Merge tag 'upstream/2015.07.21'

[youtubedl] / youtube_dl / extractor / vbox7.py

diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index df115d2516196517b1a66fe2fb12bd1fbf96b6e5..722eb52368825b92c88506ff33d79bf1f2f91a32 100644 (file)
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,42 +1,51 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
 # encoding: utf-8
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urllib_parse,
     compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_request,

-
+    compat_urlparse,
+)
+from ..utils import (

     ExtractorError,
 )
 
 
 class Vbox7IE(InfoExtractor):
     ExtractorError,
 )
 
 
 class Vbox7IE(InfoExtractor):

-    _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)'
+    _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'

     _TEST = {
         'url': 'http://vbox7.com/play:249bb972c2',
         'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {
             'id': '249bb972c2',
     _TEST = {
         'url': 'http://vbox7.com/play:249bb972c2',
         'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {
             'id': '249bb972c2',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
         },
     }
 
     def _real_extract(self, url):
             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
         },
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
+        # need to get the page 3 times for the correct jsSecretToken cookie
+        # which is necessary for the correct title
+        def get_session_id():
+            redirect_page = self._download_webpage(url, video_id)
+            session_id_url = self._search_regex(
+                r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
+                'session id url')
+            self._download_webpage(
+                compat_urlparse.urljoin(url, session_id_url), video_id,
+                'Getting session id')
+
+        get_session_id()
+        get_session_id()

 
 

-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';',
-            redirect_page, 'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id,
-            'Downloading redirect page')
+        webpage = self._download_webpage(url, video_id,
+                                         'Downloading redirect page')

 
         title = self._html_search_regex(r'<title>(.*)</title>',
 
         title = self._html_search_regex(r'<title>(.*)</title>',

-            webpage, 'title').split('/')[0].strip()
+                                        webpage, 'title').split('/')[0].strip()

 
         info_url = "http://vbox7.com/play/magare.do"
         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
 
         info_url = "http://vbox7.com/play/magare.do"
         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})


@@ -50,7 +59,6 @@ class Vbox7IE(InfoExtractor):
         return {
             'id': video_id,
             'url': final_url,
         return {
             'id': video_id,
             'url': final_url,

-            'ext': 'flv',

             'title': title,
             'thumbnail': thumbnail_url,
         }
             'title': title,
             'thumbnail': thumbnail_url,
         }