sisy_spider.py 文件源码

def parse_item(self, response):

        selector = Selector(response).xpath('//p[@align="center"]')
        for sel in selector:
            image_urls = sel.xpath('a/img/@src').extract()
            path = []
            for img in image_urls:
                path.append(urlparse.urlparse(img).path)

        item = SisyItem()                             
        item['image_urls'] = image_urls
        item['images']     = path

        return item