Python实现XML的操作

本文从以下两个方面, 用Python实现XML的操作：

一. minidom写入XML示例1

二. minidom写入XML示例2

三. ElementTree写入/修改示例

四. ElementTree读取/修改/写入示例

一. minidom写入XML示例1

1.引入包

import xml.dom.minidom

2.write XML方法

writexml(writer, indent, addindent, newl, encoding)

writer是文件对象
indent是每个tag前填充的字符，如：‘  ‘，则表示每个tag前有两个空格
addindent是每个子结点的缩近字符，如下面的例子中单引号中我直接用的tab键
newl是每个tag后填充的字符，如：‘\n‘，则表示每个tag后面有一个回车
encoding是生成的XML信息头中的encoding属性值，在输出时minidom并不真正进行编码的处理，如果你保存的文本内容中有汉字，则需要自已进行编码转换。

3.Python代码

#xmlTest_write.py
# -*- coding: utf-8 -*-

import xml.dom.minidom

#生成xml文件
def GenerateXml():
    impl = xml.dom.minidom.getDOMImplementation()
    #设置根结点emps
    dom = impl.createDocument(None, ‘emps‘, None)
    root = dom.documentElement
    employee = dom.createElement(‘emp‘)

    #增加属性
    employee.setAttribute("empno","1111")
    root.appendChild(employee)

    #设置子结点
    #ename
    nameE=dom.createElement(‘ename‘)
    nameT=dom.createTextNode(‘杰克‘)
    nameE.appendChild(nameT)
    #子节点添加属性
    nameE.setAttribute("lastname","克")

    employee.appendChild(nameE)
    #age
    nameE=dom.createElement(‘age‘)
    nameT=dom.createTextNode(‘33‘)
    nameE.appendChild(nameT)

    employee.appendChild(nameE)

    f= open(‘emplist.xml‘, ‘w‘) #w替换为a，追加
    dom.writexml(f, addindent=‘ ‘, newl=‘\n‘)
    f.close()

GenerateXml()

4.写入XML结果

<?xml version="1.0" ?>
<emps>
    <emp empno="1111">
        <ename lastname="克">杰克</ename>
        <age>33</age>
    </emp>
</emps>

二. minidom写入XML示例2

1.Python代码

#Python写xml比较简单，直接使用xml模块的minidom即可对xml文件进行写入操作
    from xml.dom.minidom import Document
    doc = Document()
    people = doc.createElement("people")
    doc.appendChild(people)
    aperson = doc.createElement("person")
    people.appendChild(aperson)
    name = doc.createElement("name")
    aperson.appendChild(name)
    personname = doc.createTextNode("Annie")
    name.appendChild(personname)
    filename = "people.xml"
    f = open(filename, "w")
    f.write(doc.toprettyxml(indent="  "))
    f.close()

2. 写入XML结果

<?xml version="1.0" ?>
<people>
  <person>
    <name>Annie</name>
  </person>
</people>

三. ElementTree写入/修改XML示例

1.写入XMl的Python代码

#coding=utf-8
import xml.etree.ElementTree as ET
#创建根节点
root = ET.Element("root")
#创建root的子节点sub1，并添加属性
firstNode = ET.SubElement(root,"sub1")
firstNode.attrib = {"name":"name attribute","age":"age attribute"}
#创建子节点1（sub1）的子节点sub2，并添加数据
secondNode = ET.SubElement(firstNode,"sub2")
secondNode.text = "test"
#创建elementtree对象，写文件
tree = ET.ElementTree(root)
tree.write("test01.xml")

2. 写入XML结果

<root>
    <sub1 age="age attribute" name="name attribute">
        <sub2>test</sub2>
    </sub1>
</root>

3. 修改XML方法

1. ElementTree.write("xmlfile"):更新xml文件
2. Element.append():为当前element对象添加子元素（element）
3. Element.set(key,value):为当前element的key属性设置value值
4. Element.remove(element):删除为element的节点

4. 修改XML的Python代码

#coding=utf-8
import xml.etree.ElementTree as ET
#读取待修改文件
updateTree = ET.parse("test.xml")
root = updateTree.getroot()
#创建新节点并添加为root的子节点
newEle = ET.Element("NewElement")
newEle.attrib = {"name":"NewElement","age":"20"}
newEle.text = "This is a new element"
root.append(newEle)

#修改sub1的name属性
sub1 = root.find("sub1")
sub1.set("name","New Name")

#修改sub2的数据值
sub2 = root.find("sub1/sub2")
sub2.text = "New Value"

#写回原文件
updateTree.write("test.xml")

5. 修改XML结果

<root>
    <sub1 age="age attribute" name="New Name">
        <sub2>New Value</sub2>
    </sub1>
    <NewElement age="20" name="NewElement">This is a new element</NewElement>
</root>

四. ElementTree读取/修改/写入示例

1. 原始文档内容（test.xml）：

<?xml version="1.0" encoding="UTF-8"?>
<framework>
  <processers>
    <processer name="AProcesser" file="lib64/A.so"
      path="/tmp">
    </processer>
    <processer name="BProcesser" file="lib64/B.so" value="fordelete">
    </processer>
    <processer name="BProcesser" file="lib64/B.so2222222"/>
    <services>
      <service name="search" prefix="/bin/search?"
        output_formatter="OutPutFormatter:service_inc">
        <chain sequency="chain1"/>
        <chain sequency="chain2"></chain>
      </service>
      <service name="update" prefix="/bin/update?">
        <chain sequency="chain3" value="fordelete"/>
      </service>
    </services>
  </processers>
</framework>

