Audio Split 音频文件分割

audio-split.py

import os
import subprocess

base_directory = "/path/to/source"  # 输入目录的基本路径
output_directory = "/path/to/dest"  # 切割后的音频文件保存的目录
segment_duration = 180  # 切割的每个片段的时长（以秒为单位）

def get_audio_encoding(input_path):
    command = f'ffprobe -v error -select_streams a:0 -show_entries stream=codec_name -of default=noprint_wrappers=1:nokey=1 "{input_path}"'
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
    out, err = process.communicate()
    encoding = out.decode().strip()
    return encoding

def split_audio_files(directory):
    print(directory)
    for root, dirs, files in os.walk(directory):
        print(root, dirs)
        for file in files:
            print(file)
            if file.endswith(".mp3") or file.endswith(".m4a"):
                input_path = os.path.join(root, file)
                filename_prefix, file_extension = os.path.splitext(file)
                
                # 获取原始文件的目录名称
                directory_name = os.path.basename(os.path.normpath(root))

                # 构建输出文件的路径和文件名
                output_directory_path = os.path.join(output_directory, directory_name)
                os.makedirs(output_directory_path, exist_ok=True)  # 创建输出目录
                
                # 构建输出文件的路径和文件名
                output_filename_pattern = f"{filename_prefix}-%02d{file_extension}"
                output_filepath_pattern = os.path.join(output_directory_path, output_filename_pattern)

                # 检查目标文件是否已存在，如果存在则跳过当前文件
                output_files = os.listdir(output_directory_path)
                if any(output_filename.startswith(filename_prefix) for output_filename in output_files):
                    print(f"目标文件 {output_filepath_pattern} 已存在，跳过当前文件")
                    continue

                # 是否生成临时文件
                isTemp = False
                # 获取音频编码
                encoding = get_audio_encoding(input_path)

                # 判断音频编码与扩展名是否一致
                if (encoding == "aac" and file.endswith(".m4a")) or (encoding == "mp3" and file.endswith(".mp3")):
                    # 对于AAC文件，直接进行分片处理
                    output_path = input_path #os.path.join(output_directory, file)
                else:
                    isTemp = True
                    # 对于非AAC文件，先重新编码为MP3再进行分片处理
                    output_filename = f"{filename_prefix}.mp3"
                    output_path = os.path.join(output_directory, output_filename)
                    reencode_command = f'ffmpeg -i "{input_path}" -c:a libmp3lame -vn "{output_path}"'
                    subprocess.run(reencode_command, shell=True, check=True)
                

                # 执行FFmpeg命令进行切割
                segment_command = f"ffmpeg -i \"{output_path}\" -f segment -segment_time {segment_duration} -start_number 1 -c copy \"{output_filepath_pattern}\""
                subprocess.run(segment_command, shell=True, check=True)

                if isTemp:
                    # 删除临时文件
                    os.remove(output_path)

    print("音频文件切割完成！")


if __name__ == '__main__':
    split_audio_files(base_directory)

audio-split1.py

import os
import shutil
import subprocess

base_directory = "/xxx"  # 输入目录的基本路径
output_directory = "/yyy"  # 切割后的音频文件保存的目录
segment_duration = 180  # 切割的每个片段的时长（以秒为单位）

def get_audio_encoding(input_path):
    command = f'ffprobe -v error -select_streams a:0 -show_entries stream=codec_name -of default=noprint_wrappers=1:nokey=1 "{input_path}"'
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
    out, err = process.communicate()
    encoding = out.decode().strip()
    return encoding

def get_audio_duration(input_path):
    command = f'ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "{input_path}"'
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
    out, err = process.communicate()
    duration = float(out.decode().strip())
    return duration

def split_audio_files(directory):
    print(directory)
    for root, dirs, files in os.walk(directory):
        print(root, dirs)
        for file in files:
            print(file)
            if file.endswith(".mp3") or file.endswith(".m4a"):
                input_path = os.path.join(root, file)
                filename_prefix, file_extension = os.path.splitext(file)
                
