爬蟲(chóng)糗事百科第一頁(yè)的段子

import requests

import re

def comenzar():

? ? ? ?r = requests.get('https://www.qiushibaike.com')pattern = '*?<.*?class="content">.*?(.*?).*?'

? ? ? ?result = re.findall(pattern,r.text,re.S)

? ? ? ?#對(duì)內(nèi)容進(jìn)行過(guò)濾

? ? ? ? num = 1

? ? ? ? for subRequest in result:

? ? ? ? ? ? ? ?filterResult = re.sub('|&quat','',subRequest)print(str(num) + '.' + filterResult + '\n')

? ? ? ? ? ? ? ?with open('糗事.txt','a',encoding = 'utf-8') as f:

? ? ? ? ? ? ? ? f.write(str(num) + '.' + filterResult + '\n\n\n')

? ? ? ? ? ? ? ? num += 1

comenzar()