diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-20 10:39:56 -0500 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-20 10:39:56 -0500 |
| commit | 232311a2f682e59078012e5b05e382982862f627 (patch) | |
| tree | 60bd21949b54bdb5588ecce31a3bb89e40617692 /beautifulsoup/builder/lxml_builder.py | |
| parent | ae349fd47c627f8166526fed8906811707d2f4b2 (diff) | |
| parent | f2532b1d63bd4a4d2be6ad9a4dce5eea03f43e7a (diff) | |
I couldn't get the XML parser to parse CDATA as CData objects, but at least I documented the current behavior.
Diffstat (limited to 'beautifulsoup/builder/lxml_builder.py')
| -rw-r--r-- | beautifulsoup/builder/lxml_builder.py | 11 |
1 files changed, 4 insertions, 7 deletions
diff --git a/beautifulsoup/builder/lxml_builder.py b/beautifulsoup/builder/lxml_builder.py index e431a62..9f4c0bd 100644 --- a/beautifulsoup/builder/lxml_builder.py +++ b/beautifulsoup/builder/lxml_builder.py @@ -11,7 +11,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): def default_parser(self): # This can either return a parser object or a class, which # will be instantiated with default arguments. - return etree.XMLParser + return etree.XMLParser(target=self, strip_cdata=False, recover=True) def __init__(self, parser=None, empty_element_tags=None): if empty_element_tags is not None: @@ -71,10 +71,6 @@ class LXMLTreeBuilderForXML(TreeBuilder): self.soup.handle_data(content) self.soup.endData(Comment) - def test_fragment_to_document(self, fragment): - """See `TreeBuilder`.""" - return u'<html><body>%s</body></html>' % fragment - class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): @@ -82,5 +78,6 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): def default_parser(self): return etree.HTMLParser - def end(self, name): - self.soup.handle_endtag(name) + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'<html><body>%s</body></html>' % fragment |