第一个爬虫：获取演员表

最新推荐文章于 2025-05-16 22:35:53 发布

FrankHuang888

最新推荐文章于 2025-05-16 22:35:53 发布

阅读量462

点赞数 2

文章标签：爬虫

本文链接：https://blog.youkuaiyun.com/qq_33323974/article/details/138138381

版权

import requests
from bs4 import BeautifulSoup

def get_actors():
    actor_list = []
    for i in range(0,10):
         link = "http://movie.douban.com/top250?start="+str(i*25)
         header = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 SE 2.X MetaSr 1.0","Host":"movie.douban.com" }
         response  = requests.get(link,headers = header)
         #print(response.status_code)
         soup = BeautifulSoup(response.text,"html.parser")
         div_list = soup.find_all('div',class_='bd')
         for each in div_list:
             actor = each.p.text.strip()
             actor_list.append(actor)
    return actor_list

actors = get_actors()
print(actors)