爬取某房产网站获取房价信息

pip install requests
pip install beautifulsoup4

import requests
from bs4 import BeautifulSoup

# 设置目标网站的URL
url = 'https://example.com/房产页面'

# 发送HTTP请求并获取页面内容
response = requests.get(url)
html = response.text

# 使用BeautifulSoup解析HTML
soup = BeautifulSoup(html, 'html.parser')

# 找到并提取感兴趣的信息
# 例如，找到房屋信息的HTML标签并提取相关数据
# 示例： house_info = soup.find('div', class_='house-info').text

# 打印或保存提取的信息
# 示例： print(house_info)

# 可以使用循环和分页机制来爬取多个页面的信息

# 注意：请确保你了解网站的HTML结构，并根据需要调整选择器等内容

python house_spider.py

from bs4 import BeautifulSoup
import re
import requests
import pandas
## pa pufangwang
class down(object):
    def __init__(self):
         self.calls = []
         self.urls = []
         self.nums = 0
    def get_down_urls(self):
        self.urls = []
        htmls =["http://www.0594.com/list-117---1_90-90_120-2----3361---1.html?pb=&od=&hasphoto=1&ft=0"
        ,'http://www.0594.com/list-117---1_90-90_120-2----3361---2.html?pb=&od=&hasphoto=1&ft=0']

        for html in htmls:
            req = requests.get(html)
            bea = BeautifulSoup(req.text)
            find_url = bea.find_all("div",class_="houseList")

            urlss =  BeautifulSoup(str(find_url))
            kkk = urlss.find_all("a")
            self.nums = int(len(kkk))
            for eatch in kkk:
                self.urls.append(eatch.get("href"))
        set(self.urls)


    def get_down_data(self,straget):
        self.calls=[]
        html = straget # 网页
        req = requests.get(html) # 获取本地相应
        bea =  BeautifulSoup(req.text) # 创建实例
        allss = bea.find_all("div",class_="inforTxt")
        dls1 = BeautifulSoup(str(allss))
        dl = dls1.find_all("dl")


        for eatch in dl:
            self.calls.append(eatch.text.replace("\n", ""))
        print(self.calls)


ds = down()
ds.get_down_urls()
dss =list(set(ds.urls))
'''for i in range(ds.nums):
  ds.get_down_data(ds.urls[i])
'''

for i in range(ds.nums):
  ds.get_down_data(dss[i])