初学音视频（五）-FLV格式分析

FLV的简单介绍：

FLV（Flash Video）是Adobe公司设计开发的一种流行的流媒体格式，由于其视频文件体积轻巧、封装简单等特点，使其很适合在互联网上进行应用。此外，FLV可以使用Flash Player进行播放，而Flash Player插件已经安装在全世界绝大部分浏览器上，这使得通过网页播放FLV视频十分容易。目前主流的视频网站如优酷网，土豆网，乐视网等网站无一例外地使用了FLV格式。FLV封装格式的文件后缀通常为“.flv”。

FLV的结构图：

• FLV包括文件头（File Header）和文件体（File Body）两部分
• 
• 由上面可以知道，tag只有三种视频0x08、音频0x09和Script0x12,不同类型的tag的部分结构各不相同，但是tag的header的结构是相同的

三种Tag的Tag Data部分的结构

Audio Tag Data结构(音频Tag)

• 音频Tag开始的第1个字节包含了音频数据的参数信息，从第2个字节开始为音频流数据
• 第1个字节的前4位的数值表示了音频编码类型
• 第1个字节的第5-6位的数值表示音频采样率第
• 第1个字节的第7位表示音频采样精度
• 第1个字节的第8位表示音频类型。
  

Video Tag Data结构（视频Tag）

• 视频Tag也用开始的第1个字节包含视频数据的参数信息，从第2个字节为视频流数据。
• 第1个字节的前4位的数值表示帧类型
• 第1个字节的后4位的数值表示视频编码类型。

Script Tag Data结构（控制帧）

• 该类型Tag又通常被称为Metadata Tag，会放一些关于FLV视频和音频的元数据信息如：duration、width、height等。
• 通常该类型Tag会跟在File Header后面作为第一个Tag出现，而且只有一个。

#include <stdio.h>  
#include <stdlib.h>  
#include <string.h>  

//Important!  
#pragma pack(1)  


#define TAG_TYPE_SCRIPT 18  
#define TAG_TYPE_AUDIO  8  
#define TAG_TYPE_VIDEO  9  

typedef unsigned char byte;  
typedef unsigned int uint;  

        //定义一个FLV格式文件的文件头
typedef struct {  
    byte Signature[3];  
    byte Version;  
    byte Flags;  
    uint DataOffset;  
} FLV_HEADER;  

        //定义一个TAG的头，不同类型的tag的部分结构各不相同，但是tag的header的结构是相同的
typedef struct {  
    byte TagType;  
    byte DataSize[3];  
    byte Timestamp[3];  
    uint Reserved;  
} TAG_HEADER;  


//reverse_bytes - turn a BigEndian byte array into a LittleEndian integer  
        //转换大端<---->小端
uint reverse_bytes(byte *p, char c) {  
    int r = 0;  
    int i;  
    for (i=0; i<c; i++)   
        r |= ( *(p+i) << (((c-1)*8)-8*i));  
    return r;  
}  

/** 
 * Analysis FLV file 
 * @param url    Location of input FLV file. 
 */  

        //2.程序入口调用这个函数，传递进来的是文件的stream
int simplest_flv_parser(char *url){  

    //whether output audio/video stream  
        //3. 定义输出是音频/视频 的流的一个标记
    int output_a=1;  
    int output_v=1;  
    //-------------  
    FILE *ifh=NULL,*vfh=NULL, *afh = NULL;  

    //FILE *myout=fopen("output_log.txt","wb+");  
    FILE *myout=stdout;  

        //4. 定义一个文件头，和tag的头
    FLV_HEADER flv;  
    TAG_HEADER tagheader;  
    uint previoustagsize, previoustagsize_z=0;  
    uint ts=0, ts_new=0;  

    ifh = fopen(url, "rb+");  
    if ( ifh== NULL) {  
        printf("Failed to open files!");  
        return -1;  
    }  

    //FLV file header  
    fread((char *)&flv,1,sizeof(FLV_HEADER),ifh);  

    fprintf(myout,"============== FLV Header ==============\n");  
    fprintf(myout,"Signature:  0x %c %c %c\n",flv.Signature[0],flv.Signature[1],flv.Signature[2]);  
    fprintf(myout,"Version:    0x %X\n",flv.Version);  
    fprintf(myout,"Flags  :    0x %X\n",flv.Flags);  
    fprintf(myout,"HeaderSize: 0x %X\n",reverse_bytes((byte *)&flv.DataOffset, sizeof(flv.DataOffset)));  
    fprintf(myout,"========================================\n");  

