FFMPEG学习----分离视音频里的PCM数据

/**
*  参考于：http://blog.csdn.net/leixiaohua1020/article/details/46890259
*/
#include <stdio.h>
#include <string.h>

extern "C"
{
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libswresample/swresample.h"
};

#pragma comment(lib, "avcodec.lib")
#pragma comment(lib, "avformat.lib")
#pragma comment(lib, "swresample.lib")
#pragma comment(lib, "avutil.lib")

// 1 second of 48khz 32bit(4Byte) audio
#define MAX_AUDIO_FRAME_SIZE 192000

int main(int argc, char* argv[])
{
AVFormatContext		*pFormatCtx = NULL;
AVCodecContext		*pCodecCtx = NULL;
AVCodec				*pCodec = NULL;
AVPacket			packet;
AVFrame				*pAudioFrame = NULL;
uint8_t				*buffer = NULL;
struct SwrContext	*audio_convert_ctx = NULL;
int					got_picture;
int					audioIndex;

char filepath[1024] = "";
printf("Usage: program.exe *.mp3\n");
if (argc == 2)
{
strcpy(filepath, argv[1]);
}
else
{
printf("Could not find a audio file\n");
return -1;
}

FILE *fp_pcm = fopen("output.pcm", "wb+");
if (fp_pcm == NULL)
{
printf("FILE open error");
return -1;
}

av_register_all();

if (avformat_open_input(&pFormatCtx, filepath, NULL, NULL) != 0)
{
printf("Couldn't open an input stream.\n");
return -1;
}
if (avformat_find_stream_info(pFormatCtx, NULL) < 0)
{
printf("Couldn't find stream information.\n");
return -1;
}
audioIndex = -1;
for (int i = 0; i < pFormatCtx->nb_streams; i++)
{
if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
{
audioIndex = i;
break;
}
}

if (audioIndex == -1)
{
printf("Couldn't find a audio stream.\n");
return -1;
}

pCodecCtx = pFormatCtx->streams[audioIndex]->codec;
pCodec = avcodec_find_decoder(pCodecCtx->codec_id);
if (pCodec == NULL)
{
printf("Codec not found.\n");
return -1;
}
if (avcodec_open2(pCodecCtx, pCodec, NULL) < 0)
{
printf("Could not open codec.\n");
return -1;
}

pAudioFrame = av_frame_alloc();
if (pAudioFrame == NULL)
{
printf("Could not alloc AVFrame\n");
return -1;
}

//音频输出参数
uint64_t out_channel_layout = AV_CH_LAYOUT_STEREO;//声道格式
AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_S16;//采样格式
int out_nb_samples = pCodecCtx->frame_size;//nb_samples: AAC-1024 MP3-1152
int out_sample_rate = 44100;//采样率
int out_nb_channels = av_get_channel_layout_nb_channels(out_channel_layout);//根据声道格式返回声道个数
int out_buffer_size = av_samples_get_buffer_size(NULL, out_nb_channels, out_nb_samples, out_sample_fmt, 1);

buffer = (uint8_t *)av_malloc(MAX_AUDIO_FRAME_SIZE);

/**
* 函数声明：struct SwrContext *swr_alloc(void);
* Allocate SwrContext.
*
* If you use this function you will need to set the parameters (manually or
* with swr_alloc_set_opts()) before calling swr_init().
*
* @see swr_alloc_set_opts(), swr_init(), swr_free()
* @return NULL on error, allocated context otherwise
*/

audio_convert_ctx = swr_alloc();
if (audio_convert_ctx == NULL)
{
printf("Could not allocate SwrContext\n");
return -1;
}

/**
* 函数声明：struct SwrContext *swr_alloc_set_opts(
* struct SwrContext *s,int64_t out_ch_layout, enum AVSampleFormat out_sample_fmt, int out_sample_rate,
* int64_t  in_ch_layout, enum AVSampleFormat  in_sample_fmt, int  in_sample_rate,
* int log_offset, void *log_ctx);
*
* Allocate SwrContext if needed and set/reset common parameters.
*
* This function does not require s to be allocated with swr_alloc(). On the
* other hand, swr_alloc() can use swr_alloc_set_opts() to set the parameters
* on the allocated context.
*
* @param s               existing Swr context if available, or NULL if not
* @param out_ch_layout   output channel layout (AV_CH_LAYOUT_*)
* @param out_sample_fmt  output sample format (AV_SAMPLE_FMT_*).
* @param out_sample_rate output sample rate (frequency in Hz)
* @param in_ch_layout    input channel layout (AV_CH_LAYOUT_*)
* @param in_sample_fmt   input sample format (AV_SAMPLE_FMT_*).
* @param in_sample_rate  input sample rate (frequency in Hz)
* @param log_offset      logging level offset
* @param log_ctx         parent logging context, can be NULL
*
* @see swr_init(), swr_free()
* @return NULL on error, allocated context otherwise
*/

