python 爬虫豆瓣top250-附源码-详细注释

import requests
from bs4 import BeautifulSoup #导入BeautifulSoup库
#由于豆瓣有反爬虫策略，headers用于伪装成浏览器访问，
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
}
#观察豆瓣top250每一页的网页，发现每次递增25，于是每次循环步长25，用来更新链接
for start in range(0,250,25):
    response = requests.get(f"https://movie.douban.com/top250?start={start}",headers=headers) #更新链接
    html = response.text #获取html文件，传递给html变量
    suop = BeautifulSoup(html,"html.parser") #调用BeautifulSoup，用html.parser来解析html
    titles = suop.findAll("span", attrs={"class": "title"}) #过滤，找到所有的span标签，class=title的信息
    for tit in titles: #遍历titles给tit
       tit_string = tit.string #只将tit的字符串提取出来赋值给tit——string
       if "/" not in tit_string: #如果不带有“/”，就输出
           print(tit_string)