Add All existing

extract_audio.py

@@ -0,0 +1,95 @@
+import os
+import ffmpeg
+import subprocess
+import re
+import json
+
+
+def sanitize_filename(name):
+    """
+    Removes invalid characters from the filename.
+    """
+    return re.sub(r'[<>:"/\\|?*@]', '_', name)
+
+
+def extract_audio_tracks(video_path):
+    """
+    Extracts all audio tracks from a video file and saves them with their respective titles.
+
+    Parameters:
+    video_path (str): Path to the video file.
+    """
+    try:
+        # Get the base name and directory of the video file
+        base_name = os.path.splitext(os.path.basename(video_path))[0]
+        directory = os.path.dirname(video_path)
+
+        # Use ffmpeg to get information about the video file
+        probe_cmd = ["ffprobe", "-v", "error", "-show_streams", "-of", "json", video_path]
+        probe_result = subprocess.run(probe_cmd, capture_output=True, text=True, check=True)
+        streams = json.loads(probe_result.stdout).get('streams', [])
+
+        # Process each audio stream
+        audio_streams = [s for s in streams if s.get('codec_type') == 'audio']
+        if not audio_streams:
+            print(f"No audio tracks found in {video_path}.")
+            return
+
+        for i, stream in enumerate(audio_streams):
+            # Extract title or fallback to index
+            title = stream.get('tags', {}).get('title', f"track_{i + 1}")
+            language = stream.get('tags', {}).get('language', 'unknown')
+            sanitized_title = sanitize_filename(title)
+            sanitized_language = sanitize_filename(language)
+            output_name = f"{base_name}__{sanitized_title}__{sanitized_language}.mp3"
+            output_path = os.path.join(directory, output_name)
+
+            # Extract the specific audio stream
+            print(f"Extracting audio: {sanitized_title} ({sanitized_language}) to {output_path}")
+            result = subprocess.run([
+                "ffmpeg", "-i", video_path,
+                "-map", f"0:a:{i}",  # Select the specific audio stream
+                "-c:a", "mp3",  # Set the codec to mp3
+                output_path,
+                "-y"  # Overwrite if exists
+            ], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+
+            if result.returncode != 0:
+                print(f"ffmpeg error for stream {i}: {result.stderr}")
+
+        print(f"Extraction completed for {video_path}.")
+    except Exception as e:
+        print(f"Error processing {video_path}: {e}")
+
+
+def process_path(input_path):
+    """
+    Processes a file or directory, extracting all audio tracks from video files.
+
+    Parameters:
+    input_path (str): Path to the video file or directory.
+    """
+    if os.path.isfile(input_path):
+        # Process a single file
+        extract_audio_tracks(input_path)
+    elif os.path.isdir(input_path):
+        # Process all video files in the directory
+        for file_name in os.listdir(input_path):
+            file_path = os.path.join(input_path, file_name)
+            if os.path.isfile(file_path) and file_name.lower().endswith(('.mp4', '.mkv', '.avi', '.mov')):
+                extract_audio_tracks(file_path)
+    else:
+        print(f"Invalid path: {input_path}")
+
+if __name__ == "__main__":
+    import argparse
+
+    # Set up argument parser
+    parser = argparse.ArgumentParser(description="Extract all audio tracks from video files.")
+    parser.add_argument("input_path", help="Path to the video file or directory.")
+    
+    # Parse arguments
+    args = parser.parse_args()
+
+    # Process the input path
+    process_path(args.input_path)