You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 lines
1.3 KiB
33 lines
1.3 KiB
From 20a32910f4a521788ba93a8c809cf0db702bed5b Mon Sep 17 00:00:00 2001
|
|
From: Kurt McKee <contactme@kurtmckee.org>
|
|
Date: Mon, 17 Dec 2012 10:41:13 -0600
|
|
Subject: [PATCH] Fix chardet support in Python 3
|
|
|
|
Fixes issue 384.
|
|
Thanks to Google user Arfrever.TFA for reporting this!
|
|
---
|
|
NEWS | 1 +
|
|
feedparser/feedparser.py | 6 +++++-
|
|
2 files changed, 6 insertions(+), 1 deletion(-)
|
|
|
|
diff --git a/feedparser/feedparser.py b/feedparser/feedparser.py
|
|
index c78e6a3..e977ae8 100644
|
|
--- a/feedparser/feedparser.py
|
|
+++ b/feedparser/feedparser.py
|
|
@@ -3766,7 +3766,11 @@ def convert_to_utf8(http_headers, data):
|
|
chardet_encoding = None
|
|
tried_encodings = []
|
|
if chardet:
|
|
- chardet_encoding = unicode(chardet.detect(data)['encoding'] or '', 'ascii', 'ignore')
|
|
+ chardet_encoding = chardet.detect(data)['encoding']
|
|
+ if not chardet_encoding:
|
|
+ chardet_encoding = ''
|
|
+ if not isinstance(chardet_encoding, unicode):
|
|
+ chardet_encoding = unicode(chardet_encoding, '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'):
|
|
--
|
|
1.8.5.5
|
|
|