lianjia_spider.py 文件源码

def parse_detail(self,response):
        #print 'in'

        loc_hxs = scrapy.Selector(response)
        loudongzongshu = loc_hxs.xpath('/html/body/div[5]/div[2]/div[2]/div[5]/span[2]/text()').extract()
        loudongzongshu = ''.join(loudongzongshu)

        fangwuzongshu = loc_hxs.xpath('/html/body/div[5]/div[2]/div[2]/div[6]/span[2]/text()').extract()
        fangwuzongshu = ''.join(fangwuzongshu)

        item = response.meta['item']
        item['address'] = loudongzongshu.encode('gbk')
        item['zonghushu'] = fangwuzongshu.encode('gbk')

        return item