                # 获取原始文件的目录名称
                directory_name = os.path.basename(os.path.normpath(root))

                # 构建输出文件的路径和文件名
                output_directory_path = os.path.join(output_directory, directory_name)
                os.makedirs(output_directory_path, exist_ok=True)  # 创建输出目录
                
                # 构建输出文件的路径和文件名
                output_filename_pattern = f"{filename_prefix}-%02d{file_extension}"
                output_filepath_pattern = os.path.join(output_directory_path, output_filename_pattern)

                # 检查目标文件是否已存在，如果存在则跳过当前文件
                output_files = os.listdir(output_directory_path)
                if any(output_filename.startswith(filename_prefix) for output_filename in output_files):
                    print(f"目标文件 {output_filepath_pattern} 已存在，跳过当前文件")
                    continue


                # 获取音频文件的时长
                duration = get_audio_duration(input_path)

                # 判断音频时长是否小于切割长度
                if duration < segment_duration:
                    # 如果音频时长小于切割长度，直接复制到目标目录
                    output_file_path = os.path.join(output_directory_path, file)
                    shutil.copy2(input_path, output_file_path)
                    print(f"音频文件 {file} 长度小于切割长度，直接复制到目标目录")
                    continue

                # 是否生成临时文件
                isTemp = False
                # 获取音频编码
                encoding = get_audio_encoding(input_path)

                # 判断音频编码与扩展名是否一致
                if (encoding == "aac" and file.endswith(".m4a")) or (encoding == "mp3" and file.endswith(".mp3")):
                    # 对于AAC文件，直接进行分片处理
                    output_path = input_path #os.path.join(output_directory, file)
                else:
                    isTemp = True
                    # 对于非AAC文件，先重新编码为MP3再进行分片处理
                    output_filename = f"{filename_prefix}.mp3"
                    output_path = os.path.join(output_directory, output_filename)
                    reencode_command = f'ffmpeg -i "{input_path}" -c:a libmp3lame -vn "{output_path}"'
                    subprocess.run(reencode_command, shell=True, check=True)
                

                # 执行FFmpeg命令进行切割
                segment_command = f"ffmpeg -i \"{output_path}\" -f segment -segment_time {segment_duration} -start_number 1 -c copy \"{output_filepath_pattern}\""
                subprocess.run(segment_command, shell=True, check=True)

                if isTemp:
                    # 删除临时文件
                    os.remove(output_path)

    print("音频文件切割完成！")


if __name__ == '__main__':
    split_audio_files(base_directory)

check-and-update-audio-extension.py

import os
import subprocess
import argparse

# 递归查找目录中的音频文件并修正扩展名
def process_directory(directory):
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith(('.mp3', '.wav', '.ogg', '.aac')):
                file_path = os.path.join(root, file)

                # 使用FFmpeg命令行工具获取音频文件的编码方式
                cmd = f'ffprobe -v error -select_streams a:0 -show_entries stream=codec_name -of default=noprint_wrappers=1:nokey=1 "{file_path}"'
                output = subprocess.check_output(cmd, shell=True, stderr=subprocess.STDOUT)

                # 根据编码方式修改扩展名
                extension = os.path.splitext(file)[1]
                new_extension = f'.{output.decode().strip()}'

                if new_extension == '.aac':
                    new_extension = '.m4a'

                if extension.lower() != new_extension.lower():
                    new_file_path = os.path.join(root, os.path.splitext(file)[0] + new_extension)
                    #os.rename(file_path, new_file_path)
                    print(f"Modified extension of '{file}' to '{new_extension}'")

    print("Extension modification complete.")


# 解析命令行参数
parser = argparse.ArgumentParser()
parser.add_argument("directory", help="目录路径")
args = parser.parse_args()

# 调用函数处理目录
process_directory(args.directory)