python中利用xml.dom模块解析xml的方法教程

<"1.0" encoding="utf-8"?>
<catalog>
 <maxid>4</maxid>
 <login username="pytest" passwd='123456'>
  <caption>Python</caption>
  <item id="4">
   <caption>test</caption>
  </item>
 </login>
 <item id="2">
  <caption>Zope</caption>
 </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

'ATTRIBUTE_NODE'

'CDATA_SECTION_NODE'

'COMMENT_NODE'

'DOCUMENT_FRAGMENT_NODE'

'DOCUMENT_NODE'

'DOCUMENT_TYPE_NODE'

'ELEMENT_NODE'

'ENTITY_NODE'

'ENTITY_REFERENCE_NODE'

'NOTATION_NODE'

'PROCESSING_INSTRUCTION_NODE'

'TEXT_NODE' 

nodeName: catalog

nodeValue: None

nodeType: 1

ELEMENT_NODE: 1 

#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

<class 'xml.dom.minicompat.NodeList'>

[<DOM Element: maxid at 0x2707a48>]

maxid

None 

#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")

pytest

123456

4

2 

#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

Python

test 

<"1.0" encoding="UTF-8" ?>
<users>
 <user id="1000001">
  <username>Admin</username>
  <email>admin@live.cn</email>
  <age>23</age>
  <sex>boy</sex>
 </user>
 <user id="1000002">
  <username>Admin2</username>
  <email>admin2@live.cn</email>
  <age>22</age>
  <sex>boy</sex>
 </user>
 <user id="1000003">
  <username>Admin3</username>
  <email>admin3@live.cn</email>
  <age>27</age>
  <sex>boy</sex>
 </user>
 <user id="1000004">
  <username>Admin4</username>
  <email>admin4@live.cn</email>
  <age>25</age>
  <sex>girl</sex>
 </user>
 <user id="1000005">
  <username>Admin5</username>
  <email>admin5@live.cn</email>
  <age>20</age>
  <sex>boy</sex>
 </user>
 <user id="1000006">
  <username>Admin6</username>
  <email>admin6@live.cn</email>
  <age>23</age>
  <sex>girl</sex>
 </user>
</users>

# -*- 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()

C:\Users\wzh94434\Desktop\xml>python user.py

user_nodes: [<DOM Element: user at 0x2758c48>, <DOM Element: user at 0x2756288>,

 <DOM Element: user at 0x2756888>, <DOM Element: user at 0x2756e88>, <DOM Elemen

t: user at 0x275e4c8>, <DOM Element: user at 0x275eac8>]

-----------------------------------------------------

No.: 1000001

name: Admin

sex: boy

age: 23

Email: admin@live.cn

-----------------------------------------------------

No.: 1000002

name: Admin2

sex: boy

age: 22

Email: admin2@live.cn

-----------------------------------------------------

No.: 1000003

name: Admin3

sex: boy

age: 27

Email: admin3@live.cn

-----------------------------------------------------

No.: 1000004

name: Admin4

sex: gril

age: 25

Email: admin4@live.cn

-----------------------------------------------------

No.: 1000005

name: Admin5

sex: boy

age: 20

Email: admin5@live.cn

-----------------------------------------------------

No.: 1000006

name: Admin6

sex: gril

age: 23

Email: admin6@live.cn　 

minidom.parse(filename)

加载读取XML文件

 

doc.documentElement

获取XML文档对象

 

node.getAttribute(AttributeName)

获取XML节点属性值

 

node.getElementsByTagName(TagName)

获取XML节点对象集合

 

node.childNodes #返回子节点列表。

 

node.childNodes[index].nodeValue

获取XML节点值

 

node.firstChild

#访问第一个节点。等价于pagexml.childNodes[0]

 

doc = minidom.parse(filename)

doc.toxml('UTF-8')

返回Node节点的xml表示的文本

 

Node.attributes["id"]

a.name #就是上面的 "id"

a.value #属性的值 

访问元素属性