diff options
author | Leonard Richardson <leonardr@segfault.org> | 2016-07-26 22:01:22 -0400 |
---|---|---|
committer | Leonard Richardson <leonardr@segfault.org> | 2016-07-26 22:01:22 -0400 |
commit | 21d4cc074cc68fa3a37d04b746e19810cd5f296f (patch) | |
tree | 8071ec17e9d2309a38edca2621f9fcfba6a8a8ad /bs4/builder | |
parent | 231c396236c3838c8e3c7ac40d6fba6f28fc00e5 (diff) | |
download | beautifulsoup4-21d4cc074cc68fa3a37d04b746e19810cd5f296f.tar.gz |
Fixed a reported (but not duplicated) bug involving processing instructions fed into the lxml HTML parser.
Diffstat (limited to 'bs4/builder')
-rw-r--r-- | bs4/builder/_lxml.py | 4 |
1 files changed, 3 insertions, 1 deletions
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): |