myspider.py 文件源码

def parse_item(self,response):
        self.logger.info('Hi,this is an item page! %s',response.url)

        item = scrapy.Item()
        item['id'] = response.xpath('//td[@id="item_id"]/text()').re(r'ID: (\d+)')
        item['name'] = response.xpath('//td[@id="item_name"]/text()').extract()
        item['description'] = response.xpath('//td[@id="item_description"]/text()').extract()
        return item