【代码分享】Python正则爬取数据

所需包 request re

爬取豆瓣电影高分榜

import requests
import re
headers = {
'User-Agent': 'Mozilla/5.0 (Linux; U; Android 8.1.0; zh-cn; BLA-AL00 Build/HUAWEIBLA-AL00) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.132 MQQBrowser/8.9 Mobile Safari/537.36'
}

url = 'https://m.douban.com/doulist/240962/'

response = requests.get(url)
results = re.findall('.*?href="(.*?)".*?cover.*?src="(.*?)"\salt="(.*?)">.*?(.*?).*?meta.*?>(.*?).*?recommend.*?>(.*?)',response.text,re.S)
for result in results:
#print(result)
print(result[0],result[1],result[2],result[3],result[4])