initial

app/parsers/media_parser.py

@@ -0,0 +1,42 @@
+from pathlib import Path
+from typing import Dict
+
+class MediaParser:
+    def parse_audio(self, file_path: Path) -> Dict:
+        return {
+            'text': '[Audio transcription pending]',
+            'needs_transcription': True,
+            'transcription_service': 'whisper',
+            'structure': {'type': 'audio'},
+            'quality': 'pending'
+        }
+
+    def parse_video(self, file_path: Path) -> Dict:
+        return {
+            'text': '[Video transcription pending]',
+            'needs_transcription': True,
+            'needs_scene_detection': True,
+            'transcription_service': 'whisper',
+            'structure': {'type': 'video'},
+            'quality': 'pending'
+        }
+
+    def parse_image(self, file_path: Path) -> Dict:
+        try:
+            from PIL import Image
+
+            with Image.open(file_path) as img:
+                width, height = img.size
+                mode = img.mode
+
+            return {
+                'text': '[Image caption/OCR pending]',
+                'needs_ocr': True,
+                'needs_caption': True,
+                'dimensions': f'{width}x{height}',
+                'mode': mode,
+                'structure': {'type': 'image', 'width': width, 'height': height},
+                'quality': 'pending'
+            }
+        except Exception as e:
+            return {'error': str(e)}