[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py
index 9ca860ab084f523c7dc5ed7b16b28ff0e91c3324..7421378a8c771543b3418a7d1f54b40cacb324e1 100644 (file)
--- a/youtube_dl/extractor/tudou.py
+++ b/youtube_dl/extractor/tudou.py
@@ -1,32 +1,49 @@
-import re
+# coding: utf-8
+
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 
 
-class TudouIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+)\.html)'
+class TudouPlaylistIE(InfoExtractor):
+    IE_NAME = 'tudou:playlist'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
+    _TESTS = [{
+        'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
+        'info_dict': {
+            'id': 'zzdE77v6Mmo',
+        },
+        'playlist_mincount': 209,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        playlist_data = self._download_json(
+            'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
+        entries = [self.url_result(
+            'http://www.tudou.com/programs/view/%s' % item['icode'],
+            'Tudou', item['icode'],
+            item['kw']) for item in playlist_data['items']]
+        return self.playlist_result(entries, playlist_id)
+
+
+class TudouAlbumIE(InfoExtractor):
+    IE_NAME = 'tudou:album'
+    _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
+    _TESTS = [{
+        'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
+        'info_dict': {
+            'id': 'v5qckFJvNJg',
+        },
+        'playlist_mincount': 45,
+    }]
 
     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,
-        }]
+        album_id = self._match_id(url)
+        album_data = self._download_json(
+            'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
+        entries = [self.url_result(
+            'http://www.tudou.com/programs/view/%s' % item['icode'],
+            'Tudou', item['icode'],
+            item['kw']) for item in album_data['items']]
+        return self.playlist_result(entries, album_id)