asyncio、aiohttp

asyncio

asyncio是Python 3.4版本引入的标准库，直接内置了对异步IO的支持。

用asyncio提供的@asyncio.coroutine可以把一个generator标记为coroutine类型，然后在coroutine内部用yield from调用另一个coroutine实现异步操作。

为了简化并更好地标识异步IO，从Python 3.5开始引入了新的语法async和await，可以让coroutine的代码更简洁易读。

请注意，async和await是针对coroutine的新语法，要使用新的语法，只需要做两步简单的替换：

1. 把@asyncio.coroutine替换为async；
2. 把yield from替换为await。

asyncio的编程模型就是一个消息循环。我们从asyncio模块中直接获取一个EventLoop的引用，然后把需要执行的协程扔到EventLoop中执行，就实现了异步IO。

用asyncio实现Hello world代码如下：

import asyncio

async def hello():
    print("Hello world!")
    # 异步调用asyncio.sleep(1):
    r = await asyncio.sleep(1)
    print("Hello again!")

# 获取EventLoop:
loop = asyncio.get_event_loop()
# 执行coroutine
loop.run_until_complete(hello())
loop.close()

async把一个函数标记为coroutine类型，然后，我们就把这个coroutine扔到EventLoop中执行。

hello()会首先打印出Hello world!，然后，await语法可以让我们方便地调用另一个generator。由于asyncio.sleep()也是一个coroutine，所以线程不会等待asyncio.sleep()，而是直接中断并执行下一个消息循环。当asyncio.sleep()返回时，线程就可以从await拿到返回值（此处是None），然后接着执行下一行语句。

把asyncio.sleep(1)看成是一个耗时1秒的IO操作，在此期间，主线程并未等待，而是去执行EventLoop中其他可以执行的coroutine了，因此可以实现并发执行。

我们用Task封装两个coroutine试试：

import threading
import asyncio


async def hello():
    print('Hello world! (%s)' % threading.currentThread())
    await asyncio.sleep(1)
    print('Hello again! (%s)' % threading.currentThread())

loop = asyncio.get_event_loop()
tasks = [hello(), hello()]
loop.run_until_complete(asyncio.wait(tasks))
loop.close()


观察执行过程：
Hello world! (<_MainThread(MainThread, started 140735195337472)>)
Hello world! (<_MainThread(MainThread, started 140735195337472)>)
(暂停约1秒)
Hello again! (<_MainThread(MainThread, started 140735195337472)>)
Hello again! (<_MainThread(MainThread, started 140735195337472)>)

由打印的当前线程名称可以看出，两个coroutine是由同一个线程并发执行的。

如果把asyncio.sleep()换成真正的IO操作，则多个coroutine就可以由一个线程并发执行。

我们用asyncio的异步网络连接来获取sina、sohu和163的网站首页：

import asyncio


async def wget(host):
    print('wget %s...' % host)
    connect = asyncio.open_connection(host, 80)
    reader, writer = await connect
    header = 'GET / HTTP/1.0\r\nHost: %s\r\n\r\n' % host
    writer.write(header.encode('utf-8'))
    await writer.drain()
    while True:
        line = await reader.readline()
        if line == b'\r\n':
            break
        print('%s header > %s' % (host, line.decode('utf-8').rstrip()))
    # Ignore the body, close the socket
    writer.close()

loop = asyncio.get_event_loop()
tasks = [wget(host) for host in ['www.sina.com.cn', 'www.sohu.com', 'www.163.com']]
loop.run_until_complete(asyncio.wait(tasks))
loop.close()

执行结果如下：

wget www.sohu.com...
wget www.sina.com.cn...
wget www.163.com...
(等待一段时间)
(打印出sohu的header)
www.sohu.com header > HTTP/1.1 200 OK
www.sohu.com header > Content-Type: text/html
...
(打印出sina的header)
www.sina.com.cn header > HTTP/1.1 200 OK
www.sina.com.cn header > Date: Wed, 20 May 2015 04:56:33 GMT
...
(打印出163的header)
www.163.com header > HTTP/1.0 302 Moved Temporarily
www.163.com header > Server: Cdn Cache Server V2.0

可见3个连接由一个线程通过coroutine并发完成。

asyncio提供了完善的异步IO支持；

异步操作需要在coroutine中通过yield from完成；

多个coroutine可以封装成一组Task然后并发执行

 

#使用asyncio
import asyncio 
import time


async def get_html(url):
    print("start get url")
    await asyncio.sleep(2)
    print("end get url")


if __name__ == "__main__":
    start_time = time.time()
    loop = asyncio.get_event_loop()
    tasks = [get_html("http://www.imooc.com") for i in range(10)]
    loop.run_until_complete(asyncio.wait(tasks))
    print(time.time()-start_time)

