firefox 实现web交互机器人

时间：2023-03-09 19:25:58
firefox 实现web交互机器人

现在仅有火狐浏览器可以这样操作 -- Filefox

下面是项目目录 --

firefox 实现web交互机器人

前端页面 -- html

<!DOCTYPE html>

<html lang="en">

<head>

    <meta charset="UTF-8">

    <title>我是玩具</title>

</head>

<body>

<p><audio id="player" controls autoplay  ></audio></p>  <!--  src  -->

<button onclick="start_reco()">录音</button>

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

<div id="content"></div>

</body>

<script type="text/javascript" src="/static/Recorder.js"></script>

<script type="text/javascript" src="/static/jquery-3.3.1.min.js"></script>

<script type="text/javascript">

    var serv = "http://192.168.11.173:9009";

    var reco = null;

    var audio_context = new AudioContext(); //音频内容对象  音频DOM 对象

    navigator.getUserMedia = (navigator.getUserMedia ||     //获取浏览器

        navigator.webkitGetUserMedia ||

        navigator.mozGetUserMedia ||

        navigator.msGetUserMedia);

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

        console.log(err)                //success回调函数    error

    });

    function create_stream(user_media) {

        var stream_input = audio_context.createMediaStreamSource(user_media);  //创建流媒体容器

        reco = new Recorder(stream_input);   // 录音的js

    }

    function start_reco() {

        reco.record();   // 开始录音

    }

    function stop_reco() {

        reco.stop();     // 停了

        reco.exportWAV(function (wav_file) {     // 输出音频

            console.log(wav_file);

            var formdata = new FormData();      // form 表单 {key:value}

            formdata.append("reco",wav_file);  // form input type="file"

            formdata.append("key","value");   // str 值int 文件 随便填

            // # <input type="text" name = "key"> value

            $.ajax({

            url: serv + "/upload",

            type: 'post',

            processData: false,   // 校验格式

            contentType: false,   // 检查内容

            data: formdata,

            dataType: 'json',

            success: function (data) {

                console.log(data);

                if(data.code == 0){

                    document.getElementById("player").src = "http://192.168.11.173:9009/get_file/"+data.filename;

                    document.getElementById("content").innerText = data.content;

                }

            }

            })

        });

        reco.clear();    // 清空

    }

</script>

</html>

项目 主 py 文件

from flask import Flask, render_template, request, jsonify, send_file

from uuid import uuid4

from other import audio2text,text2audio,my_nlp

app = Flask(__name__)

@app.route("/")

def index():

    return render_template("WebToy.html")

@app.route("/upload",methods=["POST"])

def upload():

    fi = request.files.get("reco")

    fi_name = f"{uuid4()}.wav"

    fi.save(fi_name)

    text = audio2text(fi_name)

    new_text = my_nlp(text)

    filename = text2audio(new_text)

    ret = {

        "filename":filename,

        "content":new_text,

        "code":0

    }

    return jsonify(ret)

@app.route("/get_file/<filename>")

def get_file(filename):

    return send_file(filename)

if __name__ == '__main__':

    app.run("0.0.0.0",9009,debug=True)

其他  py  文件

import os

from aip import AipSpeech

from aip import AipNlp

from uuid import uuid4

APP_ID = ''

API_KEY = '5GGaPeBu2I0LsONjlWhM04yL'

SECRET_KEY = 'Uo8zIi8VRZMRgqKkCQaqaGIorsQtkDlw'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)  # 实例化

nlp_client = AipNlp(APP_ID, API_KEY, SECRET_KEY)  # 实例化

# 读取文件

def get_file_content(filePath):

    os.system(f'ffmpeg -y  -i {filePath}  -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filePath}.pcm')

    with open(f'{filePath}.pcm', 'rb') as fp:

        return fp.read()

def audio2text(filePath):

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

        'dev_pid': 1536,

    })

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

    # print(text)

    return text

# 智能问答

import requests  # 请求模块

def to_tuling(text, uid):  # 问题

    data = {

        "reqType": 0,

        "perception": {

            "inputText": {

                "text": "上海"

            },

        },

        "userInfo": {

            "apiKey": "29f1be0165d74f7290a8cd899a4358a8",

            "userId": ""

        }

    }

    data['perception']['inputText']['text'] = text

    data['userInfo']['userId'] = uid

    res = requests.post('http://openapi.tuling123.com/openapi/api/v2', json=data)

    print(res)

    res_json = res.json()

    text = res_json.get('results')[0].get('values').get('text')

    return text

def my_nlp(text):

    if nlp_client.simnet(text, '你叫什么名字').get('score') >= 0.77:

        A = '我叫jay吧'

        return A

    if nlp_client.simnet(text, '你今年几岁了').get('score') >= 0.77:

        A = '今年999岁'

        return A

    A = to_tuling(text, '')

    return A

def text2audio(text):

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

        'vol': 5,

        'per': 4,

        'spd': 4,

        'pit': 7

    })

    filename = f'{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(f'{time.time()}.mp3', 'wb') as f:

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

            f.write(result)

    return filename

相关文章