scrapy循環爬取色花堂標題和瀏覽次數

爬蟲部分代碼

import scrapy


class ItcastSpider(scrapy.Spider):
    name = 'sehuatang' # 爬蟲名
    # allowed_domains = ['itcast.cn'] #允許爬蟲的范圍
    start_urls = ['https://rtuytuytuewr.xyz/forum-2-2.html'] # 最開始請求的url地址

    def parse(self, response):
        # 獲取行列表
        tr_list=response.xpath('//table//tr')[5:-2]
        # print(len(tr_list))
        for tr in tr_list:
            item={}
            # 影片名稱
            item["common"]=tr.xpath('./th/a[@onclick="atarget(this)"]/text()').extract_first()
            # 查看數量
            item["num"]=tr.xpath('./td[@class="num"]/em/text()').extract_first()
            yield item
        # 找到總頁數
        page_count=str(response.xpath('//*[@id="fd_page_bottom"]/div/label/span/text()').extract_first()).replace('/',"").replace("頁","")
        # 獲取當前頁
        current_page=str(response.xpath('//*[@id="fd_page_bottom"]/div/strong/text()').extract_first())
        if int(page_count)!=int(current_page):
            # 說明不是最后一頁
            # 找到下一頁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))
            # 提交任務
            yield scrapy.Request(
                url=next_url,
                callback=self.parse
            )