    //move the file pointer to the end of the header  
    fseek(ifh, reverse_bytes((byte *)&flv.DataOffset, sizeof(flv.DataOffset)), SEEK_SET);  

    //process each tag  
    do {  

        previoustagsize = _getw(ifh);  

        fread((void *)&tagheader,sizeof(TAG_HEADER),1,ifh);  

        //int temp_datasize1=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize));  
        int tagheader_datasize=tagheader.DataSize[0]*65536+tagheader.DataSize[1]*256+tagheader.DataSize[2];  
        int tagheader_timestamp=tagheader.Timestamp[0]*65536+tagheader.Timestamp[1]*256+tagheader.Timestamp[2];  

        char tagtype_str[10];  
        switch(tagheader.TagType){  
        case TAG_TYPE_AUDIO:sprintf(tagtype_str,"AUDIO");break;  
        case TAG_TYPE_VIDEO:sprintf(tagtype_str,"VIDEO");break;  
        case TAG_TYPE_SCRIPT:sprintf(tagtype_str,"SCRIPT");break;  
        default:sprintf(tagtype_str,"UNKNOWN");break;  
        }  
        fprintf(myout,"[%6s] %6d %6d |",tagtype_str,tagheader_datasize,tagheader_timestamp);  

        //if we are not past the end of file, process the tag  
        if (feof(ifh)) {  
            break;  
        }  

        //process tag by type  
        switch (tagheader.TagType) {  

        case TAG_TYPE_AUDIO:{   
            char audiotag_str[100]={0};  
            strcat(audiotag_str,"| ");  
            char tagdata_first_byte;  
            tagdata_first_byte=fgetc(ifh);  
            int x=tagdata_first_byte&0xF0;  
            x=x>>4;  
            switch (x)  
            {  
            case 0:strcat(audiotag_str,"Linear PCM, platform endian");break;  
            case 1:strcat(audiotag_str,"ADPCM");break;  
            case 2:strcat(audiotag_str,"MP3");break;  
            case 3:strcat(audiotag_str,"Linear PCM, little endian");break;  
            case 4:strcat(audiotag_str,"Nellymoser 16-kHz mono");break;  
            case 5:strcat(audiotag_str,"Nellymoser 8-kHz mono");break;  
            case 6:strcat(audiotag_str,"Nellymoser");break;  
            case 7:strcat(audiotag_str,"G.711 A-law logarithmic PCM");break;  
            case 8:strcat(audiotag_str,"G.711 mu-law logarithmic PCM");break;  
            case 9:strcat(audiotag_str,"reserved");break;  
            case 10:strcat(audiotag_str,"AAC");break;  
            case 11:strcat(audiotag_str,"Speex");break;  
            case 14:strcat(audiotag_str,"MP3 8-Khz");break;  
            case 15:strcat(audiotag_str,"Device-specific sound");break;  
            default:strcat(audiotag_str,"UNKNOWN");break;  
            }  
            strcat(audiotag_str,"| ");  
            x=tagdata_first_byte&0x0C;  
            x=x>>2;  
            switch (x)  
            {  
            case 0:strcat(audiotag_str,"5.5-kHz");break;  
            case 1:strcat(audiotag_str,"1-kHz");break;  
            case 2:strcat(audiotag_str,"22-kHz");break;  
            case 3:strcat(audiotag_str,"44-kHz");break;  
            default:strcat(audiotag_str,"UNKNOWN");break;  
            }  
            strcat(audiotag_str,"| ");  
            x=tagdata_first_byte&0x02;  
            x=x>>1;  
            switch (x)  
            {  
            case 0:strcat(audiotag_str,"8Bit");break;  
            case 1:strcat(audiotag_str,"16Bit");break;  
            default:strcat(audiotag_str,"UNKNOWN");break;  
            }  
            strcat(audiotag_str,"| ");  
            x=tagdata_first_byte&0x01;  
            switch (x)  
            {  
            case 0:strcat(audiotag_str,"Mono");break;  
            case 1:strcat(audiotag_str,"Stereo");break;  
            default:strcat(audiotag_str,"UNKNOWN");break;  
            }  
            fprintf(myout,"%s",audiotag_str);  

