From a15e40b89282ef6924873e41bb08be2eb440880f Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Tue, 26 Jul 2016 22:01:22 -0400 Subject: Fixed a reported (but not duplicated) bug involving processing instructions fed into the lxml HTML parser. --- bs4/builder/_lxml.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'bs4/builder/_lxml.py') diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 4495bb9..34bb14e 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -107,7 +107,8 @@ class LXMLTreeBuilderForXML(TreeBuilder): # the document as each one in turn. is_html = not self.is_xml if is_html: - self.processing_instruction_class = ProcessingInstruction + pass + # self.processing_instruction_class = ProcessingInstruction else: self.processing_instruction_class = XMLProcessingInstruction try_encodings = [user_specified_encoding, document_declared_encoding] @@ -235,6 +236,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): ALTERNATE_NAMES = ["lxml-html"] features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE] + processing_instruction_class = ProcessingInstruction is_xml = False def default_parser(self, encoding): -- cgit v1.2.3