【音视频】MP4解封装

一、概述

实现了读取mp4文件，提取出h264和aac文件，可以直接播放

二、实现过程

准备文件

在build路径下添加mp4文件

同时，添加main函数参数，表示输入文件和输出文件

打开文件

• 打开输入文件，初始化格式上下文

char *in_filename = argv[1];
ret = avformat_open_input(&ifmt_ctx, in_filename, NULL, NULL);if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("avformat_open_input failed:%d\n", ret);printf("avformat_open_input failed:%s\n", errors);avformat_close_input(&ifmt_ctx);//        go failed;return -1;}

• 打开输出文件

char *h264_filename = argv[2];
char *aac_filename = argv[3];
FILE *aac_fd = NULL;
FILE *h264_fd = NULL;h264_fd = fopen(h264_filename, "wb");
if(!h264_fd) {printf("fopen %s failed\n", h264_filename);return -1;
}aac_fd = fopen(aac_filename, "wb");
if(!aac_fd) {printf("fopen %s failed\n", aac_filename);return -1;
}

解封装

• 对于mp4文件，不需要使用av_find_stream_info这个函数，如果是flv则需要，因为在mp4的头部信息中已经有足够的信息拷贝到格式上下文了。
• 直接使用avformat_find_best_stream找音频流和视频流即可

video_index = av_find_best_stream(ifmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
if(video_index == -1) {printf("av_find_best_stream video_index failed\n");avformat_close_input(&ifmt_ctx);return -1;
}audio_index = av_find_best_stream(ifmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
if(audio_index == -1) {printf("av_find_best_stream audio_index failed\n");avformat_close_input(&ifmt_ctx);return -1;
}

写入头部

对于mp4文件，解码出来的音频和视频数据包都不带头部，因此我们都需要手动写入头部

• 对于h264，使用比特流过滤器直接将mp4模式转为annexb模式即可，它会自动写入sps pps starCode

• 对于aac，手动写入ADTS即可，格式就是固定头+可变头，长度为7个字节（不带校验）

• 初始化比特流过滤器

AVBSFContext *bsf_ctx = NULL;        // 对应面向对象的变量
ret = av_bsf_alloc(bsfilter, &bsf_ctx);
if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_alloc failed:%s\n", errors);avformat_close_input(&ifmt_ctx);return -1;
}
ret = avcodec_parameters_copy(bsf_ctx->par_in, ifmt_ctx->streams[video_index]->codecpar);
if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("avcodec_parameters_copy failed:%s\n", errors);avformat_close_input(&ifmt_ctx);av_bsf_free(&bsf_ctx);return -1;
}
ret = av_bsf_init(bsf_ctx);
if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_init failed:%s\n", errors);avformat_close_input(&ifmt_ctx);av_bsf_free(&bsf_ctx);return -1;
}

• 循环从格式上下文中解码出H264包和AAC包

ret = av_read_frame(ifmt_ctx, pkt);     // 不会去释放pkt的buf，如果我们外部不去释放，就会出现内存泄露if(ret < 0 ) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_read_frame failed:%s\n", errors);break;}

根据packet中的索引判断是音频包还是视频包

• 如果是视频包，先将数据包发送到比特流过滤器，然后再从比特流过滤器中拿出已经有头部的h264数据包，将带有头部的数据包写入文件
• 要使用循环来接收数据包，因为可能有多个数据包，根据不同返回值进行判断接收情况

if(pkt->stream_index == video_index) {// 处理视频ret = av_bsf_send_packet(bsf_ctx, pkt); // 内部把我们传入的buf转移到自己bsf内部if(ret < 0) {       // 基本不会进入该逻辑av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_send_packet failed:%s\n", errors);av_packet_unref(pkt);continue;}while (1) {ret = av_bsf_receive_packet(bsf_ctx, pkt);if(ret != 0) {break;}size_t size = fwrite(pkt->data, 1, pkt->size, h264_fd);if(size != pkt->size){av_log(NULL, AV_LOG_DEBUG, "h264 warning, length of writed data isn't equal pkt->size(%d, %d)\n",size,pkt->size);}av_packet_unref(pkt);}
}

