Meizitu.py 文件源码

def parse_item(self, response):
         item = CrawlmeizituItem()
         selector = scrapy.Selector(response)

         image_title = selector.xpath('//h2/a/text()').extract()
         image_url = selector.xpath('//h2/a/@href').extract()
         image_tags = selector.xpath('//div[@class="metaRight"]/p/text()').extract()
         if selector.xpath('//*[@id="picture"]/p/img/@src').extract():
            image_src = selector.xpath('//*[@id="picture"]/p/img/@src').extract()
         else:
            image_src = selector.xpath('//*[@id="maincontent"]/div/p/img/@src').extract()
         if selector.xpath('//*[@id="picture"]/p/img/@alt').extract():
             pic_name = selector.xpath('//*[@id="picture"]/p/img/@alt').extract()
         else:
            pic_name = selector.xpath('//*[@id="maincontent"]/div/p/img/@alt').extract()
         #//*[@id="maincontent"]/div/p/img/@alt
         item['title'] = image_title
         item['url'] = image_url
         item['tags'] = image_tags
         item['src'] = image_src
         item['alt'] = pic_name
         print(item)
         time.sleep(1)
         yield item