import socket, base64, hashlib

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

sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)

sock.bind(('127.0.0.1', 9527))

sock.listen(5)

# 获取客户端socket对象

conn, address = sock.accept()

# 获取客户端的【握手】信息

data = conn.recv(1024)

print(data)

def get_headers(data):

    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

ws_key = get_headers(data).get("Sec-WebSocket-Key")

# # magic string为：258EAFA5-E914-47DA-95CA-C5AB0DC85B11

magic_string = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11'

socket_str = ws_key + magic_string

socket_str_sha1 = hashlib.sha1(socket_str.encode("utf8")).digest()

socket_str_base64 = base64.b64encode(socket_str_sha1)

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" %(socket_str_base64.decode("utf8"))

conn.send(response_tpl.encode("utf8"))

while 1:

    msg = conn.recv(8096)

    print(msg)

"""

b'GET / HTTP/1.1\r\n

Host: 127.0.0.1:9527\r\n

User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:62.0) Gecko/20100101 Firefox/62.0\r\n

Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\r\n

Accept-Language: zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2\r\n

Accept-Encoding: gzip, deflate\r\n

Sec-WebSocket-Version: 13\r\n

Origin: http://localhost:63342\r\n

Sec-WebSocket-Extensions: permessage-deflate\r\n

Sec-WebSocket-Key: x/BjPHeWzOqqLxVuZq/bfw==\r\n

Cookie: session=fe2f4896-0309-4801-b8cd-9a719b26fb8d\r\n

Connection: keep-alive, Upgrade\r\n

Pragma: no-cache\r\n

Cache-Control: no-cache\r\n

Upgrade: websocket\r\n\r\n'

"""

# # magic string为：258EAFA5-E914-47DA-95CA-C5AB0DC85B11

# magic_string = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11'

#

#

# def get_headers(data):

#     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

#

#

# def get_header(data):

#     """

#      将请求头格式化成字典

#      :param data:

#      :return:

#      """

#     header_dict = {}

#     data = str(data, encoding='utf-8')

#

#     header, body = data.split('\r\n\r\n', 1)

#     header_list = header.split('\r\n')

#     for i in range(0, len(header_list)):

#         if i == 0:

#             if len(header_list[i].split(' ')) == 3:

#                 header_dict['method'], header_dict['url'], header_dict['protocol'] = header_list[i].split(' ')

#         else:

#             k, v = header_list[i].split(':', 1)

#             header_dict[k] = v.strip()

#     return header_dict

#

#

# headers = get_headers(data)  # 提取请求头信息

# # 对请求头中的sec-websocket-key进行加密

# 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"

# value = headers['Sec-WebSocket-Key'] + magic_string

# print(value)

# ac = base64.b64encode(hashlib.sha1(value.encode('utf-8')).digest())

# response_str = response_tpl % (ac.decode('utf-8'))

# # 响应【握手】信息

# conn.send(response_str.encode("utf8"))

#

# while True:

#     msg = conn.recv(8096)

#     print(msg)

上节回顾：

    websocket；握手

        浏览器 - 链接 - 服务器

        浏览器 - 发送 - 字符串(求情头) - Sec-Websocket-Key - 服务器

        服务器 - 获取Sec-Websocket-Key的值+magic_string - sha1 - base64 - 拼接一个响应头 - Sec-WebSocket-Accept值就是

        服务器 - 拼接好的响应头 - 浏览器

        浏览器 - Sec-WebSocket-Accept 解密得到 Sec-Websocket-Key - 握手成功与否

今日内容：

    websocket 加解密

        解密：

            b_str = b'\x81\xfe\x01G\xa0`~dE\xe5\xf6\x81\x18\xfd\x9b\xec;\x84\xc6\xfeF\xfc\xd4\x81-\xea\x96\xe4,\x84\xc6\xc9I\xe1\xed\x81\x14\xc9\x98\xca"\x8f\xc2\xe8D\xdb\xf4\x81\x04\xc9\x9a\xdc+\x84\xc6\xedE\xe8\xf8\x8b\x1c\xec\x99\xff*\x85\xc9\xfaG\xf6\xcc\x81\x1c\xea\x91\xd8,\x86\xd3\xc0H\xcf\xe4\x81-\xd1\x98\xe4\x05\x85\xd3\xfcD\xda\xdf\x80\x19\xeb\x99\xc3+\x84\xc7\xfbC\xe0\xfc\x83$\xd6\x9a\xda-\x85\xf3\xcfD\xd9\xf5\x8c\'\xc3\x9a\xdc-\x86\xf9\xecD\xda\xf0\x81&\xe5\x91\xd8,\x85\xc1\xc4E\xdf\xe9\x80\x19\xeb\x9b\xc7\x0b\x85\xc1\xfcH\xda\xd5\x80\x1a\xee\x9b\xc06\x88\xfe\xe1O\xdc\xf2\x83;\xf6\x96\xdb\x1d\x85\xfb\xecE\xd8\xe3\x80\x19\xeb\x98\xca*\x89\xff\xe3O\xdc\xf2\x82\x0c\xd2\x98\xee\x05\x84\xc7\xefD\xda\xf0\x8d9\xfb\x9a\xdc+\x84\xc7\xfbC\xe0\xfc\x8c\x0f\xfa\x9b\xca<\x85\xc2\xe4E\xdc\xde\x81<\xc3\x9b\xf4\x0c\x8f\xc2\xe8D\xdb\xdb\x81%\xe9\x9b\xe1(\x85\xc6\xf9I\xe1\xe9\x81\x1e\xd7\x91\xd8,\x86\xff\xc6E\xdc\xe6\x81\x1f\xf7\x9b\xc7\x0b\x84\xc7\xefF\xd0\xea\x8b\x1c\xec\x9a\xdc-\x85\xd0\xf8E\xc6\xfa\x8c\'\xca\x96\xeb\x12\x88\xe8\xe0O\xdc\xf2\x81\x1c\xf5\x9b\xf2\x1b\x85\xda\xd5D\xd9\xf7\x8b\x1c\xec\x9a\xdf\x05\x85\xdf\xfaE\xdf\xde\x8c\x10\xef\x9a\xdd+\x88\xc9\xcbD\xd9\xe1'

