From add51d411ddfce7e283ac735f6b9860633a7bb28 Mon Sep 17 00:00:00 2001
From: Leonard Richardson <leonardr@segfault.org>
Date: Fri, 17 Aug 2012 09:32:45 -0400
Subject: Got rid of a UnicodeDecodeError when attribute names contain
 non-ASCII characters.

---
 bs4/element.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'bs4/element.py')

diff --git a/bs4/element.py b/bs4/element.py
index 2e3be46..26422fd 100644
--- a/bs4/element.py
+++ b/bs4/element.py
@@ -987,7 +987,7 @@ class Tag(PageElement):
                     if isinstance(val, list) or isinstance(val, tuple):
                         val = ' '.join(val)
                     elif not isinstance(val, basestring):
-                        val = str(val)
+                        val = unicode(val)
                     elif (
                         isinstance(val, AttributeValueWithCharsetSubstitution)
                         and eventual_encoding is not None):
@@ -995,7 +995,7 @@ class Tag(PageElement):
 
                     text = self.format_string(val, formatter)
                     decoded = (
-                        str(key) + '='
+                        unicode(key) + '='
                         + EntitySubstitution.quoted_attribute_value(text))
                 attrs.append(decoded)
         close = ''
-- 
cgit v1.2.3