【FFmpeg 系列】多媒体文件处理（五）

1、FFmpeg 源码目录结构

目录	说明
libavcodec	提供了一系列编码器的实现
libavformat	实现在刘协议、容器格式及其本 IO 访问
libavutil	包括了 hash 器、解码器和各种工具函数
libavfilter	提供了各种音视频过滤器
libavdevice	提供了访问捕获设备和回放设备的接口
libswresample	实现了混音和重采样
libswscale	实现了色彩转换和缩放功能

2、FFmpeg 日志系统

• API：

// 头文件
include <libavutil/log.h>
// 设置 log 打印级别
av_log_set_level(AV_LOG_DEBUG)
// 打印输出 log 日志
av_log(NULL,AV_LOG_INFO,"...%s\n",op)

// 常用 log 日志级别如下
AV_LOG_ERROR、AV_LOG_WARNING、AV_LOG_INFO、AV_LOG_DEBUG

• 示例：

#include <stdio.h>
#include <libavutil/log.h>

int main(int argc, char *argv[]) {
    av_log_set_level(AV_LOG_DEBUG);
    av_log(NULL, AV_LOG_DEBUG, "Hello FFmpeg!=>%s\n", "debug信息");
    av_log(NULL, AV_LOG_INFO, "Hello FFmpeg!=>%s\n", "info信息");
    av_log(NULL, AV_LOG_WARNING, "Hello FFmpeg!=>%s\n", "warning信息");
    av_log(NULL, AV_LOG_ERROR, "Hello FFmpeg!=>%s\n", "error信息");

    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 1_ff_log 1_ff_log.c -I/usr/local/ffmpeg/include -L/usr/local/ffmpeg/lib -lavutil
或者
clang -g -o 1_ff_log 1_ff_log.c `pkg-config --cflags --libs libavutil`

-g: 输出有调试信息的运行文件
-o: 输出执行文  件
-L: 指定库的路径
-I: 指定头文件的路径

// 执行编译后的结果：
./1_ff_log

3、FFmpeg 文件的删除与重命名

• API：

// 文件的删除
avpriv_io_delete()
// 文件的重命名
avpriv_io_move()

• 示例：

#include <stdio.h>
#include <libavformat/avformat.h>

int main(int argc, char *argv[]) {
    int ret;
    // 文件的重命名
    ret = avpriv_io_move("./files/11.txt", "./files/22.txt");
    if (ret < 0) {
        av_log(NULL, AV_LOG_ERROR, "failed to rename\n");
        return -1;
    }
    av_log(NULL, AV_LOG_INFO, "success to rename\n");
    // 文件的删除
    ret = avpriv_io_delete("./files/mytestfile.txt");
    if (ret < 0) {
        av_log(NULL, AV_LOG_ERROR, "delete failed\n");
        return -1;
    }
    av_log(NULL, AV_LOG_INFO, "success to delete\n");
    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 2_ff_file 2_ff_file.c `pkg-config --cflags --libs libavformat`

// 执行编译后的结果：
./2_ff_file

4、FFmpeg 操作目录重要函数

• API：

// 打开目录
avio_open_dir()
// 读取目录中文件的每一项信息
avio_read_dir()
// 关闭目录
avio_close_dir()

// 操作目录的上下文
AVIODirContext
// 目录项。用于存放文件名、文件大小等信息
AVIODirEntry

• 示例：

#include <stdio.h>
#include <libavutil/avutil.h>
#include <libavformat/avformat.h>

int main(int argc, char *argv[]) {
    AVIODirContext *ctx = NULL;
    AVIODirEntry *entry = NULL;
    av_log_set_level(AV_LOG_DEBUG);

    int ret = avio_open_dir(&ctx, "./files", NULL);
    if (ret < 0) {
        av_log(NULL, AV_LOG_ERROR, "Cant open dir:%s\n", av_err2str(ret));
        goto __fail;
    }

    while (1) {
        ret = avio_read_dir(ctx, &entry);
        if (ret < 0) {
            av_log(NULL, AV_LOG_ERROR, "Cant red dir:&s\n", av_err2str(ret));
            // 跳转到__fail
            goto __fail;
        }
        // 如果entry是NULL代表是目录最末尾，则退出
        if (!entry) break;
        // 打印输出文件信息
        av_log(NULL, AV_LOG_INFO, "文件名:%s ,文件大小:%" PRId64"\n", entry->name, entry->size);
        // 释放entry
        avio_free_directory_entry(&entry);
    }

    __fail:
    avio_close_dir(&ctx);

    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 3_ff_dir 3_ff_dir.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./3_ff_dir

