利用ffmpeg提供的库（API）进行音频与视频的编码并生成文件

• Output_example.c是ffmpeg项目中很典型的一个例程，演示了如何利用ffmpeg提供的库（API）进行音频与视频的编码并生成文件。

• Output_example.c的主要功能是根据给定的文件名（通过命令行参数给定）生成一段对应的多媒体文件，文件的格式与给定的文件名相关。这里有一点需要特别的说明，就是音频与视频数据的来源问题，因为在里面经常会有初学者问及。在生成的多媒体文件中包括音频与视频，其中音频是通过"get_audio_frame"方法根据一个简单的算法产生的音频数据，视频则是通过"fill_yuv_image"方法根据一个简单的算法产生的视频数据。

• Output_example.c向AVFormatContext结构体中添加流等相应的信息，接着使用库的函数保存相应的内容，如何保存都设置在这个结构体中，这个结构本就是一个中介它在每一个函数的参数中可以体现这一点。

/*

* Libavformat API example: Output a media file in any supported
* libavformat format. The default codecs are used.
*
* Copyright (c) 2003 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include 
#include 
#include 
#include 

#ifndef M_PI
#define M_PI 3.14159265358979323846
#endif

#include "avformat.h"
#include "swscale.h"

/* 5 seconds stream duration */
#define STREAM_DURATION   5.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES  ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT PIX_FMT_YUV420P /* default pix_fmt */

static int sws_flags = SWS_BICUBIC;

[] 音频输出

/**************************************************************/ /* audio output */

float t, tincr, tincr2; int16_t *samples; uint8_t *audio_outbuf; int audio_outbuf_size; int audio_input_frame_size;

[] add_audio_stream

//add an audio output stream static AVStream * add_audio_stream(AVFormatContext *oc, int codec_id) {

   AVCodecContext *c;
   AVStream *st;

   st = av_new_stream(oc, 1);
   if (!st) {
       fprintf(stderr, "Could not alloc stream\n");
       exit(1);
   }

   c = st->codec;
   c->codec_id = codec_id;
   c->codec_type = CODEC_TYPE_AUDIO;

   /* put sample parameters */
   c->bit_rate = 64000;
   c->sample_rate = 44100;
   c->channels = 2;
   return st;

}

[] open_audio

static void open_audio(AVFormatContext *oc, AVStream *st) {

   AVCodecContext *c;
   AVCodec *codec;

   c = st->codec;

   /* find the audio encoder */
   codec = avcodec_find_encoder(c->codec_id);
   if (!codec) {
       fprintf(stderr, "codec not found\n");
       exit(1);
   }

   /* open it */
   if (avcodec_open(c, codec) < 0) {
       fprintf(stderr, "could not open codec\n");
       exit(1);
   }

   /* init signal generator */
   t = 0;
   tincr = 2 * M_PI * 110.0 / c->sample_rate;
   /* increment frequency by 110 Hz per second */
   tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;

   audio_outbuf_size = 10000;
   audio_outbuf = av_malloc(audio_outbuf_size);

   /* ugly hack for PCM codecs (will be removed ASAP with new PCM
      support to compute the input frame size in samples */
   if (c->frame_size <= 1) {
       audio_input_frame_size = audio_outbuf_size / c->channels;
       switch(st->codec->codec_id) {
       case CODEC_ID_PCM_S16LE:
       case CODEC_ID_PCM_S16BE:
       case CODEC_ID_PCM_U16LE:
       case CODEC_ID_PCM_U16BE:
           audio_input_frame_size >>= 1;
           break;
       default:
           break;
       }
   } else {
       audio_input_frame_size = c->frame_size;
   }
   samples = av_malloc(audio_input_frame_size * 2 * c->channels);

