Method parse

tests/jd_spider.py:32–41

(self, request, response)

        yield feapder.Request(url, task_id=task_id)  # 携带task_id字段

    def parse(self, request, response):
        title = response.xpath("string(//div[@class='sku-name'])").extract_first(default="").strip()

        item = Item()
        item.table_name = "jd_item"  # 指定入库的表名
        item.title = title
        item.batch_date = self.batch_date  # 获取批次信息，批次信息框架自己维护
        item.crawl_time = tools.get_current_date()  # 获取当前时间
        yield item  # 自动批量入库
        yield self.update_task_batch(request.task_id, 1)  # 更新任务状态


if __name__ == "__main__":