Python程序中的协程操作-gevent模块

Python程序中的协程操作-gevent模块

一、安装

安装：pip3 install gevent

二、Gevent模块介绍

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。

2.1 用法介绍

g1=gevent.spawn(func,1,,2,3,x=4,y=5)：创建一个协程对象g1，spawn括号内第一个参数是函数名，如eat，后面可以有多个参数，可以是位置实参或关键字实参，都是传给函数eat的

g2=gevent.spawn(func2)

g1.join()：等待g1结束

g2.join()：等待g2结束

上述两步合作一步：gevent.joinall([g1,g2])

g1.value：拿到func1的返回值

2.2 例：遇到io主动切换

import gevent,time


def eat(name):
    print('%s eat 1' % name)
    gevent.sleep(2)
    print('%s eat 2' % name)


def play(name):
    print('%s play 1' % name)
    gevent.sleep(1)
    print('%s play 2' % name)

start = time.time()
g1 = gevent.spawn(eat, 'randy')
g2 = gevent.spawn(play, name='randy')
g1.join()
g2.join()
# 或者gevent.joinall([g1,g2])
print('主')
end = time.time()
print(end-start)

randy eat 1
randy play 1
randy play 2
randy eat 2
主
2.0066120624542236

上例gevent.sleep(2)模拟的是gevent可以识别的io阻塞，而time.sleep(2)或其他的阻塞，gevent是不能直接识别的需要用下面一行代码，打补丁，就可以识别了。

from gevent import monkey;monkey.patch_all()必须放到被打补丁者的前面，如time，socket模块之前。

或者我们干脆记忆成：要用gevent，需要将from gevent import monkey;monkey.patch_all()放到文件的开头。

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)
gevent.joinall([g1,g2])
print('主')

eat food 1
play 1
play 2
eat food 2
主
2.0046091079711914

我们可以用threading.current_thread().getName()来查看每个g1和g2，查看的结果为DummyThread-n，即假线程

2.3 查看threading.current_thread().getName()

from gevent import monkey;

monkey.patch_all()
import threading
import gevent
import time


def eat():
    print(threading.current_thread().getName())
    print('eat food 1')
    time.sleep(2)
    print('eat food 2')


def play():
    print(threading.current_thread().getName())
    print('play 1')
    time.sleep(1)
    print('play 2')


start = time.time()
g1 = gevent.spawn(eat)
g2 = gevent.spawn(play)
gevent.joinall([g1, g2])
print('主')
end = time.time()
print(end - start)

DummyThread-1
eat food 1
DummyThread-2
play 1
play 2
eat food 2
主
2.004635810852051

三、Gevent之同步与异步

ffrom gevent import spawn, joinall, monkey;

monkey.patch_all()

import time


def task(pid):
    """
    Some non-deterministic task
    """
    time.sleep(0.5)
    print('Task %s done' % pid)


def synchronous():  # 同步
    for i in range(10):
        task(i)


def asynchronous():  # 异步
    g_l = [spawn(task, i) for i in range(10)]
    joinall(g_l)
    print('DONE')


if __name__ == '__main__':
    syn_start = time.time()
    print('Synchronous:')
    synchronous()
    syn_end = time.time()
    print(f'syn:{syn_end - syn_start}')

    asy_start = time.time()
    print('Asynchronous:')
    asynchronous()

    asy_end = time.time()
    print(f'asy:{asy_end - asy_start}')

#  上面程序的重要部分是将task函数封装到Greenlet内部线程的gevent.spawn。
#  初始化的greenlet列表存放在数组threads中，此数组被传给gevent.joinall 函数，
#  后者阻塞当前流程，并执行所有给定的greenlet任务。执行流程只会在 所有greenlet执行完后才会继续向下走。

Synchronous:
Task 0 done
Task 1 done
Task 2 done
Task 3 done
Task 4 done
Task 5 done
Task 6 done
Task 7 done
Task 8 done
Task 9 done
syn:5.014581918716431
Asynchronous:
Task 0 done
Task 1 done
Task 2 done
Task 3 done
Task 4 done
Task 5 done
Task 6 done
Task 7 done
Task 8 done
Task 9 done
DONE
asy:0.5006606578826904

四、Gevent之应用

通过gevent实现单线程下的socket并发

注意：from gevent import monkey;monkey.patch_all()一定要放到导入socket模块之前，否则gevent无法识别socket的阻塞。

4.1 服务端

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)

4.2 客户端

from socket import *

client=socket(AF_INET,SOCK_STREAM)
client.connect(('127.0.0.1',8080))


while True:
    msg=input('>>: ').strip()
    if not msg:continue

    client.send(msg.encode('utf-8'))
    msg=client.recv(1024)
    print(msg.decode('utf-8'))

4.3 多线程并发多个客户端

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()

4.4 爬虫

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))