#获取协程的返回值
import asyncio
import time
from functools import partial


async def get_html(url):
    print("start get url")
    await asyncio.sleep(2)
    return "bobby"


def callback(url, future):
    print(url)
    print("send email to bobby")


if __name__ == "__main__":
    start_time = time.time()
    loop = asyncio.get_event_loop()
    # get_future = asyncio.ensure_future(get_html("http://www.imooc.com"))
    task = loop.create_task(get_html("http://www.imooc.com"))
    task.add_done_callback(partial(callback, "http://www.imooc.com"))
    loop.run_until_complete(task)
    print(task.result())

#wait 和 gather
import asyncio
import time
async def get_html(url):
    print("start get url")
    await asyncio.sleep(2)
    print("end get url")

if __name__ == "__main__":
    start_time = time.time()
    loop = asyncio.get_event_loop()
    tasks = [get_html("http://www.imooc.com") for i in range(10)]
    # loop.run_until_complete(asyncio.gather(*tasks))
    # print(time.time()-start_time)

    #gather和wait的区别
    #gather更加high-level
    group1 = [get_html("http://projectsedu.com") for i in range(2)]
    group2 = [get_html("http://www.imooc.com") for i in range(2)]
    group1 = asyncio.gather(*group1)
    group2 = asyncio.gather(*group2)
    group2.cancel()
    loop.run_until_complete(asyncio.gather(group1, group2))
    print(time.time() - start_time)

import asyncio
import time

async def get_html(sleep_times):
     print("waiting")
     await asyncio.sleep(sleep_times)
     print("done after {}s".format(sleep_times))


if __name__ == "__main__":
     task1 = get_html(2)
     task2 = get_html(3)
     task3 = get_html(3)

     tasks = [task1, task2, task3]

     loop = asyncio.get_event_loop()

     try:
         loop.run_until_complete(asyncio.wait(tasks))
     except KeyboardInterrupt as e:
         all_tasks = asyncio.Task.all_tasks()
         for task in all_tasks:
             print("cancel task")
             print(task.cancel())
         loop.stop()
         loop.run_forever()
     finally:
         loop.close()


#注册协程到loop中有两种方法
#1. 通过ensure_future/create_task
#2. await


run_until_complete
# import asyncio
# loop = asyncio.get_event_loop()
# loop.run_forever()
# loop.run_until_complete()

#1. loop会被放到future中
#2. 取消future(task)

#使用多线程：在携程中集成阻塞io
import asyncio
from concurrent.futures import ThreadPoolExecutor
import socket
from urllib.parse import urlparse


def get_url(url):
    #通过socket请求html
    url = urlparse(url)
    host = url.netloc
    path = url.path
    if path == "":
        path = "/"

    #建立socket连接
    client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # client.setblocking(False)
    client.connect((host, 80)) #阻塞不会消耗cpu

    #不停的询问连接是否建立好， 需要while循环不停的去检查状态
    #做计算任务或者再次发起其他的连接请求

    client.send("GET {} HTTP/1.1\r\nHost:{}\r\nConnection:close\r\n\r\n".format(path, host).encode("utf8"))

    data = b""
    while True:
        d = client.recv(1024)
        if d:
            data += d
        else:
            break

    data = data.decode("utf8")
    html_data = data.split("\r\n\r\n")[1]
    print(html_data)
    client.close()


if __name__ == "__main__":
    import time
    start_time = time.time()
    loop = asyncio.get_event_loop()
    executor = ThreadPoolExecutor(3)
    tasks = []
    for url in range(20):
        url = "http://shop.projectsedu.com/goods/{}/".format(url)
        task = loop.run_in_executor(executor, get_url, url)
        tasks.append(task)
    loop.run_until_complete(asyncio.wait(tasks))
    print("last time:{}".format(time.time()-start_time))

 

 

aiohttp：https://pypi.org/project/aiohttp/#description

asyncio可以实现单线程并发IO操作。如果仅用在客户端，发挥的威力不大。如果把asyncio用在服务器端，例如Web服务器，由于HTTP连接就是IO操作，因此可以用单线程+coroutine实现多用户的高并发支持。

asyncio实现了TCP、UDP、SSL等协议，aiohttp则是基于asyncio实现的HTTP框架。

我们先安装aiohttp：

pip install aiohttp

然后编写一个HTTP服务器，分别处理以下URL：

• / - 首页返回b'<h1>Index</h1>'；

• /hello/{name} - 根据URL参数返回文本hello, %s!。

import asyncio

from aiohttp import web

async def index(request):
    await asyncio.sleep(0.5)
    return web.Response(body=b'<h1>Index</h1>')

async def hello(request):
    await asyncio.sleep(0.5)
    text = '<h1>hello, %s!</h1>' % request.match_info['name']
    return web.Response(body=text.encode('utf-8'))

async def init(loop):
    app = web.Application(loop=loop)
    app.router.add_route('GET', '/', index)
    app.router.add_route('GET', '/hello/{name}', hello)
    srv = await loop.create_server(app.make_handler(), '127.0.0.1', 8000)
    print('Server started at http://127.0.0.1:8000...')
    return srv

loop = asyncio.get_event_loop()
loop.run_until_complete(init(loop))
loop.run_forever()

注意aiohttp的初始化函数init()也是一个coroutine，loop.create_server()则利用asyncio创建TCP服务