若你範圍都確定的話，不如從start_urls 下手

start_urls = ['http://www.alexa.cn/siterank/{n}'.format(n=x) for x in range(2,10)]

官網上有例子，關於追蹤下一頁，官網上面的例子用的是遞歸，官網的代碼如下：

import scrapy class QuotesSpider(scrapy.Spider): name = "quotes" start_urls = [ 'http://quotes.toscrape.com/page/1/', ] def parse(self, response): for quote in response.css('p.quote'): yield { 'text': quote.css('span.text::text').extract_first(), 'author': quote.css('small.author::text').extract_first(), 'tags': quote.css('p.tags a.tag::text').extract(), } # next_page是用css选择器获取到的下一页， 在下面它递归地调用了parse方法来不断地追踪下一页 next_page = response.css('li.next a::attr(href)').extract_first() if next_page is not None: next_page = response.urljoin(next_page) yield scrapy.Request(next_page, callback=self.parse)

我自己用Scrapy寫了一個貼吧的爬蟲，取得下一頁用的也是這種遞歸的方法，程式碼如下：

import scrapy from tieba_crawler.items import ImageItem class TiebaSpider(scrapy.Spider): name = 'tbimg' def start_requests(self): url = 'http://tieba.baidu.com/f?kw=%E6%B8%A1%E8%BE%B9%E9%BA%BB%E5%8F%8B' yield scrapy.Request(url=url, callback=self.parse_post) def parse_post(self, response): post_list = response.css('ul#thread_list li.j_thread_list') for item in post_list: title = item.css('a.j_th_tit::text').extract_first() url = 'http://tieba.baidu.com' \ + item.css('a.j_th_tit::attr(href)').extract_first() yield scrapy.Request(url=url, callback=self.parse_image) page_list = response.css('p#frs_list_pager a::attr(href)').extract() if not page_list: return else: next_page = page_list[-2] if next_page: yield response.follow(next_page, callback=self.parse_post) def parse_image(self, response): img_urls = response.css('p#j_p_postlist img.BDE_Image::attr(src)').extract() yield ImageItem(image_urls=img_urls) page_list = response.css('ul.l_posts_num li.pb_list_pager a::attr(href)').extract() if not page_list: return else: next_page = page_list[-2] if next_page: yield response.follow(next_page, callback=self.parse_image)