爬虫实战之爬取房天下新房数据
本示例主要用到requests库和bs4库,requests库用来获取网页内容,bs4库则是解析网页内容,获取有用数据。
代码中url可切换当地房天下网址。
代码如下
# -*- coding:utf-8 -*-# author:zhoulong
'''
房天下天水新房信息
'''
import requests
from bs4 import BeautifulSoup
import numpy as np
import re
URL = 'http://newhouse.tianshui.fang.com/house/s/b91/'
HTML = requests.get(URL)
SOUP = BeautifulSoup(HTML.content, 'html.parser', from_encoding='gb18030')
last_page = SOUP.select('.last')
page_number = int(last_page[0]['href'].split('/')[3].split('9')[1])#根据尾页划分页码
url_demo = 'http://newhouse.tianshui.fang.com/house/s/b9{}/'#i+1,name.text.strip(),
#房价价格
house_price_list=[]
for i in range(1,(page_number+1)):
url = url_demo.format(i)
html = requests.get(url)
soup = BeautifulSoup(html.content,'html.parser',from_encoding='gb18030')
names = soup.select('.nlcd_name a')#class定位组合查找
adresses = soup.select('.address a')#查找地址
all_type = soup.findAll(name="span", attrs={"class": re.compile(r"forSale|inSale|outSale|zusale|zushou")})#出售
all_money = soup.findAll(name="div", attrs={"class": re.compile(r"nhouse_price|kanesf")})#价格
for i,name in enumerate(names):
print(i+1,' name:'+name.text.strip(),' address:'+''.join(re.split(r's+',
adresses[i].text.replace('
','').replace('',''))),
all_type[i].text,' house_price: '+all_money[i].text.replace('
',''))
house_price_list.append(re.findall('d+',all_money[i].text.replace('
','')))
house_price_list=[int(i[0]) for i in house_price_list if i]
print('*'*80)
print('* '+' 房价均价:'+str(np.mean(house_price_list))+' '*60+'*')
print('* '+' 房价最高价:'+str(np.max(house_price_list))+' '*60+'*')
print('* '+' 房价最低价:'+str(np.min(house_price_list))+' '*61+'*')
print('*'*80)
执行结果
以上是 爬虫实战之爬取房天下新房数据 的全部内容, 来源链接: utcz.com/z/522476.html