If missing encoding information due to missing feed detail, just skip parsing.

This commit is contained in:
Samuel Clay 2012-07-06 13:04:25 -07:00
parent 7dedeaaa6c
commit 298b79d9b3

View file

@ -3740,7 +3740,7 @@ def convert_to_utf8(http_headers, data):
chardet_encoding = None
tried_encodings = []
if chardet and data:
chardet_encoding = unicode(chardet.detect(data)['encoding'], 'ascii', 'ignore')
chardet_encoding = unicode(chardet.detect(data)['encoding'] or "", 'ascii', 'ignore')
# try: HTTP encoding, declared XML encoding, encoding sniffed from BOM
for proposed_encoding in (rfc3023_encoding, xml_encoding, bom_encoding,
chardet_encoding, u'utf-8', u'windows-1252', u'iso-8859-2'):