diff options
Diffstat (limited to 'bs4/builder/_lxml.py')
| -rw-r--r-- | bs4/builder/_lxml.py | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 9e8f88f..4495bb9 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -1,3 +1,5 @@ +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. __all__ = [ 'LXMLTreeBuilderForXML', 'LXMLTreeBuilder', @@ -12,6 +14,7 @@ from bs4.element import ( Doctype, NamespacedAttribute, ProcessingInstruction, + XMLProcessingInstruction, ) from bs4.builder import ( FAST, @@ -103,6 +106,10 @@ class LXMLTreeBuilderForXML(TreeBuilder): # iterate over the encodings, and tell lxml to try to parse # the document as each one in turn. is_html = not self.is_xml + if is_html: + self.processing_instruction_class = ProcessingInstruction + else: + self.processing_instruction_class = XMLProcessingInstruction try_encodings = [user_specified_encoding, document_declared_encoding] detector = EncodingDetector( markup, try_encodings, is_html, exclude_encodings) @@ -201,7 +208,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): def pi(self, target, data): self.soup.endData() self.soup.handle_data(target + ' ' + data) - self.soup.endData(ProcessingInstruction) + self.soup.endData(self.processing_instruction_class) def data(self, content): self.soup.handle_data(content) |