• 如果是音频包，则写入ADTS，使用的是MPEG-2的标准，因此这里的profile不需要改变

else if(pkt->stream_index == audio_index) {// 处理音频char adts_header_buf[7] = {0};adts_header(adts_header_buf, pkt->size,ifmt_ctx->streams[audio_index]->codecpar->profile,ifmt_ctx->streams[audio_index]->codecpar->sample_rate,ifmt_ctx->streams[audio_index]->codecpar->channels);fwrite(adts_header_buf, 1, 7, aac_fd);  // 写adts header , ts流不适用，ts流分离出来的packet带了adts headersize_t size = fwrite( pkt->data, 1, pkt->size, aac_fd);   // 写adts dataif(size != pkt->size){av_log(NULL, AV_LOG_DEBUG, "aac warning, length of writed data isn't equal pkt->size(%d, %d)\n",size,pkt->size);}av_packet_unref(pkt);
} 

adts_header函数

int adts_header(char * const p_adts_header, const int data_length,const int profile, const int samplerate,const int channels)
{int sampling_frequency_index = 3; // 默认使用48000hzint adtsLen = data_length + 7;int frequencies_size = sizeof(sampling_frequencies) / sizeof(sampling_frequencies[0]);int i = 0;for(i = 0; i < frequencies_size; i++){if(sampling_frequencies[i] == samplerate){sampling_frequency_index = i;break;}}if(i >= frequencies_size){printf("unsupport samplerate:%d\n", samplerate);return -1;}p_adts_header[0] = 0xff;         //syncword:0xfff                          高8bitsp_adts_header[1] = 0xf0;         //syncword:0xfff                          低4bitsp_adts_header[1] |= (1 << 3);    //MPEG Version:0 for MPEG-4,1 for MPEG-2  1bitp_adts_header[1] |= (0 << 1);    //Layer:0                                 2bitsp_adts_header[1] |= 1;           //protection absent:1                     1bitp_adts_header[2] = (profile)<<6;            //profile:profile               2bitsp_adts_header[2] |= (sampling_frequency_index & 0x0f)<<2; //sampling frequency index:sampling_frequency_index  4bitsp_adts_header[2] |= (0 << 1);             //private bit:0                   1bitp_adts_header[2] |= (channels & 0x04)>>2; //channel configuration:channels  高1bitp_adts_header[3] = (channels & 0x03)<<6; //channel configuration:channels 低2bitsp_adts_header[3] |= (0 << 5);               //original：0                1bitp_adts_header[3] |= (0 << 4);               //home：0                    1bitp_adts_header[3] |= (0 << 3);               //copyright id bit：0        1bitp_adts_header[3] |= (0 << 2);               //copyright id start：0      1bitp_adts_header[3] |= ((adtsLen & 0x1800) >> 11);           //frame length：value   高2bitsp_adts_header[4] = (uint8_t)((adtsLen & 0x7f8) >> 3);     //frame length:value    中间8bitsp_adts_header[5] = (uint8_t)((adtsLen & 0x7) << 5);       //frame length:value    低3bitsp_adts_header[5] |= 0x1f;                                 //buffer fullness:0x7ff 高5bitsp_adts_header[6] = 0xfc;      //11111100       //buffer fullness:0x7ff 低6bits// number_of_raw_data_blocks_in_frame：//    表示ADTS帧中有number_of_raw_data_blocks_in_frame + 1个AAC原始帧。return 0;
}

释放内存与关闭文件

• 释放格式上下文、数据包内存

if(ifmt_ctx)avformat_close_input(&ifmt_ctx);
if(pkt)av_packet_free(&pkt);

