keras flow from directory显示label index
1328
2022-08-16
用python爬虫获取房子多少钱一套(python爬取房价数据)
大数据下的房地产+时代”,互联网平台上每天有高达上百万条房地产资讯,产生网友们数亿次的阅读量。一方面国民对房地产的关注热度只增不减,另一方面房地产行业只为更加以用户为本,不断优化产业链上的各个环节以“更了解用户”为宗旨,为消费者营提供更加透明的更加多维的房地产资讯。
数据获取思路
这里对安居客网站上二手房价格的获取方法做一讲解。
step 1,获取安居客网站中某市二手房楼盘的每个区域的网址;
step 2,进入到某个区域后,得到该区域的二手房楼盘的总页数(即总共的小区数);
step 3,接下来,就可以一页一页地爬取每一页上二手房信息。
注意:若没有代理IP,个人获取的数据量有限,想要获取整个的数据则需要再寻求下其他方法(以后会安利给大家哒)。
下面给大家聊聊,我个人是怎样写python脚本获取部分数据的。
import requests
from lxml import etree
import pandas as pd
import json
import math
import random
import time
import urllib.request
# 获取安居客网站中某市二手房楼盘的每个区域的网址
def get_different_area_wang_zhi(url):
headers = {"Cache-Control": "max-age=0",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.9"}
response = requests.get(url, headers=headers).text
re = etree.HTML(response)
# 返回列表格式
wang_zhi = re.xpath('//div[@class="w1180"]//div[@class="items"]/span[@class="item-title longtag"][contains(text(),"区域:")]/../span[@class="elems-l pp-mod"]/a/@href')
return wang_zhi[1:] #第一个网址为全部的小区的网址,应该去掉
# 得到一个区域的二手房楼盘的总页数(n)
def get_one_area_number(url):
headers = {"Cache-Control": "max-age=0",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.9"}
response = requests.get(url, headers=headers).text
re = etree.HTML(response)
number = re.xpath('//div[@class="w1180"]//span[@class="tit"]/em[2]/text()')
nu = int(number[0])
n = int((nu / 30) + 2) # 这里的+3是一个弹性数值
return n
#爬取安居客的二手房小区信息
def anjuke_new(item,n,city_name):
mozilla = [
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)"
]
headers = {"Cache-Control": "max-age=0",
"User-Agent": "{}".format(random.choice(mozilla)),
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.9"}
for i in range(1,n):
url = item + "p" +str(i)+'/'
l = []
try:
print("正在爬取{}的第{}页".format(url,i))
res = requests.get(url,headers = headers).text
f = etree.HTML(res)
# 获取当前页所有小区的网址
name = f.xpath('//div[@class="list-content"]/div[@_soj="xqlb"]/div[@class="li-info"]/h3/a/text()')
price = f.xpath('//div[@class="list-content"]/div[@_soj="xqlb"]/div[@class="li-side"]/p/strong/text()')
dan_wei = f.xpath('//div[@class="list-content"]/div[@_soj="xqlb"]/div[@class="li-side"]/p[1]/text()')
address = f.xpath('//div[@class="list-content"]/div[@_soj="xqlb"]/div[@class="li-info"]/address/text()')
year = f.xpath('//div[@class="list-content"]/div[@_soj="xqlb"]/div[@class="li-info"]/p[@class="date"]/text()')
for j in range(len(price)):
d = {}
d["小区名称"] = name[j]
d["价格"] = price[j]
k = 2 * j
d["价格单位"] = dan_wei[k + 1]
d["小区地址"] = address[j]
d["建造年代"] = year[k]
l.append(d)
except:
print("爬取{}的第{}页错误".format(url, i))
with open(r"./anjuke_second_house_error.txt", "a") as f:
f.write("{}第{}页出错\n".format(url, i))
continue
print("爬取{}的第{}页完成".format(url,i))
data = pd.DataFrame(l)
data.to_csv(r"./{0}_anjuke_second_house_zero.csv".format(city_name), mode="a", header=None, encoding="utf-8_sig")
time.sleep(random.randint(5,10))
#安居客二手房主函数调用
def anjuke_second_main(url,city_name):
wang_zhi = get_different_area_wang_zhi(url)
for item in wang_zhi:
n = get_one_area_number(item)
anjuke_new(item,n,city_name)
time.sleep(random.randint(10,15))
#爬取其他城市修改url,只需要修改城市名称的简称即可,例如西安是xa,厦门是xm,具体看安居客的网址。
if __name__ == "__main__":
url = "https://xa.anjuke.com/community/"
#用于储存文件
city_name = "xian"
anjuke_second_main(url,city_name)
通过运行以上脚本,获取的数据样本如下。
版权声明:本文内容由网络用户投稿,版权归原作者所有,本站不拥有其著作权,亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容,请联系我们jiasou666@gmail.com 处理,核实后本网站将在24小时内删除侵权内容。
发表评论
暂时没有评论,来抢沙发吧~