/*
int64_t in_channel_layout = av_get_default_channel_layout(pCodecCtx->channels);//根据声道数返回默认输入声道格式
swr_alloc_set_opts(audio_convert_ctx, out_channel_layout, out_sample_fmt, out_sample_rate,
in_channel_layout, pCodecCtx->sample_fmt, pCodecCtx->sample_rate, 0, NULL);
*/

swr_alloc_set_opts(audio_convert_ctx, out_channel_layout, out_sample_fmt,out_sample_rate,
pCodecCtx->channel_layout, pCodecCtx->sample_fmt, pCodecCtx->sample_rate, 0, NULL);

/**
* 函数声明：int swr_init(struct SwrContext *s);
* Initialize context after user parameters have been set.
* @note The context must be configured using the AVOption API.
*
* @see av_opt_set_int()
* @see av_opt_set_dict()
*
* @param[in,out]   s Swr context to initialize
* @return AVERROR error code in case of failure.
*/
swr_init(audio_convert_ctx);

int	index = 0;//计数器
while (av_read_frame(pFormatCtx, &packet) >= 0)
{
if (packet.stream_index == audioIndex)
{
if (avcodec_decode_audio4(pCodecCtx, pAudioFrame, &got_picture, &packet) < 0)
{
printf("Error in decoding audio frame.\n");
return -1;
}
if (got_picture)
{
/** Convert audio.
* 函数声明：int swr_convert(struct SwrContext *s, uint8_t **out, int out_count,
*                           const uint8_t **in, int in_count);
* in and in_count can be set to 0 to flush the last few samples out at the
* end.
*
* If more input is provided than output space, then the input will be buffered.
* You can avoid this buffering by using swr_get_out_samples() to retrieve an
* upper bound on the required number of output samples for the given number of
* input samples. Conversion will run directly without copying whenever possible.
*
* @param s         allocated Swr context, with parameters set
* @param out       output buffers, only the first one need be set in case of packed audio
* @param out_count amount of space available for output in samples per channel
* @param in        input buffers, only the first one need to be set in case of packed audio
* @param in_count  number of input samples available in one channel
*
* @return number of samples output per channel, negative value on error
*/

swr_convert(audio_convert_ctx, &buffer, MAX_AUDIO_FRAME_SIZE, (const uint8_t **)pAudioFrame->data, pAudioFrame->nb_samples);
printf("index:%5d\t pts:%lld\t packet size:%d\n", index, packet.pts, packet.size);
//Write PCM
fwrite(buffer, 1, out_buffer_size, fp_pcm);
index++;
}
}
av_free_packet(&packet);
}

fclose(fp_pcm);
swr_free(&audio_convert_ctx);
av_free(buffer);
av_frame_free(&pAudioFrame);
avcodec_close(pCodecCtx);
avformat_close_input(&pFormatCtx);

return 0;
}

与解析视频里的YUV/RGB（http://blog.csdn.net/x_iya/article/details/52248929）相同的是，解析出音频的AVFrame同样需要转换。

由于ffmpeg最新版本（从2.1开始貌似）使用avcodec_decode_audio4函数来解码音频，但解码得到的数据类型为float 4bit，而播放器播放的格式一般为S16（signed 16bit）,就需要对解码得到的数据进行转换，然而，ffmpeg已经帮我们做好了，只需调用API就可以了，这个函数就是：swr_convert

输出：



使用Audacity打开（注意参数）





问题：

1.有些格式的视频不符合标准，获得的pCodecCtx->frame_size为0

雷老师，我使用wmv格式的视频进行测试，结果不能进行得到正确的pcm文件，文件大小始终为0，发现是out_nb_samples = pCodecCtx->frame_size发生错误，其中pCodecCtx->frame_size为0，导致av_samples_get_buffer_size算出的大小是负数。问过有经验组长，他告诉我有些格式的视频不符合标准，不能从文件头中获取到信息，要在读入一帧后获取，也就是ret = avcodec_decode_audio4( pCodecCtx, pFrame,&got_picture, packet);之后，从pFrame中获取信息。 发现错误，重新修改程序，就能得到数据了。

2.对于采样率为48000Hz的视频，解析为采样率为44100Hz的pcm时出现杂音，将out_sample_rate设置为

int out_sample_rate = 48000;则没有问题。