如何在FFMpeg中获取输入设备名
这篇文章是19年在实习时候写的。
简单来说，其实ffmpeg是有相应的接口的，如avdevice_list_input_sources可以查询设备名，甚至在avdevice.h的注释里可以看到，还有可以根据设备名获取设备支持的分辨率、格式等信息的API。
但是在网上的方法里面，一个是通过
AVFormatContext *pFormatCtx = avformat_alloc_context();
AVDictionary* options = NULL;
av_dict_set(&options, "list_devices", "true", 0);
AVInputFormat *iformat = av_find_input_format("dshow");
puts("Device Option Info======");
avformat_open_input(&pFormatCtx, "video=dummy", iformat, &options);
在stdout中打印信息，从而可以解析这些信息来获取。
另一种是通过调用COM接口来获取，参见https://blog.csdn.net/jhqin/article/details/5929796
他们的本质都是通过COM接口来获取信息，ffmpeg也是调用的同样的函数，只是没提供返回的接口，而是打印了出来，也就说ffmpeg由于dshow部分的一些函数官方还没写完，所以就只能用这种蛋疼的方法。
那么怎么做才能完美呢？
当然是自己实现对应的接口了……
从dshow.c可以看出：
AVInputFormat ff_dshow_demuxer = {
.name = "dshow",
.long_name = NULL_IF_CONFIG_SMALL("DirectShow capture"),
.priv_data_size = sizeof(struct dshow_ctx),
.read_header = dshow_read_header,
.read_packet = dshow_read_packet,
.read_close = dshow_read_close,
.flags = AVFMT_NOFILE,
.priv_class = &dshow_class,
};
里面只有这些实现了，而AVInputFormat 完整的接口呢？
typedef struct AVInputFormat {
/**
* A comma separated list of short names for the format. New names
* may be appended with a minor bump.
*/
const char *name;
/**
* Descriptive name for the format, meant to be more human-readable
* than name. You should use the NULL_IF_CONFIG_SMALL() macro
* to define it.
*/
const char *long_name;
/**
* Can use flags: AVFMT_NOFILE, AVFMT_NEEDNUMBER, AVFMT_SHOW_IDS,
* AVFMT_GENERIC_INDEX, AVFMT_TS_DISCONT, AVFMT_NOBINSEARCH,
* AVFMT_NOGENSEARCH, AVFMT_NO_BYTE_SEEK, AVFMT_SEEK_TO_PTS.
*/
int flags;
/**
* If extensions are defined, then no probe is done. You should
* usually not use extension format guessing because it is not
* reliable enough
*/
const char *extensions;
const struct AVCodecTag * const *codec_tag;
const AVClass *priv_class; ///< AVClass for the private context
/**
* Comma-separated list of mime types.
* It is used check for matching mime types while probing.
* @see av_probe_input_format2
*/
const char *mime_type;
/*****************************************************************
* No fields below this line are part of the public API. They
* may not be used outside of libavformat and can be changed and
* removed at will.
* New public fields should be added right above.
*****************************************************************
*/
struct AVInputFormat *next;
/**
* Raw demuxers store their codec ID here.
*/
int raw_codec_id;
/**
* Size of private data so that it can be allocated in the wrapper.
*/
int priv_data_size;
/**
* Tell if a given file has a chance of being parsed as this format.
* The buffer provided is guaranteed to be AVPROBE_PADDING_SIZE bytes
* big so you do not have to check for that unless you need more.
*/
int (*read_probe)(AVProbeData *);
/**
* Read the format header and initialize the AVFormatContext
* structure. Return 0 if OK. 'avformat_new_stream' should be
* called to create new streams.
*/
int (*read_header)(struct AVFormatContext *);
/**
* Read one packet and put it in 'pkt'. pts and flags are also
* set. 'avformat_new_stream' can be called only if the flag
* AVFMTCTX_NOHEADER is used and only in the calling thread (not in a
* background thread).
