线程-线程池-concurrent.futures模块

Posted 2020-12-09 hedger-lee

线程池-concurrent.futures模块

介绍

concurrent.futures模块提供了高度封装的异步调用接口

ThreadPoolExecutor：线程池，提供异步调用
ProcessPoolExecutor: 进程池，提供异步调用

方法

submit(fn, *args, **kwargs)
# 异步提交任务

map(func, *iterables, timeout=None, chunksize=1) 
# 取代for循环submit的操作

shutdown(wait=True) 
# 相当于进程池的pool.close()+pool.join()操作
wait=True，等待池内所有任务执行完毕回收完资源后才继续
wait=False，立即返回，并不会等待池内的任务执行完毕
但不管wait参数为何值，整个程序都会等到所有任务执行完毕
submit和map必须在shutdown之前

result(timeout=None)
# 取得结果

add_done_callback(fn)
# 回调函数

done()
#判断某一个线程是否完成

cancle()
# 取消某个任务

用法

ThreadPoolExecutor和ProcessPoolExecutor用法一致

from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor

import os,time,random
def task(n):
    print(‘%s is runing‘ %os.getpid())
    time.sleep(random.randint(1,3))
    return n**2

if __name__ == ‘__main__‘:

    executor=ProcessPoolExecutor(max_workers=3)

    futures=[]
    for i in range(11):
        future=executor.submit(task,i)
        futures.append(future)
    executor.shutdown(True)
    print(‘+++>‘)
    for future in futures:
        print(future.result())

map用法

from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor

import os,time,random
def task(n):
    print(‘%s is runing‘ %os.getpid())
    time.sleep(random.randint(1,3))
    return n**2

if __name__ == ‘__main__‘:

    executor=ThreadPoolExecutor(max_workers=3)

    # for i in range(11):
    #     future=executor.submit(task,i)

    executor.map(task,range(1,12)) #map取代了for+submit

使用回调函数

from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor
from multiprocessing import Pool
import requests
import json
import os

def get_page(url):
    print(‘<进程%s> get %s‘ %(os.getpid(),url))
    respone=requests.get(url)
    if respone.status_code == 200:
        return {‘url‘:url,‘text‘:respone.text}

def parse_page(res):
    res=res.result()
    print(‘<进程%s> parse %s‘ %(os.getpid(),res[‘url‘]))
    parse_res=‘url:<%s> size:[%s]
‘ %(res[‘url‘],len(res[‘text‘]))
    with open(‘db.txt‘,‘a‘) as f:
        f.write(parse_res)


if __name__ == ‘__main__‘:
    urls=[
        ‘https://www.baidu.com‘,
        ‘https://www.python.org‘,
        ‘https://www.openstack.org‘,
        ‘https://help.github.com/‘,
        ‘http://www.sina.com.cn/‘
    ]

    # p=Pool(3)
    # for url in urls:
    #     p.apply_async(get_page,args=(url,),callback=pasrse_page)
    # p.close()
    # p.join()

    p=ProcessPoolExecutor(3)
    for url in urls:
        p.submit(get_page,url).add_done_callback(parse_page) #parse_page拿到的是一个future对象obj，需要用obj.result()拿到结果