5、FFmpeg 多媒体文件基本概念

• 多媒体文件其实是一个容器
• 在容器里面有很多流（Stream/Track），每个流互不相交
• 每个流是由不同的编码器编码的
• 从流中读出的数据称为包
• 在一个包中包含着一个或者多个帧
• 几个重要的结构体

// 格式上下文
AVFotmatContext
// 流
AVStream
// 包
AVPacket

• FFmpeg 操作流数据的基本步骤：
  

6、FFmpeg 打印音/视频信息

• API：

// 将 FFmpeg 所定义的编解码库、格式库全都注册
av_register_arr()
// 打开多媒体文件
avfotmat_open_input()
// 关闭多媒体文件
avformat_close_input()
// 打印多媒体信息中的 mata 信息
av_dump_format()

• 示例：

#include <stdio.h>
#include <libavutil/log.h>
#include <libavformat/avformat.h>

int main(int argc, char *argv[]) {
    int ret;
    AVFormatContext *fmt_ctx = NULL;
    av_log_set_level(AV_LOG_INFO);

    av_register_all();

    ret = avformat_open_input(&fmt_ctx, "./files/sample.mp4", NULL, NULL);
    if (ret < 0) {
        av_log(NULL, AV_LOG_ERROR, "Can't open file: %s\n", av_err2str(ret));
        return -1;
    }

    av_dump_format(fmt_ctx, 0, "./files/sample.mp4", 0);

    avformat_close_input(&fmt_ctx);

    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 4_ff_meta 4_ff_meta.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./4_ff_meta

7、FFmpeg 抽取音频数据

• API：

// 初始化数据包结构体
av_init_packet()
// 在多媒体文件中找到最好的一路流
av_find_best_stream()
// 获取当前这路流中的数据包
av_read_frame()
// 是否包引用计数，释放资源，防止内存泄漏
av_packet_unref()

• 示例：

#include <stdio.h>
#include <libavutil/log.h>
#include <libavformat/avio.h>
#include <libavformat/avformat.h>

#define ADTS_HEADER_LEN  7;

static int get_audio_obj_type(int aactype) {
    // AAC HE V2 = AAC LC + SBR + PS
    // AAV HE = AAC LC + SBR
    // 所以无论是 AAC_HEv2 还是 AAC_HE 都是 AAC_LC
    switch (aactype) {
        case 0:
        case 2:
        case 3:
            return aactype + 1;
        case 1:
        case 4:
        case 28:
            return 2;
        default:
            return 2;
    }
}

static int get_sample_rate_index(int freq, int aactype) {
    int i = 0;
    int freq_arr[13] = {
            96000, 88200, 64000, 48000, 44100, 32000,
            24000, 22050, 16000, 12000, 11025, 8000, 7350
    };

    // 如果是 AAC HEv2 或 AAC HE, 则频率减半
    if (aactype == 28 || aactype == 4) {
        freq /= 2;
    }

    for (i = 0; i < 13; i++) {
        if (freq == freq_arr[i]) {
            return i;
        }
    }
    return 4;// 默认是44100
}

static int get_channel_config(int channels, int aactype) {
    //如果是 AAC HEv2 通道数减半
    if (aactype == 28) {
        return (channels / 2);
    }
    return channels;
}

static void adts_header(char *szAdtsHeader, int dataLen, int aactype, int frequency, int channels) {
    int audio_object_type = get_audio_obj_type(aactype);
    int sampling_frequency_index = get_sample_rate_index(frequency, aactype);
    int channel_config = get_channel_config(channels, aactype);

    printf("aot=%d, freq_index=%d, channel=%d\n", audio_object_type, sampling_frequency_index, channel_config);

    int adtsLen = dataLen + 7;

    szAdtsHeader[0] = 0xff;         //syncword:0xfff                          高8bits
    szAdtsHeader[1] = 0xf0;         //syncword:0xfff                          低4bits
    szAdtsHeader[1] |= (0 << 3);    //MPEG Version:0 for MPEG-4,1 for MPEG-2  1bit
    szAdtsHeader[1] |= (0 << 1);    //Layer:0                                 2bits
    szAdtsHeader[1] |= 1;           //protection absent:1                     1bit

    szAdtsHeader[2] =
            (audio_object_type - 1) << 6;            //profile:audio_object_type - 1                      2bits
    szAdtsHeader[2] |=
            (sampling_frequency_index & 0x0f) << 2; //sampling frequency index:sampling_frequency_index  4bits
    szAdtsHeader[2] |= (0 << 1);                             //private bit:0                                      1bit
    szAdtsHeader[2] |=
            (channel_config & 0x04) >> 2;           //channel configuration:channel_config               高1bit

