scrapy循环爬取色花堂标题和浏览次数

爬虫部分代码

import scrapy


class ItcastSpider(scrapy.Spider):
    name = 'sehuatang' # 爬虫名
    # allowed_domains = ['itcast.cn'] #允许爬虫的范围
    start_urls = ['https://rtuytuytuewr.xyz/forum-2-2.html'] # 最开始请求的url地址

    def parse(self, response):
        # 获取行列表
        tr_list=response.xpath('//table//tr')[5:-2]
        # print(len(tr_list))
        for tr in tr_list:
            item={}
            # 影片名称
            item["common"]=tr.xpath('./th/a[@onclick="atarget(this)"]/text()').extract_first()
            # 查看数量
            item["num"]=tr.xpath('./td[@class="num"]/em/text()').extract_first()
            yield item
        # 找到总页数
        page_count=str(response.xpath('//*[@id="fd_page_bottom"]/div/label/span/text()').extract_first()).replace('/',"").replace("页","")
        # 获取当前页
        current_page=str(response.xpath('//*[@id="fd_page_bottom"]/div/strong/text()').extract_first())
        if int(page_count)!=int(current_page):
            # 说明不是最后一页
            # 找到下一页url地址
            next_url = response.xpath('//*[@id="fd_page_bottom"]/div/a[@class="nxt"]/@href').extract_first()
            next_url='https://rtuytuytuewr.xyz/'+next_url
            print(next_url,int(page_count),int(current_page))
            # 提交任务
            yield scrapy.Request(
                url=next_url,
                callback=self.parse
            )