簡述

將MP4視頻內的音頻提取出來，該工具類的解決思路如下：

1、提取視頻音頻pcm資料

2、將pcm資料封裝音頻頭保存，

Maven依賴

        <dependency>
            <groupId>cn.hutool</groupId>
            <artifactId>hutool-all</artifactId>
            <version>5.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.bytedeco</groupId>
            <artifactId>javacv-platform</artifactId>
            <version>1.5.5</version>
        </dependency>

說明一下，這里用到了hutools工具包，因為可以大幅簡化代碼，如果有自己的讀取檔案流的工具類，可以不使用，

代碼

上代碼

import cn.hutool.core.io.FileUtil;
import cn.hutool.core.lang.UUID;
import lombok.extern.slf4j.Slf4j;
import org.bytedeco.javacpp.Loader;

import java.io.BufferedOutputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.Optional;

/** @Author huyi @Date 2021/10/20 12:11 @Description: mp4提取音頻工具類 */
@Slf4j
public class Mp4ExtractAudioUtils {

  /**
   * 獲取視頻的檔案pcm檔案地址
   *
   * @param url MP4
   * @return
   * @throws Exception
   */
  public static String getMp4Pcm(String url, String tmpDir) throws Exception {
    Optional<String> pcmPath = Optional.empty();
    try {
      pcmPath = convertMP4toPCM(Paths.get(url), Paths.get(tmpDir));
    } catch (Exception exception) {
      exception.printStackTrace();
      throw new Exception("轉換pcm例外:" + exception.getMessage());
    }
    if (pcmPath.isPresent()) {
      return pcmPath.get();
    } else {
      throw new Exception("視頻轉換音頻失敗");
    }
  }
  /**
   * 將單個PM4檔案進行片頭和片尾歌曲洗掉后，轉換為PCM檔案
   *
   * @param mp4Path
   * @param pcmDir
   * @return 轉換完成后的pcm檔案路徑
   */
  public static Optional<String> convertMP4toPCM(Path mp4Path, Path pcmDir) {
    String ffmpeg = Loader.load(org.bytedeco.ffmpeg.ffmpeg.class);
    // 基于ffmpeg進行pcm轉換
    // 基于輸入路徑的md5值來命名，也可以基于系統時間戳來命名
    String pcmFile = pcmDir.resolve(UUID.randomUUID() + ".pcm").toString();
    ProcessBuilder pcmBuilder =
        new ProcessBuilder(
            ffmpeg,
            "-y",
            "-i",
            mp4Path.toAbsolutePath().toString(),
            "-vn",
            "-acodec",
            "pcm_s16le",
            "-f",
            "s16le",
            "-ac",
            "1",
            "-ar",
            "16000",
            pcmFile);
    try {
      // inheritIO是指將 子流程的IO與當前java流程的IO設定為相同
      pcmBuilder.inheritIO().start().waitFor();
    } catch (InterruptedException | IOException e) {
      log.error("ffmpeg將mp4轉換為pcm時出錯", e);
      return Optional.empty();
    }
    // 回傳pcm檔案路徑
    return Optional.of(pcmFile);
  }

  /**
   * 根據PCM檔案構建wav的header欄位
   *
   * @param srate Sample rate - 8000, 16000, etc.
   * @param channel Number of channels - Mono = 1, Stereo = 2, etc..
   * @param format Number of bits per sample (16 here)
   * @throws IOException
   */
  public static byte[] buildWavHeader(int dataLength, int srate, int channel, int format)
      throws IOException {
    byte[] header = new byte[44];

    long totalDataLen = dataLength + 36;
    long bitrate = srate * channel * format;

    header[0] = 'R';
    header[1] = 'I';
    header[2] = 'F';
    header[3] = 'F';
    header[4] = (byte) (totalDataLen & 0xff);
    header[5] = (byte) ((totalDataLen >> 8) & 0xff);
    header[6] = (byte) ((totalDataLen >> 16) & 0xff);
    header[7] = (byte) ((totalDataLen >> 24) & 0xff);
    header[8] = 'W';
    header[9] = 'A';
    header[10] = 'V';
    header[11] = 'E';
    header[12] = 'f';
    header[13] = 'm';
    header[14] = 't';
    header[15] = ' ';
    header[16] = (byte) format;
    header[17] = 0;
    header[18] = 0;
    header[19] = 0;
    header[20] = 1;
    header[21] = 0;
    header[22] = (byte) channel;
    header[23] = 0;
    header[24] = (byte) (srate & 0xff);
    header[25] = (byte) ((srate >> 8) & 0xff);
    header[26] = (byte) ((srate >> 16) & 0xff);
    header[27] = (byte) ((srate >> 24) & 0xff);
    header[28] = (byte) ((bitrate / 8) & 0xff);
    header[29] = (byte) (((bitrate / 8) >> 8) & 0xff);
    header[30] = (byte) (((bitrate / 8) >> 16) & 0xff);
    header[31] = (byte) (((bitrate / 8) >> 24) & 0xff);
    header[32] = (byte) ((channel * format) / 8);
    header[33] = 0;
    header[34] = 16;
    header[35] = 0;
    header[36] = 'd';
    header[37] = 'a';
    header[38] = 't';
    header[39] = 'a';
    header[40] = (byte) (dataLength & 0xff);
    header[41] = (byte) ((dataLength >> 8) & 0xff);
    header[42] = (byte) ((dataLength >> 16) & 0xff);
    header[43] = (byte) ((dataLength >> 24) & 0xff);

    return header;
  }

  /**
   * 默認寫入的pcm資料是16000采樣率，16bit，可以按照需要修改
   *
   * @param filePath
   * @param pcmData
   */
  public static String writeToFile(String filePath, byte[] pcmData) {
    BufferedOutputStream bos = null;
    try {
      bos = new BufferedOutputStream(new FileOutputStream(filePath));
      byte[] header = buildWavHeader(pcmData.length, 16000, 1, 16);
      bos.write(header, 0, 44);
      bos.write(pcmData);
      bos.close();
      return filePath;
    } catch (Exception e) {
      e.printStackTrace();
      return filePath;
    } finally {
      if (bos != null) {
        try {
          bos.close();
        } catch (IOException e) {
          e.printStackTrace();
        }
      }
    }
  }

  /**
   * 提取音頻
   * @param mp4Path MP4地址
   * @param tmpDir 臨時檔案夾
   * @param resultPath 最終結果音頻地址
   * @return 音頻地址
   * @throws Exception 例外
   */
  public static String extractAudio(String mp4Path, String tmpDir, String resultPath)
      throws Exception {
    String pcmPath = getMp4Pcm(mp4Path, tmpDir);
    return writeToFile(resultPath, FileUtil.readBytes(pcmPath));
  }

  public static void main(String[] args) throws Exception {
    System.out.println(
        extractAudio(
            "C:\\Users\\huyi\\Desktop\\測驗.mp4",
            "C:\\Users\\huyi\\Desktop",
            "C:\\Users\\huyi\\Desktop\\測驗.wav"));
  }
}

執行結果：