    szAdtsHeader[3] = (channel_config & 0x03) << 6;     //channel configuration:channel_config      低2bits
    szAdtsHeader[3] |= (0 << 5);                      //original：0                               1bit
    szAdtsHeader[3] |= (0 << 4);                      //home：0                                   1bit
    szAdtsHeader[3] |= (0 << 3);                      //copyright id bit：0                       1bit
    szAdtsHeader[3] |= (0 << 2);                      //copyright id start：0                     1bit
    szAdtsHeader[3] |= ((adtsLen & 0x1800) >> 11);           //frame length：value   高2bits

    szAdtsHeader[4] = (uint8_t)((adtsLen & 0x7f8) >> 3);     //frame length:value    中间8bits
    szAdtsHeader[5] = (uint8_t)((adtsLen & 0x7) << 5);       //frame length:value    低3bits
    szAdtsHeader[5] |= 0x1f;                                 //buffer fullness:0x7ff 高5bits
    szAdtsHeader[6] = 0xfc;
}

int main(int argc, char *argv[]) {
    int err_code;
    char errors[1024];

    // char *src_filename = NULL;
    // char *dst_filename = NULL;
    const char *src_filename = "./files/sample.mp4";
    const char *dst_filename = "./files/sample.aac";

    FILE *dst_fd = NULL;

    int audio_stream_index = -1;
    int len;

    AVFormatContext *ofmt_ctx = NULL;
    AVOutputFormat *output_fmt = NULL;

    AVStream *out_stream = NULL;

    AVFormatContext *fmt_ctx = NULL;
    AVFrame *frame = NULL;
    AVPacket pkt;

    av_log_set_level(AV_LOG_DEBUG);

    // if(argc < 3){
    //     av_log(NULL, AV_LOG_DEBUG, "the count of parameters should be more than three!\n");
    //     return -1;
    // }

    // src_filename = argv[1];
    // dst_filename = argv[2];

    if (src_filename == NULL || dst_filename == NULL) {
        av_log(NULL, AV_LOG_DEBUG, "src or dts file is null, plz check them!\n");
        return -1;
    }
    // 创建一个新的二进制文件（输出文件），"wb"代表可写
    dst_fd = fopen(dst_filename, "wb");
    if (!dst_fd) {
        av_log(NULL, AV_LOG_DEBUG, "Could not open destination file %s\n", dst_filename);
        return -1;
    }

    // 打开输入媒体文件，并分配格式上下文
    if ((err_code = avformat_open_input(&fmt_ctx, src_filename, NULL, NULL)) < 0) {
        av_strerror(err_code, errors, 1024);
        av_log(NULL, AV_LOG_DEBUG, "Could not open source file: %s, %d(%s)\n",
               src_filename,
               err_code,
               errors);
        return -1;
    }

    // 检索音频流
    if ((err_code = avformat_find_stream_info(fmt_ctx, NULL)) < 0) {
        av_strerror(err_code, errors, 1024);
        av_log(NULL, AV_LOG_DEBUG, "failed to find stream information: %s, %d(%s)\n",
               src_filename,
               err_code,
               errors);
        return -1;
    }

    // 转储输入信息
    av_dump_format(fmt_ctx, 0, src_filename, 0);

    frame = av_frame_alloc();
    if (!frame) {
        av_log(NULL, AV_LOG_DEBUG, "Could not allocate frame\n");
        return AVERROR(ENOMEM);
    }

    // 初始化数据包
    av_init_packet(&pkt);
    pkt.data = NULL;
    pkt.size = 0;

    // 寻找最佳音频流
    audio_stream_index = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
    if (audio_stream_index < 0) {
        av_log(NULL, AV_LOG_DEBUG, "Could not find %s stream in input file %s\n",
               av_get_media_type_string(AVMEDIA_TYPE_AUDIO),
               src_filename);
        return AVERROR(EINVAL);
    }

    /*
     #define FF_PROFILE_AAC_MAIN 0
     #define FF_PROFILE_AAC_LOW  1
     #define FF_PROFILE_AAC_SSR  2
     #define FF_PROFILE_AAC_LTP  3
     #define FF_PROFILE_AAC_HE   4
     #define FF_PROFILE_AAC_HE_V2 28
     #define FF_PROFILE_AAC_LD   22
     #define FF_PROFILE_AAC_ELD  38
     #define FF_PROFILE_MPEG2_AAC_LOW 128
     #define FF_PROFILE_MPEG2_AAC_HE  131
    */
    int aac_type = fmt_ctx->streams[1]->codecpar->profile;
    int channels = fmt_ctx->streams[1]->codecpar->channels;
    int sample_rate = fmt_ctx->streams[1]->codecpar->sample_rate;

    if (fmt_ctx->streams[1]->codecpar->codec_id != AV_CODEC_ID_AAC) {
        av_log(NULL, AV_LOG_ERROR, "the audio type is not AAC!\n");
        goto __ERROR;
    } else {
        av_log(NULL, AV_LOG_INFO, "the audio type is AAC!\n");
    }

