v0.07.5 - yt-dlp logging w/ interval

README.md

@@ -49,7 +49,8 @@ After launching the bot, you can interact with it via Telegram:
 
 ## Changes
 
-- v0.07.4 - fixes for non-youtube url's
+- v0.07.5 - 10-second interval update for `yt-dlp` logging
+- v0.07.4 - fixes for non-youtube urls
 - v0.07.2 - job queues fine-tuned to be more informative
 - v0.07.1 - job queues introduced
 - v0.07 - transcript queuing, more precise transcript time estimates

src/main.py

@@ -3,7 +3,7 @@
 # openai-whisper transcriber-bot for Telegram
 
 # version of this program
-version_number = "0.07.4"
+version_number = "0.07.5"
 
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 # https://github.com/FlyingFathead/whisper-transcriber-telegram-bot/

src/transcription_handler.py

@@ -1,7 +1,7 @@
 # transcription_handler.py
 # ~~~
 # openai-whisper transcriber-bot for Telegram
-# v0.07.4
+# v0.07.5
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 # https://github.com/FlyingFathead/whisper-transcriber-telegram-bot/
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -117,25 +117,46 @@ async def download_audio(url, output_path):
  command = [
  "yt-dlp",
  "--extract-audio",
+ # "--quiet", # Add quiet flags to suppress output
  "--audio-format", "mp3",
  "--cache-dir", cache_dir, # Specify the custom cache directory
  url,
  "-o", output_path
  ]
 
- # Start the subprocess and capture stdout and stderr
+ # Start the subprocess
  process = await asyncio.create_subprocess_exec(*command, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE)
 
- # Communicate with the process to retrieve its output and error message
- stdout, stderr = await process.communicate()
+ # Initialize an empty buffer and set the initial time marker
+ output_buffer = ''
+ last_log_time = time.time()
+ log_interval = 10 # seconds
+
+ while True:
+ chunk = await process.stdout.read(1)
+ if not chunk: # Break if no more output
+ break
+
+ output_buffer += chunk.decode()
+
+ # Log at regular time intervals, regardless of the content
+ current_time = time.time()
+ if current_time - last_log_time >= log_interval:
+ if output_buffer.strip():
+ logger.info(output_buffer.strip())
+ output_buffer = '' # Reset the buffer
+ last_log_time = current_time
+
+ # After the loop, ensure to log any remaining output
+ if output_buffer.strip():
+ logger.info(output_buffer.strip())
 
- # Log the stdout and stderr
- if stdout:
- logger.info(f"yt-dlp stdout: {stdout.decode().strip()}")
+ # Check for any error output
+ stderr = await process.stderr.read()
  if stderr:
  logger.error(f"yt-dlp stderr: {stderr.decode().strip()}")
 
- # Check if the file was downloaded successfully
+ # Verify the download success
  if os.path.exists(output_path):
  logger.info(f"Audio downloaded successfully: {output_path}")
  else: