python 制作網站篩選工具(附源碼)

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

#取源文件中的網址並且去重
def get_url(old_file):
  with open(old_file,'r',encoding='gbk')as f:
    urllist=list(set(f.readlines()))
    return urllist

#主體，發送請求，通過異常捕獲判斷能否響應，通過狀態碼判斷網閘能否正常訪問
def request(url):
  url=url.strip()
  #構造請求頭信息
  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:
    #忽略證書安全警告
    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
    r=requests.get(url,headers=headers,timeout=10,verify=False)#timeout設置超時時間，我設置瞭10s，使用verif=False忽略sll認證
    if r.status_code==200:
      cost_time=r.elapsed.total_seconds()#計算訪問耗時
      print(url,' ----->【能訪問】訪問耗時:\033[35;46m{:.2f}s\033[0m'.format(cost_time))
      can_access_save_to_txt(url)
    else:
      print(url,' ----->不能訪問,狀態碼為:\033[31;44m{}\033[0m'.format(r.status_code))
  except:
    print(url, ' ----->不能訪問,原因：\033[31;44m不能響應\033[0m')


#將能訪問的網址保存到new_file
def can_access_save_to_txt(result):
  result=result.strip()
  #篩選出不是.apk的url,此判斷可以不加
  if not result.endswith('.apk'):
    with open(aim_file,'a')as f:
      f.write(result+'\n')


def main():
  s_time=time.time()
  #使用線程池，創建四條線程。
  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 程序正常執行結束退出！共耗時:【{sum_time//60}分鐘】 \033[0m')
  elif sum_time/60>1:
    print(f'\033[38;46m 程序正常執行結束退出！共耗時:【{sum_time//60*60}小時】 \033[0m')


if __name__ == '__main__':
  orign_file=r'E:\test.txt'
  #篩選後能訪問的網址
  aim_file="./data/test_can_access.txt"
  #篩選後不能訪問的網址
  main()