    // 从媒体文件中读取帧信息
    while (av_read_frame(fmt_ctx, &pkt) >= 0) {
        if (pkt.stream_index == audio_stream_index) {
            char adts_header_buf[7];
            adts_header(adts_header_buf, pkt.size, aac_type, sample_rate, channels);
            fwrite(adts_header_buf, 1, 7, dst_fd);

            len = fwrite(pkt.data, 1, pkt.size, dst_fd);
            if (len != pkt.size) {
                av_log(NULL, AV_LOG_DEBUG, "warning, length of writed data isn't equal pkt.size(%d, %d)\n", len,
                       pkt.size);
            }
        }
        av_packet_unref(&pkt);
    }

    __ERROR:
    // 关闭输入媒体文件
    avformat_close_input(&fmt_ctx);
    if (dst_fd) {
        fclose(dst_fd);
    }
    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 5_extra_audio 5_ff_extra_audio.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./5_extra_audio

8、FFmpeg 抽取视频 H264 数据

• API：

// 简单来说就是用来区分视频一帧与另外一帧的（每帧前加帧长度、每帧前面加特征码等手段）
Start code
// 里面包含了解码的视频帧参数，例如：视频帧的宽高、帧率等等参数
SPS/PPS
// 获取 SPS/PPS
codec->extradata

• 示例：

#include <stdio.h>
#include <libavutil/log.h>
#include <libavformat/avio.h>
#include <libavformat/avformat.h>

#ifndef AV_WB32
#   define AV_WB32(p, val) do {                 \
        uint32_t d = (val);                     \
        ((uint8_t*)(p))[3] = (d);               \
        ((uint8_t*)(p))[2] = (d)>>8;            \
        ((uint8_t*)(p))[1] = (d)>>16;           \
        ((uint8_t*)(p))[0] = (d)>>24;           \
    } while(0)
#endif

#ifndef AV_RB16
#   define AV_RB16(x)                           \
    ((((const uint8_t*)(x))[0] << 8) |          \
      ((const uint8_t*)(x))[1])
#endif

static int alloc_and_copy(AVPacket *out,
                          const uint8_t *sps_pps, uint32_t sps_pps_size,
                          const uint8_t *in, uint32_t in_size) {
    uint32_t offset = out->size;
    uint8_t nal_header_size = 4;
    int err;

    err = av_grow_packet(out, sps_pps_size + in_size + nal_header_size);
    if (err < 0)
        return err;

    if (sps_pps)
        memcpy(out->data + offset, sps_pps, sps_pps_size);
    memcpy(out->data + sps_pps_size + nal_header_size + offset, in, in_size);
    if (!offset) {
        AV_WB32(out->data + sps_pps_size, 1);
    } else {
        (out->data + offset + sps_pps_size)[0] =
        (out->data + offset + sps_pps_size)[1] = 0;
        (out->data + offset + sps_pps_size)[2] = 1;
    }

    return 0;
}

int h264_extradata_to_annexb(const uint8_t *codec_extradata, const int codec_extradata_size, AVPacket *out_extradata,
                             int padding) {
    uint16_t unit_size = 0;
    uint64_t total_size = 0;
    uint8_t *out = NULL;
    uint8_t unit_nb = 0;
    uint8_t sps_done = 0;
    uint8_t sps_seen = 0;
    uint8_t pps_seen = 0;
    uint8_t sps_offset = 0;
    uint8_t pps_offset = 0;

    /**
     * AVCC
     * bits
     *  8   version ( always 0x01 )
     *  8   avc profile ( sps[0][1] )
     *  8   avc compatibility ( sps[0][2] )
     *  8   avc level ( sps[0][3] )
     *  6   reserved ( all bits on )
     *  2   NALULengthSizeMinusOne    // 这个值是（前缀长度-1），值如果是3，那前缀就是4，因为4-1=3
     *  3   reserved ( all bits on )
     *  5   number of SPS NALUs (usually 1)
     *
     *  repeated once per SPS:
     *  16     SPS size
     *
     *  variable   SPS NALU data
     *  8   number of PPS NALUs (usually 1)
     *  repeated once per PPS
     *  16    PPS size
     *  variable PPS NALU data
     */

    const uint8_t *extradata = codec_extradata + 4; //extradata存放数据的格式如上，前4个字节没用，所以将其舍弃
    static const uint8_t nalu_header[4] = {0, 0, 0, 1}; //每个H264裸数据都是以 0001 4个字节为开头的

    extradata++;//跳过一个字节，这个也没用

    sps_offset = pps_offset = -1;

