在Python中，通过套接字发送大量数据的正确方法是什么？

Question

最近我编写了一些代码（客户机和服务器）来发送图像-客户机只需使用socket模块Sending image over sockets (ONLY) in Python, image can not be open就可以将图像上载到服务器。

然而，图像发送部分现在是我所关心的。这是我使用的原始图像：

在我的服务器代码（接收图像）中，我有以下几行：

myfile = open(basename % imgcounter, 'wb')
myfile.write(data)

data = sock.recv(40960000)
if not data:
     myfile.close()
     break
myfile.write(data)
myfile.close()

sock.sendall("GOT IMAGE")
sock.shutdown()

但我不认为这是最好的方法。我认为我应该实现服务器，以便它以块的形式接收数据：

#!/usr/bin/env python

import random
import socket, select
from time import gmtime, strftime
from random import randint

imgcounter = 1
basename = "image%s.png"

HOST = '127.0.0.1'
PORT = 2905

connected_clients_sockets = []

server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
server_socket.bind((HOST, PORT))
server_socket.listen(10)

connected_clients_sockets.append(server_socket)

while True:

    read_sockets, write_sockets, error_sockets = select.select(connected_clients_sockets, [], [])

    for sock in read_sockets:

        if sock == server_socket:

            sockfd, client_address = server_socket.accept()
            connected_clients_sockets.append(sockfd)

        else:
            try:

                data = sock.recv(4096)
                txt = str(data)

                if data:

                    if data.startswith('SIZE'):
                        tmp = txt.split()
                        size = int(tmp[1])

                        print 'got size %s' % size

                        sock.sendall("GOT SIZE")

                    elif data.startswith('BYE'):
                        sock.shutdown()

                    else :

                        myfile = open(basename % imgcounter, 'wb')
                        myfile.write(data)

                        amount_received = 0
                        while amount_received < size:
                            data = sock.recv(4096)
                            amount_received += len(data)

                            print amount_received

                            if not data:
                                break
                            myfile.write(data)
                        myfile.close()

                        sock.sendall("GOT IMAGE")
                        sock.shutdown()
            except:
                sock.close()
                connected_clients_sockets.remove(sock)
                continue
        imgcounter += 1
server_socket.close()

但当我这样做时，服务器会打印：

got size 54674
4096
8192
12288
16384
20480
24576
28672
32768
36864
40960
45056
49152
50578

然后好像挂了，客户也挂了。但是，在服务器端，我只能看到客户端要发送的图像的一部分：

好像少了一些字节。仅使用套接字发送大量数据（图像、其他类型的文件）的正确方式是什么？

Answer 1

我假设您使用裸套接字进行此操作有一个特定的原因，例如自我启发，这意味着我不会回答“您不小心忘记了只使用HTTP和Twisted”，这也许您已经heard before:-p了。但实际上，您应该在某个点上查看更高级别的库，因为它们要容易得多！

定义协议

如果您只想发送图像，那么它可以很简单：

1. Client -> server: 8 bytes：大端，图像长度。
2. Client -> server: length bytes：所有图像数据。
3. （Client <- server: 1 byte, value 0：表示接收到传输-可选步骤您可能不在乎是否使用TCP，而只是假设它是可靠的。）

编码

服务器.py

import os
from socket import *
from struct import unpack


class ServerProtocol:

    def __init__(self):
        self.socket = None
        self.output_dir = '.'
        self.file_num = 1

    def listen(self, server_ip, server_port):
        self.socket = socket(AF_INET, SOCK_STREAM)
        self.socket.bind((server_ip, server_port))
        self.socket.listen(1)

    def handle_images(self):

        try:
            while True:
                (connection, addr) = self.socket.accept()
                try:
                    bs = connection.recv(8)
                    (length,) = unpack('>Q', bs)
                    data = b''
                    while len(data) < length:
                        # doing it in batches is generally better than trying
                        # to do it all in one go, so I believe.
                        to_read = length - len(data)
                        data += connection.recv(
                            4096 if to_read > 4096 else to_read)

                    # send our 0 ack
                    assert len(b'\00') == 1
                    connection.sendall(b'\00')
                finally:
                    connection.shutdown(SHUT_WR)
                    connection.close()

                with open(os.path.join(
                        self.output_dir, '%06d.jpg' % self.file_num), 'w'
                ) as fp:
                    fp.write(data)

                self.file_num += 1
        finally:
            self.close()

    def close(self):
        self.socket.close()
        self.socket = None

        # could handle a bad ack here, but we'll assume it's fine.

if __name__ == '__main__':
    sp = ServerProtocol()
    sp.listen('127.0.0.1', 55555)
    sp.handle_images()

客户端.py

from socket import *
from struct import pack


class ClientProtocol:

    def __init__(self):
        self.socket = None

    def connect(self, server_ip, server_port):
        self.socket = socket(AF_INET, SOCK_STREAM)
        self.socket.connect((server_ip, server_port))

    def close(self):
        self.socket.shutdown(SHUT_WR)
        self.socket.close()
        self.socket = None

    def send_image(self, image_data):

        # use struct to make sure we have a consistent endianness on the length
        length = pack('>Q', len(image_data))

        # sendall to make sure it blocks if there's back-pressure on the socket
        self.socket.sendall(length)
        self.socket.sendall(image_data)

        ack = self.socket.recv(1)

        # could handle a bad ack here, but we'll assume it's fine.

if __name__ == '__main__':
    cp = ClientProtocol()

    image_data = None
    with open('IMG_0077.jpg', 'r') as fp:
        image_data = fp.read()

    assert(len(image_data))
    cp.connect('127.0.0.1', 55555)
    cp.send_image(image_data)
    cp.close()

Answer 2

问题是您没有为接收到的第一个数据块递增amount_received。

修正如下：

#!/usr/bin/env python

import random
import socket, select
from time import gmtime, strftime
from random import randint

imgcounter = 1
basename = "image%s.png"

HOST = '127.0.0.1'
PORT = 2905

connected_clients_sockets = []

server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
server_socket.bind((HOST, PORT))
server_socket.listen(10)

connected_clients_sockets.append(server_socket)

while True:

    read_sockets, write_sockets, error_sockets = select.select(connected_clients_sockets, [], [])

    for sock in read_sockets:

        if sock == server_socket:

            sockfd, client_address = server_socket.accept()
            connected_clients_sockets.append(sockfd)

        else:
            try:

                data = sock.recv(4096)
                txt = str(data)

                if data:

                    if data.startswith('SIZE'):
                        tmp = txt.split()
                        size = int(tmp[1])

                        print 'got size %s' % size

                        sock.sendall("GOT SIZE")

                    elif data.startswith('BYE'):
                        sock.shutdown()

                    else :

                        myfile = open(basename % imgcounter, 'wb')
                        myfile.write(data)

                        amount_received = len(data) #  The fix!
                        while amount_received < size:
                            data = sock.recv(4096)
                            amount_received += len(data)

                            print amount_received

                            if not data:
                                break
                            myfile.write(data)
                        myfile.close()

                        sock.sendall("GOT IMAGE")
                        sock.shutdown()
            except:
                sock.close()
                connected_clients_sockets.remove(sock)
                continue
        imgcounter += 1
server_socket.close()