diff options
| author | Anisse Astier <anisse@astier.eu> | 2014-04-07 23:09:53 +0200 |
|---|---|---|
| committer | Anisse Astier <anisse@astier.eu> | 2014-04-07 23:10:16 +0200 |
| commit | ec0fafbb1915b830035f621f4660c7e46b1a53ed (patch) | |
| tree | bc61a4c5573a6f779d980f3095936ec62e9e4066 | |
| parent | a5863bdf331e6a54068912ea216612e812d7100d (diff) | |
[extractor/common] fallback on utf-8 when charset is not found
fixes #2721
| -rw-r--r-- | youtube_dl/extractor/common.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index da4193734..9653d44eb 100644 --- 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]): |