            //if the output file hasn't been opened, open it.  
            if(output_a!=0&&afh == NULL){  
                afh = fopen("output.mp3", "wb");  
            }  

            //TagData - First Byte Data  
            int data_size=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize))-1;  
            if(output_a!=0){  
                //TagData+1  
                for (int i=0; i<data_size; i++)  
                    fputc(fgetc(ifh),afh);  

            }else{  
                for (int i=0; i<data_size; i++)  
                    fgetc(ifh);  
            }  
            break;  
        }  
        case TAG_TYPE_VIDEO:{  
            char videotag_str[100]={0};  
            strcat(videotag_str,"| ");  
            char tagdata_first_byte;  
            tagdata_first_byte=fgetc(ifh);  
            int x=tagdata_first_byte&0xF0;  
            x=x>>4;  
            switch (x)  
            {  
            case 1:strcat(videotag_str,"key frame  ");break;  
            case 2:strcat(videotag_str,"inter frame");break;  
            case 3:strcat(videotag_str,"disposable inter frame");break;  
            case 4:strcat(videotag_str,"generated keyframe");break;  
            case 5:strcat(videotag_str,"video info/command frame");break;  
            default:strcat(videotag_str,"UNKNOWN");break;  
            }  
            strcat(videotag_str,"| ");  
            x=tagdata_first_byte&0x0F;  
            switch (x)  
            {  
            case 1:strcat(videotag_str,"JPEG (currently unused)");break;  
            case 2:strcat(videotag_str,"Sorenson H.263");break;  
            case 3:strcat(videotag_str,"Screen video");break;  
            case 4:strcat(videotag_str,"On2 VP6");break;  
            case 5:strcat(videotag_str,"On2 VP6 with alpha channel");break;  
            case 6:strcat(videotag_str,"Screen video version 2");break;  
            case 7:strcat(videotag_str,"AVC");break;  
            default:strcat(videotag_str,"UNKNOWN");break;  
            }  
            fprintf(myout,"%s",videotag_str);  

            fseek(ifh, -1, SEEK_CUR);  
            //if the output file hasn't been opened, open it.  
            if (vfh == NULL&&output_v!=0) {  
                //write the flv header (reuse the original file's hdr) and first previoustagsize  
                    vfh = fopen("output.flv", "wb");  
                    fwrite((char *)&flv,1, sizeof(flv),vfh);  
                    fwrite((char *)&previoustagsize_z,1,sizeof(previoustagsize_z),vfh);  
            }  
#if 0  
            //Change Timestamp  
            //Get Timestamp  
            ts = reverse_bytes((byte *)&tagheader.Timestamp, sizeof(tagheader.Timestamp));  
            ts=ts*2;  
            //Writeback Timestamp  
            ts_new = reverse_bytes((byte *)&ts, sizeof(ts));  
            memcpy(&tagheader.Timestamp, ((char *)&ts_new) + 1, sizeof(tagheader.Timestamp));  
#endif  


            //TagData + Previous Tag Size  
            int data_size=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize))+4;  
            if(output_v!=0){  
                //TagHeader  
                fwrite((char *)&tagheader,1, sizeof(tagheader),vfh);  
                //TagData  
                for (int i=0; i<data_size; i++)  
                    fputc(fgetc(ifh),vfh);  
            }else{  
                for (int i=0; i<data_size; i++)  
                    fgetc(ifh);  
            }  
            //rewind 4 bytes, because we need to read the previoustagsize again for the loop's sake  
            fseek(ifh, -4, SEEK_CUR);  

            break;  
            }  
        default:  

            //skip the data of this tag  
            fseek(ifh, reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize)), SEEK_CUR);  
        }  

        fprintf(myout,"\n");  

    } while (!feof(ifh));  


    _fcloseall();  

    return 0;  
}  
int main(){

        //1. 程序入口
        simplest_flv_parser("/hoem/huangyu/HYtestyinshipin/flv/cuc_ieschool.flv");  

}