python 制作网站筛选工具(附源码)

import time
import requests
import urllib3
from concurrent.futures import ThreadPoolExecutor

#取源文件中的网址并且去重
def get_url(old_file):
  with open(old_file,'r',encoding='gbk')as f:
    urllist=list(set(f.readlines()))
    return urllist

#主体，发送请求，通过异常捕获判断能否响应，通过状态码判断网闸能否正常访问
def request(url):
  url=url.strip()
  #构造请求头信息
  headers = {
    'Connection': 'keep-alive',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
  }
  try:
    #忽略证书安全警告
    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
    r=requests.get(url,headers=headers,timeout=10,verify=False)#timeout设置超时时间，我设置了10s，使用verif=False忽略sll认证
    if r.status_code==200:
      cost_time=r.elapsed.total_seconds()#计算访问耗时
      print(url,' ----->【能访问】访问耗时:\033[35;46m{:.2f}s\033[0m'.format(cost_time))
      can_access_save_to_txt(url)
    else:
      print(url,' ----->不能访问,状态码为:\033[31;44m{}\033[0m'.format(r.status_code))
  except:
    print(url, ' ----->不能访问,原因：\033[31;44m不能响应\033[0m')


#将能访问的网址保存到new_file
def can_access_save_to_txt(result):
  result=result.strip()
  #筛选出不是.apk的url,此判断可以不加
  if not result.endswith('.apk'):
    with open(aim_file,'a')as f:
      f.write(result+'\n')


def main():
  s_time=time.time()
  #使用线程池，创建四条线程。
  pool=ThreadPoolExecutor(max_workers=4)
  urls=get_url(orign_file)
  for url in urls:
    pool.submit(request,url)
  pool.shutdown()
  e_time=time.time()
  sum_time=int(e_time-s_time)
  if sum_time>60:
    print(f'\033[38;46m 程序正常执行结束退出！共耗时:【{sum_time//60}分钟】 \033[0m')
  elif sum_time/60>1:
    print(f'\033[38;46m 程序正常执行结束退出！共耗时:【{sum_time//60*60}小时】 \033[0m')


if __name__ == '__main__':
  orign_file=r'E:\test.txt'
  #筛选后能访问的网址
  aim_file="./data/test_can_access.txt"
  #筛选后不能访问的网址
  main()