            c_str = b'\x81\xfe\x02d\xbe@<\x07'

            # 123 \x81

            #[\x81,\x83,\xc8,\xbd,\xa6,\x9c,\xf9,\x8f,\x95]

            #

            #

            #

            #--------

            #

            # 0111111 127

            # 0111110 126

            data_lenth = b_str[1] & 127

            # print(data_lenth)

            # data_lenth == 127 之后的多少位为数据长度3-10字节代表数据长度 11-14为mask_key

            if data_lenth == 127:

                extend_payload_len = b_str[2:10]

                mask = b_str[10:14]

                data = b_str[14:]

            # data_lenth == 126 之后的多少位为数据长度3-4字节代表数据长度 65535 5-8为mask_key

            if data_lenth == 126:

                extend_payload_len = b_str[2:4]

                mask = b_str[4:8]

                data = b_str[8:]

            # data_lenth <= 125 当前的 data_lenth 就是数据的长度 125      3-6为mask_key

            if data_lenth <= 125:

                extend_payload_len = b_str[1]

                mask = b_str[2:6]

                data = b_str[6:]

            str_byte = bytearray()

            for i in range(len(data)):

                byte = data[i] ^ mask[i % 4]  #

                str_byte.append(byte)

            print(str_byte.decode("utf8"))#

        加密：

            import struct

            msg_bytes = "先帝创业未半而中道崩殂，今天下三分，益州疲弊，此诚危急存亡之秋也。然侍卫之臣不懈于内，忠志之士忘身于外者，盖追先帝之殊遇，欲报之于陛下也。诚宜开张圣听，以光先帝遗德，恢弘志士之气，不宜妄自菲薄，引喻失义，以塞忠谏之路也".encode("utf8")

            token = b"\x81"

            length = len(msg_bytes)

            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)

from aip import AipSpeech

import os

from uuid import uuid4

from wav2pcm import wav_to_pcm

APP_ID = ''

API_KEY = 'zdU6ldOh7CeQvFFzw9GWhwZr'

SECRET_KEY = 'h5eVzR2G4EPFf78uzceC1zHL6Qj88RCY'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

# client.setConnectionTimeoutInMillis(5000)  # 建立连接的超时时间（单位：毫秒)

# client.setSocketTimeoutInMillis(10000)  # 通过打开的连接传输数据的超时时间（单位：毫秒）

# 语音合成

def new_synthesis(text):

    result = client.synthesis(text, 'zh', 1, {

        'vol': 5,  # 音量，取值0-15，默认为5中音量

        'spd': 5,  # 语速，取值0-9，默认为5中语速

        'pit': 5,  # 音调，取值0-9，默认为5中语调

        'per': 4  # 发音人选择, 0为女声，1为男声，3为情感合成-度逍遥，4为情感合成-度丫丫，默认为普通女

    })

    audio_file_path = str(uuid4()) + ".mp3"

    # 识别正确返回语音二进制 错误则返回dict 参照下面错误码

    if not isinstance(result, dict):

        with open(audio_file_path, 'wb') as f:

            f.write(result)

    return audio_file_path

# 读取文件

def get_file_content(pcm_file_path):

    with open(pcm_file_path, 'rb') as fp:

        return fp.read()

# 语音识别

def new_asr(filePath):

    # 将录音机文件wma转换成pcm

    pcm_file_path = wav_to_pcm(filePath)

    # 识别本地文件

    res = client.asr(get_file_content(pcm_file_path), 'pcm', 16000, {

        'dev_pid': 1536,

    })

    try:

        text = res.get('result')[0]

    except Exception as e:

        text = "对不起,没有听清你说的啥,请再说一遍。"

    os.remove(pcm_file_path)

    return text

if __name__ == '__main__':

    new_asr('audio.wma')

# wav2pcm.py 文件内容

import os

def wav_to_pcm(wav_file):

