爬取豆瓣高分电影榜实例

import requests
from bs4 import BeautifulSoup

seq = 0
for preSumCount in range(0,301,25):
    response = requests.get(
        ‘https://www.douban.com/doulist/240962/?start=%s&sort=seq&playable=0&sub_type=‘%preSumCount
    )
    #查看该网址编码格式
    # print(response.apparent_encoding)
    content = response.text

    soup = BeautifulSoup(content,features=‘html.parser‘)

    obj_list = soup.find_all(‘div‘,class_=‘doulist-item‘,)

    with open(‘豆瓣高分电影‘, ‘a‘, encoding=‘utf-8‘) as f:
        for obj in obj_list:
            try:
                seq +=1
                title = obj.find(‘div‘,class_=‘title‘)
                url = title.find(‘a‘).attrs[‘href‘]
                movie = title.text.strip(‘"‘).strip()

                score = obj.find(‘span‘,class_=‘rating_nums‘).text

                info = ‘排名:‘+str(seq)+‘  ‘ + movie + ‘   ‘ +‘评分:‘+score + ‘   ‘ +url +‘\n‘
                print(info,end=‘‘)
                f.write(info)




            except:
                print(seq,‘ 不存在‘)