diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-20 15:10:48 -0500 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-20 15:10:48 -0500 |
| commit | 784dca53bc03943472f58b05b6fcdff801343dac (patch) | |
| tree | 76d78c8831f0acb5a3a41bc628ffbd62b0bbfc6d /beautifulsoup/builder/_lxml.py | |
| parent | 232311a2f682e59078012e5b05e382982862f627 (diff) | |
| parent | 89961f4de3ab1e88b15dd9c0aaa0af77a7c32262 (diff) | |
Discovered that html5lib can't be made to support SoupStrainers, and changed the test suite appropriately.
Diffstat (limited to 'beautifulsoup/builder/_lxml.py')
| -rw-r--r-- | beautifulsoup/builder/_lxml.py | 88 |
1 files changed, 88 insertions, 0 deletions
diff --git a/beautifulsoup/builder/_lxml.py b/beautifulsoup/builder/_lxml.py new file mode 100644 index 0000000..c2f368c --- /dev/null +++ b/beautifulsoup/builder/_lxml.py @@ -0,0 +1,88 @@ +__all__ = [ + 'LXMLTreeBuilderForXML', + 'LXMLTreeBuilder', + ] + +from lxml import etree +from beautifulsoup.element import Comment, Doctype +from beautifulsoup.builder import TreeBuilder, HTMLTreeBuilder +from beautifulsoup.dammit import UnicodeDammit +import types + +class LXMLTreeBuilderForXML(TreeBuilder): + DEFAULT_PARSER_CLASS = etree.XMLParser + + @property + def default_parser(self): + # This can either return a parser object or a class, which + # will be instantiated with default arguments. + 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: + self.empty_element_tags = set(empty_element_tags) + if parser is None: + # Use the default parser. + parser = self.default_parser + if callable(parser): + # Instantiate the parser with default arguments + parser = parser(target=self, strip_cdata=False) + self.parser = parser + self.soup = None + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + """ + :return: A 3-tuple (markup, original encoding, encoding + declared within markup). + """ + if isinstance(markup, unicode): + return markup, None, None + + try_encodings = [user_specified_encoding, document_declared_encoding] + dammit = UnicodeDammit(markup, try_encodings, isHTML=True) + return (dammit.markup, dammit.original_encoding, + dammit.declared_html_encoding) + + def feed(self, markup): + self.parser.feed(markup) + self.parser.close() + + def close(self): + pass + + def start(self, name, attrs): + self.soup.handle_starttag(name, attrs) + + def end(self, name): + self.soup.endData() + completed_tag = self.soup.tagStack[-1] + self.soup.handle_endtag(name) + + def pi(self, target, data): + pass + + def data(self, content): + self.soup.handle_data(content) + + def doctype(self, name, pubid, system): + self.soup.endData() + doctype = Doctype.for_name_and_ids(name, pubid, system) + self.soup.object_was_parsed(doctype) + + def comment(self, content): + "Handle comments as Comment objects." + self.soup.endData() + self.soup.handle_data(content) + self.soup.endData(Comment) + + +class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): + + @property + def default_parser(self): + return etree.HTMLParser + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'<html><body>%s</body></html>' % fragment |