使用Python爬取安居客二手房房价数据

作为一个Python新手，公司突然安排我爬取房价数据，真让人有点头大啊！幸好网上的大佬们经验丰富，给予了很多代码上的帮助。本文代码在网友pythoner111爬虫项目–爬取安居客二手房信息的基础上修改，爬取过程顺利，若有不足之处还请大家指出修改。

import requests
import bs4
import time
import random
import pandas as pd
import openpyxl

house_info=[]

for i in range(1,100):
    url="https://bj.anjuke.com/sale/p"+str(i)+"/#filtersort"
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36"
    }
    print("开始爬取安居客平台北京二手房第%s页信息....." %(str(i)))
    response = requests.get(url=url, headers=headers)
    #生成bs4对象
    bsoup=bs4.BeautifulSoup(response.text,'lxml')

    house_list=bsoup.find_all('li', class_="list-item")

    for house in house_list:
      #bs4解析文件
       titile = house.find('a').text.strip()
       house_type = house.find('div', class_='details-item').span.text
       area = house.find('div', class_='details-item').contents[3].text
       try:
          address = house.find('span',class_='comm-address').text.strip()
       except AttributeError:
          address='error'
       #爬取过程中，有些房子缺少地址信息，使用try except的方法可以防止报错
       price = house.find('span', class_='price-det').text.strip()
       unit_price = house.find('span', class_='unit-price').text.strip()

       pd1= pd.DataFrame({'titile': titile, 'house_type': house_type,
                 'area': area, 'address': address, 'price': price, 'unit_price': unit_price},index=[0])
       house_info.append(pd1)

    second=random.randrange(3,5)
    time.sleep(second)

house_info2=pd.concat(house_info)
house_info2.to_excel('beijing.xlsx',index=False)