From 4f9a654766df9ddd05e3ef274b4715b42668724f Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Sun, 2 Jun 2013 19:12:07 -0400 Subject: Turns out we had two bits of code to strip byte-order marks. --- bs4/builder/_lxml.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'bs4/builder/_lxml.py') diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 92ace07..fa5d498 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -97,7 +97,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): try_encodings = [user_specified_encoding, document_declared_encoding] detector = EncodingDetector(markup, try_encodings, is_html) for encoding in detector.encodings: - yield (markup, encoding, document_declared_encoding, False) + yield (detector.markup, encoding, document_declared_encoding, False) def feed(self, markup): if isinstance(markup, bytes): -- cgit v1.2.3