    /* retrieve sps and pps unit(s) */
    unit_nb = *extradata++ & 0x1f; /* 取 SPS 个数，理论上可以有多个, 但我没有见到过多 SPS 的情况*/
    if (!unit_nb) {
        goto pps;
    } else {
        sps_offset = 0;
        sps_seen = 1;
    }

    while (unit_nb--) {
        int err;

        unit_size = AV_RB16(extradata);
        total_size += unit_size + 4; //加上4字节的h264 header, 即 0001
        if (total_size > INT_MAX - padding) {
            av_log(NULL, AV_LOG_ERROR,
                   "Too big extradata size, corrupted stream or invalid MP4/AVCC bitstream\n");
            av_free(out);
            return AVERROR(EINVAL);
        }

        //2:表示上面 unit_size 的所占字结数
        //这句的意思是 extradata 所指的地址，加两个字节，再加 unit 的大小所指向的地址
        //是否超过了能访问的有效地址空间
        if (extradata + 2 + unit_size > codec_extradata + codec_extradata_size) {
            av_log(NULL, AV_LOG_ERROR, "Packet header is not contained in global extradata, "
                                       "corrupted stream or invalid MP4/AVCC bitstream\n");
            av_free(out);
            return AVERROR(EINVAL);
        }

        //分配存放 SPS 的空间
        if ((err = av_reallocp(&out, total_size + padding)) < 0)
            return err;

        memcpy(out + total_size - unit_size - 4, nalu_header, 4);
        memcpy(out + total_size - unit_size, extradata + 2, unit_size);
        extradata += 2 + unit_size;
        pps:
        //当 SPS 处理完后，开始处理 PPS
        if (!unit_nb && !sps_done++) {
            unit_nb = *extradata++; /* number of pps unit(s) */
            if (unit_nb) {
                pps_offset = total_size;
                pps_seen = 1;
            }
        }
    }

    //余下的空间清0
    if (out) {
        memset(out + total_size, 0, padding);
    }

    if (!sps_seen)
        av_log(NULL, AV_LOG_WARNING,
               "Warning: SPS NALU missing or invalid. "
               "The resulting stream may not play.\n");

    if (!pps_seen)
        av_log(NULL, AV_LOG_WARNING,
               "Warning: PPS NALU missing or invalid. "
               "The resulting stream may not play.\n");

    out_extradata->data = out;
    out_extradata->size = total_size;

    return 0;
}

int h264_mp4toannexb(AVFormatContext *fmt_ctx, AVPacket *in, FILE *dst_fd) {

    AVPacket *out = NULL;
    AVPacket spspps_pkt;

    int len;
    uint8_t unit_type;
    int32_t nal_size;
    uint32_t cumul_size = 0;
    const uint8_t *buf;
    const uint8_t *buf_end;
    int buf_size;
    int ret = 0, i;

    out = av_packet_alloc();

    buf = in->data;
    buf_size = in->size;
    buf_end = in->data + in->size;

    do {
        ret = AVERROR(EINVAL);
        //因为每个视频帧的前 4 个字节是视频帧的长度
        //如果buf中的数据都不能满足4字节，所以后面就没有必要再进行处理了
        if (buf + 4 > buf_end)
            goto fail;

        //将前四字节转换成整型,也就是取出视频帧长度
        for (nal_size = 0, i = 0; i < 4; i++)
            nal_size = (nal_size << 8) | buf[i];

        buf += 4; //跳过4字节（也就是视频帧长度），从而指向真正的视频帧数据
        unit_type = *buf & 0x1f; //视频帧的第一个字节里有NAL TYPE

        //如果视频帧长度大于从 AVPacket 中读到的数据大小，说明这个数据包肯定是出错了
        if (nal_size > buf_end - buf || nal_size < 0)
            goto fail;

        /* prepend only to the first type 5 NAL unit of an IDR picture, if no sps/pps are already present */
        if (unit_type == 5) {

            //在每个I帧之前都加 SPS/PPS
            h264_extradata_to_annexb(fmt_ctx->streams[in->stream_index]->codecpar->extradata,
                                     fmt_ctx->streams[in->stream_index]->codecpar->extradata_size,
                                     &spspps_pkt,
                                     AV_INPUT_BUFFER_PADDING_SIZE);

            if ((ret = alloc_and_copy(out,
                                      spspps_pkt.data, spspps_pkt.size,
                                      buf, nal_size)) < 0)
                goto fail;
        } else {
            if ((ret = alloc_and_copy(out, NULL, 0, buf, nal_size)) < 0)
                goto fail;
        }


        len = fwrite(out->data, 1, out->size, dst_fd);
        if (len != out->size) {
            av_log(NULL, AV_LOG_DEBUG, "warning, length of writed data isn't equal pkt.size(%d, %d)\n",
                   len,
                   out->size);
        }
        fflush(dst_fd);

        next_nal:
        buf += nal_size;
        cumul_size += nal_size + 4;//s->length_size;
    } while (cumul_size < buf_size);

    fail:
    av_packet_free(&out);

    return ret;
}

int main(int argc, char *argv[]) {
    int err_code;
    char errors[1024];

