import xml.dom.minidom import sys def getElementsByAttrib(self, value, AName="ID-REF", list=[]): if self.nodeType == self.ELEMENT_NODE and \ self.hasAttribute(AName) and \ (self.getAttribute(AName) == value): list.append(value) for child in self.childNodes: list = list + getElementsByAttrib(child, value, AName) #list = list + getElementsByAttrib(child, value, AName, []) return list xml.dom.minidom.Node.getElementsByAttrib = getElementsByAttrib IN_FILENAME = "index.html" dom = xml.dom.minidom.parse(IN_FILENAME) print dom.getElementsByAttrib("group","class")