Imported Upstream version 2014.11.21

[youtubedl] / youtube_dl / extractor / c56.py

diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py
index 690bc7c25fe2574faa473b122e8427137599c3cd..cb96c3876b7cbf02220d06ad86a44414d69c9fa8 100644 (file)
--- a/youtube_dl/extractor/c56.py
+++ b/youtube_dl/extractor/c56.py
@@ -2,39 +2,46 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

 
 from .common import InfoExtractor
 
 
 class C56IE(InfoExtractor):
 
 from .common import InfoExtractor
 
 
 class C56IE(InfoExtractor):

-    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
+    _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'

     IE_NAME = '56.com'
     _TEST = {
         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
     IE_NAME = '56.com'
     _TEST = {
         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',

-        'file': '93440716.flv',

         'md5': 'e59995ac63d0457783ea05f93f12a866',
         'info_dict': {
         'md5': 'e59995ac63d0457783ea05f93f12a866',
         'info_dict': {

+            'id': '93440716',
+            'ext': 'flv',

             'title': '网事知多少 第32期：车怒',
             'title': '网事知多少 第32期：车怒',

+            'duration': 283.813,

         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')

-        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
-                                           text_id, 'Downloading video info')
-        info = json.loads(info_page)['info']
-        formats = [{
-            'format_id': f['type'],
-            'filesize': int(f['filesize']),
-            'url': f['url']
-        } for f in info['rfiles']]
+
+        page = self._download_json(
+            'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
+
+        info = page['info']
+
+        formats = [
+            {
+                'format_id': f['type'],
+                'filesize': int(f['filesize']),
+                'url': f['url']
+            } for f in info['rfiles']
+        ]

         self._sort_formats(formats)
 
         return {
             'id': info['vid'],
             'title': info['Subject'],
         self._sort_formats(formats)
 
         return {
             'id': info['vid'],
             'title': info['Subject'],

+            'duration': int(info['duration']) / 1000.0,

             'formats': formats,
             'thumbnail': info.get('bimg') or info.get('img'),
         }
             'formats': formats,
             'thumbnail': info.get('bimg') or info.get('img'),
         }