1.代碼可以直接運行,請下載anaconda并安裝，用spyder方便查看變量
或者可以查看生成的excel文件
2.依賴庫，命令行運行(WIN10打開命令行快捷鍵：windows+x組合鍵，然后按a鍵)：
pip install BeautifulSoup4
pip install requests
3.爬取的網(wǎng)站是藍房網(wǎng)(廈門)，可以進入http://house.lanfw.com/xm/search-y1/進行觀察
4.關(guān)于如何判斷代碼是python2還是python3,print('')為python3，print ''為python2
簡而言之就是print需要用括號的就是python3,下面代碼如是。
5.爬取53個頁面并進行解析，程序運行后需要等待大概30秒

# -*- coding: utf-8 -*-
"""
Created on Mon Jan 15 21:35:52 2018

@author: Steven Lei
"""

def getHousesDetails(url):
  from bs4 import BeautifulSoup
  import requests
  request = requests.get(url)
  request.encoding = 'utf-8'
  soup = BeautifulSoup(request.text,'lxml')
  houses = soup.select('.lpList')
  housesDetails = []
  for house in houses:
    #獲取樓盤名字
    houseName = house.select('.title h2 a')[0].text
    #獲取樓盤地址
    address = house.select('.lpTxt div')[1].select('p')[1].text.strip('樓盤地址： 查看地圖')
    if(len(address) >= 16):
        houseDetailHref = house.select('.title h2 a')[0]['href']
        request = requests.get(houseDetailHref)
        request.encoding = 'utf-8'
        soup = BeautifulSoup(request.text,'lxml')
        address = soup.select('.toplpMsg ul li div i')[0].text.strip('樓盤地址：')
    #獲取樓盤開盤時間
    openTime = house.select('.lpTxt div')[1].select('p')[3].text.strip('開盤時間：')
    #獲取樓盤價格
    price = house.select('.price p b')[0].text
    #獲取樓盤銷售狀態(tài)
    def numberToString(number):
      switcher = {
          1: "在售",
          3: "尾盤",
          5: "未售",
          15: "售罄"
      }
      return switcher.get(number,'未知')
    saleStatusImg = house.select('.title p img')[0]['src']
    saleStatusId = int(saleStatusImg.lstrip('/public/images/state_').rstrip('.jpg'))
    saleStatus = numberToString(saleStatusId)
    #將所有樓盤信息做成樓盤信息字典
    houseDetails = {}
    houseDetails['houseName'] = houseName 
    houseDetails['address'] = address
    houseDetails['openTime'] = openTime
    houseDetails['price'] = price
    houseDetails['saleStatus'] = saleStatus
    housesDetails.append(houseDetails)
  return housesDetails    

def getAllHousesDetails():
  maxPageNumber = 54
  urlBefore = 'http://house.lanfw.com/xm/search-y{}'
  allHousesDetails = []
  for i in range(1,maxPageNumber+1):
    url = urlBefore.format(i)
    allHousesDetails.extend(getHousesDetails(url))
  import pandas
  dataframe = pandas.DataFrame(allHousesDetails)
  return dataframe

if __name__ == '__main__':
  allHousesDetails = getAllHousesDetails()
  allHousesDetails.to_excel('houseDetails2.xlsx')