concurrent.futures 使用及解析

from concurrent.futures import ThreadPoolExecutor, as_completed, wait, FIRST_COMPLETED
from concurrent.futures import Future
from multiprocessing import Pool

#未来对象，task的返回容器


#线程池， 为什么要线程池
#主线程中可以获取某一个线程的状态或者某一个任务的状态，以及返回值
#当一个线程完成的时候我们主线程能立即知道
#futures可以让多线程和多进程编码接口一致
import time

def get_html(times):
    time.sleep(times)
    print("get page {} success".format(times))
    return times



executor = ThreadPoolExecutor(max_workers=2)
#通过submit函数提交执行的函数到线程池中, submit 是立即返回
# task1 = executor.submit(get_html, (3))
# task2 = executor.submit(get_html, (2))


#要获取已经成功的task的返回
urls = [3,2,4]
all_task = [executor.submit(get_html, (url)) for url in urls]
wait(all_task, return_when=FIRST_COMPLETED)
print("main")

# for future in as_completed(all_task): #谁先完成，谁先打印
#     data = future.result()
#     print("get {} page".format(data))

#通过executor的map获取已经完成的task的值，顺序
# for data in executor.map(get_html, urls):
#     print("get {} page".format(data))


# #done方法用于判定某个任务是否完成
# print(task1.done())
# print(task2.cancel())
# time.sleep(3)
# print(task1.done())
#
# #result方法可以获取task的执行结果
# print(task1.result())

 

多进程

import time
from concurrent.futures import ThreadPoolExecutor, as_completed
from concurrent.futures import ProcessPoolExecutor
#多进程编程
#耗cpu的操作，用多进程编程， 对于io操作来说， 使用多线程编程，进程切换代价要高于线程

#1. 对于耗费cpu的操作，多进程由于多线程
# def fib(n):
#     if n<=2:
#         return 1
#     return fib(n-1)+fib(n-2)
#
# if __name__ == "__main__":
#     with ThreadPoolExecutor(3) as executor:
#         all_task = [executor.submit(fib, (num)) for num in range(25,40)]
#         start_time = time.time()
#         for future in as_completed(all_task):
#             data = future.result()
#             print("exe result: {}".format(data))
#
#         print("last time is: {}".format(time.time()-start_time))

#2. 对于io操作来说，多线程优于多进程
def random_sleep(n):
    time.sleep(n)
    return n

if __name__ == "__main__":
    with ProcessPoolExecutor(3) as executor:
        all_task = [executor.submit(random_sleep, (num)) for num in [2]*30]
        start_time = time.time()
        for future in as_completed(all_task):
            data = future.result()
            print("exe result: {}".format(data))

        print("last time is: {}".format(time.time()-start_time))