XML模块（二十四）

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，不过，古时候，在json还没诞生的黑暗年代，

大家只能选择用xml呀，至今很多传统公司如金融行业的很多系统的接口还主要是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：

# print(root.iter('year')) #全文搜索
# print(root.find('country')) #在root的子节点找，只找一个
# print(root.findall('country')) #在root的子节点找，找所有

查：

import xml.etree.ElementTree as ET

tree = ET.parse('xml_l')
root = tree.getroot()
#　只拿year节点
for year in root.iter('year'):
    print(year.tag,year.text)
'''
year 2008
year 2011
year 2011
'''

 

import xml.etree.ElementTree as ET

tree = ET.parse('xml_l')
root = tree.getroot()
for i in root:
    print(i)
    print(i.tag)  #　tag 标签名
    print(i.attrib) #　属性{'name': 'Liechtenstein'}
    for j in i:
        print(j.tag)
        print(j.attrib) # {'updated': 'yes'}
        print(j.text)
'''
<Element 'country' at 0x022D96F0>
country
{'name': 'Liechtenstein'}
rank
{'updated': 'yes'}
2
year
{}
2008
gdppc
{}
141100
neighbor
{'name': 'Austria', 'direction': 'E'}
None
neighbor
{'name': 'Switzerland', 'direction': 'W'}
None
<Element 'country' at 0x022D9840>
country
{'name': 'Singapore'}
rank
{'updated': 'yes'}
5
year
{}
2011
gdppc
{}
59900
neighbor
{'name': 'Malaysia', 'direction': 'N'}
None
<Element 'country' at 0x022D9960>
country
{'name': 'Panama'}
rank
{'updated': 'yes'}
69
year
{}
2011
gdppc
{}
13600
neighbor
{'name': 'Costa Rica', 'direction': 'W'}
None
neighbor
{'name': 'Colombia', 'direction': 'E'}
None
'''

修改：

import xml.etree.ElementTree as ET

tree = ET.parse("xml_l")
root = tree.getroot()

# 修改
for year in root.iter('year'):
    new_year = int(year.text) + 1
    year.text = str(new_year)
    year.set('update','yes')    # 增加属性
tree.write("new_xml.xml")

new_xml.xml

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

 

import xml.etree.ElementTree as ET

tree = ET.parse("xml_l")
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 = 'NewYear'
            year2.attrib = {'update':'yes'}
            country.append(year2) # 往country下添加子节点
tree.write('xml_l_swap.xml')

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    <year2 update="yes">NewYear</year2></country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    <year2 update="yes">NewYear</year2></country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2011</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    <year2 update="yes">NewYear</year2></country>
</data>

 

删除：

import xml.etree.ElementTree as ET

tree = ET.parse("xml_l")
root = tree.getroot()

# 删除
for country in root.findall('country'):
    rank = int(country.find('rank').text)
    if rank > 50:
        root.remove(country)
tree.write('new_xml2.xml')

new_xml2.xml

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
    </data>

创建XML:

import xml.etree.ElementTree as ET

my_xml = ET.Element("namelist")
name = ET.SubElement(my_xml, "name", attrib={"enrolled":"yes"})
age = ET.SubElement(name, "age", attrib={"checked":"no"})
sex = ET.SubElement(name, "sex")
sex.text = "man"
name2 = ET.SubElement(my_xml, "name1", attrib={"enrolled":"no"})
age = ET.SubElement(name2, "age")
age.text = "18"

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

text.xml

<?xml version='1.0' encoding='utf-8'?>
<namelist>
    <name enrolled="yes">
        <age checked="no" />
        <sex>man</sex>
    </name>
    <name1 enrolled="no">
        <age>18</age>
    </name1>
</namelist>