websocket 原理

自己写一个websocket

原理更多参考--   https://www.cnblogs.com/zunzunQ/p/8549180.html

原理简介:
    client端 握手请求中 包含一个base64 encode的随机字符串,
    server端 magic_string+str    sha1摘要之后base64加密, 发给client
    服务器完成协议升级后（HTTP->Websocket），服务端就可以主动推送信息给客户端啦  (回调机制)

import socket, hashlib, base64

sock = socket.socket()
sock.bind(('127.0.0.1', 9000))
sock.listen(5)
'''
b'GET / HTTP/1.1\r\n
Host: 127.0.0.1:9000\r\n
Connection: Upgrade\r\n
Pragma: no-cache\r\n
Cache-Control: no-cache\r\n
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36\r\n
Upgrade: websocket\r\n   --建立--
Origin: http://localhost:63342\r\n
Sec-WebSocket-Version: 13\r\n
Accept-Encoding: gzip, deflate, br\r\n
Accept-Language: zh-CN,zh;q=0.9\r\n
Sec-WebSocket-Key: vNtQ8bVSNRPL5p+xo1X5CA==\r\n  验证 一按钥匙
Sec-WebSocket-Extensions: permessage-deflate; client_max_window_bits\r\n\r\n
'''
'''
b'GET / HTTP/1.1\r\n   -- 单纯http地址栏访问
Host: 127.0.0.1:9000\r\n
Connection: keep-alive\r\n
Pragma: no-cache\r\n
Cache-Control: no-cache\r\n
Upgrade-Insecure-Requests: 1\r\n
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36\r\n
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8\r\n
Accept-Encoding: gzip, deflate, br\r\n
Accept-Language: zh-CN,zh;q=0.9\r\n\r\n'
'''
conn, addr = sock.accept()
data = conn.recv(1024)
# print(data)

def get_header(data): # 获取头部信息
    header_dict = {}
    header_str = data.decode('utf8')
    for i in header_str.split('\r\n'):
        if str(i).startswith('Sec-WebSocket-Key'):
            header_dict['Sec-WebSocket-Key'] = i.split(':')[1].strip()
    return header_dict

headers = get_header(data)
magic_string = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11'  # magic_string = 魔法字符串
value = headers['Sec-WebSocket-Key'] + magic_string
print(value)  #mzrsVOiYogmzB8fYcyMBpw==258EAFA5-E914-47DA-95CA-C5AB0DC85B11
ac = base64.b64encode(hashlib.sha1(value.encode('utf-8')).digest())  # 固定加密算法
print(ac) #b'0Cu1dAA7U6tFsJS4EVkIDLcvKDU='
response_tpl = "HTTP/1.1 101 Switching Protocols\r\n" \
               "Upgrade:websocket\r\n" \
               "Connection: Upgrade\r\n" \
               "Sec-WebSocket-Accept: %s\r\n" \
               "WebSocket-Location: ws://127.0.0.1:9527\r\n\r\n"
response_str = response_tpl % (ac.decode('utf-8'))
conn.send(response_str.encode('utf8'))  # 响应握手信息

while True:
    msg = conn.recv(8096)
    print(msg)

解密过程  分析

hashstr = b'\x81\x89\xbc\xb8,\xb5Y6\xa5P\x12\x0b\xc8\x0f:'
# b'\x81    \x83    \xceH\xb6\x85\xffz\x85'

# 将第二个字节也就是 \x83 第9-16位 进行与127进行 与位 运算
payload = hashstr[1] & 127
print(payload)
if payload == 127:
    extend_payload_len = hashstr[2:10]  # 顾头不顾尾
    mask = hashstr[10:14]
    decoded = hashstr[14:]
# 当位运算结果等于127时,则第3-10个字节为数据长度
# 第11-14字节为mask 解密所需字符串
# 则数据为第15字节至结尾

if payload == 126:
    extend_payload_len = hashstr[2:4]
    mask = hashstr[4:8]
    decoded = hashstr[8:]
# 当位运算结果等于126时,则第3-4个字节为数据长度  255*255+510=65535 21845汉字
# 第5-8字节为mask 解密所需字符串
# 则数据为第9字节至结尾

if payload <= 125:
    extend_payload_len = None
    mask = hashstr[2:6]
    decoded = hashstr[6:]

# 当位运算结果小于等于125时,则这个数字就是数据的长度
# 第3-6字节为mask 解密所需字符串
# 则数据为第7字节至结尾

str_byte = bytearray()  # 字节流

for i in range(len(decoded)):
    byte = decoded[i] ^ mask[i % 4]  # 异或运算  上下为0就是0  上下有1就是1
    str_byte.append(byte)

print(str_byte.decode("utf8"))  # 主要解决中文  厉害了

# # 1字节 = 8 bit  与位运算
#
# 11111111  最大255
# 2/4/8/16/32/64/138/256

加密过程 -- 分析

import struct
msg_bytes = "hello".encode("utf8")  #转bytes
token = b"\x81"       # 数据标准格式
length = len(msg_bytes)  #第二位就是数据长度

if length < 126:
    token += struct.pack("B", length)
elif length == 126:
    token += struct.pack("!BH", 126, length)
else:
    token += struct.pack("!BQ", 127, length)

msg = token + msg_bytes

print(msg)

总结

WebSocket的工作原理
.握手
    客户端   Sec-WebSocket-Key
    响应     base64(sha1(Sec-WebSocket-Key + magic_string))

.解密：
    与127 进行"与"位运算 结果是两个数的最小值
    . ==  第3-10个字节表示该数据的长度
    . ==  第3-4个字节表示该数据的长度
    . <=  当前这个数字就是Websocket发送的数据长度