embed images

meetus/frame_extractor.py

@@ -16,17 +16,19 @@ logger = logging.getLogger(__name__)
 class FrameExtractor:
     """Extract frames from video files."""
 
-    def __init__(self, video_path: str, output_dir: str = "frames"):
+    def __init__(self, video_path: str, output_dir: str = "frames", quality: int = 75):
         """
         Initialize frame extractor.
 
         Args:
             video_path: Path to video file
             output_dir: Directory to save extracted frames
+            quality: JPEG quality for saved frames (0-100)
         """
         self.video_path = video_path
         self.output_dir = Path(output_dir)
         self.output_dir.mkdir(parents=True, exist_ok=True)
+        self.quality = quality
 
     def extract_by_interval(self, interval_seconds: int = 5) -> List[Tuple[str, float]]:
         """
@@ -56,8 +58,16 @@ class FrameExtractor:
                 frame_filename = f"frame_{saved_count:05d}_{timestamp:.2f}s.jpg"
                 frame_path = self.output_dir / frame_filename
 
-                # Use high quality for text readability (95 = high quality JPEG)
-                cv2.imwrite(str(frame_path), frame, [cv2.IMWRITE_JPEG_QUALITY, 95])
+                # Downscale to 1600px width for smaller file size (but still readable)
+                height, width = frame.shape[:2]
+                if width > 1600:
+                    ratio = 1600 / width
+                    new_width = 1600
+                    new_height = int(height * ratio)
+                    frame = cv2.resize(frame, (new_width, new_height), interpolation=cv2.INTER_LANCZOS4)
+
+                # Save with configured quality (matches embed quality)
+                cv2.imwrite(str(frame_path), frame, [cv2.IMWRITE_JPEG_QUALITY, self.quality])
                 frames_info.append((str(frame_path), timestamp))
                 saved_count += 1
 
@@ -90,16 +100,24 @@ class FrameExtractor:
         output_pattern = self.output_dir / f"{video_name}_%05d.jpg"
 
         try:
-            # Use FFmpeg's scene detection filter with high quality output
+            # Use FFmpeg's scene detection filter with downscaling
             stream = ffmpeg.input(self.video_path)
             stream = ffmpeg.filter(stream, 'select', f'gt(scene,{threshold/100})')
             stream = ffmpeg.filter(stream, 'showinfo')
+            # Scale to 1600px width (maintains aspect ratio, still readable)
+            # Use simple conditional: if width > 1600, scale to 1600, else keep original
+            stream = ffmpeg.filter(stream, 'scale', w='min(1600,iw)', h=-1)
+
+            # Convert JPEG quality (0-100) to FFmpeg qscale (2-31, lower=better)
+            # Rough mapping: qscale ≈ (100 - quality) / 10, clamped to 2-31
+            qscale = max(2, min(31, int((100 - self.quality) / 10 + 2)))
+
             stream = ffmpeg.output(
                 stream,
                 str(output_pattern),
                 vsync='vfr',
                 frame_pts=1,
-                **{'q:v': '2'}  # High quality JPEG
+                **{'q:v': str(qscale)}  # Matches configured quality
             )
 
             # Run with stderr capture to get showinfo output