PuppyServer/aiDogProject_docker/aiDogProject/aiDogApp/dbOperate_upload_Uvoice.py

import pyaudio
import wave
import pymysql
import time
from datetime import datetime
from pydub import AudioSegment
import uuid
import os
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "aiDogProject.settings")
import django
django.setup()
from aiDogApp.models import *
from .generalRequest import req_url  # Importing your generalRequest.py method

# Audio recording settings
SAMPLE_RATE = 16000
BIT_RATE = 16
CHANNELS = 1
RECORD_SECONDS = 2
CHUNK = 1024
FORMAT = pyaudio.paInt16

# 连接mysql数据库
# def get_db_connection():
    # return pymysql.connect(
    #     host='127.0.0.1',
    #     port=3306,
    #     user='root',
    #     password='',
    #     database='aidog'
    # )

# 录制音频 并存储为WAV文件
def record_audio(file_path,mp3_path, duration=4):
    # Audio settings
    sample_rate = 16000
    channels = 1
    bit_rate = pyaudio.paInt16
    chunk_size = 1024

    audio = pyaudio.PyAudio()

    # Start recording
    stream = audio.open(format=bit_rate, channels=channels,
                        rate=sample_rate, input=True,
                        frames_per_buffer=chunk_size)

    print("Recording...")

    frames = []
    for _ in range(0, int(sample_rate / chunk_size * duration)):
        data = stream.read(chunk_size)
        frames.append(data)

    print("Recording complete.")

    # Stop and close the stream
    stream.stop_stream()
    stream.close()
    audio.terminate()

    # Save audio to file
    with wave.open(file_path, 'wb') as wf:
        wf.setnchannels(channels)
        wf.setsampwidth(audio.get_sample_size(bit_rate))
        wf.setframerate(sample_rate)
        wf.writeframes(b''.join(frames))
  # Convert to MP3
    audio_segment = AudioSegment.from_wav(file_path)
    audio_segment.export(mp3_path, format="mp3")

    # Remove the intermediate WAV file
    os.remove(file_path)

# Function to insert audio information into MySQL database
def insert_voice_data(uid, feature_id, wav_file_path,command_type,record_time):
    try:
        # conn = get_db_connection()
        # cursor = conn.cursor()

        # 读取 WAV 文件 为二进制数据
        with open(wav_file_path, 'rb') as wav_file:
            wav_data = wav_file.read()


        # 插入到声纹信息表中
        #     口令类型（0：叫名字     1：坐下，2：站起，3：摇尾巴，4：走过来，5 抬左手，6：抬右手）
        if command_type == 0:
            # 口令类型（0：叫名字

            # insert_query = """
            #         INSERT INTO voice_feature_info (uid, voice_feature_id, voice_name_command,command_type)
            #         VALUES (%s, %s, %s, %s)
            #     """
            # # cursor.execute(insert_query, (uid, feature_id, wav_data, command_type))
            VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id,
                                                                                       voice_name_command=wav_data,
                                                                                       record_time=record_time)
        elif command_type == 1:
            # 口令类型（1：坐下
            VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id,
                                                                                       voice_sit_command=wav_data,
                                                                                       record_time=record_time)
        elif command_type == 2:
            # 口令类型（2：站起
            VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id,
                                                                                       voice_stand_command=wav_data,
                                                                                       record_time=record_time
                                                                                       )
        elif command_type == 3:
            # 口令类型（3：摇尾巴
            VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id,
                                                                                       voice_wagtail_command=wav_data,
                                                                                       record_time=record_time)
        else:
            # 口令类型（4：走过来
            VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id,
                                                                                       voice_come_command=wav_data,
                                                                                       record_time=record_time)

        # conn.commit()
        print(f"Data inserted into database for UID: {uid}")
        return True


    # 抛出异常
    except Exception as err:
        print(f"Error: {err}")
        return False
    # finally:
        # cursor.close()
        # conn.close()

APPId = "4522d502"
APISecret = "Zjc5MjJhMzBmMDYxNTg4MTNlMTg1MmQw"
APIKey = "f7a9f0ceae3ff7ebfc0c89efeb18810d"
file_path = './media/讯飞开放平台.mp3'#读取数据库路径下音源
# Main method to record audio, save locally, insert to DB, and call req_url()
def process_voice_recording(uid,voice_feature_id, command_type):
    # 定义本地缓存路径
    cache_directory = "audio_cache"
    if not os.path.exists(cache_directory):
        os.makedirs(cache_directory)

    # 创建一个唯一的文件名
    timestamp = int(time.time())
    timestamp11 = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    file_path = os.path.join(cache_directory, f"voice_{uid}_{timestamp}.wav")
    mp3_path=os.path.join(cache_directory, f"voice_{uid}_{timestamp}.mp3")
    # 录制wav音频 并存储到cache
    record_audio(file_path,mp3_path)

    # 插入到数据库 声纹信息表
    if insert_voice_data(uid, voice_feature_id, mp3_path,command_type,timestamp11):
        # 如果插入成功，调用generalRequest.py里的第三方声纹识别API
        res='xxx'
        res=req_url(api_name='createFeature', APPId=APPId,
                               APIKey=APIKey, APISecret=APISecret, file_path=mp3_path, featureId=voice_feature_id,groupId=uid)  # 传参数 缓存音频路径，声纹id
        print(f"音频文件缓存在 {mp3_path} 并且传参到 req_url().")
        yy = datetime.today()
        end_timestamp = datetime.strftime(yy, '%Y-%m-%d %H:%M:%S')
        # return res
        return (f"音频文件缓存在 {mp3_path} 并且传参到 req_url().返回内容为{res}.请求时间为:---{timestamp11}.返回时间为:---{end_timestamp}")

    else:
        print("Failed to insert voice data into database.")
        return ("Failed to insert voice data into database.")
    # 移除缓存中的wav文件
    # os.remove(file_path)

# Example Usage:
# if __name__ == "__main__":
#     user_uid = 'JTYNZP9O'  # 用户ID
#     feature_id = 'sfggcvvh1212'  # 用户声纹 ID
#     command_type=1
#
#     process_voice_recording(user_uid, feature_id,command_type)