python-task9-xml模块

xml概念

XML是可扩展标记语言（Extensible Markup Language）的缩写

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，之前用来做接口(格式)，同样也是可以增删查改

1.可以创建xml文档

2.可以遍历xml文档

3.可以修改xml文件

4.可以删除xml文档内容

创建xml文件

import xml.etree.ElementTree as ET

new_xml = ET.Element("namelist")                                                 # 根节点：namelist
person_info = ET.SubElement(new_xml, "person_info", attrib={"enrolled": "yes"})  # namelist的子节点：person_info
name = ET.SubElement(person_info, "name")                                        # person_info的子节点：name
age = ET.SubElement(person_info, "age", attrib={"checked": "no"})                # person_info的子节点：age，属性：checked= "no"
sex = ET.SubElement(person_info, "sex")                                         # person_info的子节点：sex
name.text = 'dbf-'                                                               # name为dbf-
age.text = '18'                                                                  # age为18
person_info2 = ET.SubElement(new_xml, "person_info", attrib={"enrolled": "no"})  # person_infolist的子节点：person_info2
age = ET.SubElement(person_info2, "age")                                         # person_info的子节点：age
age.text = '19'                                                                  # age为19

et = ET.ElementTree(new_xml)                                                     # 生成文档对象
et.write("test.xml", encoding="utf-8", xml_declaration=True)                     # 打开文件并写入

ET.dump(new_xml)       

遍历xml文件

import xml.etree.ElementTree as ET

tree = ET.parse("xml_test.xml")     # 打开xml_test文件
root = tree.getroot()               # 获取内存地址
print(root)
print(root.tag)                     # 标签名

# 遍历xml文档
for child in root:
    print(child.tag, child.attrib)  # 打印二级标签和属性
    for i in child:
        print(i.tag, i.text)        # 打印三级标签和内容

# 只遍历year 节点
for node in root.iter('year'):
    print(node.tag, node.text)      # 打印指定标签和内容

修改xml文件

import xml.etree.ElementTree as ET

tree = ET.parse("xml_test.xml")                 # 打开文件
root = tree.getroot()                           # 获取地址

# 修改
for node in root.iter('year'):                  # 寻找所有year标签
    new_year = int(node.text) + 1               # 给所有year加一
    node.text = str(new_year)
    node.set("updated", "yes")                  # 添加属性updated = yes

tree.write("xml_test.xml")                      # 写回原文件

# 删除node
for country in root.findall('country'):         # 寻找所有country标签
    rank = int(country.find('rank').text)       # 找到rank
    if rank > 50:
        root.remove(country)                    # 删除满足条件的country标签

tree.write('output.xml')                        # 写回原文件