python的异步IO模块

Posted 2021-02-12 Maple_feng

asyncio模块：示例一

import asyncio


@asyncio.coroutine
def func1():
    print(\'before...func1......\')
    yield from asyncio.sleep(5)
    print(\'end...func1......\')


tasks = [func1(), func1()]

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

asyncio模块：示例二

import asyncio


@asyncio.coroutine
def fetch_async(host, url=\'/\'):
    print(host, url)
    reader, writer = yield from asyncio.open_connection(host, 80)

    request_header_content = """GET %s HTTP/1.0\\r\\nHost: %s\\r\\n\\r\\n""" % (url, host,)
    request_header_content = bytes(request_header_content, encoding=\'utf-8\')

    writer.write(request_header_content)
    yield from writer.drain()
    text = yield from reader.read()
    print(host, url, text)
    writer.close()

tasks = [
    fetch_async(\'www.cnblogs.com\', \'/angelyan/\'),
    fetch_async(\'dig.chouti.com\', \'/pic/show?nid=4073644713430508&lid=10273091\')
]

loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

 

asyncio模块+aiohttp模块：示例三

import aiohttp
import asyncio


@asyncio.coroutine
def fetch_async(url):
    print(url)
    response = yield from aiohttp.request(\'GET\', url)
    # data = yield from response.read()
    # print(url, data)
    print(url, response)
    response.close()


tasks = [fetch_async(\'http://www.google.com/\'), fetch_async(\'http://www.chouti.com/\')]

event_loop = asyncio.get_event_loop()
results = event_loop.run_until_complete(asyncio.gather(*tasks))
event_loop.close()

asyncio模块+requests模块：示例四

import asyncio
import requests


@asyncio.coroutine
def fetch_async(func, *args):
    loop = asyncio.get_event_loop()
    future = loop.run_in_executor(None, func, *args)
    response = yield from future
    print(response.url, response.content)


tasks = [
    fetch_async(requests.get, \'http://www.cnblogs.com/angelyan/\'),
    fetch_async(requests.get, \'http://dig.chouti.com/pic/show?nid=4073644713430508&lid=10273091\')
]

loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

gevent模块+requests模块：示例五

import gevent

import requests
from gevent import monkey

monkey.patch_all()


def fetch_async(method, url, req_kwargs):
    print(method, url, req_kwargs)
    response = requests.request(method=method, url=url, **req_kwargs)
    print(response.url, response.content)

# ##### 发送请求 #####
gevent.joinall([
    gevent.spawn(fetch_async, method=\'get\', url=\'https://www.python.org/\', req_kwargs={}),
    gevent.spawn(fetch_async, method=\'get\', url=\'https://www.yahoo.com/\', req_kwargs={}),
    gevent.spawn(fetch_async, method=\'get\', url=\'https://github.com/\', req_kwargs={}),
])

# ##### 发送请求（协程池控制最大协程数量） #####
# from gevent.pool import Pool
# pool = Pool(None)
# gevent.joinall([
#     pool.spawn(fetch_async, method=\'get\', url=\'https://www.python.org/\', req_kwargs={}),
#     pool.spawn(fetch_async, method=\'get\', url=\'https://www.yahoo.com/\', req_kwargs={}),
#     pool.spawn(fetch_async, method=\'get\', url=\'https://www.github.com/\', req_kwargs={}),
# ])

 

grequests模块：示例六

import grequests


request_list = [
    grequests.get(\'http://httpbin.org/delay/1\', timeout=0.001),
    grequests.get(\'http://fakedomain/\'),
    grequests.get(\'http://httpbin.org/status/500\')
]


# ##### 执行并获取响应列表 #####
# response_list = grequests.map(request_list)
# print(response_list)


# ##### 执行并获取响应列表（处理异常） #####
# def exception_handler(request, exception):
# print(request,exception)
#     print("Request failed")

# response_list = grequests.map(request_list, exception_handler=exception_handler)
# print(response_list)

twisted模块：示例七

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.internet import defer
from twisted.web.client import getPage
from twisted.internet import reactor

def one_done(arg):
    print(arg)

def all_done(arg):
    print(\'done\')
    reactor.stop()

@defer.inlineCallbacks
def task(url):
    res = getPage(bytes(url, encoding=\'utf8\')) # 发送Http请求
    res.addCallback(one_done)
    yield res

url_list = [
    \'http://www.cnblogs.com\',
    \'http://www.cnblogs.com\',
    \'http://www.cnblogs.com\',
    \'http://www.cnblogs.com\',
]

defer_list = [] # [对象1，对象2，对象2(已经向url发送请求)]
for url in url_list:
    v = task(url)
    defer_list.append(v)

d = defer.DeferredList(defer_list)
d.addBoth(all_done)


reactor.run() # 死循环

tornado模块：示例八

from tornado.httpclient import AsyncHTTPClient
from tornado.httpclient import HTTPRequest
from tornado import ioloop


def handle_response(response):
    """
    处理返回值内容（需要维护计数器，来停止IO循环），调用 ioloop.IOLoop.current().stop()
    :param response: 
    :return: 
    """
    if response.error:
        print("Error:", response.error)
    else:
        print(response.body)


def func():
    url_list = [
        \'http://www.baidu.com\',
        \'http://www.bing.com\',
    ]
    for url in url_list:
        print(url)
        http_client = AsyncHTTPClient()
        http_client.fetch(HTTPRequest(url), handle_response)


