]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/played.py
Merge tag 'upstream/2015.11.27.1'
[youtubedl] / youtube_dl / extractor / played.py
index 645a1e06dc8f3678b30d4e41b38ea13396c7a3e0..2856af96f49cf7928a0dd4fe79ccd287592fb3c1 100644 (file)
@@ -5,9 +5,10 @@ import re
 import os.path
 
 from .common import InfoExtractor
 import os.path
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
 from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
+    ExtractorError,
+    sanitized_Request,
 )
 
 
 )
 
 
@@ -23,15 +24,19 @@ class PlayedIE(InfoExtractor):
             'ext': 'flv',
             'title': 'youtube-dl_test_video.mp4',
         },
             'ext': 'flv',
             'title': 'youtube-dl_test_video.mp4',
         },
+        'skip': 'Removed for copyright infringement.',  # oh wow
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         orig_webpage = self._download_webpage(url, video_id)
         orig_webpage = self._download_webpage(url, video_id)
-        fields = re.findall(
-            r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
-        data = dict(fields)
+
+        m_error = re.search(
+            r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
+        if m_error:
+            raise ExtractorError(m_error.group('msg'), expected=True)
+
+        data = self._hidden_inputs(orig_webpage)
 
         self._sleep(2, video_id)
 
 
         self._sleep(2, video_id)
 
@@ -39,7 +44,7 @@ class PlayedIE(InfoExtractor):
         headers = {
             b'Content-Type': b'application/x-www-form-urlencoded',
         }
         headers = {
             b'Content-Type': b'application/x-www-form-urlencoded',
         }
-        req = compat_urllib_request.Request(url, post, headers)
+        req = sanitized_Request(url, post, headers)
         webpage = self._download_webpage(
             req, video_id, note='Downloading video page ...')
 
         webpage = self._download_webpage(
             req, video_id, note='Downloading video page ...')