X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=9653d44eb33db4efb74e97529cdd2aaea0dc1c03;hb=e51880fd32c2087885b203f7dffd48c01b68d99a;hp=78f238f8428c5df0fce2dcc26f66b1301595e62b;hpb=ce328530a9009ffb5f0f486fc5178520d972f07a;p=youtube-dl

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 78f238f84..9653d44eb 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -251,7 +251,21 @@ class InfoExtractor(object):
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
-        content = webpage_bytes.decode(encoding, 'replace')
+        try:
+            content = webpage_bytes.decode(encoding, 'replace')
+        except LookupError:
+            content = webpage_bytes.decode('utf-8', 'replace')
+
+        if (u'<title>Access to this site is blocked</title>' in content and
+                u'Websense' in content[:512]):
+            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                u'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += u' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+
         return (content, urlh)
 
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):