AJK.py 文件源码

def parse(self, response):
        soup = BeautifulSoup(response.body, 'html.parser')
        #?????
        infos = soup.findAll(attrs={'class': 'item-mod'})
        # ????
        pagesUrl = soup.find(attrs={'class': 'list-page'})
        print("????????")
        # ????
        number = int(pagesUrl.find(attrs={'class': 'total'}).em.string)
        # ??????????50???
        pages = number // 50
        if (number % 50 > 0):
            pages = pages + 1
        print("??" + str(pages))
        purl = pagesUrl.find(attrs={'class': 'pagination'}).a['href']
        purl = purl[0:-3]
        for i in range(1, pages + 1):
            temp = purl + "p" + str(i) + "/"
            print("???????????" + temp)
            print("????" + temp)
            yield scrapy.Request(temp, callback=self.parse_item)
            print("??????")