Python模块--xml处理模块

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，在json还没诞生之前，只能选择用xml。

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)
    for i in child:
        print(i.tag, i.text)

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

处理结果

<Element 'data' at 0x00000226637B1F48>
data
country {'name': 'Liechtenstein'}
rank 2
year 2008
gdppc 141100
neighbor None
neighbor None
country {'name': 'Singapore'}
rank 5
year 2011
gdppc 59900
neighbor None
country {'name': 'Panama'}
rank 69
year 2011
gdppc 13600
neighbor None
neighbor None
year 2008
year 2011
year 2011

修改xml文档内容

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")

tree.write("xmltest.xml")

处理结果

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year updated="yes">2009</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year updated="yes">2012</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year updated="yes">2012</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>

删除xml文档内容

import xml.etree.ElementTree as ET

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

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

tree.write('xmltest.xml')

处理结果

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year updated="yes">2009</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year updated="yes">2012</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
</data>

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

处理结果

<?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>

 

参考：http://www.cnblogs.com/alex3714/articles/5161349.html