ioloop.IOLoop.current().add_callback(func)
ioloop.IOLoop.current().start()

twisted模块：示例九

from twisted.internet import reactor
from twisted.web.client import getPage
import urllib.parse


def one_done(arg):
    print(arg)
    reactor.stop()

post_data = urllib.parse.urlencode({\'check_data\': \'adf\'})
post_data = bytes(post_data, encoding=\'utf8\')
headers = {b\'Content-Type\': b\'application/x-www-form-urlencoded\'}
response = getPage(bytes(\'http://dig.chouti.com/login\', encoding=\'utf8\'),
                   method=bytes(\'POST\', encoding=\'utf8\'),
                   postdata=post_data,
                   cookies={},
                   headers=headers)
response.addBoth(one_done)

reactor.run()

select模块：示例十

import select
import socket
import time


class AsyncTimeoutException(TimeoutError):
    """
    请求超时异常类
    """

    def __init__(self, msg):
        self.msg = msg
        super(AsyncTimeoutException, self).__init__(msg)


class HttpContext(object):
    """封装请求和相应的基本数据"""

    def __init__(self, sock, host, port, method, url, data, callback, timeout=5):
        """
        sock: 请求的客户端socket对象
        host: 请求的主机名
        port: 请求的端口
        port: 请求的端口
        method: 请求方式
        url: 请求的URL
        data: 请求时请求体中的数据
        callback: 请求完成后的回调函数
        timeout: 请求的超时时间
        """
        self.sock = sock
        self.callback = callback
        self.host = host
        self.port = port
        self.method = method
        self.url = url
        self.data = data

        self.timeout = timeout

        self.__start_time = time.time()
        self.__buffer = []

    def is_timeout(self):
        """当前请求是否已经超时"""
        current_time = time.time()
        if (self.__start_time + self.timeout) < current_time:
            return True

    def fileno(self):
        """请求sockect对象的文件描述符，用于select监听"""
        return self.sock.fileno()

    def write(self, data):
        """在buffer中写入响应内容"""
        self.__buffer.append(data)

    def finish(self, exc=None):
        """在buffer中写入响应内容完成，执行请求的回调函数"""
        if not exc:
            response = b\'\'.join(self.__buffer)
            self.callback(self, response, exc)
        else:
            self.callback(self, None, exc)

    def send_request_data(self):
        content = """%s %s HTTP/1.0\\r\\nHost: %s\\r\\n\\r\\n%s""" % (
            self.method.upper(), self.url, self.host, self.data,)

        return content.encode(encoding=\'utf8\')


class AsyncRequest(object):
    def __init__(self):
        self.fds = []
        self.connections = []

    def add_request(self, host, port, method, url, data, callback, timeout):
        """创建一个要请求"""
        client = socket.socket()
        client.setblocking(False)
        try:
            client.connect((host, port))
        except BlockingIOError as e:
            pass
            # print(\'已经向远程发送连接的请求\')
        req = HttpContext(client, host, port, method, url, data, callback, timeout)
        self.connections.append(req)
        self.fds.append(req)

    def check_conn_timeout(self):
        """检查所有的请求，是否有已经连接超时，如果有则终止"""
        timeout_list = []
        for context in self.connections:
            if context.is_timeout():
                timeout_list.append(context)
        for context in timeout_list:
            context.finish(AsyncTimeoutException(\'请求超时\'))
            self.fds.remove(context)
            self.connections.remove(context)

    def running(self):
        """事件循环，用于检测请求的socket是否已经就绪，从而执行相关操作"""
        while True:
            r, w, e = select.select(self.fds, self.connections, self.fds, 0.05)

            if not self.fds:
                return

            for context in r:
                sock = context.sock
                while True:
                    try:
                        data = sock.recv(8096)
                        if not data:
                            self.fds.remove(context)
                            context.finish()
                            break
                        else:
                            context.write(data)
                    except BlockingIOError as e:
                        break
                    except TimeoutError as e:
                        self.fds.remove(context)
                        self.connections.remove(context)
                        context.finish(e)
                        break

            for context in w:
                # 已经连接成功远程服务器，开始向远程发送请求数据
                if context in self.fds:
                    data = context.send_request_data()
                    context.sock.sendall(data)
                    self.connections.remove(context)

            self.check_conn_timeout()


if __name__ == \'__main__\':
    def callback_func(context, response, ex):
        """
        :param context: HttpContext对象，内部封装了请求相关信息
        :param response: 请求响应内容
        :param ex: 是否出现异常（如果有异常则值为异常对象；否则值为None）
        :return:
        """
        print(context, response, ex)

    obj = AsyncRequest()
    url_list = [
        {\'host\': \'www.google.com\', \'port\': 80, \'method\': \'GET\', \'url\': \'/\', \'data\': \'\', \'timeout\': 5,
         \'callback\': callback_func},
        {\'host\': \'www.baidu.com\', \'port\': 80, \'method\': \'GET\', \'url\': \'/\', \'data\': \'\', \'timeout\': 5,
         \'callback\': callback_func},
        {\'host\': \'www.bing.com\', \'port\': 80, \'method\': \'GET\', \'url\': \'/\', \'data\': \'\', \'timeout\': 5,
         \'callback\': callback_func},
    ]
    for item in url_list:
        print(item)
        obj.add_request(**item)

    obj.running()