def get_css_class_dict(node): """ Given an xml.dom.minidom.Node, returns a map from every "class" attribute from it to a list of nodes with this class. For example, for the document below: >>> doc = xml.dom.minidom.parseString( ... ''' ... ... ...
... ... ... ''') ...we will get this: >>> d = get_css_class_dict(doc) >>> d['a'] # doctest: +ELLIPSIS [, ] >>> d['b'] # doctest: +ELLIPSIS [] """ css_class_dict = {} if node.attributes is not None and 'class' in node.attributes: css_classes = node.attributes['class'].value for css_class in css_classes.split(): css_class_list = css_class_dict.get(css_class, []) css_class_list.append(node) css_class_dict[css_class] = css_class_list childNodes = getattr(node, 'childNodes', []) for cn in childNodes: ccd = get_css_class_dict(cn) for css_class, nodes_list in ccd.items(): css_class_list = css_class_dict.get(css_class, []) css_class_list.extend(nodes_list) css_class_dict[css_class] = css_class_list return css_class_dict