BookSpider.py 文件源码

def parse(self, response):
        links = response.xpath("//*[@class = 'tagCol']/descendant::a/@href").extract()
        for href in links:
            for pageNum in np.linspace(0, 180, 10): # ????Tag??10???
                full_url = response.urljoin(href + "/?start=" + str(int(pageNum)) + "&type=S") # ?type=S  ????????
                yield scrapy.Request(full_url, callback=self.parse_tag_per_page)

    # ???????????????