python操作XML格式文件的一些常见方法

<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="Singapore">
        <rank updated="yes">5</rank>
        <year>2026</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </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>

#导包
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>

root = ET.XML(content)

country_object = root.find("country")
print(country_object)  #<Element 'country' at 0x0000020D57DFB220>

country_object.tag  #country

country_object.attrib   #{'name': 'Liechtenstein'}

gdppc_object.text    #141100

# 获取data标签的孩子标签
for child in root:
    print(child.tag, child.attrib)
    #获取child标签的孩子标签
    for node in child:
        print(node.tag, node.attrib, node.text)

# 获取data里面所有year标签
for child in root.iter('year'):
    print(child.tag, child.text)

# 查找所有的country标签
v1 = root.findall('country')

# 查找country里面的rank标签,找第一个
v2 = root.find('country').find('rank')

#修改rank文本
rank.text = "999"
tree = ET.ElementTree(root)
tree.write("new.xml", encoding='utf-8')

#修改rank属性
rank.set('update', '2020-11-11')
tree = ET.ElementTree(root)
tree.write("new.xml", encoding='utf-8')

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

root.remove( root.find('country') )
tree = ET.ElementTree(root)
tree.write("new.xml", encoding='utf-8')

<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')
# 创建大儿子，与root还没有关系
son1=ET.Element('son',{'name':'儿1'})
#创建小儿子，与root还没有关系
son2=ET.Element('son',{'name':'儿2'})

#创建2个孙子
grandson1=ET.Element('grandson',{'name':'儿11'})
grandson2=ET.Element('grandson',{'name':'儿12'})

# 创建两个孙子，与son1还没有关系
son1.append(grandson1)
son1.append(grandson2)

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

#root节点放到根节点中
tree=ET.ElementTree(root)
#保存xml文件
# short_empty_elements=True,节点中没有元素，用简写方式显示例：<grandson name="儿11" />
tree.write('file/root.xml',encoding='utf-8',short_empty_elements=True)

<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，与root还没有关系
son1 = root.makeelement('son', {'name': '儿1'})

#创建小儿子，与root还没有关系
son2 = root.makeelement('son', {"name": '儿2'})

# 创建两个孙子，与son1还没有关系
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root节点的子标签大儿子
son1 = ET.SubElement(root, "son", attrib={'name': '儿1'})
# 创建root节点的子标签小儿子
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")
#<![CDATA[你好呀]]直接添加到文本里
root.text = "<![CDATA[你好呀]]"

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

pip install xmltodict

<note date="23/04/2022">
    <to>tom</to>
    <from>mary</from>
    <msg>love</msg></note>

import jsonimport xmltodictdef xml_to_json(xml_str):
    """parse是的xml解析器，参数需要
    :param xml_str: xml字符串
    :return: json字符串
    """
    xml_parse = xmltodict.parse(xml_str)
    # json库dumps()是将dict转化成json格式,loads()是将json转化成dict格式。
    # dumps()方法的ident=1,格式化json
    json_str = json.dumps(xml_parse, indent=1)
    return json_str
 
 
XML_PATH = './1.xml'  # xml文件的路径with open(XML_PATH, 'r') as f:
    xmlfile = f.read()
    with open(XML_PATH[:-3] + 'json', 'w') as newfile:
        newfile.write(xml_to_json(xmlfile))

{
  "student": {
    "course": {
      "name": "math",
      "score": "90"
    },
    "info": {
      "sex": "male",
      "name": "name"
    },
    "stid": "10213"
  }}

import xmltodictimport jsondef json_to_xml(python_dict):
    """xmltodict库的unparse()json转xml
    :param Python_dict: python的字典对象
    :return: xml字符串
    """
    xml_str = xmltodict.unparse(python_dict)
    return xml_str
 
 
JSON_PATH = './test.json'  # json文件的路径with open(JSON_PATH, 'r') as f:
    jsonfile = f.read()
    python_dict = json.loads(jsonfile)  # 将json字符串转换为python字典对象
    with open(JSON_PATH[:-4] + 'xml', 'w') as newfile:
        newfile.write(json_to_xml(python_dict))