浅用chatgpt
import requests
from bs4 import BeautifulSoup
# 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/58.0.3029.110 Safari/537.36'}
# 设置要爬取的页面数量
page_num = 5
# 循环爬取每一页的数据
for i in range(page_num):
url = 'https://movie.douban.com/top250?start=' + str(i * 25) + '&filter='
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
movie_list = soup.find_all('div', class_='info')
# 循环解析每一部电影的信息
for movie in movie_list:
title = movie.find('span', class_='title').text
rating = movie.find('span', class_='rating_num').text
if float(rating) >= 9.5:
print(title + ' ' + rating)