diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2016-07-16 11:51:31 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2016-07-16 11:51:31 -0400 |
| commit | e4ff05f0783605350171f6623d4055837c2af14f (patch) | |
| tree | 7ed51d902a9705ce8e8fb84587fe715b9830ec5c /bs4/builder/_lxml.py | |
| parent | b0d82663f225c501f1417bcc155c156327134404 (diff) | |
Added a separate class for XML processing instructions, which have a slightly different format from SGML processing instructions. [bug=1504383]
Diffstat (limited to 'bs4/builder/_lxml.py')
| -rw-r--r-- | bs4/builder/_lxml.py | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index bfec582..67cdb4c 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -5,6 +5,7 @@ __all__ = [ 'LXMLTreeBuilder', ] +from pdb import set_trace from io import BytesIO from StringIO import StringIO import collections @@ -14,6 +15,7 @@ from bs4.element import ( Doctype, NamespacedAttribute, ProcessingInstruction, + XMLProcessingInstruction, ) from bs4.builder import ( FAST, @@ -105,6 +107,10 @@ 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) @@ -203,7 +209,7 @@ 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) |