所用到的模块:from concurrent.futures import ThreadPoolExecutor,as_completed,wait,FIRST_COMPLETED
1、建立线程池:executor = ThreadPoolExecutor(max_workers= )
2、提交执行函数到线程池:task = executor.submit(func,(args))
3、获取执行结果:task.result()
4、判断线程是否完成:task.done()
5、取消还没执行的线程:task.cancel()
6、利用as_completed获取线程完成结果
all_task = [executor.submit(get_html,(url)) for url in urls]
for future in as_completed(all_task):
data = future.result()
print("get page {}".format(data))
7、通过executor的map获取已经完成的task值
for data in executor.map(get_html,urls):
print(data)
8、使用wait()方法阻塞线程
全篇代码如下
from concurrent.futures import ThreadPoolExecutor,as_completed,wait,FIRST_COMPLETED
#线程池,为什么要线程池
#主线程中可以获取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,(5))
# task2 = executor.submit(get_html,(4))
# task3 = executor.submit(get_html,(1))
# time.sleep(6)
urls = [4,2,3]
all_task = [executor.submit(get_html,(url)) for url in urls]
wait(all_task,return_when=FIRST_COMPLETED)
for future in as_completed(all_task):
data = future.result()
print("get page {}".format(data))
#通过executor的map获取已经完成的task的值
# for data in executor.map(get_html,urls):
# print("get page {}".format(data))
#
# #通过result方法可以获取task的执行结果
# print(task1.result())
# #通过done方法判断线程是否完成
# print(task1.done())
# #通过cancel方法取消还没运行的线程
# print(task3.cancel())