Audio in progress

Sources/pyOpenRPA/Robot/Audio.py

@@ -3,12 +3,53 @@ import pyaudio
 from pydub import AudioSegment
 import threading
 import wave
+import time
+from pyOpenRPA.Utils import Text
 
 
-def DeviceSystemSoundSearchIndex():
+def DeviceMicrophoneIndex():
+    """L-,W+: Выполнить поиск устройства, с помощью которого можно будет выполнить захват c микрофона.
+    """
+    p = pyaudio.PyAudio()
+    lDeviceInfoDict = p.get_default_input_device_info()
+    lDefaultIndexInt = lDeviceInfoDict["index"]
+    return lDefaultIndexInt
+
+def DeviceSystemSoundIndex():
     """L-,W+: Выполнить поиск устройства, с помощью которого можно будет выполнить захват аудио, которое поступает из приложений. Например: аудиоконференции Zoom, whatsapp, telegram и т.д.
     """
-    pass
+    p = pyaudio.PyAudio()
+    inInputBool = True
+    inIsLoopbackBool = True
+    if inInputBool == True:
+        lDeviceInfoDict = p.get_default_output_device_info()
+        lDefaultIndexInt = lDeviceInfoDict["index"]
+        lDefaultNameStr = lDeviceInfoDict["name"]
+        lCatchIndexInt = None
+        lCatchDiffRatioFloat = 0.0
+        for lItemDict in DeviceListGet():
+            lCompareBool = False
+            if lItemDict["MaxOutputChannelsInt"]>0:
+                if inIsLoopbackBool==True and lItemDict["HostApiStr"]=="Windows WASAPI": lCompareBool = True
+                elif inIsLoopbackBool==False: lCompareBool = True
+            if lCompareBool == True:
+                lDiffRationFloat = Text.SimilarityNoCase(in1Str=lDefaultNameStr, in2Str=lItemDict["NameStr"])
+                if lDiffRationFloat> lCatchDiffRatioFloat: lCatchIndexInt=lItemDict["IndexInt"]
+    else:
+        lDeviceInfoDict = p.get_default_output_device_info()
+        lDefaultIndexInt = lDeviceInfoDict["index"]
+        lDefaultNameStr = lDeviceInfoDict["name"]
+        lCatchIndexInt = None
+        lCatchDiffRatioFloat = 0.0
+        for lItemDict in DeviceListGet():
+            lCompareBool = False
+            if lItemDict["MaxInputChannelsInt"]>0:
+                if inIsLoopbackBool==True and lItemDict["HostApiStr"]=="Windows WASAPI": lCompareBool = True
+                elif inIsLoopbackBool==False: lCompareBool = True
+            if lCompareBool == True:
+                lDiffRationFloat = Text.SimilarityNoCase(in1Str=lDefaultNameStr, in2Str=lItemDict["NameStr"])
+                if lDiffRationFloat> lCatchDiffRatioFloat: lCatchIndexInt=lItemDict["IndexInt"]
+    return lCatchIndexInt
 
 def DeviceListGet():
     """L-,W+: Вернуть список аудио устройст (входящих и исходящих, микрофонов и динамиков).
@@ -42,7 +83,7 @@ def DeviceListGet():
 class Recorder:
 
     mStatusStr = "0_READY"
-    mAudio = pyaudio.PyAudio()
+    mAudio = None
     mCaptureThread = None
     mStream = None
 
@@ -52,16 +93,22 @@ class Recorder:
     mRecordedFramesList = []
     mUseLoopbackBool = True
     mSampleRateInt = None
-    mSampleSizeInt = mAudio.get_sample_size(pyaudio.paInt16)
+    mSampleSizeInt = None
 
     mCaptureBool = True
-    mFileNameStr = "aux"
+    mFilePathStr = "out"
     mFileFormatStr = "mp3"
+    
 
     def __init__(self, inDeviceInt=None):
         self.mDeviceInt = inDeviceInt
-
-    def CaptureStart(self):
+        if inDeviceInt == None: self.mDeviceInt = DeviceSystemSoundIndex()
+    
+    def CaptureStart(self, inFilePathStr = "out", inFileFormatStr = "mp3", inDoChunkBool = False):
+        self.mFilePathStr = inFilePathStr
+        self.mFileFormatStr = inFileFormatStr
+        self.mAudio = pyaudio.PyAudio()
+        self.mSampleSizeInt = self.mAudio.get_sample_size(pyaudio.paInt16)
         lDeviceInfoDict = self.mAudio.get_device_info_by_index(self.mDeviceInt)
         #Open stream
         self.mSampleRateInt = int(lDeviceInfoDict["defaultSampleRate"])
@@ -77,32 +124,21 @@ class Recorder:
         self.mCaptureThread.start()
 
     def __Capture__(self):
-        while self.mCaptureBool == True:
+        while self.mCaptureBool==True:
             self.mRecordedFramesList.append(self.mStream.read(self.mFramesInt))
         self.mStream.stop_stream()
         self.mStream.close()
         #Close module
         self.mAudio.terminate()
-        print("done")
 
     def CaptureStop(self):
         self.mCaptureBool=False
         self.mCaptureThread.join()
-        print("done2")
         self.CaptureChunk()
-        print("done3")
-        
-       
         
