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 5a136a9527613e2fb076c1169b3ef5e90c24eafd..3794bcded273235f3fc2a77097b1ca6e48fab348 100644 (file)
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,54 +1,64 @@
-import re
+# encoding: utf-8
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-    compat_urllib_request,
-
+    compat_urlparse,
+)
+from ..utils import (
     ExtractorError,
+    sanitized_Request,
 )
 
 
 class Vbox7IE(InfoExtractor):
-    """Information Extractor for Vbox7"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://vbox7.com/play:249bb972c2',
-        u'file': u'249bb972c2.flv',
-        u'md5': u'99f65c0c9ef9b682b97313e052734c3f',
-        u'info_dict': {
-            u"title": u"\u0421\u043c\u044f\u0445! \u0427\u0443\u0434\u043e - \u0447\u0438\u0441\u0442 \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u0438 - \u0421\u043a\u0440\u0438\u0442\u0430 \u043a\u0430\u043c\u0435\u0440\u0430"
-        }
+        'url': 'http://vbox7.com/play:249bb972c2',
+        'md5': '99f65c0c9ef9b682b97313e052734c3f',
+        'info_dict': {
+            'id': '249bb972c2',
+            'ext': 'mp4',
+            'title': 'Смях! Чудо - чист за секунди - Скрита камера',
+        },
     }
 
-    def _real_extract(self,url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group(1)
+    def _real_extract(self, url):
+        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')
 
-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
+        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, u'title').split('/')[0].strip()
+                                        webpage, 'title').split('/')[0].strip()
 
-        ext = "flv"
-        info_url = "http://vbox7.com/play/magare.do"
-        data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
-        info_request = compat_urllib_request.Request(info_url, data)
+        info_url = 'http://vbox7.com/play/magare.do'
+        data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
+        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, u'Downloading info webpage')
+        info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
         if info_response is None:
-            raise ExtractorError(u'Unable to extract the media url')
+            raise ExtractorError('Unable to extract the media url')
         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
 
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': title,
             'thumbnail': thumbnail_url,
-        }]
+        }