利用Python轻松解析XML文件

<bookstore>
  <book category="编程">
    <title>Python编程入门</title>
    <author>张伟</author>
    <year>2023</year>
    <price>59.99</price>
  </book>
  <book category="设计">
    <title>UI设计原则</title>
    <author>李娜</author>
    <year>2022</year>
    <price>49.99</price>
  </book>
</bookstore>

import xml.etree.ElementTree as ET

# 解析XML文件
tree = ET.parse('bookstore.xml')
root = tree.getroot()

# 遍历所有book元素
for book in root.findall('book'):
    title = book.find('title').text
    author = book.find('author').text
    price = book.find('price').text
    print(f"书名：{title}，作者：{author}，价格：{price}")

for book in root.findall('book'):
    category = book.get('category')
    print(f"类别：{category}")

<ns:bookstore xmlns:ns="http://example.com/books">
  <ns:book>...</ns:book>
</ns:bookstore>

# 注册命名空间
ET.register_namespace('ns', 'http://example.com/books')
# 查找时需要加上命名空间前缀
for book in root.findall('ns:book', {'ns': 'http://example.com/books'}):
    # 处理book元素

from lxml import etree

tree = etree.parse('bookstore.xml')
# 使用XPath查找所有价格大于50的书
expensive_books = tree.xpath('//book[price>50]/title/text()')
print(expensive_books)  # 输出：['Python编程入门']

pip install lxml

from xml.sax.saxutils import escape

unsafe = '"This" & "That"'
safe = escape(unsafe)
print(safe)  # 输出："This" & "That"

with open('bookstore.xml', 'r', encoding='gbk') as f:
    tree = ET.parse(f)

for book in root.findall('book'):
    price = float(book.find('price').text)
    book.find('price').text = str(price * 1.1)

​​​​​​​# 保存修改后的文件
tree.write('bookstore_updated.xml')

new_root = ET.Element('bookstore')
book = ET.SubElement(new_root, 'book', {'category':'小说'})
ET.SubElement(book, 'title').text = '三体'
ET.SubElement(book, 'author').text = '刘慈欣'

# 生成XML字符串
xml_str = ET.tostring(new_root, encoding='unicode')
print(xml_str)

for event, elem in ET.iterparse('large_file.xml'):
    if elem.tag == 'book':
        # 处理book元素
        elem.clear()  # 及时清理已处理的元素

import xmlschema
schema = xmlschema.XMLSchema('schema.xsd')
schema.validate('bookstore.xml')

import pandas as pd
df = pd.read_xml('bookstore.xml')
print(df)