爬虫的小技能

# [('金台路交通部部委楼南北大三居带客厅   单位自持物业', '3室1厅', '91.22平米'), ('西山枫林 高楼层南向两居 户型方正 采光好', '2室1厅', '94.14平米')]
f = open('lianjia.html','r',encoding='utf-8')
s = f.read()
parttern1 = '<div class="info clear">.*?<a class="".*?>(?P<title>.*?)</a>.*?<span class="divide">/</span>(?P<house_type>.*?)<span class="divide">/</span>(?P<size>.*?)<span class="divide">/</span>'
parttern = '.*?"">(.*?)</a>.*?<span class="divide">/</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>'
# parttern = '.*?"">(.*?)</a>.*?</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>(.*?)<span class="divide">/</span>'
import re
ret1 = re.findall(parttern,s,re.S)
ret2 = re.findall(parttern1,s,re.S)      . 匹配除换行符以外的所有字符,,但是加上  re.S 就可以匹配所有的字符
print(ret1)
print(ret2)
f.close()