python爬虫实战项目-爬取豆瓣电影top250

废话不多说，直接上代码

import requests
from bs4 import BeautifulSoup
import csv
import time

def crawl_douban_movie_top_250():
    base_url = 'https://movie.douban.com/top250?start='
    headers = { # 用户代理（User-Agent）头部信息，模拟真实的浏览器请求
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36'
    }

    movie_list = []

    for i in range(10):
        url = base_url + str(i * 25)
        response = requests.get(url, headers=headers)
        soup = BeautifulSoup(response.text, 'html.parser')
        movie_items = soup.select('.item')

        for movie_item in movie_items:
            title = movie_item.select_one('.title').text.strip()
            info = movie_item.select_one('.bd p').text.strip()
            rating = movie_item.select_one('.rating_num').text.strip()
            rating_count = movie_item.select_one('.star span:last-child').text.strip('人评价')
            quote = movie_item.select_one('.inq')
            if quote:
                quote = quote.text.strip()
            else:
                quote = ''
            movie_list.append([title, info, rating, rating_count, quote])
            print(f'成功爬取电影：{title}')

        # 添加延时等待，规避频繁请求被限制
        time.sleep(2)

    save_to_csv(movie_list)

def save_to_csv(movie_list):
    with open('douban_movie_top_250.csv', 'w', encoding='utf-8-sig', newline='') as file:
        writer = csv.writer(file)
        writer.writerow(['电影名称', '简介', '评分', '评价人数', '引言'])
        writer.writerows(movie_list)

if __name__ == '__main__':
    crawl_douban_movie_top_250()