第6关 csv&excel 【课后习题】豆瓣电影

一、题目

记得我们第三关的时候爬取了豆瓣TOP250的电影名/评分/推荐语/链接，现在呢，我们要把它们存储下来，记得用今天课上学的csv和excel，分别存储下来哦～

import requests, bs4, csv

file = open("movie_top250.csv",'w',newline="")
writer = csv.writer(file)
writer.writerow(["序号","电影名","评分","推荐语","链接"])

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}
for x in range(10):
    url = 'https://movie.douban.com/top250?start=' + str(x * 25) + '&filter='
    res = requests.get(url, headers=headers)
    bs = bs4.BeautifulSoup(res.text, 'html.parser')
    bs = bs.find('ol', class_="grid_view")
    for titles in bs.find_all('li'):
        num = titles.find('em', class_="").text
        title = titles.find('span', class_="title").text
        comment = titles.find('span', class_="rating_num").text
        url_movie = titles.find('a')['href']

        if titles.find('span', class_="inq") != None:
            tes = titles.find('span', class_="inq").text
            writer.writerow([num,title,comment,tes,url_movie])
            # print(num + '.' + title + '——' + comment + '\n' + '推荐语：' + tes + '\n' + url_movie)
        else:
            # print(num + '.' + title + '——' + comment + '\n' + '\n' + url_movie)
            writer.writerow([num, title, comment,"",url_movie])
file.close()