• 关闭输出文件

 if(h264_fd) {fclose(h264_fd);
}
if(aac_fd) {fclose(aac_fd);
}

完整代码

main.c

#include <stdio.h>#include "libavutil/log.h"
#include "libavformat/avformat.h"#define ERROR_STRING_SIZE 1024#define ADTS_HEADER_LEN  7;const int sampling_frequencies[] = {96000,  // 0x088200,  // 0x164000,  // 0x248000,  // 0x344100,  // 0x432000,  // 0x524000,  // 0x622050,  // 0x716000,  // 0x812000,  // 0x911025,  // 0xa8000   // 0xb// 0xc d e f是保留的
};int adts_header(char * const p_adts_header, const int data_length,const int profile, const int samplerate,const int channels)
{int sampling_frequency_index = 3; // 默认使用48000hzint adtsLen = data_length + 7;int frequencies_size = sizeof(sampling_frequencies) / sizeof(sampling_frequencies[0]);int i = 0;for(i = 0; i < frequencies_size; i++){if(sampling_frequencies[i] == samplerate){sampling_frequency_index = i;break;}}if(i >= frequencies_size){printf("unsupport samplerate:%d\n", samplerate);return -1;}p_adts_header[0] = 0xff;         //syncword:0xfff                          高8bitsp_adts_header[1] = 0xf0;         //syncword:0xfff                          低4bitsp_adts_header[1] |= (1 << 3);    //MPEG Version:0 for MPEG-4,1 for MPEG-2  1bitp_adts_header[1] |= (0 << 1);    //Layer:0                                 2bitsp_adts_header[1] |= 1;           //protection absent:1                     1bitp_adts_header[2] = (profile)<<6;            //profile:profile               2bitsp_adts_header[2] |= (sampling_frequency_index & 0x0f)<<2; //sampling frequency index:sampling_frequency_index  4bitsp_adts_header[2] |= (0 << 1);             //private bit:0                   1bitp_adts_header[2] |= (channels & 0x04)>>2; //channel configuration:channels  高1bitp_adts_header[3] = (channels & 0x03)<<6; //channel configuration:channels 低2bitsp_adts_header[3] |= (0 << 5);               //original：0                1bitp_adts_header[3] |= (0 << 4);               //home：0                    1bitp_adts_header[3] |= (0 << 3);               //copyright id bit：0        1bitp_adts_header[3] |= (0 << 2);               //copyright id start：0      1bitp_adts_header[3] |= ((adtsLen & 0x1800) >> 11);           //frame length：value   高2bitsp_adts_header[4] = (uint8_t)((adtsLen & 0x7f8) >> 3);     //frame length:value    中间8bitsp_adts_header[5] = (uint8_t)((adtsLen & 0x7) << 5);       //frame length:value    低3bitsp_adts_header[5] |= 0x1f;                                 //buffer fullness:0x7ff 高5bitsp_adts_header[6] = 0xfc;      //11111100       //buffer fullness:0x7ff 低6bits// number_of_raw_data_blocks_in_frame：//    表示ADTS帧中有number_of_raw_data_blocks_in_frame + 1个AAC原始帧。return 0;
}// 程序本身 input.mp4  out.h264 out.aac
int main(int argc, char **argv)
{// 判断参数if(argc != 4) {printf("usage app input.mp4  out.h264 out.aac");return -1;}char *in_filename = argv[1];char *h264_filename = argv[2];char *aac_filename = argv[3];FILE *aac_fd = NULL;FILE *h264_fd = NULL;h264_fd = fopen(h264_filename, "wb");if(!h264_fd) {printf("fopen %s failed\n", h264_filename);return -1;}aac_fd = fopen(aac_filename, "wb");if(!aac_fd) {printf("fopen %s failed\n", aac_filename);return -1;}AVFormatContext *ifmt_ctx = NULL;int video_index = -1;int audio_index = -1;AVPacket *pkt = NULL;int ret = 0;char errors[ERROR_STRING_SIZE+1];  // 主要是用来缓存解析FFmpeg api返回值的错误stringifmt_ctx = avformat_alloc_context();if(!ifmt_ctx) {printf("avformat_alloc_context