}

[] get_audio_frame

/* prepare a 16 bit dummy audio frame of 'frame_size' samples and

  'nb_channels' channels */

static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels) {

   int j, i, v;
   int16_t *q;

   q = samples;
   for(j=0;j
} 
[] write_audio_frame 
static void write_audio_frame(AVFormatContext *oc, AVStream *st) { 
   AVCodecContext *c;
   AVPacket pkt;
   av_init_packet(&pkt);

   c = st->codec;

   get_audio_frame(samples, audio_input_frame_size, c->channels);

   pkt.size= avcodec_encode_audio(c, audio_outbuf, audio_outbuf_size, samples);

   pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
   pkt.flags |= PKT_FLAG_KEY;
   pkt.stream_index= st->index;
   pkt.data= audio_outbuf;

   /* write the compressed frame in the media file */
   if (av_write_frame(oc, &pkt) != 0) {
       fprintf(stderr, "Error while writing audio frame\n");
       exit(1);
   }

} 
[] close_audio 
static void close_audio(AVFormatContext *oc, AVStream *st) { 
   avcodec_close(st->codec);

   av_free(samples);
   av_free(audio_outbuf);

} 


[] 视频输出 
/**************************************************************/ /* video output */ 
AVFrame *picture, *tmp_picture; uint8_t *video_outbuf; int frame_count, video_outbuf_size; 
[] add_video_stream 
/* add a video output stream */ static AVStream *add_video_stream(AVFormatContext *oc, int codec_id) { 
   AVCodecContext *c;
   AVStream *st;

   st = av_new_stream(oc, 0);
   if (!st) {
       fprintf(stderr, "Could not alloc stream\n");
       exit(1);
   }

   c = st->codec;
   c->codec_id = codec_id;
   c->codec_type = CODEC_TYPE_VIDEO;
   /* put sample parameters */
   c->bit_rate = 400000;
   /* resolution must be a multiple of two */
   c->width = 352;
   c->height = 288;
   /* time base: this is the fundamental unit of time (in seconds) in terms
      of which frame timestamps are represented. for fixed-fps content,
      timebase should be 1/framerate and timestamp increments should be
      identically 1. */
   c->time_base.den = STREAM_FRAME_RATE;
   c->time_base.num = 1;
   c->gop_size = 12; /* emit one intra frame every twelve frames at most */
   c->pix_fmt = STREAM_PIX_FMT;
   if (c->codec_id == CODEC_ID_MPEG2VIDEO) {
       /* just for testing, we also add B frames */
       c->max_b_frames = 2;
   }
   if (c->codec_id == CODEC_ID_MPEG1VIDEO){
       /* needed to avoid using macroblocks in which some coeffs overflow
          this doesnt happen with normal video, it just happens here as the
          motion of the chroma plane doesnt match the luma plane */
       c->mb_decision=2;
   }
   // some formats want stream headers to be separate
   if(!strcmp(oc->oformat->name, "mp4") || !strcmp(oc->oformat->name, "mov") || !strcmp(oc->oformat->name, "3gp"))
       c->flags |= CODEC_FLAG_GLOBAL_HEADER;

   return st;

} 
[] alloc_picture 
static AVFrame *alloc_picture(int pix_fmt, int width, int height) { 
   AVFrame *picture;
   uint8_t *picture_buf;
   int size;

   picture = avcodec_alloc_frame();
   if (!picture)
       return NULL;
   size = avpicture_get_size(pix_fmt, width, height);
   picture_buf = av_malloc(size);
   if (!picture_buf) {
       av_free(picture);
       return NULL;
   }
   avpicture_fill((AVPicture *)picture, picture_buf,
                  pix_fmt, width, height);
   return picture;

} 
[] open_video 
static void open_video(AVFormatContext *oc, AVStream *st) { 
   AVCodec *codec;
   AVCodecContext *c;

   c = st->codec;

   /* find the video encoder */
   codec = avcodec_find_encoder(c->codec_id);
   if (!codec) {
       fprintf(stderr, "codec not found\n");
       exit(1);
   }

   /* open the codec */
   if (avcodec_open(c, codec) < 0) {
       fprintf(stderr, "could not open codec\n");
       exit(1);
   }

   video_outbuf = NULL;
   if (!(oc->oformat->flags & AVFMT_RAWPICTURE)) {
       /* allocate output buffer */
       /* XXX: API change will be done */
       /* buffers passed into lav* can be allocated any way you prefer,
          as long as they're aligned enough for the architecture, and
          they're freed appropriately (such as using av_free for buffers
          allocated with av_malloc) */
       video_outbuf_size = 200000;
       video_outbuf = av_malloc(video_outbuf_size);
   }