* @return 0 on success, < 0 on error.
* When returning an error, pkt must not have been allocated
* or must be freed before returning
*/
int (*read_packet)(struct AVFormatContext *, AVPacket *pkt);
/**
* Close the stream. The AVFormatContext and AVStreams are not
* freed by this function
*/
int (*read_close)(struct AVFormatContext *);
/**
* Seek to a given timestamp relative to the frames in
* stream component stream_index.
* @param stream_index Must not be -1.
* @param flags Selects which direction should be preferred if no exact
* match is available.
* @return >= 0 on success (but not necessarily the new offset)
*/
int (*read_seek)(struct AVFormatContext *,
int stream_index, int64_t timestamp, int flags);
/**
* Get the next timestamp in stream[stream_index].time_base units.
* @return the timestamp or AV_NOPTS_VALUE if an error occurred
*/
int64_t (*read_timestamp)(struct AVFormatContext *s, int stream_index,
int64_t *pos, int64_t pos_limit);
/**
* Start/resume playing - only meaningful if using a network-based format
* (RTSP).
*/
int (*read_play)(struct AVFormatContext *);
/**
* Pause playing - only meaningful if using a network-based format
* (RTSP).
*/
int (*read_pause)(struct AVFormatContext *);
/**
* Seek to timestamp ts.
* Seeking will be done so that the point from which all active streams
* can be presented successfully will be closest to ts and within min/max_ts.
* Active streams are all streams that have AVStream.discard < AVDISCARD_ALL.
*/
int (*read_seek2)(struct AVFormatContext *s, int stream_index, int64_t min_ts, int64_t ts, int64_t max_ts, int flags);
/**
* Returns device list with it properties.
* @see avdevice_list_devices() for more details.
*/
int (*get_device_list)(struct AVFormatContext *s, struct AVDeviceInfoList *device_list);
/**
* Initialize device capabilities submodule.
* @see avdevice_capabilities_create() for more details.
*/
int (*create_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
/**
* Free device capabilities submodule.
* @see avdevice_capabilities_free() for more details.
*/
int (*free_device_capabilities)(struct AVFormatContext *s, struct AVDeviceCapabilitiesQuery *caps);
} AVInputFormat;
看到没，还有个get_device_list和create_device_capabilities没实现，这俩函数指针对应着从ffmpeg的dshow获取输入的设备名，以及设备名对应的可用的设备参数的信息。
那么接下来的问题就很简单，我们把这两个接口实现即可，既然之前都能打印到stdout，说明对COM的封装函数都写好了，只是没有返回数据而已。我们把对应的函数制作一个副本，改成返回数据的形式，实现接口即可。
在avdevice/dshow.c中1073行附近，找个空，增加一个函数:
static int dshow_get_device_list(AVFormatContext *avctx, AVDeviceInfoList *device_list)
{
IEnumMoniker *classenum = NULL;
ICreateDevEnum *devenum = NULL;
IMoniker *m = NULL;
int r = 0;
const GUID *device_guid[2] = { &CLSID_VideoInputDeviceCategory,
&CLSID_AudioInputDeviceCategory };
device_list->nb_devices = 0;
device_list->devices = NULL;
r = CoInitialize(0);
if(r != S_OK){
return AVERROR(EIO);
}
r = CoCreateInstance(&CLSID_SystemDeviceEnum, NULL, CLSCTX_INPROC_SERVER,
&IID_ICreateDevEnum, (void **) &devenum);
if (r != S_OK) {
av_log(avctx, AV_LOG_ERROR, "Could not enumerate system devices.\n");
r = AVERROR(EIO);
goto fail2;
}
