Python利用ElementTree实现快速解析XML文件

<bookstore>
  <book category="编程">
    <title>Python从入门到精通</title>
    <author>张伟</author>
    <year>2023</year>
  </book>
  <book category="小说">
    <title>三体</title>
    <author>刘慈欣</author>
    <year>2008</year>
  </book>
</bookstore>

import xml.etree.ElementTree as ET

xml_string = """
<bookstore>
  <book category="编程">
    <title>Python从入门到精通</title>
    <author>张伟</author>
  </book>
</bookstore>
"""

root = ET.fromstring(xml_string)  # 从字符串加载

tree = ET.parse('books.xml')  # 从文件加载
root = tree.getroot()

for book in root.findall('book'):
    print("找到一本书：")
    print(f"类别：{book.get('category')}")
    print(f"书名：{book.find('title').text}")
    print(f"作者：{book.find('author').text}")

# 查找第一个匹配的节点
first_book = root.find('book')

# 查找所有匹配节点
all_books = root.findall('book')

# 用XPath查找（更强大）
titles = root.findall('.//title')  # 查找所有title节点

# 获取属性
category = book.get('category')

# 获取文本内容
title = book.find('title').text

# 处理可能不存在的节点
year = book.find('year')
if year is not None:
    print(year.text)

<ns:book xmlns:ns="http://example.com">
  <ns:title>XML解析指南</ns:title>
</ns:book>

ns = {'ns': 'http://example.com'}
title = root.find('ns:title', ns).text

import requests

url = "https://example.com/rss"
response = requests.get(url)
root = ET.fromstring(response.content)

for item in root.findall('.//item'):
    print(f"标题：{item.find('title').text}")
    print(f"链接：{item.find('link').text}")
    print("----")

for event, elem in ET.iterparse('big_file.xml'):
    if elem.tag == 'book':
        print(elem.find('title').text)
        elem.clear()  # 及时清理内存

from lxml import etree  # 需要安装：pip install lxml

# 比标准库快3-5倍
parser = etree.XMLParser(remove_blank_text=True)
tree = etree.parse('books.xml', parser)

with open('data.xml', 'r', encoding='utf-8') as f:
    tree = ET.parse(f)

from xml.sax.saxutils import escape
safe_text = escape('文本&特殊字符<>"')

from xml.dom import minidom
xml_str = ET.tostring(root)
pretty_xml = minidom.parseString(xml_str).toprettyxml()

import xml.etree.ElementTree as ET

def parse_xml(file_path):
    tree = ET.parse(file_path)
    root = tree.getroot()
    
    results = []
    for book in root.findall('book'):
        data = {
            'category': book.get('category'),
            'title': book.find('title').text,
            'author': book.find('author').text,
            'year': book.find('year').text if book.find('year') is not None else None
        }
        results.append(data)
    
    return results

# 使用示例
books = parse_xml('books.xml')
for book in books:
    print(f"{book['title']}（{book['year']}）")