   /* allocate the encoded raw picture */
   picture = alloc_picture(c->pix_fmt, c->width, c->height);
   if (!picture) {
       fprintf(stderr, "Could not allocate picture\n");
       exit(1);
   }

   /* if the output format is not YUV420P, then a temporary YUV420P
      picture is needed too. It is then converted to the required
      output format */
   tmp_picture = NULL;
   if (c->pix_fmt != PIX_FMT_YUV420P) {
       tmp_picture = alloc_picture(PIX_FMT_YUV420P, c->width, c->height);
       if (!tmp_picture) {
           fprintf(stderr, "Could not allocate temporary picture\n");
           exit(1);
       }
   }

} 

[编辑] fill_yuv_image 
/* prepare a dummy image */ static void fill_yuv_image(AVFrame *pict, int frame_index, int width, int height) { 
   int x, y, i;

   i = frame_index;

   /* Y */
   for(y=0;ydata[0][y * pict->linesize[0] + x] = x + y + i * 3;
       }
   }

   /* Cb and Cr */
   for(y=0;ydata[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
           pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
       }
   }

} 
[] write_video_frame 
static void write_video_frame(AVFormatContext *oc, AVStream *st) { 
   int out_size, ret;
   AVCodecContext *c;
   static struct SwsContext *img_convert_ctx;

   c = st->codec;

   if (frame_count >= STREAM_NB_FRAMES) {
       /* no more frame to compress. The codec has a latency of a few
          frames if using B frames, so we get the last frames by
          passing the same picture again */
   } else {
       if (c->pix_fmt != PIX_FMT_YUV420P) {
           /* as we only generate a YUV420P picture, we must convert it
              to the codec pixel format if needed */
           if (img_convert_ctx == NULL) {
               img_convert_ctx = sws_getContext(c->width, c->height,
                                                PIX_FMT_YUV420P,
                                                c->width, c->height,
                                                c->pix_fmt,
                                                sws_flags, NULL, NULL, NULL);
               if (img_convert_ctx == NULL) {
                   fprintf(stderr, "Cannot initialize the conversion context\n");
                   exit(1);
               }
           }
           fill_yuv_image(tmp_picture, frame_count, c->width, c->height);
           sws_scale(img_convert_ctx, tmp_picture->data, tmp_picture->linesize,
                     0, c->height, picture->data, picture->linesize);
       } else {
           fill_yuv_image(picture, frame_count, c->width, c->height);
       }
   }


   if (oc->oformat->flags & AVFMT_RAWPICTURE) {
       /* raw video case. The API will change slightly in the near
          futur for that */
       AVPacket pkt;
       av_init_packet(&pkt);

       pkt.flags |= PKT_FLAG_KEY;
       pkt.stream_index= st->index;
       pkt.data= (uint8_t *)picture;
       pkt.size= sizeof(AVPicture);

       ret = av_write_frame(oc, &pkt);
   } else {
       /* encode the image */
       out_size = avcodec_encode_video(c, video_outbuf, video_outbuf_size, picture);
       /* if zero size, it means the image was buffered */
       if (out_size > 0) {
           AVPacket pkt;
           av_init_packet(&pkt);

           pkt.pts= av_rescale_q(c->coded_frame->pts, c->time_base, st->time_base);
           if(c->coded_frame->key_frame)
               pkt.flags |= PKT_FLAG_KEY;
           pkt.stream_index= st->index;
           pkt.data= video_outbuf;
           pkt.size= out_size;

           /* write the compressed frame in the media file */
           ret = av_write_frame(oc, &pkt);
       } else {
           ret = 0;
       }
   }
   if (ret != 0) {
       fprintf(stderr, "Error while writing video frame\n");
       exit(1);
   }
   frame_count++;

} 
[] close_video 
static void close_video(AVFormatContext *oc, AVStream *st) { 
   avcodec_close(st->codec);
   av_free(picture->data[0]);
   av_free(picture);
   if (tmp_picture) {
       av_free(tmp_picture->data[0]);
       av_free(tmp_picture);
   }
   av_free(video_outbuf);