failed\n");//        fclose(aac_fd);return -1;}ret = avformat_open_input(&ifmt_ctx, in_filename, NULL, NULL);if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("avformat_open_input failed:%d\n", ret);printf("avformat_open_input failed:%s\n", errors);avformat_close_input(&ifmt_ctx);//        go failed;return -1;}video_index = av_find_best_stream(ifmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);if(video_index == -1) {printf("av_find_best_stream video_index failed\n");avformat_close_input(&ifmt_ctx);return -1;}audio_index = av_find_best_stream(ifmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);if(audio_index == -1) {printf("av_find_best_stream audio_index failed\n");avformat_close_input(&ifmt_ctx);return -1;}// h264_mp4toannexbconst AVBitStreamFilter *bsfilter = av_bsf_get_by_name("h264_mp4toannexb");      // 对应面向对象的方法if(!bsfilter) {avformat_close_input(&ifmt_ctx);printf("av_bsf_get_by_name h264_mp4toannexb failed\n");return -1;}AVBSFContext *bsf_ctx = NULL;        // 对应面向对象的变量ret = av_bsf_alloc(bsfilter, &bsf_ctx);if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_alloc failed:%s\n", errors);avformat_close_input(&ifmt_ctx);return -1;}ret = avcodec_parameters_copy(bsf_ctx->par_in, ifmt_ctx->streams[video_index]->codecpar);if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("avcodec_parameters_copy failed:%s\n", errors);avformat_close_input(&ifmt_ctx);av_bsf_free(&bsf_ctx);return -1;}ret = av_bsf_init(bsf_ctx);if(ret < 0) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_init failed:%s\n", errors);avformat_close_input(&ifmt_ctx);av_bsf_free(&bsf_ctx);return -1;}pkt = av_packet_alloc();av_init_packet(pkt);while (1) {ret = av_read_frame(ifmt_ctx, pkt);     // 不会去释放pkt的buf，如果我们外部不去释放，就会出现内存泄露if(ret < 0 ) {av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_read_frame failed:%s\n", errors);break;}// av_read_frame 成功读取到packet，则外部需要进行buf释放if(pkt->stream_index == video_index) {// 处理视频ret = av_bsf_send_packet(bsf_ctx, pkt); // 内部把我们传入的buf转移到自己bsf内部if(ret < 0) {       // 基本不会进入该逻辑av_strerror(ret, errors, ERROR_STRING_SIZE);printf("av_bsf_send_packet failed:%s\n", errors);av_packet_unref(pkt);continue;}
//            av_packet_unref(pkt); // 这里不需要去释放内存while (1) {ret = av_bsf_receive_packet(bsf_ctx, pkt);if(ret != 0) {break;}size_t size = fwrite(pkt->data, 1, pkt->size, h264_fd);if(size != pkt->size){av_log(NULL, AV_LOG_DEBUG, "h264 warning, length of writed data isn't equal pkt->size(%d, %d)\n",size,pkt->size);}av_packet_unref(pkt);}} else if(pkt->stream_index == audio_index) {// 处理音频char adts_header_buf[7] = {0};adts_header(adts_header_buf, pkt->size,ifmt_ctx->streams[audio_index]->codecpar->profile,ifmt_ctx->streams[audio_index]->codecpar->sample_rate,ifmt_ctx->streams[audio_index]->codecpar->channels);fwrite(adts_header_buf, 1, 7, aac_fd);  // 写adts header , ts流不适用，ts流分离出来的packet带了adts headersize_t size = fwrite( pkt->data, 1, pkt->size, aac_fd);   // 写adts dataif(size != pkt->size){av_log(NULL, AV_LOG_DEBUG, "aac warning, length of writed data isn't equal pkt->size(%d, %d)\n",size,pkt->size);}av_packet_unref(pkt);} else {av_packet_unref(pkt);       // 释放buffer}}printf("while finish\n");
failed:if(h264_fd) {fclose(h264_fd);}if(aac_fd) {fclose(aac_fd);}if(pkt)av_packet_free(&pkt);if(ifmt_ctx)avformat_close_input(&ifmt_ctx);printf("Hello World!\n");return 0;
}

更多资料：https://github.com/0voice