爬虫html网页

import requests
from bs4 import BeautifulSoup

def function():
    # 目标URL（示例：豆瓣电影Top250）
    url = "https://movie.douban.com/top250"

    # 设置请求头，模拟浏览器访问
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }

    data = {}
    # 发送HTTP请求
    response = requests.get(url, params=data,headers=headers)

    # 检查请求是否成功
    if response.status_code == 200:
        # 解析HTML内容
        soup = BeautifulSoup(response.text, "html.parser")

        # 提取电影标题（示例：提取所有class为"title"的span标签）
        movie_titles = soup.find_all("span", class_="title")
            
        # 打印结果
        for idx, title in enumerate(movie_titles, 1):
            print(f"{idx}. {title.get_text()}")
    else:
        print(f"请求失败，状态码：{response.status_code}")

function()