[extractor/common] fallback on utf-8 when charset is not found

fixes #2721

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index da4193734971122c2ef72f3dca4acecd93e5f784..9653d44eb33db4efb74e97529cdd2aaea0dc1c03 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -251,7 +251,10 @@ 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]):