diff options
Diffstat (limited to 'bs4/builder')
| -rw-r--r-- | bs4/builder/_html5lib.py | 12 | ||||
| -rw-r--r-- | bs4/builder/_htmlparser.py | 3 | ||||
| -rw-r--r-- | bs4/builder/_lxml.py | 53 |
3 files changed, 55 insertions, 13 deletions
diff --git a/bs4/builder/_html5lib.py b/bs4/builder/_html5lib.py index 0d7a1a9..7ce69aa 100644 --- a/bs4/builder/_html5lib.py +++ b/bs4/builder/_html5lib.py @@ -8,6 +8,7 @@ from bs4.builder import ( HTML_5, HTMLTreeBuilder, ) +from bs4.element import NamespacedAttribute import html5lib from html5lib.constants import ( DataLossWarning, @@ -58,9 +59,6 @@ class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder): def __init__(self, soup, namespaceHTMLElements): self.soup = soup - if namespaceHTMLElements: - warnings.warn("namespaceHTMLElements not supported yet", - DataLossWarning) super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements) def documentClass(self): @@ -76,9 +74,7 @@ class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder): self.soup.object_was_parsed(doctype) def elementClass(self, name, namespace): - if namespace is not None: - warnings.warn("BeautifulSoup cannot represent elements in any namespace", DataLossWarning) - tag = self.soup.new_tag(name) + tag = self.soup.new_tag(name, namespace) return Element(tag, self.soup, namespace) def commentClass(self, data): @@ -144,6 +140,8 @@ class Element(html5lib.treebuilders._base.Node): def setAttributes(self, attributes): if attributes is not None and attributes != {}: for name, value in list(attributes.items()): + if isinstance(name, tuple): + name = NamespacedAttribute(*name) self.element[name] = value # The attributes may contain variables that need substitution. # Call set_up_substitutions manually. @@ -189,7 +187,7 @@ class Element(html5lib.treebuilders._base.Node): TextNode(child, self.soup)) def cloneNode(self): - tag = self.soup.new_tag(self.element.name) + tag = self.soup.new_tag(self.element.name, self.namespace) node = Element(tag, self.soup, self.namespace) for key,value in self.attributes: node.attributes[key] = value diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index 62473cf..c307ff8 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -40,7 +40,8 @@ HTMLPARSER = 'html.parser' class BeautifulSoupHTMLParser(HTMLParser): def handle_starttag(self, name, attrs): - self.soup.handle_starttag(name, dict(attrs)) + # XXX namespace + self.soup.handle_starttag(name, None, None, dict(attrs)) def handle_endtag(self, name): self.soup.handle_endtag(name) diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index cc3cb86..870d59e 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -5,7 +5,7 @@ __all__ = [ import collections from lxml import etree -from bs4.element import Comment, Doctype +from bs4.element import Comment, Doctype, NamespacedAttribute from bs4.builder import ( FAST, HTML, @@ -42,6 +42,15 @@ class LXMLTreeBuilderForXML(TreeBuilder): parser = parser(target=self, strip_cdata=False) self.parser = parser self.soup = None + self.nsmaps = None + + def _getNsTag(self, tag): + # Split the namespace URL out of a fully-qualified lxml tag + # name. Copied from lxml's src/lxml/sax.py. + if tag[0] == '{': + return tuple(tag[1:].split('}', 1)) + else: + return (None, tag) def prepare_markup(self, markup, user_specified_encoding=None, document_declared_encoding=None): @@ -63,15 +72,49 @@ class LXMLTreeBuilderForXML(TreeBuilder): self.parser.close() def close(self): - pass - - def start(self, name, attrs): - self.soup.handle_starttag(name, attrs) + self.nsmaps = None + + def start(self, name, attrs, nsmap={}): + nsprefix = None + # Invert each namespace map as it comes in. + if len(nsmap) == 0 and self.nsmaps != None: + # There are no new namespaces for this tag, but namespaces + # are in play, so we need a separate tag stack to know + # when they end. + self.nsmaps.append(None) + elif len(nsmap) > 0: + # A new namespace mapping has come into play. + if self.nsmaps is None: + self.nsmaps = [] + inverted_nsmap = dict((value, key) for key, value in nsmap.items()) + self.nsmaps.append(inverted_nsmap) + # Also treat the namespace mapping as a set of attributes on the + # tag, so we can recreate it later. + attrs = attrs.copy() + for prefix, namespace in nsmap.items(): + attribute = NamespacedAttribute( + "xmlns", prefix, "http://www.w3.org/2000/xmlns/") + attrs[attribute] = namespace + namespace, name = self._getNsTag(name) + if namespace is not None: + for inverted_nsmap in reversed(self.nsmaps): + if inverted_nsmap is not None and namespace in inverted_nsmap: + nsprefix = inverted_nsmap[namespace] + break + self.soup.handle_starttag(name, namespace, nsprefix, attrs) def end(self, name): self.soup.endData() completed_tag = self.soup.tagStack[-1] self.soup.handle_endtag(name) + if self.nsmaps != None: + # This tag, or one of its parents, introduced a namespace + # mapping, so pop it off the stack. + self.nsmaps.pop() + if len(self.nsmaps) == 0: + # Namespaces are no longer in play, so don't bother keeping + # track of the namespace stack. + self.nsmaps = None def pi(self, target, data): pass |