python asyncio 使用ThreadPoolExecutor和asyncio完成阻塞IO请求

#使用多线程:在协程中集成阻塞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
Host:{}
Connection:close

".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("

")[1]
    print(html_data)
    client.close()


# 如果在协程中要用到阻塞IO,就把他放到线程池里面去运行,在运行的时候,本质还是线程池,同步的
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))
原文地址:https://www.cnblogs.com/callyblog/p/11220572.html