def parse(self, response): sel = Selector(response) for link in sel.xpath('//div[1]/ul/*/div/h3/a/@href').extract(): request = scrapy.Request(link, callback=self.parse_item) yield request
pages = sel.xpath("//div[@class='navigation']/div[@id='wp_page_numbers']/ul/li/a/@href").extract()
print('pages: %s' % pages)
if len(pages) > 5:
page_link = pages[-5]
page_link = page_link.replace('/a/', '')
request = scrapy.Request('http://www.meizitu.com/a/%s' % page_link, callback=self.parse)
yield request
是采集 5 页?