X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdumpert.py;h=c9fc9b5a9df65cd8681ce8e0933473ea9658202d;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=e43bc81b22c08bccb4ad87204353781c07dbf8a5;hpb=87270c84166bb014ba1043a6eeee7330694b0649;p=youtube-dl

diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py
index e43bc81b2..c9fc9b5a9 100644
--- a/youtube_dl/extractor/dumpert.py
+++ b/youtube_dl/extractor/dumpert.py
@@ -2,14 +2,18 @@
 from __future__ import unicode_literals
 
 import base64
+import re
 
 from .common import InfoExtractor
-from ..utils import qualities
+from ..utils import (
+    qualities,
+    sanitized_Request,
+)
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
-    _TEST = {
+    _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
         'info_dict': {
@@ -17,13 +21,22 @@ class DumpertIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ik heb nieuws voor je',
             'description': 'Niet schrikken hoor',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        protocol = mobj.group('protocol')
+
+        url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
+        req = sanitized_Request(url)
+        req.add_header('Cookie', 'nsfw=1; cpc=10')
+        webpage = self._download_webpage(req, video_id)
 
         files_base64 = self._search_regex(
             r'data-files="([^"]+)"', webpage, 'data files')