下载短篇小说存储到文件夹中

还是上次的网站，

哎嘿嘿嘿

上代码

import requests
import re
import os


class Update:
    def __init__(self):
        self.count1 = 0
        self.count2 = 0
        self.head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                                   'Chrome/41.0.2272.118 Safari/537.36'}

    def main(self):  # 获取文章标题和内容，存放到self.lst()里
        for i in range(1, 6):
            url = 'https://www.kanunu8.com/files/little/6-' + str(i) + '.html'
            html = requests.get(url, headers=self.head).content.decode('gbk')
            # print(html)

            pattern1 = re.compile(r"<td width='98%'> <a href='(.*?)' target='_blank'>(.*?)</a></td>", re.S)
            t1 = pattern1.findall(html)  # 获取所有的小说的链接
            for ur in t1:
                try:
                    t = Update.getText(self, ur)
                    print('\t第%d页下载完成。。' % (t1.index(ur) + 1))
                    Update.writeTo(ur[1], t)
                    print('\t 第%d页写入完成。。' % (t1.index(ur) + 1))
                    self.count1 += 1
                except:
                    print('第%d出错。。。跳过本页。。' % (t1.index(ur) + 1))
                    self.count2 += 1
                    continue
            print('第%d页下载完成，开始下载第%d页' % (i, i + 1))
        print('全部短篇下载完成!-*-\n\t成功%d篇\n\t失败%d篇' % (self.count1, self.count2))

    def getText(self, url0):  # 通过主页获得的链接来获得每一页的小说内容
        url = 'https://www.kanunu8.com' + url0[0]
        html = requests.get(url, headers=self.head).content.decode('gbk')

        pattern = re.compile(r'<td height="20" valign="top">(.*?)</td>', re.S)
        t1 = pattern.findall(html)
        t1 = re.sub(r'<.*?>', '', t1[0])
        t1 = re.sub(r'&\w*?;', '', t1)
        t1 = re.sub(r'\s\s\s+', ',', t1)
        return t1

    @staticmethod
    def createPath(pathname):
        ifexists = os.path.exists(pathname)
        if not ifexists:
            os.makedirs(pathname)
        os.chdir(pathname)

    @staticmethod
    def writeTo(title, content):
        with open(title + '-爬取.txt', 'w') as f:
            f.write(content)
        f.close()


if __name__ == '__main__':
    u = Update()
    u.createPath('短篇小说集')
    u.main()

哎嘿嘿嘿！
觉得还可的点个赞再走嘞