爬虫小练习

import requests
import re

link="http://www.santostang.com/"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0'
           }
r=requests.get(link,headers=headers)
html=r.text
#print(html)

title_list=re.findall('<h1 class="post-title"><a href=.*?>(.*?)</a></h1>',html)
print(title_list)