    // char *src_filename = NULL;
    // char *dst_filename = NULL;
    const char *src_filename = "./files/sample.mp4";
    const char *dst_filename = "./files/sample.h264";

    FILE *dst_fd = NULL;

    int video_stream_index = -1;

    AVFormatContext *fmt_ctx = NULL;
    AVPacket pkt;

    av_log_set_level(AV_LOG_DEBUG);

    // if (argc < 3) {
    //     av_log(NULL, AV_LOG_DEBUG, "the count of parameters should be more than three!\n");
    //     return -1;
    // }
    //
    // src_filename = argv[1];
    // dst_filename = argv[2];

    if (src_filename == NULL || dst_filename == NULL) {
        av_log(NULL, AV_LOG_ERROR, "src or dts file is null, plz check them!\n");
        return -1;
    }

    dst_fd = fopen(dst_filename, "wb");
    if (!dst_fd) {
        av_log(NULL, AV_LOG_DEBUG, "Could not open destination file %s\n", dst_filename);
        return -1;
    }

    // 打开输入媒体文件，并分配格式上下文
    if ((err_code = avformat_open_input(&fmt_ctx, src_filename, NULL, NULL)) < 0) {
        av_strerror(err_code, errors, 1024);
        av_log(NULL, AV_LOG_DEBUG, "Could not open source file: %s, %d(%s)\n",
               src_filename,
               err_code,
               errors);
        return -1;
    }

    // 转储输入信息
    av_dump_format(fmt_ctx, 0, src_filename, 0);

    // 初始化数据包
    av_init_packet(&pkt);
    pkt.data = NULL;
    pkt.size = 0;

    // 寻找最佳视频流
    video_stream_index = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
    if (video_stream_index < 0) {
        av_log(NULL, AV_LOG_DEBUG, "Could not find %s stream in input file %s\n",
               av_get_media_type_string(AVMEDIA_TYPE_VIDEO),
               src_filename);
        return AVERROR(EINVAL);
    }

    // 从媒体文件中读取帧
    while (av_read_frame(fmt_ctx, &pkt) >= 0) {
        if (pkt.stream_index == video_stream_index) {
            h264_mp4toannexb(fmt_ctx, &pkt, dst_fd);
        }
        // 释放 pkt->data
        av_packet_unref(&pkt);
    }

    // 关闭输入媒体文件
    avformat_close_input(&fmt_ctx);
    if (dst_fd) {
        fclose(dst_fd);
    }
    return 0;
}

• 编译与运行：

// 命令编译：
clang -g -o 6_extra_video 6_extra_video.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./6_extra_video

9、FFmpeg 将 MP4 转换为 FLV 格式

• API：

// 分配一个输出上下文
avfotmat_alloc_output_context2()
// 释放输出上下文，防止内存泄漏
avfotmat_free_context()
// 创建一个新的流媒体
avfotmat_new_stream()
// 拷贝流媒体相关参数
avcodec_parameters_copy()
// 写入多媒体文件头信息
avformat_write_header()
// 写入多媒体帧数据
av_write_frame()
// 交叉写入多媒体帧数据
av_interleaved_write_frame()
// 写入多媒体文件尾部信息
av_write_trailer()

• 示例：

#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>

static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt, const char *tag) {
    AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;

    printf("%s: pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
           tag,
           av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
           av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
           av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
           pkt->stream_index);
}

int main(int argc, char **argv) {
    AVOutputFormat *ofmt = NULL;
    AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
    AVPacket pkt;
    const char *in_filename, *out_filename;
    int ret, i;
    int stream_index = 0;
    int *stream_mapping = NULL;
    int stream_mapping_size = 0;

    if (argc < 3) {
        printf("usage: %s input output\n"
               "API example program to remux a media file with libavformat and libavcodec.\n"
               "The output format is guessed according to the file extension.\n"
               "\n", argv[0]);
        return 1;
    }

    in_filename = argv[1];
    out_filename = argv[2];


    if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0) {
        fprintf(stderr, "Could not open input file '%s'", in_filename);
        goto end;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) {
        fprintf(stderr, "Failed to retrieve input stream information");
        goto end;
    }

    av_dump_format(ifmt_ctx, 0, in_filename, 0);

    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
    if (!ofmt_ctx) {
        fprintf(stderr, "Could not create output context\n");
        ret = AVERROR_UNKNOWN;
        goto end;
    }

    stream_mapping_size = ifmt_ctx->nb_streams;
    stream_mapping = av_mallocz_array(stream_mapping_size, sizeof(*stream_mapping));
    if (!stream_mapping) {
        ret = AVERROR(ENOMEM);
        goto end;
    }

    ofmt = ofmt_ctx->oformat;

