Edit Question - KnowledgeHub

Title Body

I am currently running the following code based on Chapter 12.5 of the Python Cookbook: from xml.parsers import expat class Element(object): def __init__(self, name, attributes): self.name = name self.attributes = attributes self.cdata = '' self.children = [] def addChild(self, element): self.children.append(element) def getAttribute(self,key): return self.attributes.get(key) def getData(self): return self.cdata def getElements(self, name=''): if name: return [c for c in self.children if c.name == name] else: return list(self.children) class Xml2Obj(object): def __init__(self): self.root = None self.nodeStack = [] def StartElement(self, name, attributes): element = Element(name.encode(), attributes) if self.nodeStack: parent = self.nodeStack[-1] parent.addChild(element) else: self.root = element self.nodeStack.append(element) def EndElement(self, name): self.nodeStack.pop() def CharacterData(self,data): if data.strip(): data = data.encode() element = self.nodeStack[-1] element.cdata += data def Parse(self, filename): Parser = expat.ParserCreate() Parser.StartElementHandler = self.StartElement Parser.EndElementHandler = self.EndElement Parser.CharacterDataHandler = self.CharacterData ParserStatus = Parser.Parse(open(filename).read(),1) return self.root I am working with XML documents of about 1 GB in size. Does anyone know a faster way to parse these?

Tags (comma-separated) Cancel