python基础2-xml模块

 

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的格式如下，就是通过<>节点来区别数据结构的：

<?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>

xml协议在各个语言里的都 是支持的，在python中可以用以下模块操作xml 

import xml.etree.ElementTree as ET

tree = ET.parse("test.xml")
root = tree.getroot()
print(root.tag)
#遍历xml文档
for child in root:
    print(child.tag,child.attrib)
    for i in child:
        print(i.tag,i.text,i.attrib)

#只遍历year节点
for node in root.iter('year'):
    print(node.tag,node.text)

修改和删除xml文档内容

import xml.etree.ElementTree as ET

tree = ET.parse("test.xml")
root = tree.getroot()

#修改
for node in root.iter('year'):
    new_year = int(node.text) + 1
    node.text = str(new_year)
    #可以加属性
    node.set("updated","yes")

tree.write("test.xml")

#删除
for country in root.findall("country"):
    rank = int(country.find("rank").text)
    if rank >50:
        root.remove(country)

tree.write('output.xml')

自己创建xml文档

import xml.etree.ElementTree as ET

new_xml = ET.Element("personinfolist")
personinfo = ET.SubElement(new_xml,"personinfo",attrib={"enrolled":"yes"})
name = ET.SubElement(personinfo,"name")
name.text = "luoliyu"
age = ET.SubElement(personinfo,"age",attrib={"checked":"no"})
sex = ET.SubElement(personinfo,"sex")
sex.text = '33'
personinfo2 = ET.SubElement(new_xml,"personinfo",attrib={"enrolled":"no"})
age = ET.SubElement(personinfo2,"age")
age.text = '19'

et = ET.ElementTree(new_xml) #生成文档对象
et.write("new.xml", encoding="utf-8",xml_declaration=True)

ET.dump(new_xml) #打印生成的格式