xml 模块

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>

 

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

#三种查找方式
#1、在root的子节点找，只找一个
print(root.find('country')) 
#2、在root的子节点找，找所有
print(root.findall('country')) 
#3、从正树形结构中查找
print(list(root.iter('rank'))) #全文搜索

for country in root.findall('country'):
    rank=country.find('rank')
print(rank.tag,rank.attrib,rank.text)

#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)

#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')

 

#自己创建xml文档
import xml.etree.ElementTree as ET

new_xml = ET.Element("namelist")
name = ET.SubElement(new_xml,"name",attrib={"enrolled":"yes"})
age = ET.SubElement(name,"age",attrib={"checked":"no"})
sex = ET.SubElement(name,"sex")
sex.text = '33'
name2 = ET.SubElement(new_xml,"name",attrib={"enrolled":"no"})
age = ET.SubElement(name2,"age")
age.text = '19'
 
et = ET.ElementTree(new_xml) #生成文档对象
et.write("test.xml", encoding="utf-8",xml_declaration=True)
 
ET.dump(new_xml) #打印生成的格式