python xml.dom模块解析xml

阅读目录

• 1. 什么是xml？有何特征？
• 2. 获得标签属性
• 3. 获得子标签
• 4. 获得标签属性值
• 5. 获得标签对之间的数据
• 6. 例子
• 7. 总结

xml version="1.0" encoding="utf-8"?>
catalog>
    maxid>4maxid>
    login username="pytest" passwd=‘123456‘>
        caption>Pythoncaption>
        item id="4">
            caption>testcaption>
        item>
    login>
    item id="2">
        caption>Zopecaption>
    item>
catalog>

#coding: utf-8
import xml.dom.minidom
dom = xml.dom.minidom.parse("del.xml")  #打开xml文档

root = dom.documentElement              #得到xml文档对象
print "nodeName:", root.nodeName        #每一个结点都有它的nodeName，nodeValue，nodeType属性
print "nodeValue:", root.nodeValue      #nodeValue是结点的值，只对文本结点有效
print "nodeType:", root.nodeType
print "ELEMENT_NODE:", root.ELEMENT_NODE

#coding: utf-8
import xml.dom.minidom
dom = xml.dom.minidom.parse("del.xml")  

root = dom.documentElement
bb = root.getElementsByTagName(‘maxid‘)
print type(bb)
print bb
b = bb[0]
print b.nodeName
print b.nodeValue

#coding: utf-8
import xml.dom.minidom
dom = xml.dom.minidom.parse("del.xml")  

root = dom.documentElement
itemlist = root.getElementsByTagName(‘login‘)
item = itemlist[0]
print item.getAttribute("username")
print item.getAttribute("passwd")

itemlist = root.getElementsByTagName("item")
item = itemlist[0]                   #通过在itemlist中的位置区分
print item.getAttribute("id") 

item2 = itemlist[1]                  #通过在itemlist中的位置区分

print item2.getAttribute("id")

#coding: utf-8
import xml.dom.minidom
dom = xml.dom.minidom.parse("del.xml")  

root = dom.documentElement
itemlist = root.getElementsByTagName(‘caption‘)

item = itemlist[0]
print item.firstChild.data

item2 = itemlist[1]
print item2.firstChild.data

xml version="1.0" encoding="UTF-8" ?>
users>
    user id="1000001">
        username>Adminusername>
        email>admin@live.cnemail>
        age>23age>
        sex>boysex>
    user>
    user id="1000002">
        username>Admin2username>
        email>admin2@live.cnemail>
        age>22age>
        sex>boysex>
    user>
    user id="1000003">
        username>Admin3username>
        email>admin3@live.cnemail>
        age>27age>
        sex>boysex>
    user>
    user id="1000004">
        username>Admin4username>
        email>admin4@live.cnemail>
        age>25age>
        sex>girlsex>
    user>
    user id="1000005">
        username>Admin5username>
        email>admin5@live.cnemail>
        age>20age>
        sex>boysex>
    user>
    user id="1000006">
        username>Admin6username>
        email>admin6@live.cnemail>
        age>23age>
        sex>girlsex>
    user>

# -*- coding:utf-8 -*-
from xml.dom import minidom

def get_attrvalue(node, attrname):
     return node.getAttribute(attrname) if node else ‘‘

def get_nodevalue(node, index = 0):
    return node.childNodes[index].nodeValue if node else ‘‘

def get_xmlnode(node, name):
    return node.getElementsByTagName(name) if node else []

def get_xml_data(filename = ‘user.xml‘):
    doc = minidom.parse(filename) 
    root = doc.documentElement

    user_nodes = get_xmlnode(root, ‘user‘)
    print "user_nodes:", user_nodes

    user_list=[]
    for node in user_nodes: 
        user_id = get_attrvalue(node, ‘id‘) 
        node_name = get_xmlnode(node, ‘username‘)
        node_email = get_xmlnode(node, ‘email‘)
        node_age = get_xmlnode(node, ‘age‘)
        node_sex = get_xmlnode(node, ‘sex‘)

        user_name =get_nodevalue(node_name[0])
        user_email = get_nodevalue(node_email[0])
        user_age = int(get_nodevalue(node_age[0]))
        user_sex = get_nodevalue(node_sex[0])

        user = {}
        user[‘id‘] , user[‘username‘] , user[‘email‘] , user[‘age‘] , user[‘sex‘] = (
            int(user_id), user_name , user_email , user_age , user_sex
        )
        user_list.append(user)
    return user_list

def test_load_xml():
    user_list = get_xml_data()
    for user in user_list :
        print ‘-----------------------------------------------------‘
        if user:
            user_str=‘No.:\t%d\nname:\t%s\nsex:\t%s\nage:\t%s\nEmail:\t%s‘ % (int(user[‘id‘]) , user[‘username‘], user[‘sex‘] , user[‘age‘] , user[‘email‘])
            print user_str

if __name__ == "__main__":
    test_load_xml()