糗事百科前十页保存到txt

import requests

from bs4 import BeautifulSoup

# -*-coding:utf-8 -*-

import io

import sys

#改变标准输出的默认编码

sys.stdout=io.TextIOWrapper(sys.stdout.buffer, encoding= 'utf8')

# vscode打印中文问题

headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'}

base_url = 'https://www.qiushibaike.com/8hr/page/'   # 设定一个网址不变的部分，然后我们只要每次在这个后面加数字就可以了

file = open( 'qiubai.txt', 'w')

num = 1

while 1:

    

     file.write( '第' + str(num) + '页' + ' \n ')

    r = requests.get(base_url + str(num), headers = headers)

     # r = requests.get('https://www.qiushibaike.com', headers = headers)

    content = r.text

    soup = BeautifulSoup(content, 'lxml')

    divs_hot = soup.find_all( class_ = 'article block untagged mb15 typs_hot')

     for div in divs_hot:

         if div.find_all( class_ = 'thumb'):

             continue

        joke = div.span.get_text()

         # print('--热门--')

         # print(joke)

         # print('------')

         file.write( '--热门--')

         file.write(joke + ' \n ')

         file.write( '------' + ' \n ')

        

        

    divs_long = soup.find_all( class_ = 'article block untagged mb15 typs_long')

     for div in divs_long:

         if div.find_all( class_ = 'thumb'):

             continue

        joke = div.span.get_text()

         # print('--长篇--')

         # print(joke)

         # print('------')

         file.write( '--长篇--')

         file.write(joke + ' \n ')

         file.write( '------' + ' \n ')

        

    divs_recent = soup.find_all( class_ = 'article block untagged mb15 typs_recent')

     for div in divs_recent:

         if div.find_all( class_ = 'thumb'):

             continue

        joke = div.span.get_text()

         # print('--近期--')

         # print(joke)

         # print('------')

         file.write( '--近期--')

         file.write(joke + ' \n ')

         file.write( '------' + ' \n ')

    divs_old = soup.find_all( class_ = 'article block untagged mb15 typs_old')

     for div in divs_old:

         if div.find_all( class_ = 'thumb'):

             continue

        joke = div.span.get_text()

         # print('--经典--')

         # print(joke)

         # print('------')

         file.write( '--经典--')

         file.write(joke + ' \n ')

         file.write( '------' + ' \n ')

     print( '第 {} 页，完成！'.format(num))

    num += 1

     if num > 10:

         break

file.close