爬虫札记2——正则re模块爬取maoyan

import re
import requests

for i in range(10):
    url = 'https://maoyan.com/board/4?offset={}'.format(i)
    content = requests.get(url).text
    pattern = re.compile('<dl.*?board-wrapper.*?href="https://ask.hellobi.com/(.*?)".*?title="(.*?)".*?movie-item-info.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?</dl>', re.S)
    results = re.findall(pattern, content)
    print(results)