gj10 python socket编程

10.1 HTTP、Socket、TCP这几个概念

五层网络模型

socket 不属于任何协议，是一个API，通过socket 可以和传输层的打交道，然后在之上可以实现自己的功能和协议

10.2 client和server实现通信

Socket编程

http 是短连接无状态

10.3 socket实现聊天和多用户连接

import socket
import threading

server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
server.bind(('127.0.0.1', 8000))
server.listen(5)

def handle_sock(sock, addr):
    while True:
        data = sock.recv(1024)
        print(data.decode("utf8"))
        re_data = input("s>>>")
        sock.send(re_data.encode("utf8"))

# 获取从客户端发送的数据
# 一次获取1k的数据
while True:
    sock, addr = server.accept()

    # 用线程去处理新接收的连接(用户)
    client_thread = threading.Thread(target=handle_sock, args=(sock, addr))
    client_thread.start()

    # data = sock.recv(1024)
    # print(data.decode("utf8"))
    # re_data = input()
    # sock.send(re_data.encode("utf8"))
    # server.close()
    # sock.close()

import socket

client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
#                              ipv4        tcp
client.connect(('127.0.0.1', 8000))
while True:
    re_data = input(">>>")
    client.send(re_data.encode("utf8"))
    data = client.recv(1024)
    print(data.decode("utf8"))
# client.send("bobby".encode("utf8"))
# data = client.recv(1024)
# print (data.decode("utf8"))
# client.close()

10.4 socket模拟http请求

#requests -> urlib -> socket
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()
    # for url in range(20):
    #     #     url = "http://www.baidu.com/?goods/{}/".format(url)
    #     #     get_url(url)
    url = "http://www.baidu.com"
    get_url(url)
    print(time.time()-start_time)

-