recognition.py

import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import threading


# 收到websocket错误的处理
def on_error(ws, error):
    print("### error:", error)


# 收到websocket关闭的处理
def on_close(ws):
    print("### closed ###")


class Recognition(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret):
        global frame
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.frames = []
        self.result = ''

        # 公共参数(common)
        self.CommonArgs = {"app_id": self.APPID}
        # 业务参数(business)，更多个性化参数可在官网查看
        self.BusinessArgs = {"domain": "iat", "language": "zh_cn", "accent": "mandarin", "vinfo":1,"vad_eos":10000}
        websocket.enableTrace(False)
        return

    def recognize(self):
        wsUrl = self.create_url()
        self.ws = websocket.WebSocketApp(wsUrl, on_open=self.on_open, on_message=self.on_message,
                                         on_error=on_error, on_close=on_close)
        self.ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})

    def run_recognize(self):
        t = threading.Thread(target=self.recognize)
        t.setDaemon(True)
        t.start()

    # 生成url
    def create_url(self):
        url = 'wss://ws-api.xfyun.cn/v2/iat'
        # 生成RFC1123格式的时间戳
        now = datetime.now()
        date = format_date_time(mktime(now.timetuple()))

        # 拼接字符串
        signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + "/v2/iat " + "HTTP/1.1"
        # 进行hmac-sha256进行加密
        signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),
                                 digestmod=hashlib.sha256).digest()
        signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (
            self.APIKey, "hmac-sha256", "host date request-line", signature_sha)
        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
        # 将请求的鉴权参数组合为字典
        v = {
            "authorization": authorization,
            "date": date,
            "host": "ws-api.xfyun.cn"
        }
        # 拼接鉴权参数，生成url
        url = url + '?' + urlencode(v)
        # print("date: ",date)
        # print("v: ",v)
        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致
        # print('websocket url :', url)
        return url

    # 收到websocket消息的处理
    def on_message(self, message):
        try:
            code = json.loads(message)["code"]
            sid = json.loads(message)["sid"]
            if code != 0:
                errMsg = json.loads(message)["message"]
                print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))

            else:
                data = json.loads(message)["data"]["result"]["ws"]
                for i in data:
                    for w in i["cw"]:
                        self.result += w["w"]
        except Exception as e:
            print("receive msg,but parse exception:", e)

    # 收到websocket连接建立的处理
    def on_open(self):
        def run():
            intervel = 0.04  # 发送音频间隔(单位:s)
            while True:
                if len(self.frames) == 0:
                    continue
                i, f = self.frames.pop(0)
                # 第一帧处理
                # 发送第一帧音频，带business 参数
                # appid 必须带上，只需第一帧发送
                if i == 0:
                    d = {"common": self.CommonArgs,
                        "business": self.BusinessArgs,
                        "data": {"status": 0, "format": "audio/L16;rate=16000",
                                "audio": str(base64.b64encode(f), 'utf-8'),
                                "encoding": "raw"}}
                    d = json.dumps(d)
                    self.ws.send(d)
                # 最后一帧处理
                elif i == -1:
                    d = {"data": {"status": 2, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(f), 'utf-8'),
                                  "encoding": "raw"}}
                    self.ws.send(json.dumps(d))
                    time.sleep(1)
                    print('close')
                    self.frames = []
                    self.ws.close()
                    break
                # 中间帧处理
                else:
                    d = {"data": {"status": 1, "format": "audio/L16;rate=16000",
                                "audio": str(base64.b64encode(f), 'utf-8'),
                                "encoding": "raw"}}
                    self.ws.send(json.dumps(d))

                # 模拟音频采样间隔
                time.sleep(intervel)
        t = threading.Thread(target=run)
        t.setDaemon(True)
        t.start()