lxml 解析xml\html

复制代码

from lxml import etree

# XML文档示例
xml_doc = """
<root>
    <book>
        <title>Python编程指南</title>
        <author>张三</author>
    </book>
    <book>
        <title>Python高级编程</title>
        <author>李四</author>
    </book>
</root>
"""

# 创建ElementTree对象并解析XML文档
root = etree.fromstring(xml_doc)

# 使用XPath定位元素并打印内容
books = root.xpath('//book')
for book in books:
    title = book.xpath('title/text()')[0]
    author = book.xpath('author/text()')[0]
    print(f"书名：{title}，作者：{author}")

复制代码

# HTML文档示例
html_doc = """
<html>
<body>
    <h1>标题</h1>
    <p>段落1</p>
    <p>段落2</p>
</body>
</html>
"""

# 创建HTML解析器并解析HTML文档
parser = etree.HTMLParser()
root = etree.fromstring(html_doc, parser)

# 遍历HTML元素并打印内容
for element in root.iter():
    print(element.tag, element.text)

复制代码

from lxml import html
import requests
 
# 发送HTTP请求获取网页内容
response = requests.get('https://example.com')
html_content = response.content
 
# 使用lxml解析HTML内容并提取信息
tree = html.fromstring(html_content)
title = tree.xpath('//title/text()')[0]
paragraphs = tree.xpath('//p/text()')
print('标题:', title)
print('段落:')
for p in paragraphs:
    print(p)