class QiubaiSpider(scrapy.Spider):
  name = 'qiubai'
  # allowed_domains = ['www.xxx.com']
  start_urls = ['https://www.qiushibaike.com/text/']

  url = 'https://www.qiushibaike.com/text/page/%d/'#通用的url模板
  pageNum = 1
  #parse第一次调用表示的是用来解析第一页对应页面中的段子内容和作者
  def parse(self, response):
    div_list = response.xpath('//*[@id="content-left"]/div')
    all_data = []
    for div in div_list:
      author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()

      content = div.xpath('./a[1]/div/span//text()').extract()
      content = ''.join(content)

      # 将解析的数据存储到item对象
      item = QiubaiproItem()
      item['author'] = author
      item['content'] = content

      # 将item提交给管道
      yield item # item一定是提交给了优先级最高的管道类

    if self.pageNum <= 5:
      self.pageNum += 1
      new_url = format(self.url%self.pageNum)
      #手动请求(get)的发送
      yield scrapy.Request(new_url,callback=self.parse)

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持python博客。