} 


[] 媒体文件输出-main() 
/**************************************************************/ /* media file output */ 
int main(int argc, char **argv) { 
   const char *filename;
   AVOutputFormat *fmt;
   AVFormatContext *oc;
   AVStream *audio_st, *video_st;
   double audio_pts, video_pts;
   int i;

   /* initialize libavcodec, and register all codecs and formats */
   av_register_all();

   if (argc != 2) {
       printf("usage: %s output_file\n"
              "API example program to output a media file with libavformat.\n"
              "The output format is automatically guessed according to the file extension.\n"
              "Raw images can also be output by using '%%d' in the filename\n"
              "\n", argv[0]);
       exit(1);
   }

   filename = argv[1];

   /* auto detect the output format from the name. default is
      mpeg. */
   fmt = guess_format(NULL, filename, NULL);
   if (!fmt) {
       printf("Could not deduce output format from file extension: using MPEG.\n");
       fmt = guess_format("mpeg", NULL, NULL);
   }
   if (!fmt) {
       fprintf(stderr, "Could not find suitable output format\n");
       exit(1);
   }

   /* allocate the output media context */
   oc = av_alloc_format_context();
   if (!oc) {
       fprintf(stderr, "Memory error\n");
       exit(1);
   }
   oc->oformat = fmt;
   snprintf(oc->filename, sizeof(oc->filename), "%s", filename);

   /* add the audio and video streams using the default format codecs
      and initialize the codecs */
   video_st = NULL;
   audio_st = NULL;
   if (fmt->video_codec != CODEC_ID_NONE) {
       video_st = add_video_stream(oc, fmt->video_codec);
   }
   if (fmt->audio_codec != CODEC_ID_NONE) {
       audio_st = add_audio_stream(oc, fmt->audio_codec);
   }

   /* set the output parameters (must be done even if no
      parameters). */
   if (av_set_parameters(oc, NULL) < 0) {
       fprintf(stderr, "Invalid output format parameters\n");
       exit(1);
   }

   dump_format(oc, 0, filename, 1);

   /* now that all the parameters are set, we can open the audio and
      video codecs and allocate the necessary encode buffers */
   if (video_st)
       open_video(oc, video_st);
   if (audio_st)
       open_audio(oc, audio_st);

   /* open the output file, if needed */
   if (!(fmt->flags & AVFMT_NOFILE)) {
       if (url_fopen(&oc->pb, filename, URL_WRONLY) < 0) {
           fprintf(stderr, "Could not open '%s'\n", filename);
           exit(1);
       }
   }

   /* write the stream header, if any */
   av_write_header(oc);

   for(;;) {
       /* compute current audio and video time */
       if (audio_st)
           audio_pts = (double)audio_st->pts.val * audio_st->time_base.num / audio_st->time_base.den;
       else
           audio_pts = 0.0;

       if (video_st)
           video_pts = (double)video_st->pts.val * video_st->time_base.num / video_st->time_base.den;
       else
           video_pts = 0.0;

       if ((!audio_st || audio_pts >= STREAM_DURATION) &&
           (!video_st || video_pts >= STREAM_DURATION))
           break;

       /* write interleaved audio and video frames */
       if (!video_st || (video_st && audio_st && audio_pts < video_pts)) {
           write_audio_frame(oc, audio_st);
       } else {
           write_video_frame(oc, video_st);
       }
   }

   /* close each codec */
   if (video_st)
       close_video(oc, video_st);
   if (audio_st)
       close_audio(oc, audio_st);

   /* write the trailer, if any */
   av_write_trailer(oc);

   /* free the streams */
   for(i = 0; i < oc->nb_streams; i++) {
       av_freep(&oc->streams[i]->codec);
       av_freep(&oc->streams[i]);
   }

   if (!(fmt->flags & AVFMT_NOFILE)) {
       /* close the output file */
       url_fclose(&oc->pb);
   }

   /* free the stream */
   av_free(oc);

   return 0;

} 

取自""