soufang_spider.py 文件源码

def parse_detail(self,response):

        loc_hxs = scrapy.Selector(response)
        build_num_ = loc_hxs.xpath('/html/body/div[3]/div[4]/div[1]/div[2]/div[2]/ul/li[2]/text()').extract()
        build_num = ''.join(build_num_)

        total_households_ = loc_hxs.xpath('/html/body/div[3]/div[4]/div[1]/div[2]/div[2]/ul/li[4]/text()').extract()
        total_households = ''.join(total_households_)

        plot_ratio_ = loc_hxs.xpath('/html/body/div[3]/div[4]/div[1]/div[2]/div[2]/ul/li[6]/text()').extract()
        plot_ratio = ''.join(plot_ratio_)

        green_ratio_ = loc_hxs.xpath('/html/body/div[3]/div[4]/div[1]/div[2]/div[2]/ul/li[8]/text()').extract()
        green_ratio = ''.join(green_ratio_)

        property_fee_ = loc_hxs.xpath('/html/body/div[3]/div[4]/div[1]/div[2]/div[2]/ul/li[10]/text()').extract()
        property_fee = ''.join(property_fee_)

        item = response.meta['item']
        item['build_num'] = build_num.encode('gbk')
        item['total_households'] = total_households.encode('gbk')
        item['plot_ratio'] = plot_ratio.encode('gbk')
        item['greening_ratio'] = green_ratio.encode('gbk')
        item['properity_fee'] = property_fee.encode('gbk')

        return item