【PythonPlanet】爬虫_电影

豆瓣电影TOP250

import requests
from bs4 import BeautifulSoup
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}
for n in range(11):
    # 获取数据
    url_page = 'https://movie.douban.com/top250?start='+str(n*25)+'&filter='
    res_moves = requests.get(url_page,headers=headers)
    # 解析数据
    bs_moves = BeautifulSoup(res_moves.text,'html.parser')
    top_moves = bs_moves.find('ol',class_='grid_view')
    for tops in top_moves.find_all('li'):
        num = tops.find('em').text
        title = tops.find('span',class_='title').text
        try:
            comment = tops.find('span',class_='inq').text
        except:
            comment = ''
        score = tops.find('span',class_='rating_num').text
        url_move = tops.find('a')['href']
        print(num+'.'+title+'--'+comment+'--'+score+'--'+url_move)