    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        AVStream *out_stream;
        AVStream *in_stream = ifmt_ctx->streams[i];
        AVCodecParameters *in_codecpar = in_stream->codecpar;

        if (in_codecpar->codec_type != AVMEDIA_TYPE_AUDIO &&
            in_codecpar->codec_type != AVMEDIA_TYPE_VIDEO &&
            in_codecpar->codec_type != AVMEDIA_TYPE_SUBTITLE) {
            stream_mapping[i] = -1;
            continue;
        }

        stream_mapping[i] = stream_index++;

        out_stream = avformat_new_stream(ofmt_ctx, NULL);
        if (!out_stream) {
            fprintf(stderr, "Failed allocating output stream\n");
            ret = AVERROR_UNKNOWN;
            goto end;
        }

        ret = avcodec_parameters_copy(out_stream->codecpar, in_codecpar);
        if (ret < 0) {
            fprintf(stderr, "Failed to copy codec parameters\n");
            goto end;
        }
        out_stream->codecpar->codec_tag = 0;
    }
    av_dump_format(ofmt_ctx, 0, out_filename, 1);

    if (!(ofmt->flags & AVFMT_NOFILE)) {
        ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
        if (ret < 0) {
            fprintf(stderr, "Could not open output file '%s'", out_filename);
            goto end;
        }
    }

    ret = avformat_write_header(ofmt_ctx, NULL);
    if (ret < 0) {
        fprintf(stderr, "Error occurred when opening output file\n");
        goto end;
    }

    while (1) {
        AVStream *in_stream, *out_stream;

        ret = av_read_frame(ifmt_ctx, &pkt);
        if (ret < 0)
            break;

        in_stream = ifmt_ctx->streams[pkt.stream_index];
        if (pkt.stream_index >= stream_mapping_size ||
            stream_mapping[pkt.stream_index] < 0) {
            av_packet_unref(&pkt);
            continue;
        }

        pkt.stream_index = stream_mapping[pkt.stream_index];
        out_stream = ofmt_ctx->streams[pkt.stream_index];
        log_packet(ifmt_ctx, &pkt, "in");

        /* copy packet */
        pkt.pts = av_rescale_q_rnd(pkt.pts, in_stream->time_base, out_stream->time_base,
                                   AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
        pkt.dts = av_rescale_q_rnd(pkt.dts, in_stream->time_base, out_stream->time_base,
                                   AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
        pkt.duration = av_rescale_q(pkt.duration, in_stream->time_base, out_stream->time_base);
        pkt.pos = -1;
        log_packet(ofmt_ctx, &pkt, "out");

        ret = av_interleaved_write_frame(ofmt_ctx, &pkt);
        if (ret < 0) {
            fprintf(stderr, "Error muxing packet\n");
            break;
        }
        av_packet_unref(&pkt);
    }

    av_write_trailer(ofmt_ctx);
    end:

    avformat_close_input(&ifmt_ctx);

    /* close output */
    if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
        avio_closep(&ofmt_ctx->pb);
    avformat_free_context(ofmt_ctx);

    av_freep(&stream_mapping);

    if (ret < 0 && ret != AVERROR_EOF) {
        fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
        return 1;
    }

    return 0;
}

• 编译与运行：

clang -g -o 7_ff_mp4_muxing_flv 7_ff_mp4_muxing_flv.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./7_ff_mp4_muxing_flv ./files/sample.mp4 ./files/sample.flv

10、FFmpeg 从 MP4 截取一段视频

• API：

// 跳一段时间做 seek 操作
av_seek_frame()

• 示例：

#include <stdlib.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>

static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt, const char *tag) {
    AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;

    printf("%s: pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
           tag,
           av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
           av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
           av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
           pkt->stream_index);
}

int cut_video(double from_seconds, double end_seconds, const char *in_filename, const char *out_filename) {
    AVOutputFormat *ofmt = NULL;
    AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
    AVPacket pkt;
    int ret, i;

    //av_register_all();

    if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0) {
        fprintf(stderr, "Could not open input file '%s'", in_filename);
        goto end;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) {
        fprintf(stderr, "Failed to retrieve input stream information");
        goto end;
    }

    av_dump_format(ifmt_ctx, 0, in_filename, 0);

    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
    if (!ofmt_ctx) {
        fprintf(stderr, "Could not create output context\n");
        ret = AVERROR_UNKNOWN;
        goto end;
    }

    ofmt = ofmt_ctx->oformat;