for(int sourcetype = 0; sourcetype<2; sourcetype++){
r = ICreateDevEnum_CreateClassEnumerator(devenum, device_guid[sourcetype],
(IEnumMoniker **) &classenum, 0);
if (r != S_OK) {
av_log(avctx, AV_LOG_ERROR, "Could not enumerate dshow devices (or none found).\n");
r = AVERROR(EIO);
goto fail2;
}
while (IEnumMoniker_Next(classenum, 1, &m, NULL) == S_OK) {
IPropertyBag *bag = NULL;
char *friendly_name = NULL;
char *unique_name = NULL;
VARIANT var;
VariantInit(&var);
IBindCtx *bind_ctx = NULL;
LPOLESTR olestr = NULL;
LPMALLOC co_malloc = NULL;
int i;
r = CoGetMalloc(1, &co_malloc);
if (r != S_OK)
goto fail1;
r = CreateBindCtx(0, &bind_ctx);
if (r != S_OK)
goto fail1;
/* GetDisplayname works for both video and audio, DevicePath doesn't */
r = IMoniker_GetDisplayName(m, bind_ctx, NULL, &olestr);
if (r != S_OK)
goto fail1;
unique_name = dup_wchar_to_utf8(olestr);
/* replace ':' with '_' since we use : to delineate between sources */
for (i = 0; i < strlen(unique_name); i++) {
if (unique_name[i] == ':')
unique_name[i] = '_';
}
r = IMoniker_BindToStorage(m, 0, 0, &IID_IPropertyBag, (void *) &bag);
if (r != S_OK)
goto fail1;
var.vt = VT_BSTR;
r = IPropertyBag_Read(bag, L"FriendlyName", &var, NULL);
if (r != S_OK)
goto fail1;
friendly_name = dup_wchar_to_utf8(var.bstrVal);
char *friendly_name2 = av_malloc(strlen(friendly_name)+7);
strcpy(friendly_name2,sourcetype==0?"video=":"audio=");
strcat(friendly_name2,friendly_name);
av_free(friendly_name);
device_list->nb_devices +=1;
device_list->devices = av_realloc( device_list->devices, device_list->nb_devices * sizeof(AVDeviceInfo*));
AVDeviceInfo* newDevice = av_malloc(sizeof(AVDeviceInfo));
newDevice->device_description = friendly_name2;
newDevice->device_name = unique_name;
device_list->devices[device_list->nb_devices - 1] = newDevice;
fail1:
VariantClear(&var);
if (olestr && co_malloc)
IMalloc_Free(co_malloc, olestr);
if (bind_ctx)
IBindCtx_Release(bind_ctx);
if (bag)
IPropertyBag_Release(bag);
IMoniker_Release(m);
}
}
fail2:
if (devenum)
ICreateDevEnum_Release(devenum);
if (classenum)
IEnumMoniker_Release(classenum);
CoUninitialize();
return r;
}
然后滚动到dshow.c最后一页，在.read_close后面增加一行，变成：
AVInputFormat ff_dshow_demuxer = {
.name = "dshow",
.long_name = NULL_IF_CONFIG_SMALL("DirectShow capture"),
.priv_data_size = sizeof(struct dshow_ctx),
.read_header = dshow_read_header,
.read_packet = dshow_read_packet,
.read_close = dshow_read_close,
.get_device_list= dshow_get_device_list, //这一行是新加的。
.flags = AVFMT_NOFILE,
.priv_class = &dshow_class,
};
那么怎么使用呢？下面是一个获取音视频设备名，并且分别放在两个vector中的示例函数
void GetDeviceList(vector<string> *audio, vector<string> *video)
{
AVDeviceInfoList *list = nullptr;
avdevice_list_input_sources(NULL, "dshow", NULL, &list);
if (!list) return;
for (int i = 0; i < list->nb_devices; i++) {
if (video && memcmp(list->devices[i]->device_description, "video", 5) == 0) {
video->push_back(list->devices[i]->device_description);
}
else if (audio && memcmp(list->devices[i]->device_description, "audio", 5) == 0) {
audio->push_back(list->devices[i]->device_description);
}
}
avdevice_free_list_devices(&list);
}
