XML模块

目录

• 什么是XML
• python操作xml
• 创建xml数据
• XML格式转字典dict
• 字典dict转xml格式

什么是XML

XML是可扩展标记语言（eXtensible Markup Language），标准通用标记语言的子集，是一种用于标记电子文件使其具有结构性的标记语言。被设计用来传输和存储数据，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。

xml的格式如下，就是通过<>节点来其区别数据结构的：

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year update="yes" updated="yes">2012</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" updated="yes">2015</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
    
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year update="yes" updated="yes">2015</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>

python操作xml

import xml.etree.ElementTree as ET

tree = ET.parse("xml_test")     # parse解析,把xml数据解析开给对象tree
root = tree.getroot()       # 拿到根节点(对象)
print(root.tag)     # tag: 打印对象的标签名字

# 遍历xml文档
for i in root:
    print(i.tag, i.attrib)      # attrib: 拿属性
    for j in i:
        print(j.tag, j.text)      # text: 标签包裹的内容
        
# 只遍历根节点的year
for node in root.iter('year'):
    print(node.tag, node.text)
    
# 修改
for node in root.iter("year"):
    new_year = int(node.text) + 1       # 对year进行操作加1
    node.text =str(new_year)        # 将操作后的新值赋值

    node.set("updated", "yes")      # 给year增加属性updated="yes"

tree.write('xml_test')      # 修改后必须得写入文件才算完成


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

tree.write("xml_test1")

创建xml数据

# 创建xml数据
import xml.etree.ElementTree as ET

new_xml = ET.Element("namelist")  # Element:创建了根节点<namelist></nameliat>
name = ET.SubElement(new_xml, "name1", attrib={"enrolled": "yes"})  # Subelement:创建子节点
# <name1 enrolled="yes"></name1>

age = ET.SubElement(name, "age", attrib={"check": "no"})  # 在name下在创建子节点age，内容为23
sex = ET.SubElement(name, "sex")  # 在name下在创建子节点sex，内容为男
sex.text = '男'

name = ET.SubElement(new_xml, "name2", attrib={"enrolled": "no"})  # Subelement创建子节点
# <name1 enrolled="yes"></name1>
age = ET.SubElement(name, "age")  # 在name下在创建子节点age，内容为19
age.text = '19'
sex = ET.SubElement(name, "sex")  # 在name下在创建子节点sex

et = ET.ElementTree(new_xml)  # 生成文档对象
et.write("new_xml", encoding="UTF-8", xml_declaration=True)

XML格式转字典dict

data_xml = """
    <xml>
        <rank updated="yes">69</rank>
        <year update="yes" updated="yes">2015</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
    </xml>
"""
import xml.etree.ElementTree as ET
def xml_to_dict(data_xml):
    data = ET.fromstring(data_xml)
    data_dic = {}
    # 遍历data对象，将data的标签作为字典的key，标签内容作为字典的value，存入到字典中
    for child in data:
        data_dic[child.tag] = child.text
    return data_dic

字典dict转xml格式

data_dict = {'name':'Bob','age':18,'gender':'male'}
def dict_to_xml(data_dict):
    data_xml_list = []
    for key,value in data_dict.items():
        data_xml_list.append(f'<{key}>{value}</{key}>')
    xml_str = ''.join(data_xml_list)
    data_xml = f'<xml>{xml_str}</xml>'
    return data_xml