房天下爬虫

#！/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
import pandas
def gethousedetail(url):
    info ={}
    res = requests.get(url)
    soup = BeautifulSoup(res.text,'html.parser')
    info['title']=soup.select('title')[0].text.strip()
    info['price']=soup.select('.zongjia1 .red20b')[0].text.strip()
    for dd in soup.select('dd'):
        if '：' in dd.text.strip():
            k,v = dd.text.strip().split('：')
            info[k]=v
    return info
res = requests.get('http://esf.sh.fang.com/')
domain = 'http://esf.sh.fang.com'
soup = BeautifulSoup(res.text,'html.parser')
houseary = []
for house in soup.select('.houseList dl'):
    urls = domain + house.select('.title a')[0]['href']
    houseary.append(gethousedetail(urls))

df =pandas.DataFrame(houseary)
df.to_excel('house.xlsx',index=False)