采用Scrapy框架爬取链家二手房数据

文件夹结构

1.items

import scrapy
class LianjiaItem(scrapy.Item):
    # define the fields for your item here like:
    # 房屋名称
    name = scrapy.Field()
    # 房屋户型
    type = scrapy.Field()
    # 建筑面积
    area = scrapy.Field()
    # 房屋朝向
    direction = scrapy.Field()
    # 装修情况
    fitment = scrapy.Field()
    # 有无电梯
    elevator = scrapy.Field()
    # 房屋总价
    total_price = scrapy.Field()
    # 房屋单价
    unit_price = scrapy.Field()
    # 房屋产权
    property = scrapy.Field()

2. lianjia_spider

import scrapy
from scrapy import Request
from lianjia.items import LianjiaItem
import sys
reload(sys)
sys.setdefaultencoding('utf8')

class LianjiaSpiderSpider(scrapy.Spider):
   name = 'lianjia_spider'
   # 获取初始请求
   def start_requests(self):
       # 生成请求对象
       url =