豆瓣阅读网站：（https://book.douban.com/tag/小说）

难点：

import cchardet import requests from bs4 import BeautifulSoup  class Douban(object):     '''bs爬豆瓣数据实战‘’      def __init__(self):         self.url = 'https://book.douban.com/tag/小说'         # 如果爬不到完整的页面，可能是因为cookies问题，需要加上cookies         self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/5。。。。。。。。。。。 Safari/537.36',         'Cookie':'ll="118281"; bid=BpEz4O5XrAo; __utmz=30149280.1631957091.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); dbcl2="221725636:d/GlYal/TfQ"; push_doumail_num=0; __utmv=30149280.22172; __gads=ID=ff013b82325bae46-229e8985cecb00。。。。。。。。。。。。。。。。。。。。。。。。。4-3202-4c71-89a7-84b66f896fc5=user_id:1; gr_session_id_22c937bbd8ebd703f2d8e9445f7dfd03_05f066f4-3202-4c71-89a7-84b66f896fc5=true; __utmt_douban=1; _pk_id.100001.8cb4=9bffb40cc78edf5e.1631957089.2.1632456399.1631957260.; __utmt=1; __utmb=30149280.13.10.1632452655'}         self.proxies = {'http':'27.191.60.252:3256'}      def send(self):         ‘发送请求’         res = requests.get(url=self.url,headers=self.headers,proxies=self.proxies).content         self.encoding = cchardet.detect(res)['encoding']         return res.decode(self.encoding)      def clean(self,res):                  # 1 转换成bs4对象         soup = BeautifulSoup(res)         # 2 得到书的名字         # 通过某一层(标签)的属性 标签名[属性名=属性值         data = soup.select('li[class="subject-item"]')         # print(data)          # 建立一个空列表来存储数据         book_list = []         for dara in data:             book_name = dara.select('h2 a')[0].get('title')  书名通过标签的属性获得             book_url = dara.select('h2 a')[0].get('href') #通过标签的属性获得书链接             book_appraise = dara.select('span[class="rating_nums"]')[0].get_text() ##通过标签属性获得书的评分             # print(book_name)             # print(book_url)             # print(book_appraise)             # print(type(book_name))             # print(['{%s:%s},%s'] % (book_name,book_url,book_appraise) )                          total = [book_name,book_url,book_appraise]             book_list.append(total)             # print('=============')          # print(book_list)         return book_list                       def save(self,res):                  with open(10天/douban.txt','w',encoding='utf-8') as f:             for i in range(len(res)):                                  for a in res[i]:                     print(a)                     f.write(str(a) '\r')              print(‘成功保存’)      def run(self):                  # 1 发送请求         res = self.send()         # 2 保存数据(取消保存，最后一步入库)         # self.save(res)         # 3 清洗         data = self.clean(res)         # 4 入库（Excel，数据库）         self.save(data)   if __name__ == '__main__':     Douban().run()      # 以列表的形式保存     # d = [{'d':'sdf'},'da']     # # print(type(d))