python之xml序列化

这篇文章主要为大家详细介绍了python序列化功能之xml具有一定的参考价值，感兴趣的小伙伴们可以参考一下

<?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>

上面是一段xml文本的示例，如果要对xml文本进行处理，需要导入一个模块。

import xml.etree.ElementTree as ET

＃由于xml模块的名字太长，使用as给它取了个别名，叫ET。

#!/usr/bin/env python
'''
xml 格式概述
有根节点、子节点  属性 值得概念  有类似于html的开始和结束
'''
import xml.etree.ElementTree as ET

tree = ET.parse("xmltest.xml")
root = tree.getroot()
print(root.tag)    ###data

'''
#遍历xml文档
for child in root:
    print(child.tag, child.attrib)
    for i in child:
        print("--->",i.tag,i.text)  ###列出子序列的所有数据

#只遍历year 节点
for node in root.iter('year'):     ###iter 方法 有过滤的意思
    print(node.tag,node.text)   ##列出年份  node.tag  tag 有标记的意思    node.text  text 有值的意思


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

tree.write("xmltest-1.xml")  ###新的内容在年份的位置上就加1了

#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')      #####结果是把大于50的panma 这个国家下面的内容就删除了
'''

###新建 xml
new_xml = ET.Element("namelist")
name = ET.SubElement(new_xml,"name",attrib={"enrolled":"yes"})   ###enrolled 是注册的意思
age = ET.SubElement(name,"age",attrib={"checked":"no"})
sex = ET.SubElement(name,"sex")
age.text = '33'
sex.text = 'female'
name2 = ET.SubElement(new_xml,"name2",attrib={"enrolled":"no"})
age = ET.SubElement(name2,"age")
sex = ET.SubElement(name2,"sex")
age.text = '19'
sex.text = 'male'
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


#结果会生成如下所示的情况
'''
<?xml version='1.0' encoding='utf-8'?>
<namelist>
    <name enrolled="yes">
        <age checked="no">33</age>
        <sex>female</sex>
    </name>
    <name2 enrolled="no">
        <age>19</age>
        <sex>male</sex>
    </name2>
</namelist>
''