使用Python处理XML

1．解析XML文件

使用Python单纯解析XML的最基本的方法就是直接使用Python自带的minidom库。

比如有如下XML文件：

<?xml version="1.0"?><root><singlenode>This is a single node</singlenode><multinode>This is first one</multinode><multinode>This is second one</multinode><multinode>This is third one</multinode><complexNode name="complex"><childnode>This is a child node</childnode></complexNode></root>

 

使用如下代码获取里面每一项内容：

from xml.dom import minidomif __name__ == '__main__':    try:        xmldoc = minidom.parse("test.xml")                singleNode = xmldoc.getElementsByTagName("singlenode")[0]                        print("Data of singleNode: %s"%(singleNode.firstChild.data))                multiNodes = xmldoc.getElementsByTagName("multinode")        for multiNode in multiNodes:            print("Data of multiNode: %s"%(multiNode.firstChild.data))        complexNode = xmldoc.getElementsByTagName("complexNode")[0]        print("The name attribute of complexNode: %s"%(complexNode.getAttribute("name")))                childNode = complexNode.getElementsByTagName("childnode")[0]        print("Data of childNode: %s"%(childNode.firstChild.data))    except:        print("Error: Parse XML file failed.")

 

输出结果如下：

Data of multiNode: This is second one

Data of multiNode: This is third one

The name attribute of complexNode: ComplexNode

Data of childNode: This is a child node

 

2．生成与保存XML文件

同样可以直接使用Python自带的库来生成和保存XML文件。比如要生成上例使用的XML文件：

from xml.dom import minidomimport codecsif __name__ == '__main__':    #generate new XMLDoc    impl = minidom.getDOMImplementation()    newdoc = impl.createDocument(None, "root", None)    rootNode = newdoc.documentElement        singleNode = newdoc.createElement("singlenode")    singleNode.appendChild(newdoc.createTextNode("This is a single node"))    rootNode.appendChild(singleNode)        multipleNodeTexts = ["This is first one", "This is second one", "This is third one"]    for multipleNodeText in multipleNodeTexts:        multipleNode = newdoc.createElement("multinode")        multipleNode.appendChild(newdoc.createTextNode(multipleNodeText))        rootNode.appendChild(multipleNode)        complexNode = newdoc.createElement("complexNode")    rootNode.appendChild(complexNode)    complexNode.setAttribute("name", "ComplexNode")        childNode = newdoc.createElement("childnode")    childNode.appendChild(newdoc.createTextNode("This is a child node"))    complexNode.appendChild(childNode)        #Save this XML to file    result_file = open("result.xml", 'wb+')    writer = codecs.lookup('utf-8')[3](result_file)    newdoc.writexml(writer, encoding='utf-8')    writer.close()    

 

3.运用XSL

运用XSL和后面要介绍的通过XMLSchema来进行校验都需要使用第三方库了。这里介绍的是一个比较流行的开源库libxml2，这是一个C库，我们使用这个库的python binding（当然也可以使用Python直接调用C接口）。

使用如下代码可以使用test.xsl为test.xml文件作转换，并将结果保存到test.html文件里面：

import libxml2import libxsltif __name__ == '__main__':    styledoc = libxml2.parseFile("test.xsl")    style = libxslt.parseStylesheetDoc(styledoc)    doc = libxml2.parseFile("test.xml")    result = style.applyStylesheet(doc, None)    style.saveResultToFilename("test.html", result, 0)    style.freeStylesheet()    doc.freeDoc()    result.freeDoc()    

 

4. 通过XMLSchema来对XML文件进行校验

如下代码使用test.xsd来对test.xml文件进行校验：

import sysimport libxml2if __name__ == '__main__':    #Parse xml file    try:        doc = libxml2.readFile("test.xml", None, libxml2.XML_PARSE_HUGE)    except:        print("The xml file is invalid")        sys.exit()        #Parse schema    schema = None    try:        ctxt = libxml2.schemaNewParserCtxt("test.xsd")        schema = ctxt.schemaParse()        del ctxt    except:        print("Error: Parse schema failed")        doc.freeDoc()        sys.exit()    validationCtxt = schema.schemaNewValidCtxt()    instance_Err = validationCtxt.schemaValidateDoc(doc)    del validationCtxt    del schema            doc.freeDoc()    if instance_Err != 0:        print("The XML file is not valid")    else:        print("The XML file is valid")

 

附录：

Libxml2的python binding

http://www.xmlsoft.org/python.html