Python XML模块

一、定义：

xml是实现不同语言或程序之间进行数据交换的协议，跟json差不多，但json使用起来更简单。

xml就是实现解析xml文件的模块

二、XML文件实例：

<?xml version="1.0"?>
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2011</year>
        <gdppc>13600</gdppc>
        <neighbor name="Costa Rica" direction="W"/>
        <neighbor name="Colombia" direction="E"/>
    </country>
</data>

三、代码实例

import xml.etree.ElementTree as ET
 
tree = ET.parse("xmltest.xml")
root = tree.getroot()
print(root.tag)
 
#遍历xml文档
for child in root:
    print('========>',child.tag,child.attrib,child.attrib['name'])
    for i in child:
        print(i.tag,i.attrib,i.text)
 
#只遍历year 节点
for node in root.iter('year'):
    print(node.tag,node.text)
#---------------------------------------

import xml.etree.ElementTree as ET
 
tree = ET.parse("xmltest.xml")
root = tree.getroot()
 
#修改
for node in root.iter('year'):
    new_year=int(node.text)+1
    node.text=str(new_year)
    node.set('updated','yes')
    node.set('version','1.0')
tree.write('test.xml')
 
 
#删除node
for country in root.findall('country'):
   rank = int(country.find('rank').text)
   if rank > 50:
     root.remove(country)
 
tree.write('output.xml')

#在country内添加（append）节点year2
import xml.etree.ElementTree as ET
tree = ET.parse("a.xml")
root=tree.getroot()
for country in root.findall('country'):
    for year in country.findall('year'):
        if int(year.text) > 2000:
            year2=ET.Element('year2')
            year2.text='新年'
            year2.attrib={'update':'yes'}
            country.append(year2) #往country节点下添加子节点

tree.write('a.xml.swap')

import xml.etree.ElementTree as ET
tree=ET.parse('a.xml')
root=tree.getroot()

for child in root:
    print('====>',child.tag)
    for i in child:
        print(i.tag,i.attrib,i.text)

#查找element元素的三种方式
years=root.iter('year') #扫描整个xml文档树，找到所有
for i in years:
    print(i)

res1=root.find('country') #谁来调，就从谁下一层开始找,只找一个
print(res1)

res2=root.findall('country') #谁来调，就从谁下一层开始找,只找一个
print(res2)


#修改
years=root.iter('year') #扫描整个xml文档树，找到所有
for year in years:
    year.text=str(int(year.text)+1)
    year.set('updated','yes')
    year.set('version','1.0')
tree.write('a.xml')


#删除
for county in root.iter('country'):
    # print(county.tag)
    rank=county.find('rank')
    if int(rank.text) > 10:
        county.remove(rank)
tree.write('a.xml')

#增加节点
for county in root.iter('country'):
    e=ET.Element('egon')
    e.text='hello'
    e.attrib={'age':'18'}
    county.append(e)

tree.write('a.xml')