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

#IO密集型任務
#多個進程同時下載多個網頁
#利用Queue+多進程
#由于是IO密集型,所以同樣可以利用threading模塊

import multiprocessing

def main():
  tasks = multiprocessing.JoinableQueue()
  results = multiprocessing.Queue()
  cpu_count = multiprocessing.cpu_count() #進程數目==CPU核數目

  create_process(tasks, results, cpu_count)  #主進程馬上創建一系列進程,但是由于阻塞隊列tasks開始為空,副進程全部被阻塞
  add_tasks(tasks) #開始往tasks中添加任務
  parse(tasks, results) #最后主進程等待其他線程處理完成結果


def create_process(tasks, results, cpu_count):
  for _ in range(cpu_count):
    p = multiprocessing.Process(target=_worker, args=(tasks, results)) #根據_worker創建對應的進程
    p.daemon = True #讓所有進程可以隨主進程結束而結束
    p.start() #啟動

def _worker(tasks, results):
  while True:  #因為前面所有線程都設置了daemon=True,故不會無限循環
    try:
      task = tasks.get()  #如果tasks中沒有任務,則阻塞
      result = _download(task)
      results.put(result)  #some exceptions do not handled
    finally:
      tasks.task_done()

def add_tasks(tasks):
  for url in get_urls(): #get_urls() return a urls_list
    tasks.put(url)

def parse(tasks, results):
  try: 
    tasks.join()
  except KeyboardInterrupt as err:
    print "Tasks has been stopped!"
    print err

  while not results.empty():
    _parse(results)



if __name__ == '__main__':
  main()


          

            
def handler():
  futures = set()

  with concurrent.futures.ProcessPoolExecutor(max_workers=cpu_count) as executor:
    for task in get_task(tasks):
      future = executor.submit(task)
      futures.add(future)

def wait_for(futures):
  try:
    for future in concurrent.futures.as_completed(futures):
      err = futures.exception()
      if not err:
        result = future.result()
      else:
        raise err
  except KeyboardInterrupt as e:
    for future in futures:
      future.cancel()
    print "Task has been canceled!"
    print e
  return result