python xml文档读写

àì夳堔傛蜴生んèń 2023-07-10 12:49 8阅读 0赞

1. minidom模块读写xml

#!/usr/bin/python
    # -*- coding: utf-8 -*-
    # xml读写
    from xml.dom import minidom
    
    
    def getxmlcontent():
        doc = minidom.parse('theme.xml')
        rootEle = doc.documentElement
        # themeNode = doc.getElementsByTagName('Theme')
        themeNodeList = rootEle.getElementsByTagName('Theme')
        print('Id\tName\tAuthor\tMail')
        for node in themeNodeList:
            id = node.getAttribute('id')
            name = node.getElementsByTagName('Name')[0].childNodes[0].nodeValue
            author = node.getElementsByTagName('Author')[0].childNodes[0].nodeValue
            mail = node.getElementsByTagName('Mail')[0].childNodes[0].nodeValue
            print(id + '\t' + name + '\t' + author + '\t' + mail)
    
    
    def createXmlDoc():
        nameList = ['Lily', 'Tom', 'Sara', 'James', 'Lambo', 'David']
        doc = minidom.Document()
        root = doc.createElement('Classroom')
        for i in range(0, 5):
            student = doc.createElement('Student')
            student.setAttribute('id', str(i))
            name = doc.createTextNode(nameList[i])
            age = doc.createTextNode(str(i + 20))
            student.appendChild(name)
            student.appendChild(age)
            root.appendChild(student)
        print(doc.toxml())
        with open('user.xml', 'w+', encoding='utf-8') as f:
            doc.writexml(f, indent='', addindent='\t', newl='\n', encoding='utf-8')
    
    
    if __name__ == '__main__':
        getxmlcontent()
        createXmlDoc()

代码中的theme.xml

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
    <FileZilla3>
        <Theme id="01">
            <Name>FlatZilla</Name>
            <Author>Boaz Lederer</Author>
            <Mail>aniboaz@gmail.com</Mail>
            <size primary="1">16x16</size>
            <size primary="1">24x24</size>
            <size primary="1">32x32</size>
            <size primary="1">48x48</size>
        </Theme>
        <Theme id="02">
            <Name>LonE</Name>
            <Author>Ricardo Cabral</Author>
            <Mail>ricardolcabral@gmail.com</Mail>
            <size primary="1">16x16</size>
            <size primary="1">32x32</size>
            <size primary="1">48x48</size>
        </Theme>
    </FileZilla3>

2. etree模块读写xml文档

#!/usr/bin/python
    # -*- coding: utf-8 -*-
    from xml.etree import cElementTree as ET
    
    #读取
    def getxml(fileName) :
        doc = ET.parse(fileName)
        root = doc.getroot()    #获取根节点
        print(root.tag) #标签名
        for child in root:  #节点本身是可迭代对象
            print(child.tag,child.attrib)   #标签和属性
            for i in child:
                print(i.tag,i.text)
    
    #创建xml文档
    def creatXml(fileName) :
        root = ET.Element('market') #创建根节点
        item = ET.Element('item',{'id':'001'})
        name = ET.SubElement(item,'name')   #创建子节点，不需要append
        name.text = 'dress' #子节点添加文本
        price = ET.SubElement(item,'price')
        price.text = '$100'
        root.append(item)   #追加子节点
        tree = ET.ElementTree(root)
        ET.dump(root)   #在终端打印文档内容
        tree.write(fileName,encoding='utf-8',xml_declaration=True)  #写入文件
    
    
    def insertNodes(fileName) :
        tree = ET.parse(fileName)
        root = tree.getroot()
        ele = ET.Element('item')
        ele.set('id','002') #设置属性值
        root.append(ele)
        name = ET.Element('name')
        name.text = 'skirt'
        price = ET.Element('price')
        price.text = '$10'
        ele.append(name)
        ele.append(price)
        tree.write(fileName,encoding='utf-8',xml_declaration=True)  #写入文件，新增生效
    
    
    def modifyNodes(fileName) :
        tree = ET.parse(fileName)
        root = tree.getroot()
        root.tag = 'Mall'
        for child in root:
            attrList = child.attrib #获取属性列表，字典型
            if attrList["id"] =='002' :
                priceTag = child.find('.//price')   #正则表达式查找，find返回第一个匹配的元素，findall返回所有匹配元素列表
                priceTag.text = '$20'
                child.set('id','003')
        tree.write(fileName,encoding='utf-8',xml_declaration=True)
    
    def removeNodes(fileName):
        tree = ET.parse(fileName)
        root = tree.getroot()
        for i in root:
            if i.attrib["id"] =='003':
                root.remove(i)  #删除节点
        tree.write(fileName,encoding='utf-8',xml_declaration=True)
    
    if __name__ == '__main__' :
        fileName = 'test.xml'
        creatXml(fileName)
        insertNodes(fileName)
        getxml(fileName)
        modifyNodes(fileName)
        removeNodes(fileName)

3. ElementTree与minidom的比较

ElementTree使用更灵活，且运行效率比minidom快。自己写的测试程序来看，资源充足的情况下，时间效率要快一倍

minidom对特殊格式支持的更广泛，如CDATA。ElementTree不支持CDATA格式内容的操作。