python爬虫爬取豆瓣电影Top250之我小试

我的第一个爬虫作品，一天完成，纪念一下！

代码如下：

import requests

from bs4 import BeautifulSoup

urls =['https://movie.douban.com/top250?start={}&filter='.format(str(i*25)) for i in range(0,10)]

def get_movieinfo(urls,data = None):

web_data=requests.get(urls)

soup =BeautifulSoup(web_data.text,'lxml')

for data in soup.select('.item'):

rank = data.select('em')[0].text

name = data.select('.info')[0].select('a')[0].text.split('\n')[1]

score = data.select('.rating_num')[0].text

link = data.select('a')[0]['href']

director_actor = data.select('.bd')[0].text.split('\n')[2].lstrip('  ')

time_country = data.select('.bd')[0].text.split('\n')[3].lstrip('  ')

print(rank, name, score, link,director_actor, time_country)

for a in urls:

get_movieinfo(a)

结果如下截图：