote-tracking branch 'yasoob/master'

test/tests.json

@@ -686,5 +686,14 @@
         "upload_date": "20130624",
         "uploader": "Hurts"
     }
+  },
+  {
+    "name": "Tudou",
+    "url": "http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html",
+    "file": "159447792.f4v",
+    "md5": "ad7c358a01541e926a1e413612c6b10a",
+    "info_dict": {
+        "title": "卡马乔国足开大脚长传冲吊集锦"
+    }
   }
 ]

youtube_dl/extractor/__init__.py

@@ -58,6 +58,7 @@ from .youku import YoukuIE
 from .youporn import YouPornIE
 from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
 from .zdf import ZDFIE
+from .tudou import TudouIE
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
@@ -129,6 +130,7 @@ def gen_extractors():
         BreakIE(),
         VevoIE(),
         JukeboxIE(),
+        TudouIE(),
         GenericIE()
     ]
 

youtube_dl/extractor/tudou.py

@@ -0,0 +1,32 @@
+import re
+
+from .common import InfoExtractor
+
+
+class TudouIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+)\.html)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(2).replace('.html','')
+        webpage = self._download_webpage(url, video_id)
+        video_id = re.search('"k":(.+?),',webpage).group(1)
+        title = re.search(",kw:\"(.+)\"",webpage)
+        if title is None:
+            title = re.search(",kw: \'(.+)\'",webpage)
+        title = title.group(1)
+        thumbnail_url = re.search(",pic: \'(.+?)\'",webpage)
+        if thumbnail_url is None:
+            thumbnail_url = re.search(",pic:\"(.+?)\"",webpage)
+        thumbnail_url = thumbnail_url.group(1)
+        info_url = "http://v2.tudou.com/f?id="+str(video_id)
+        webpage = self._download_webpage(info_url, video_id, "Opening the info webpage")
+        final_url = re.search('\>(.+?)\<\/f\>',webpage).group(1)
+        ext = (final_url.split('?')[0]).split('.')[-1]
+        return [{
+            'id':        video_id,
+            'url':       final_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+        }]