from bs4 import BeautifulSoup
# 创建解析对象
soup = BeautifulSoup(html_content, 'lxml')
# 查找单个元素
title = soup.find('h1', class_='main-title')
print(title.text.strip())
# CSS选择器查找
articles = soup.select('div.article-list article')
for article in articles:
title = article.select_one('h2.title').text
link = article.select_one('a')['href']
print(f"标题: {title}, 链接: {link}")
lxml基于libxml2库,XPath功能强大,适合复杂结构的精准定位:
性能优势:解析速度比BeautifulSoup快3-5倍
XPath表达式:支持路径、条件、轴等高级语法
应用场景:动态表格、嵌套列表、多层级DOM
from lxml import html
# 解析HTML
tree = html.fromstring(html_content)
# XPath定位
titles = tree.xpath('//div[@class="article"]//h2/text()')
links = tree.xpath('//div[@class="article"]//a/@href')
for i, title inenumerate(titles):
print(f"{i+1}. {title} -> {links[i]}")