concurrent.futures
异步执行进程线程池的模块,一个抽象类,定义submit,map,shutdown方法
from concurrent.futures import ProcessPoolExecutor,ThreadPoolExecutor import time,os,random def task(n): print(os.getpid(),'is running') time.sleep(random.randint(1,3)) return n**2 if __name__ == '__main__': p = ProcessPoolExecutor() obj = p.map(task,range(10)) p.shutdown() print(list(obj))
线程池就是
ProcessPoolExecutor换成
ThreadPoolExecutor
import os,time,requests,re from concurrent.futures import ThreadPoolExecutor def get_page(url): print(url) ret = requests.get(url).text return {'url':url,'text':ret} def get_p(res): res = res.result() rep = re.compile(r'<a href="/films/d+" title="(?P<name>.*?)" class="image-link.*?<p class="star">(?P<star>.*?)</p>',re.S) ret = rep.finditer(res['text']) with open('db.txt','a',encoding='utf-8')as f: for i in ret: s = "name:%s"%i.group("name")+i.group('star') f.write(s+' ') if __name__ == '__main__': t = time.time() p = ThreadPoolExecutor() urls = [ 'http://maoyan.com/board/7', 'http://maoyan.com/board/6', 'http://maoyan.com/board/1', 'http://maoyan.com/board/2', 'http://maoyan.com/board/4', ] for url in urls: p.submit(get_page,url).add_done_callback(get_p) p.shutdown() print(time.time()-t)
协程
协程:是单线程下的并发,又称微线程,纤程。英文名Coroutine。一句话说明什么是线程:协程是一种用户态的轻量级线程,即协程是由用户程序自己控制调度的。、
需要强调的是:
#1. python的线程属于内核级别的,即由操作系统控制调度(如单线程遇到io或执行时间过长就会被迫交出cpu执行权限,切换其他线程运行) #2. 单线程内开启协程,一旦遇到io,就会从应用程序级别(而非操作系统)控制切换,以此来提升效率(!!!非io操作的切换与效率无关)
对比操作系统控制线程的切换,用户在单线程内控制协程的切换
优点如下:
#1. 协程的切换开销更小,属于程序级别的切换,操作系统完全感知不到,因而更加轻量级 #2. 单线程内就可以实现并发的效果,最大限度地利用cpu
缺点如下:
#1. 协程的本质是单线程下,无法利用多核,可以是一个程序开启多个进程,每个进程内开启多个线程,每个线程内开启协程 #2. 协程指的是单个线程,因而一旦协程出现阻塞,将会阻塞整个线程
总结协程特点:
- 必须在只有一个单线程里实现并发
- 修改共享数据不需加锁
- 用户程序里自己保存多个控制流的上下文栈
- 附加:一个协程遇到IO操作自动切换到其它协程(如何实现检测IO,yield、greenlet都无法实现,就用到了gevent模块(select机制))
Greenlet
from greenlet import greenlet def eat(name): print('%s eat 1' %name) g2.switch('egon') print('%s eat 2' %name) g2.switch() def play(name): print('%s play 1' %name) g1.switch() print('%s play 2' %name) g1=greenlet(eat) g2=greenlet(play) g1.switch('egon')#可以在第一次switch时传入参数,以后都不需要
Gevent介绍
Gevent 是一个第三方库,可以轻松通过gevent实现并发同步或异步编程,在gevent中用到的主要模式是Greenlet, 它是以C扩展模块形式接入Python的轻量级协程。 Greenlet全部运行在主程序操作系统进程的内部,但它们被协作式地调度。
记得打猴子补丁
from gevent import monkey;monkey.patch_all() import gevent import time def eat(): print('eat food 1') time.sleep(2) print('eat food 2') def play(): print('play 1') time.sleep(1) print('play 2') g1=gevent.spawn(eat) g2=gevent.spawn(play_phone) gevent.joinall([g1,g2]) print('主')
from gevent import monkey;monkey.patch_all() import gevent import requests import time def get_page(url): print('GET: %s' %url) response=requests.get(url) if response.status_code == 200: print('%d bytes received from %s' %(len(response.text),url)) start_time=time.time() gevent.joinall([ gevent.spawn(get_page,'https://www.python.org/'), gevent.spawn(get_page,'https://www.yahoo.com/'), gevent.spawn(get_page,'https://github.com/'), ]) stop_time=time.time() print('run time is %s' %(stop_time-start_time))
from gevent import monkey;monkey.patch_all() from socket import * import gevent #如果不想用money.patch_all()打补丁,可以用gevent自带的socket # from gevent import socket # s=socket.socket() def server(server_ip,port): s=socket(AF_INET,SOCK_STREAM) s.setsockopt(SOL_SOCKET,SO_REUSEADDR,1) s.bind((server_ip,port)) s.listen(5) while True: conn,addr=s.accept() gevent.spawn(talk,conn,addr) def talk(conn,addr): try: while True: res=conn.recv(1024) print('client %s:%s msg: %s' %(addr[0],addr[1],res)) conn.send(res.upper()) except Exception as e: print(e) finally: conn.close() if __name__ == '__main__': server('127.0.0.1',8080)
from threading import Thread from socket import * import threading def client(server_ip,port): c=socket(AF_INET,SOCK_STREAM) #套接字对象一定要加到函数内,即局部名称空间内,放在函数外则被所有线程共享,则大家公用一个套接字对象,那么客户端端口永远一样了 c.connect((server_ip,port)) count=0 while True: c.send(('%s say hello %s' %(threading.current_thread().getName(),count)).encode('utf-8')) msg=c.recv(1024) print(msg.decode('utf-8')) count+=1 if __name__ == '__main__': for i in range(500): t=Thread(target=client,args=('127.0.0.1',8080)) t.start()
多线程+协程!!
关键:加入猴子补丁monkey后,所有子线程遇到IO会阻塞,所有程序卡住不运行
解决方法:设置
from gevent import monkey;monkey.patch_all(thread=False)
https://stackoverflow.com/questions/9192539/using-gevent-monkey-patching-with-threading-makes-thread-work-serially