多线程与多进程

concurrent.futures 模块 拥有ThreadPoolExecutor (线程池)、ProcessPoolExecutor (进程池)两个类。

线程池-ThreadPoolExecutor

1. 主线程可以获取某一个线程（或者任务的）的状态，以及返回值。
2. 当一个线程完成的时候，主线程能够立即知道。
3. 让多线程和多进程的编码接口一致。

常用方法 done判断是否完成 result获取返回值 submit 提交要执行的函数与参数

# 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
-----------------------result-------------------------------
task1: False
task2: False
task3: False
crawl task1 finished
crawl task2 finished
task1: True
task2: True
task3: False
1
crawl task3 finished

wait(fs, timeout=None, return_when=ALL_COMPLETED) fs等待执行的线程队列 timeout等待最大时间 return_when等待返回结果的条件

from concurrent.futures import ThreadPoolExecutor, wait, FIRST_COMPLETED, ALL_COMPLETED
import time

def spider(page):
    time.sleep(page)
    print(f"crawl task{page} finished")
    return page

with ThreadPoolExecutor(max_workers=5) as t: 
    all_task = [t.submit(spider, page) for page in range(1, 5)]
    wait(all_task, return_when=FIRST_COMPLETED)
    print('finished')
    print(wait(all_task, timeout=2.5))

# 运行结果
crawl task1 finished
finished
crawl task2 finished
crawl task3 finished
DoneAndNotDoneFutures(done={<Future at 0x28c8710 state=finished returned int>, <Future at 0x2c2bfd0 state=finished returned int>, <Future at 0x2c1b7f0 state=finished returned int>}, not_done={<Future at 0x2c3a240 state=running>})
crawl task4 finished

as_completed() 判断任务是否结束。 生成器方法在没有任务完成的时候，会一直阻塞，除非设置了 timeout。

# coding: utf-8
from concurrent.futures import ThreadPoolExecutor, as_completed
import time


def spider(page):
    time.sleep(page)
    print(f"crawl task{page} finished")
    return page

def main():
    with ThreadPoolExecutor(max_workers=5) as t:
        obj_list = []
        for page in range(1, 5):
            obj = t.submit(spider, page)
            obj_list.append(obj)

        for future in as_completed(obj_list):
            data = future.result()
            print(f"main: {data}")

# 执行结果
crawl task1 finished
main: 1
crawl task2 finished
main: 2
crawl task3 finished
main: 3
crawl task4 finished
main: 4

map(fn, *iterables, timeout=None)

import time
from concurrent.futures import ThreadPoolExecutor

def spider(page):
    time.sleep(page)
    return page

start = time.time()
executor = ThreadPoolExecutor(max_workers=4)

i = 1
for result in executor.map(spider, [2, 3, 1, 4]):
    print("task{}:{}".format(i, result))
    i += 1

#  运行结果
task1:2
task2:3
task3:1
task4:4