使用 ffmpeg 库提取文本字幕

sudo apt-get install ffmpeg

ffmpeg -i input_video.mp4 -vn -an -codec:s:0 srt -y output_subtitle.srt

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

int main(int argc, char *argv[]) {
    AVFormatContext *pFormatCtx;
    int i, j;
    int video_stream_index = -1;
    int audio_stream_index = -1;
    int subtitle_stream_index = -1;

    // Register all formats and codecs
    av_register_all();
    avformat_network_init();

    // Open video file
    if (avformat_open_input(&pFormatCtx, argv[1], NULL, NULL) != 0) {
        printf("Could not open file.\n");
        return -1;
    }

    // Retrieve stream information
    if (avformat_find_stream_info(pFormatCtx, NULL) < 0) {
        printf("Could not find stream information.\n");
        return -1;
    }

    // Find the first video stream
    for (i = 0; i < pFormatCtx->nb_streams; i++) {
        if (pFormatCtx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && video_stream_index < 0) {
            video_stream_index = i;
        }
        if (pFormatCtx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO && audio_stream_index < 0) {
            audio_stream_index = i;
        }
        if (pFormatCtx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE && subtitle_stream_index < 0) {
            subtitle_stream_index = i;
        }
    }

    // Find the decoder for the video stream
    AVCodecParameters *pCodecPar = pFormatCtx->streams[subtitle_stream_index]->codecpar;
    AVCodec *pCodec = avcodec_find_decoder(pCodecPar->codec_id);
    if (pCodec == NULL) {
        printf("Unsupported codec.\n");
        return -1;
    }

    // Allocate a codec context for the decoder
    AVCodecContext *pCodecCtx = avcodec_alloc_context3(pCodec);
    if (!pCodecCtx) {
        printf("Could not allocate video codec context.\n");
        return -1;
    }

    // Initialize the video decoder
    if (avcodec_parameters_to_context(pCodecCtx, pCodecPar) < 0) {
        printf("Could not copy codec parameters to decoder context.\n");
        return -1;
    }

    if (avcodec_open2(pCodecCtx, pCodec, NULL) < 0) {
        printf("Could not open codec.\n");
        return -1;
    }

    // Allocate video frame
    AVFrame *pFrame = av_frame_alloc();
    if (pFrame == NULL) {
        printf("Could not allocate video frame.\n");
        return -1;
    }

    // Allocate an AVPacket
    AVPacket *pkt = av_packet_alloc();
    if (pkt == NULL) {
        printf("Could not allocate AVPacket.\n");
        return -1;
    }

    // Read frames from the video file
    while (av_read_frame(pFormatCtx, pkt) >= 0) {
        if (pkt->stream_index == subtitle_stream_index) {
            int frame_decoded = 0;
            int ret = avcodec_decode_subtitle2(pCodecCtx, pFrame, &frame_decoded, pkt);
            if (ret >= 0 && frame_decoded) {
                for (j = 0; j < pFrame->nb_side_data; j++) {
                    AVPacketSideData sd = pFrame->side_data[j];
                    if (sd.type == AV_PKT_DATA_SUBTITLE_POSITION) {
                        AVSubtitlePosition *pos = (AVSubtitlePosition *)sd.data;
                        printf("Subtitle position: %d,%d,%d,%d\n", pos->x, pos->y, pos->w, pos->h);
                    }
                }
                for (j = 0; j < pFrame->nb_side_data; j++) {
                    AVPacketSideData sd = pFrame->side_data[j];
                    if (sd.type == AV_PKT_DATA_SUBTITLE_TEXT) {
                        char *text = (char *)sd.data;
                        printf("Subtitle text: %s\n", text);
                    }
                }
            }
        }
        av_packet_unref(pkt);
    }

    // Free the RGB image
    av_frame_free(&pFrame);

    // Close the video file
    avcodec_close(pCodecCtx);
    avformat_close_input(&pFormatCtx);

    return 0;
}