Register new version in the changelog.

[youtubedl] / youtube_dl / extractor / tudou.py

diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py
index dcd823d0838dca23b27298cbf05ad47cc4261637..5f7ac4b35b6c4576e5fb0998d56eb21ec522b58a 100644 (file)
--- a/youtube_dl/extractor/tudou.py
+++ b/youtube_dl/extractor/tudou.py
@@ -2,14 +2,12 @@
 
 from __future__ import unicode_literals
 
 
 from __future__ import unicode_literals
 

-import re
-import json
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_str

 
 
 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',


@@ -28,42 +26,40 @@ class TudouIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }, {
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }, {

-        'url': 'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
-        'info_dict': {
-            'title': 'todo.mp4',
-        },
-        'add_ie': ['Youku'],
-        'skip': 'Only works from China'
+        'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html',
+        'only_matching': True,

     }]
 
     }]
 

-    def _url_for_id(self, id, quality = None):
-        info_url = "http://v2.tudou.com/f?id="+str(id)
+    _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
+
+    def _url_for_id(self, video_id, quality=None):
+        info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)

         if quality:
             info_url += '&hd' + quality
         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')
+        xml_data = self._download_xml(info_url, video_id, "Opening the info XML page")
+        final_url = xml_data.text

         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)
 
         webpage = self._download_webpage(url, video_id)
 

-        m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage)
-        if m and m.group(1):
-            return {
-                '_type': 'url',
-                'url': 'youku:' + m.group(1),
-                'ie_key': 'Youku'
-            }
+        youku_vcode = self._search_regex(
+            r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None)
+        if youku_vcode:
+            return self.url_result('youku:' + youku_vcode, ie='Youku')

 
         title = self._search_regex(
 
         title = self._search_regex(

-            r",kw:\s*['\"](.+?)[\"']", webpage, 'title')
+            r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title')

         thumbnail_url = self._search_regex(
         thumbnail_url = self._search_regex(

-            r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False)
+            r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False)
+
+        player_url = self._search_regex(
+            r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]',
+            webpage, 'player URL', default=self._PLAYER_URL)

 
 

-        segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
-        segments = json.loads(segs_json)
+        segments = self._parse_json(self._search_regex(
+            r'segs: \'([^\']+)\'', webpage, 'segments'), video_id)

         # It looks like the keys are the arguments that have to be passed as
         # the hd field in the request url, we pick the higher
         # Also, filter non-number qualities (see issue #3643).
         # It looks like the keys are the arguments that have to be passed as
         # the hd field in the request url, we pick the higher
         # Also, filter non-number qualities (see issue #3643).


@@ -73,7 +69,7 @@ class TudouIE(InfoExtractor):
         result = []
         len_parts = len(parts)
         if len_parts > 1:
         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)
         for part in parts:
             part_id = part['k']
             final_url = self._url_for_id(part_id, quality)


@@ -84,7 +80,15 @@ class TudouIE(InfoExtractor):
                 'ext': ext,
                 'title': title,
                 'thumbnail': thumbnail_url,
                 'ext': ext,
                 'title': title,
                 'thumbnail': thumbnail_url,

+                'http_headers': {
+                    'Referer': player_url,
+                },

             }
             result.append(part_info)
 
             }
             result.append(part_info)
 

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