doubanBookSpider.py 文件源码

def parse(self, response):
        selector = Selector(response)
        books = selector.xpath('//div[@class="info"]/h2/a/@href').extract()
        for book in books:
            print book
            yield Request(book, callback=self.parse_item)

        nextPage = selector.xpath('//span[@class="next"]/a/@href').extract()
        if nextPage:
            print nextPage[0]
            yield Request(self.url+nextPage[0],callback=self.parse)