2. Python操作xml代码：

# -*- coding:utf-8 -*-
‘‘‘
Created on 2018年8月30日
@author: Administrator
‘‘‘
from xml.etree.ElementTree import ElementTree,Element
def read_xml(in_path):
  ‘‘‘‘‘读取并解析xml文件
    in_path: xml路径
    return: ElementTree‘‘‘
  tree = ElementTree()
  tree.parse(in_path)
  return tree
def write_xml(tree, out_path):
  ‘‘‘‘‘将xml文件写出
    tree: xml树
    out_path: 写出路径‘‘‘
  tree.write(out_path, encoding="utf-8",xml_declaration=True)
def if_match(node, kv_map):
  ‘‘‘‘‘判断某个节点是否包含所有传入参数属性
    node: 节点
    kv_map: 属性及属性值组成的map‘‘‘
  for key in kv_map:
    if node.get(key) != kv_map.get(key):
      return False
  return True
#---------------search -----
def find_nodes(tree, path):
  ‘‘‘‘‘查找某个路径匹配的所有节点
    tree: xml树
    path: 节点路径‘‘‘
  return tree.findall(path)
def get_node_by_keyvalue(nodelist, kv_map):
  ‘‘‘‘‘根据属性及属性值定位符合的节点，返回节点
    nodelist: 节点列表
    kv_map: 匹配属性及属性值map‘‘‘
  result_nodes = []
  for node in nodelist:
    if if_match(node, kv_map):
      result_nodes.append(node)
  return result_nodes
#---------------change -----
def change_node_properties(nodelist, kv_map, is_delete=False):
  ‘‘‘‘‘修改/增加 /删除 节点的属性及属性值
    nodelist: 节点列表
    kv_map:属性及属性值map‘‘‘
  for node in nodelist:
    for key in kv_map:
      if is_delete:
        if key in node.attrib:
          del node.attrib[key]
      else:
        node.set(key, kv_map.get(key))
def change_node_text(nodelist, text, is_add=False, is_delete=False):
  ‘‘‘‘‘改变/增加/删除一个节点的文本
    nodelist:节点列表
    text : 更新后的文本‘‘‘
  for node in nodelist:
    if is_add:
      node.text += text
    elif is_delete:
      node.text = ""
    else:
      node.text = text
def create_node(tag, property_map, content):
  ‘‘‘‘‘新造一个节点
    tag:节点标签
    property_map:属性及属性值map
    content: 节点闭合标签里的文本内容
    return 新节点‘‘‘
  element = Element(tag, property_map)
  element.text = content
  return element
def add_child_node(nodelist, element):
  ‘‘‘‘‘给一个节点添加子节点
    nodelist: 节点列表
    element: 子节点‘‘‘
  for node in nodelist:
    node.append(element)
def del_node_by_tagkeyvalue(nodelist, tag, kv_map):
  ‘‘‘‘‘同过属性及属性值定位一个节点，并删除之
    nodelist: 父节点列表
    tag:子节点标签
    kv_map: 属性及属性值列表‘‘‘
  for parent_node in nodelist:
    children = parent_node.getchildren()
    for child in children:
      if child.tag == tag and if_match(child, kv_map):
        parent_node.remove(child)
if __name__ == "__main__":
  #1. 读取xml文件
  tree = read_xml("D://test.xml")
  #2. 属性修改
  #A. 找到父节点
  nodes = find_nodes(tree, "processers/processer")
  #B. 通过属性准确定位子节点
  result_nodes = get_node_by_keyvalue(nodes, {"name":"BProcesser"})
  #C. 修改节点属性
  change_node_properties(result_nodes, {"age": "1"})
  #D. 删除节点属性
  change_node_properties(result_nodes, {"value":""}, True)
  #3. 节点修改
  #A.新建节点
  a = create_node("person", {"age":"15","money":"200000"}, "this is the firest content")
  #B.插入到父节点之下
  add_child_node(result_nodes, a)
  #4. 删除节点
  #定位父节点
  del_parent_nodes = find_nodes(tree, "processers/services/service")
  #准确定位子节点并删除之
  target_del_node = del_node_by_tagkeyvalue(del_parent_nodes, "chain", {"sequency" : "chain1"})
  #5. 修改节点文本
  #定位节点
  text_nodes = get_node_by_keyvalue(find_nodes(tree, "processers/services/service/chain"), {"sequency":"chain3"})
  change_node_text(text_nodes, "new text")
  #6. 输出到结果文件
  write_xml(tree, "D://xiugai.xml")

3.更改之后的内容（xiugai.xml）：

<?xml version=‘1.0‘ encoding=‘utf-8‘?>
<framework>
  <processers>
    <processer file="lib64/A.so" name="AProcesser" path="/tmp">
    </processer>
    <processer age="1" file="lib64/B.so" name="BProcesser">
    <person age="15" money="200000">this is the firest content</person></processer>
    <processer age="1" file="lib64/B.so2222222" name="BProcesser"><person age="15" money="200000">this is the firest content</person></processer>
    <services>
      <service name="search" output_formatter="OutPutFormatter:service_inc" prefix="/bin/search?">
        <chain sequency="chain2" />
      </service>
      <service name="update" prefix="/bin/update?">
        <chain sequency="chain3" value="fordelete">new text</chain>
      </service>
    </services>
  </processers>
</framework>

参考文章：

https://docs.python.org/3.5/library/xml.dom.minidom.html
https://docs.python.org/3.5/library/xml.etree.elementtree.html
https://blog.csdn.net/Tcorpion/article/details/75247168?locationNum=8&fps=1
https://blog.csdn.net/tcorpion/article/details/75244681
https://blog.csdn.net/weixin_39909877/article/details/78852287
https://www.jb51.net/article/146558.htm

原文地址：https://www.cnblogs.com/huzixia/p/10391956.html