基于Python的XML格式的文件

XML文件是可拓展标记语言，是一种简单的数据存储语言，被设计用来传输和存储数据

在Python中XML的一些方法

• 读取文件和内容

#引用xml模块
from xml.etree import ElementTree as ET

# ET去打开xml文件
tree = ET.parse("files/xo.xml")

# 获取根标签
root = tree.getroot()

print(root) # <Element 'data' at 0x7f94e02763b0>

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content) # 获取根标签 
print(root)  # <Element 'data' at 0x7fdaa019cea0>

• 读取节点数据

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein" id="999" >
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

# 获取根标签 data
root = ET.XML(content)

country_object = root.find("country") # 获取XML文件中的country标签
print(country_object.tag, country_object.attrib)# 获取country标签名   获取country标签地属性
gdppc_object = country_object.find("gdppc")# 获取gdppc标签
print(gdppc_object.tag,gdppc_object.attrib,gdppc_object.text)# 获取gdppc标签的名称   获取gdppc属性(没有属性为:{})  获取gdppc标签里面的内容

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

# 获取根标签 data
root = ET.XML(content)

# 获取data标签的孩子标签
for child in root:
    # child.tag = conntry 获取到两个country标签
    # child.attrib = {"name":"Liechtenstein"}
    print(child.tag, child.attrib)
    for node in child:
        print(node.tag, node.attrib, node.text) # 获取到reank标签

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)

# 找到子子孙孙的year标签
for child in root.iter('year'):
    print(child.tag, child.text)

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)
v1 = root.findall('country') # 找到所有的country标签
print(v1)

v2 = root.find('country').find('rank') # 找到country标签中的rank标签
print(v2.text)

• 删除和修改节点

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)

# 修改节点内容和属性
rank = root.find('country').find('rank')
print(rank.text)
rank.text = "999" # 修改rank标签里面的内容
rank.set('update', '2020-11-11') # 为rank标签新增一个update属性
print(rank.text, rank.attrib)
############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("new.xml", encoding='utf-8')


# 删除节点
root.remove( root.find('country') )
print(root.findall('country'))

############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("newnew.xml", encoding='utf-8')

• 构建文档

<home>
    <son name="儿1">
        <grandson name="儿11"></grandson>
        <grandson name="儿12"></grandson>
    </son>
    <son name="儿2"></son>
</home>

from xml.etree import ElementTree as ET

# 创建根标签
root = ET.Element("home")

# 创建节点大儿子
son1 = ET.Element('son', {'name': '儿1'})
# 创建小儿子
son2 = ET.Element('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
grandson1 = ET.Element('grandson', {'name': '儿11'})
grandson2 = ET.Element('grandson', {'name': '儿12'})
son1.append(grandson1)
son1.append(grandson2)

# 把儿子添加到根节点中
root.append(son1)
root.append(son2)

tree = ET.ElementTree(root)
tree.write('oooo.xml', encoding='utf-8', short_empty_elements=False) #short_empty_elements 是否采取短标签的形式创建

<famliy>
    <son name="儿1">
        <grandson name="儿11"></grandson>
        <grandson name="儿12"></grandson>
    </son>
    <son name="儿2"></son>
</famliy>

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("famliy")


# 创建大儿子
son1 = root.makeelement('son', {'name': '儿1'})
# 创建小儿子
son2 = root.makeelement('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
grandson1 = son1.makeelement('grandson', {'name': '儿11'})
grandson2 = son1.makeelement('grandson', {'name': '儿12'})

son1.append(grandson1)
son1.append(grandson2)


# 把儿子添加到根节点中
root.append(son1)
root.append(son2)

tree = ET.ElementTree(root)
tree.write('oooo.xml',encoding='utf-8')

<famliy>
	<son name="儿1">
    	<age name="儿11">孙子</age>
    </son>
	<son name="儿2"></son>
</famliy>

from xml.etree import ElementTree as ET


# 创建根节点
root = ET.Element("famliy")


# 创建节点大儿子
son1 = ET.SubElement(root, "son", attrib={'name': '儿1'})
# 创建小儿子
son2 = ET.SubElement(root, "son", attrib={"name": "儿2"})

# 在大儿子中创建一个孙子
grandson1 = ET.SubElement(son1, "age", attrib={'name': '儿11'})
grandson1.text = '孙子'


et = ET.ElementTree(root)  #生成文档对象
et.write("test.xml", encoding="utf-8")

<user><![CDATA[你好呀]]</user>

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("user")
root.text = "<![CDATA[你好呀]]"

et = ET.ElementTree(root)  # 生成文档对象
et.write("test.xml", encoding="utf-8")