     def CaptureChunk(self):
-        print("CaptureChunk 1")
-        waveFile = wave.open(f"{self.mFileNameStr}.{self.mFileFormatStr}", 'wb')
-        waveFile.setnchannels(self.mChannelCountInt)
-        waveFile.setsampwidth(self.mSampleSizeInt)
-        waveFile.setframerate(self.mSampleRateInt)
-        waveFile.writeframes(b''.join(self.mRecordedFramesList))
-        waveFile.close()
-        lSound = AudioSegment(
+        # Advanced usage, if you have raw audio data:
+        sound = AudioSegment(
             # raw audio data (bytes)
             data=b''.join(self.mRecordedFramesList),
             # 2 byte (16 bit) samples
@@ -112,11 +148,7 @@ class Recorder:
             # stereo
             channels=self.mChannelCountInt
         )
-        print("CaptureChunk 2")
-        print(len(self.mRecordedFramesList))
-        
-        lSound.export(f"{self.mFileNameStr}.{self.mFileFormatStr}", format=self.mFileFormatStr)
-        print("CaptureChunk 3")
+        sound.export(f"{self.mFilePathStr}.{self.mFileFormatStr}", format=f"{self.mFileFormatStr}")
         self.mRecordedFramesList = []
 
     def FileListGet(self):

Sources/pyOpenRPA/Utils/Text.py

@@ -0,0 +1,7 @@
+import difflib
+
+def SimilarityNoCase(in1Str, in2Str):
+  normalized1 = in1Str.lower()
+  normalized2 = in2Str.lower()
+  matcher = difflib.SequenceMatcher(None, normalized1, normalized2)
+  return matcher.ratio()

Tools/Jupyter-notebooks/Audio.ipynb

@@ -15,19 +15,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "123\n"
+     "ename": "AttributeError",
+     "evalue": "'Recorder' object has no attribute 'test'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-1-ef80e2b488aa>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mpyOpenRPA\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mRobot\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mAudio\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[0mlRec\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mAudio\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mRecorder\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minDeviceInt\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mlRec\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mAttributeError\u001b[0m: 'Recorder' object has no attribute 'test'"
      ]
     }
    ],
    "source": [
-    "print(123)"
+    "from pyOpenRPA.Robot import Audio\n",
+    "lRec = Audio.Recorder(inDeviceInt=10)\n",
+    "lRec.test()"
    ]
   },
   {
@@ -43,19 +49,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "done\n",
-      "done2\n",
-      "CaptureChunk 1\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "lRec.CaptureStop()"
    ]
@@ -197,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -205,7 +201,11 @@
      "output_type": "stream",
      "text": [
       "Starting...\n",
-      "End.\n"
+      "End.\n",
+      "2\n",
+      "2\n",
+      "48000\n",
+      "382976\n"
      ]
     },
     {
@@ -214,7 +214,7 @@
        "<_io.BufferedRandom name='out.mp3'>"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -228,7 +228,7 @@
     "#Use module\n",
     "p = pyaudio.PyAudio()\n",
     "\n",
-    "recordtime = 15\n",
+    "recordtime = 2\n",
     "device_id = 10\n",
     "device_info = p.get_device_info_by_index(device_id)\n",
     "#Open stream\n",
@@ -269,12 +269,16 @@
     "    # stereo\n",
     "    channels=channelcount\n",
     ")\n",
+    "print(channelcount)\n",
+    "print(p.get_sample_size(pyaudio.paInt16))\n",
+    "print(int(device_info[\"defaultSampleRate\"]))\n",
+    "print(len(b''.join(recorded_frames)))\n",
     "sound.export(\"out.mp3\", format=\"mp3\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -288,22 +292,123 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0.36363636363636365"
+       "0.647887323943662"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "similarity(\"sadsdasd\",\"sadfsdfd                 \")"
+    "similarity_no_case(\"Ìèêðîôîí (Realtek High Definiti\",\"Динамики (Realtek High Definition Audio)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'index': 1,\n",
+       " 'structVersion': 2,\n",
+       " 'name': 'Ìèêðîôîí (Realtek High Definiti',\n",
+       " 'hostApi': 0,\n",
+       " 'maxInputChannels': 2,\n",
+       " 'maxOutputChannels': 0,\n",
+       " 'defaultLowInputLatency': 0.09,\n",
+       " 'defaultLowOutputLatency': 0.09,\n",
+       " 'defaultHighInputLatency': 0.18,\n",
+       " 'defaultHighOutputLatency': 0.18,\n",
+       " 'defaultSampleRate': 44100.0}"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "p.get_default_input_device_info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pyaudio\n",
+    "p = pyaudio.PyAudio()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<pyaudio.PyAudio at 0x1a6b5ab2438>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "p"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "False"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "not (False ^ True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from pyOpenRPA.Robot import Audio\n",
+    "Audio.DeviceMicrophoneIndex()"
    ]
   },
   {

changelog.md

@@ -19,7 +19,7 @@ AGT - AGENT
 - ОБЩЕЕ
 - - Jupyter: запуск из других дисков, отличных от C://
 - - Utils: Функции подготовки файлов / директорий
-- - Utils: String - similarity
+- - Utils: Text - SimilarityNoCase - Сверка двух строк на схождение (коэффициент от 0.0 до 1.0)
 
 [1.3.0]
 - ПОРТИРОВАНО НА LINUX (Ubuntu, Debian, Astra), адаптация функций