    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        AVStream *in_stream = ifmt_ctx->streams[i];
        AVStream *out_stream = avformat_new_stream(ofmt_ctx, NULL);
        if (!out_stream) {
            fprintf(stderr, "Failed allocating output stream\n");
            ret = AVERROR_UNKNOWN;
            goto end;
        }

        ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
        if (ret < 0) {
            fprintf(stderr, "Failed to copy context from input to output stream codec context\n");
            goto end;
        }
        out_stream->codecpar->codec_tag = 0;
    }
    av_dump_format(ofmt_ctx, 0, out_filename, 1);

    if (!(ofmt->flags & AVFMT_NOFILE)) {
        ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
        if (ret < 0) {
            fprintf(stderr, "Could not open output file '%s'", out_filename);
            goto end;
        }
    }

    ret = avformat_write_header(ofmt_ctx, NULL);
    if (ret < 0) {
        fprintf(stderr, "Error occurred when opening output file\n");
        goto end;
    }

    ret = av_seek_frame(ifmt_ctx, -1, from_seconds * AV_TIME_BASE, AVSEEK_FLAG_ANY);
    if (ret < 0) {
        fprintf(stderr, "Error seek\n");
        goto end;
    }

    int64_t *dts_start_from = malloc(sizeof(int64_t) * ifmt_ctx->nb_streams);
    memset(dts_start_from, 0, sizeof(int64_t) * ifmt_ctx->nb_streams);
    int64_t *pts_start_from = malloc(sizeof(int64_t) * ifmt_ctx->nb_streams);
    memset(pts_start_from, 0, sizeof(int64_t) * ifmt_ctx->nb_streams);

    while (1) {
        AVStream *in_stream, *out_stream;

        ret = av_read_frame(ifmt_ctx, &pkt);
        if (ret < 0)
            break;

        in_stream = ifmt_ctx->streams[pkt.stream_index];
        out_stream = ofmt_ctx->streams[pkt.stream_index];

        log_packet(ifmt_ctx, &pkt, "in");

        if (av_q2d(in_stream->time_base) * pkt.pts > end_seconds) {
            av_packet_unref(&pkt);
            break;
        }

        if (dts_start_from[pkt.stream_index] == 0) {
            dts_start_from[pkt.stream_index] = pkt.dts;
            printf("dts_start_from: %s\n", av_ts2str(dts_start_from[pkt.stream_index]));
        }
        if (pts_start_from[pkt.stream_index] == 0) {
            pts_start_from[pkt.stream_index] = pkt.pts;
            printf("pts_start_from: %s\n", av_ts2str(pts_start_from[pkt.stream_index]));
        }

        /* copy packet */
        pkt.pts = av_rescale_q_rnd(pkt.pts - pts_start_from[pkt.stream_index], in_stream->time_base,
                                   out_stream->time_base, AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
        pkt.dts = av_rescale_q_rnd(pkt.dts - dts_start_from[pkt.stream_index], in_stream->time_base,
                                   out_stream->time_base, AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX);
        if (pkt.pts < 0) {
            pkt.pts = 0;
        }
        if (pkt.dts < 0) {
            pkt.dts = 0;
        }
        pkt.duration = (int) av_rescale_q((int64_t) pkt.duration, in_stream->time_base, out_stream->time_base);
        pkt.pos = -1;
        log_packet(ofmt_ctx, &pkt, "out");
        printf("\n");

        ret = av_interleaved_write_frame(ofmt_ctx, &pkt);
        if (ret < 0) {
            fprintf(stderr, "Error muxing packet\n");
            break;
        }
        av_packet_unref(&pkt);
    }
    free(dts_start_from);
    free(pts_start_from);

    av_write_trailer(ofmt_ctx);
    end:

    avformat_close_input(&ifmt_ctx);

    /* close output */
    if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
        avio_closep(&ofmt_ctx->pb);
    avformat_free_context(ofmt_ctx);

    if (ret < 0 && ret != AVERROR_EOF) {
        fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
        return 1;
    }

    return 0;
}

int main(int argc, char *argv[]) {
    if (argc < 5) {
        fprintf(stderr, "Usage: command startime, endtime, srcfile, outfile");
        return -1;
    }

    double startime = atoi(argv[1]);
    double endtime = atoi(argv[2]);
    cut_video(startime, endtime, argv[3], argv[4]);

    return 0;
}

• 编译与运行：

clang -g -o 8_ff_cut_video 8_ff_cut_video.c `pkg-config --cflags --libs libavutil libavformat`

// 执行编译后的结果：
./8_ff_cut_video 0 5 ./files/sample.mp4 ./files/sample2.mp4

11、实现一个简单的抖音业务功能

• 业务要求：

（1）将两个媒体文件中分别抽取音频与视频轨；
（2）将音频与视频合成一个新的文件；
（3）对音频与视频轨进行裁剪。

• 示例：

// 待完善