基于bs4+requests的安居客爬虫

2018-09-10 11:09:01 浏览数 (1)

1.代码可以直接运行,请下载anaconda并安装,用spyder方便查看变量 或者可以查看生成的excel文件 2.依赖库,命令行运行(WIN10打开命令行快捷键:windows x组合键,然后按a键): pip install BeautifulSoup4 pip install requests 3.爬取的网站是安居客(厦门)网站,可以进入https://xm.fang.anjuke.com/loupan/all/进行观察 4.关于如何判断代码是python2还是python3,print('')为python3,print ''为python2

代码语言:javascript复制
# -*- coding: utf-8 -*-
"""
Created on Sun Jan 14 19:07:39 2018

@author: Steven Lei
"""

def getHousesDetails(url):
  import requests
  from bs4 import BeautifulSoup
  
  request = requests.get(url)
  request.encoding = 'utf-8'
  soup = BeautifulSoup(request.text,'lxml')
  houses = soup.select('.item-mod')[3:]
  housesDetails = []
  for house in houses:
    #获取楼盘名字
    houseName = house.select('.items-name')[0].text
    #获取楼盘价格
    priceBefore = house.select('.price')
    if(len(priceBefore) == 0):
        priceBefore = house.select('.price-txt')
    price = priceBefore[0].text
    #获取楼盘地址
    address = house.select('.list-map')[0].text
    if(address[-1] == '.'):
      href = house.select('.pic')[0]['href']
      request = requests.get(href)
      request.encoding = 'utf-8'
      soup = BeautifulSoup(request.text,'lxml')
      address = soup.select('.lpAddr-text')[0].text
    #获取房屋面积
    houseSizeBefore = house.select('.huxing span')
    if(len(houseSizeBefore) >0):
      houseSize = houseSizeBefore[-1].text
    else:
      houseSize = ''
    #获取销售状态
    saleStatus = house.select('.tag-panel i')[0].text
    #获取户型
    if(len(house.select('.tag-panel i')) == 2):
      houseType = house.select('.tag-panel i')[1].text
    else:
      houseType = house.select('.tag-panel span')[0].text
    #将获取的信息做成房屋信息字典
    houseDetail = {}
    houseDetail['houseName'] = houseName
    houseDetail['price'] = price
    houseDetail['address'] = address
    houseDetail['houseSize'] = houseSize
    houseDetail['saleStatus'] = saleStatus
    houseDetail['houseType'] = houseType
    print(houseDetail)
    housesDetails.append(houseDetail)
  return housesDetails

def getAllHouseDetails():
  import pandas
  urlBefore = 'https://xm.fang.anjuke.com/loupan/all/p{}/'
  allHouseDetails = []
  for i in range(1,8):
    url = urlBefore.format(i)
    allHouseDetails.extend(getHousesDetails(url))
  dataframe = pandas.DataFrame(allHouseDetails)
  return dataframe

if __name__ == '__main__':
  #houseDetails = getHousesDetails('https://xm.fang.anjuke.com/loupan/all/p1/')
  allHouseDetails = getAllHouseDetails()
  allHouseDetails.to_excel('anjukeHousesDetails.xlsx')
  print(allHouseDetails.head(10))

0 人点赞