    # 假设 wav_file = "音频文件.wav"

    # wav_file.split(".") 得到["音频文件","wav"] 拿出第一个结果"音频文件"  与 ".pcm" 拼接 等到结果 "音频文件.pcm"

    pcm_file = "%s.pcm" % (wav_file.split(".")[0])

    # 就是此前我们在cmd窗口中输入命令,这里面就是在让Python帮我们在cmd中执行命令

    os.system("ffmpeg -y  -i %s  -acodec pcm_s16le -f s16le -ac 1 -ar 16000 %s" % (wav_file, pcm_file))

    os.remove(wav_file)

    return pcm_file

# 基于百度ai的Simnet的 实现短文本相似度

from aip import AipNlp

APP_ID = ''

API_KEY = 'zdU6ldOh7CeQvFFzw9GWhwZr'

SECRET_KEY = 'h5eVzR2G4EPFf78uzceC1zHL6Qj88RCY'

client = AipNlp(APP_ID, API_KEY, SECRET_KEY)

def new_simnet(text1, text2):

    ret = client.simnet(text1, text2)

    return ret.get('score')

import requests

def tuling_answer(text):

    to_tuling_url = "http://openapi.tuling123.com/openapi/api/v2"  # 接口地址

    json_data = {

        "reqType": 0,

        "perception": {

            "inputText": {

                "text": text

            },

        },

        "userInfo": {

            "apiKey": "93e5736f3b9e496bbb63a0f29afa4d4d",

            "userId": "test123"

        }

    }

    res = requests.post(to_tuling_url, json=json_data).json()

    answer = res.get("results")[0]['values']['text']

    return answer

if __name__ == '__main__':

    tuling_answer('北京天气')

<!DOCTYPE html>

<html lang="en">

<head>

    <meta charset="UTF-8">

    <title>Title</title>

</head>

<body>

<audio src="" autoplay controls id="player"></audio>

<button onclick="start_reco()">录制消息</button>

<br>

<button onclick="stop_reco()">发送语音消息</button>

</body>

<script src="/static/Recorder.js"></script>

<script type="application/javascript">

    var serv = "http://127.0.0.1:9527";

    var ws_serv = "ws://127.0.0.1:9528/ws";

    var get_music = serv + "/get_audio/";

    var ws = new WebSocket(ws_serv);

    ws.onmessage = function (data) {

        console.log(data.data,111111111)

        document.getElementById("player").src = get_music + data.data

    };

    var reco = null;

    var audio_context = new AudioContext();

    navigator.getUserMedia = (navigator.getUserMedia ||

        navigator.webkitGetUserMedia ||

        navigator.mozGetUserMedia ||

        navigator.msGetUserMedia);

    navigator.getUserMedia({audio: true}, create_stream, function (err) {

        console.log(err)

    });

    function create_stream(user_media) {

        var stream_input = audio_context.createMediaStreamSource(user_media);

        reco = new Recorder(stream_input);

    }

    function start_reco() {

        reco.record();

    }

    function stop_reco() {

        reco.stop();

        get_audio();

        reco.clear();

    }

    function get_audio() {

        reco.exportWAV(function (wav_file) {

            ws.send(wav_file);

        })

    }

</script>

</html>

from flask import Flask, send_file, render_template

from queue import Queue

import os

q = Queue()  # type:Queue

app = Flask(__name__)  # type:Flask

@app.route("/index")

def index():

    return render_template("index1.html")

temp_file_name = []

@app.route('/get_audio/<filename>')

def get_audio(filename):

    # 利用队列存储临时生成的文件名，下一次请求来的时候删除文件

    if not q.empty():

        temp = q.get()

        print(temp)

        os.remove(temp)

    q.put(filename)

    return send_file(filename)

if __name__ == '__main__':

    app.run(host='0.0.0.0', port=9527)

from flask import Flask, request

from geventwebsocket.websocket import WebSocket

from gevent.pywsgi import WSGIServer

from geventwebsocket.handler import WebSocketHandler

from uuid import uuid4

from baidu_asr_and_synthesis import new_asr, new_synthesis

from simple_questions_answers import question_answer

app = Flask(__name__)  # type:Flask

@app.route('/ws')

def ws():

    user_websocket = request.environ.get('wsgi.websocket')  # type:WebSocket

    if user_websocket:

        while 1:

            res = user_websocket.receive()

            # 保存接收音频文件

            rev_file_name = ("%s" + ".wav") % str(uuid4())

            with open(rev_file_name, 'wb') as f:

                f.write(res)

            print(rev_file_name)

            # 将接收的音频文件转换为文本

            audio_to_text = new_asr(rev_file_name)

            print('audio_to_text',audio_to_text)

            # 根据问题文本回答问题

            answer_text = question_answer(audio_to_text)

            print('answer_text',answer_text)

            # 将问题答案转成音频文件

            answer_audio_file_path = new_synthesis(answer_text)

            print('answer_audio_file_path',answer_audio_file_path)

            # 将音频文件路径发给前端

            user_websocket.send(answer_audio_file_path)

if __name__ == '__main__':

    http_serv = WSGIServer(('0.0.0.0', 9528), app, handler_class=WebSocketHandler)

    http_serv.serve_forever()