技術標籤：pythonpython

1. 通過開發者工具找到試題連結地址；
2. 對試題連結的url進行分析，發現index是試題id名稱，構造隨機數，可使用range或者excel拉出全部；
3. 對json資料進行欄位分析
4. 我這裡分開寫了兩個指令碼，一個是獲取資料一個是轉成excel，本文主要為多程序獲取資料
5. 開發環境python3.9.1/windows10/vscode

6. #coding:utf-8
   import requests
   from concurrent.futures import ProcessPoolExecutor
   import json
   
   # 通過url獲取資料
   # url = 'http://mnks.jxedt.com/get_question?r=0.5376675619396274&index=3'
   urls_list = []
   with open('D:/YYFX/ip.txt','r') as f:
       for line in f:
           #print line,
           urls_list.append(line.replace('\n', ''))
   #模擬瀏覽器header
   hea = {'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'}
   #程序
   pool = ProcessPoolExecutor(20)
   def get_page(url):
       #requests.get 自帶 json.load
       
       response = requests.get('http://%s'%(url),headers = hea,timeout = 30 ,verify=False)
       response = response.content
       #將bytes轉換成字串
       response = response.decode('utf-8')
       return  response
   
   def read_data(future,*args,**kwargs):
       response = future.result()
       state = json.loads(response)
   #     print(response.status_code,response.url)
   
       print (state)
       #product = response1["question"]+'\n'
       with open('%s.json'%'data','a',encoding='utf-8') as f:
   #儲存json資料防止亂碼
           f.write(json.dumps(state,ensure_ascii=False) + '\n')
       f.close()
   
   
   def main():
       for url in urls_list:
           done = pool.submit(get_page,url)
           done.add_done_callback(read_data)
   if __name__ == '__main__':
       main()
       pool.shutdown(wait=True)
       f.close()