## 1. 线程池的基本用法
# coding: utf-8
from concurrent.futures import ThreadPoolExecutor
import time
def spider(page):
time.sleep(page)
print(f"crawl task{page} finished")
return page
with ThreadPoolExecutor(max_workers=5) as t: # 创建一个最大容纳数量为5的线程池
task1 = t.submit(spider, 1)
task2 = t.submit(spider, 2) # 通过submit提交执行的函数到线程池中
task3 = t.submit(spider, 3)
print(f"task1: {task1.done()}") # 通过done来判断线程是否完成
print(f"task2: {task2.done()}")
print(f"task3: {task3.done()}")
time.sleep(2.5)
print(f"task1: {task1.done()}")
print(f"task2: {task2.done()}")
print(f"task3: {task3.done()}")
print(task1.result()) # 通过result来获取返回值
executor = ThreadPoolExecutor(max_workers=5)
all_task = [executor.submit(send_data,"a" ) for i in range(1,2)]
'''
上面的代码等价于下面的:
all_task = []
for i in range(1,2):
task = executor.submit(send_data,"b" ) # "b"是给 方法send_data 传参,如果send_data有多个参数, executor.submit(send_data,"b","c","d" )
all_task.append(task)
'''
for future in as_completed(all_task):
print("finish the task")
obj_data = future.result()
print("obj_data is ", obj_data)
def send_data(a):
print("a is ", a)
as_completed: 上面虽然提供了判断任务是否结束的方法,但是不能在主线程中一直判断啊。最好的方法是当某个任务结束了,就给主线程返回结果,而不是一直判断每个任务是否结束。 ThreadPoolExecutorThreadPoolExecutor 中 的 as_completed() 就是这样一个方法,当子线程中的任务执行完后,直接用 result() 获取返回结果
参考:
wait ,map的用法可以参考下面的链接: https://www.jianshu.com/p/6d6e4f745c27