day16作业

day16作业

使用requests爬取某租房网站数据

import requests
from re import *

response = requests.get('https://cd.zu.ke.com/zufang')
result = response.text

data_address = []
data_name1 = findall(r'<a target="_blank" href=".*">([()\u4e00-\u9fa5]*)<',result)
data_name2 = findall(r'<a href="/zufang/.*" target="_blank">([()\u4e00-\u9fa5]*)</a>-<a title="', result)
data_name3 = findall(r'<a title="([()\u4e00-\u9fa5]*).*</a>', result)
for x in range(len(data_name1)):
    data_address.append(data_name1[x]+'-'+data_name2[x]+'-'+data_name3[x])
data_price = []
data = []

data_size = findall(r' ([.0-9]*㎡)', result)
data_price1 = findall(r'content__list--item-price"><em>([.0-9]*)</em> 元/月', result)
for x in data_price1:
    data_price.append(x+r'元/月')


for x in range(len(data_price)):
    data.append(data_address[x]+'\t面积：'+data_size[x]+'\t租金'+data_price[x])
for x in data:
    print(x)