爬虫实验：打印电影名

FrankHuang888

于 2024-04-23 20:48:07 发布

阅读量131

点赞数 2

文章标签：爬虫

本文链接：https://blog.csdn.net/qq_33323974/article/details/138138092

版权

import requests
from bs4 import BeautifulSoup

def get_movies():
    movie_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_='hd')
         for each in div_list:
             movie = each.a.span.text.strip()
             movie_list.append(movie)
    return movie_list

movies = get_movies()
print(movies)