在python中解析具有多个根的xml数据

from lxml import etree

xml_data = '''
<root1>
    <child1>Content1</child1>
</root1>
<root2>
    <child2>Content2</child2>
</root2>
'''

# 使用lxml的etree.fromstring方法解析XML数据
root_elements = etree.fromstring(xml_data, parser=etree.XMLParser(recover=True))

for root in root_elements:
    print(f"Root tag: {root.tag}")
    for child in root:
        print(f"  Child tag: {child.tag}, content: {child.text}")

import xml.etree.ElementTree as ET

xml_data = '''
<root1>
    <child1>Content1</child1>
</root1>
<root2>
    <child2>Content2</child2>
</root2>
'''

# 手动分割XML数据
root_elements = xml_data.strip().split('</root>')

for root_element in root_elements:
    if not root_element:
        continue
    root_element = f'<root>{root_element}</root>'
    root = ET.fromstring(root_element)
    print(f"Root tag: {root.tag}")
    for child in root:
        print(f"  Child tag: {child.tag}, content: {child.text}")

import re
import xml.etree.ElementTree as ET

xml_data = '''
<root1>
    <child1>Content1</child1>
</root1>
<root2>
    <child2>Content2</child2>
</root2>
'''

# 使用正则表达式提取根元素
root_elements = re.findall(r'<root\d+>.*?</root\d+>', xml_data, re.DOTALL)

for root_element in root_elements:
    root = ET.fromstring(root_element)
    print(f"Root tag: {root.tag}")
    for child in root:
        print(f"  Child tag: {child.tag}, content: {child.text}")