python:xml模块

#!usr/bin/env python
# -*- coding:utf-8 -*-

__author__ = "Samson"

#############################################################################################################
# xml是实现不同语言或程序之间进行数据交换的协议，和json差不多，但json使用起来简单；不过，以前，在json还没诞生之际，
#只能选择用xml啊，至今很多公司如金融行业的很多系统的接口主要还是xml文件
#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("xmltest.xml")
root = tree.getroot()
print(root)
print(root.tag)

#遍历xml文档
for child in root:
    print(child.tag,child.attrib)#打印标签和属性名(<country name="Liechtenstein">)
    for i in child:
        print(i.tag,i.text)#打印标签和值

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


##修改和删除xml文档内容
#修改
for node in root.iter("year"):
    new_year = int(node.text)+1
    node.text = str(new_year)
    node.set("updated","yes")
tree.write("xmltest.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')


##自己创建xml文档
new_xml = ET.Element("namelist")#根节点
name = ET.SubElement(new_xml, "name", attrib={"enrolled": "yes"})#根节点的子节点
age = ET.SubElement(name, "age", attrib={"checked": "no"})#name的子节点
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
#结果：    <?xml version='1.0' encoding='utf-8'?>
#           <namelist><name enrolled="yes"><age checked="no" /><sex>33</sex></name><name enrolled="no"><age>19</age></name></namelist>