Merge tag 'upstream/2016.02.22'

[youtubedl] / youtube_dl / extractor / vbox7.py

diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index dd026748dcbb536f9f49181b0d211bf0a9157777..3794bcded273235f3fc2a77097b1ca6e48fab348 100644 (file)
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -4,10 +4,11 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,

-    compat_urllib_request,
+    compat_urlparse,

 )
 from ..utils import (
     ExtractorError,
 )
 from ..utils import (
     ExtractorError,

+    sanitized_Request,

 )
 
 
 )
 
 


@@ -26,19 +27,29 @@ class Vbox7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        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,
+        # 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()
+
+        webpage = self._download_webpage(url, video_id,

                                          'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',
                                         webpage, 'title').split('/')[0].strip()
 
                                          'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',
                                         webpage, 'title').split('/')[0].strip()
 

-        info_url = "http://vbox7.com/play/magare.do"
+        info_url = 'http://vbox7.com/play/magare.do'

         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})

-        info_request = compat_urllib_request.Request(info_url, data)
+        info_request = sanitized_Request(info_url, data)

         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
         if info_response is None:
         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
         if info_response is None: