def get_info(self, response): item = baidu_item() item['id']=response.meta['id'] item['name']=response.meta['name'] redirect_url_list = response.xpath('''//h3/a/@href''').extract() for url in redirect_url_list: if "http" in url or "https" in url: scrapy.Request(url=url, headers=self.headers, timeout=5,meta={'item':item})def parse(self, response): item=response.meta['item'] if self.filter_domain(response.url) == 0: if len(re.findall('/', response.url)) <= 3: if self.filter_figure(response.url): if re.findall('[^/]+(?!.*/)', response.url): if self.filter_figure(response.url): item['url']=[response.url]
现在情况是这样,我在循环的时候写一个 url 规则,但是如果按照item['url']=[response.url] 这种写法每次只能传递一个url,我现在要把循环一遍的url 传递给item['url'] 怎么写呢?
慕无忌1623718
相关分类