Python格式化XML的三种常见方法详解

<person>
    <name>Alice</name>
    <age>25</age>
    <skills>
        <skill>Python</skill>
        <skill>Data Analysis</skill>
    </skills>
</person>

from xml.dom import minidom

xml_str = """
<person>
<name>Alice</name><age>25</age>
<skills><skill>Python</skill><skill>Data Analysis</skill></skills>
</person>
"""

# 解析XML字符串
dom = minidom.parseString(xml_str)

# 获取格式化后的XML字符串
formatted_xml = dom.toprettyxml(indent="  ", encoding="utf-8").decode()

print("格式化后的XML:")
print(formatted_xml)

<?xml version="1.0" ?>
<person>
  <name>Alice</name>
  <age>25</age>
  <skills>
    <skill>Python</skill>
    <skill>Data Analysis</skill>
  </skills>
</person>

# 从文件读取并格式化
with open("input.xml", "r") as f:
    dom = minidom.parse(f)
    formatted_xml = dom.toprettyxml(indent="    ")

# 写入格式化后的XML到新文件
with open("output_formatted.xml", "w") as f:
    f.write(formatted_xml)

pip install lxml

from lxml import etree

xml_str = """
<person>
<name>Alice</name><age>25</age>
<skills><skill>Python</skill><skill>Data Analysis</skill></skills>
</person>
"""

# 解析XML
root = etree.fromstring(xml_str)

# 创建ElementTree对象
tree = etree.ElementTree(root)

# 格式化输出（方法1）
formatted_xml = etree.tostring(
    root, 
    pretty_print=True, 
    encoding="unicode", 
    xml_declaration=True
)

print("格式化后的XML:")
print(formatted_xml)

# 更复杂的格式化选项
formatted_xml = etree.tostring(
    root,
    pretty_print=True,
    encoding="unicode",
    doctype='<!DOCTYPE person SYSTEM "person.dtd">',  # 可选DOCTYPE
    xml_declaration=True,
    with_tail=True  # 保留元素后的文本
)

# 从文件读取并格式化
parser = etree.XMLParser(remove_blank_text=True)  # 可选：移除空白文本
tree = etree.parse("input.xml", parser)

# 写入格式化后的XML
tree.write(
    "output_lxml.xml",
    pretty_print=True,
    encoding="utf-8",
    xml_declaration=True,
    doctype='<!DOCTYPE person SYSTEM "person.dtd">'
)

import xml.etree.ElementTree as ET

def prettify(element, indent="  ", level=0):
    """递归格式化ElementTree元素"""
    result = []
    # 处理元素开始标签
    result.append(indent * level + f"<{element.tag}")
    if element.attrib:
        for k, v in element.attrib.items():
            result.append(f' {k}="{v}"')
    result.append(">\n")
    
    # 处理子元素
    for child in element:
        result.append(prettify(child, indent, level + 1))
    
    # 处理文本内容
    if element.text and element.text.strip():
        result.append(indent * (level + 1) + element.text.strip() + "\n")
    
    # 处理元素结束标签
    result.append(indent * level + f"</{element.tag}>\n")
    
    return "".join(result)

# 示例使用
xml_str = """
<person>
<name>Alice</name><age>25</age>
<skills><skill>Python</skill><skill>Data Analysis</skill></skills>
</person>
"""

root = ET.fromstring(xml_str)
formatted_xml = prettify(root)

print("手动格式化的XML:")
print(formatted_xml)

import requests
from lxml import etree

response = requests.get('https://example.com/api/data.xml')
if response.status_code == 200:
    root = etree.fromstring(response.content)
    pretty_xml = etree.tostring(
        root, 
        pretty_print=True, 
        encoding="unicode"
    )
    print("格式化后的API响应:")
    print(pretty_xml)
else:
    print(f"请求失败，状态码: {response.status_code}")

from lxml import etree

# 原始配置
config = """
<config>
<database><host>localhost</host><port>5432</port></database>
<logging level="INFO"/>
</config>
"""

# 解析并格式化
root = etree.fromstring(config)
formatted_config = etree.tostring(
    root,
    pretty_print=True,
    encoding="unicode",
    xml_declaration=True
)

# 保存到文件
with open("config_formatted.xml", "w") as f:
    f.write(formatted_config)

import time
from xml.dom import minidom
from lxml import etree
import xml.etree.ElementTree as ET

# 生成大型XML
large_xml = "<root>" + "".join([f"<item id='{i}'/>" for i in range(10000)]) + "</root>"

# 测试minidom
start = time.time()
dom = minidom.parseString(large_xml)
_ = dom.toprettyxml()
print(f"minidom耗时: {time.time()-start:.2f}秒")

# 测试lxml
start = time.time()
root = etree.fromstring(large_xml)
_ = etree.tostring(root, pretty_print=True, encoding="unicode")
print(f"lxml耗时: {time.time()-start:.2f}秒")

# 测试ElementTree手动格式化（仅小样本）
small_xml = "<root>" + "".join([f"<item id='{i}'/>" for i in range(100)]) + "</root>"
start = time.time()
root = ET.fromstring(small_xml)
_ = prettify(root)
print(f"ElementTree手动格式化耗时: {time.time()-start:.2f}秒")