feat(pdf-to-jpg): convert pdf pages to resized jpgs

pdf_to_jpg.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env -S uv run --script
+# /// script
+# dependencies = ["pdf2image", "Pillow"]
+# ///
+
+import argparse
+import logging
+from pathlib import Path
+import pdf2image
+from PIL import Image
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s: %(message)s")
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Convert PDF pages to JPG images.", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument("pdf_path", type=Path, help="Path to the PDF file.")
+    return parser.parse_args()
+
+
+def save_images(images: list[Image.Image], save_dir: Path, base_name: str) -> None:
+    for i, img in enumerate(images, start=1):
+        width, height = img.size
+        if width > 2000:
+            ratio = 2000 / width
+            new_size = (2000, int(height * ratio))
+            img = img.resize(new_size, resample=Image.LANCZOS)
+        out_path = save_dir / f"{base_name}-{i:03d}.jpg"
+        img.save(out_path, format="JPEG")
+        logging.info(f"Saved {out_path}")
+
+
+def main() -> None:
+    args = parse_args()
+    pdf_path: Path = args.pdf_path
+    if not pdf_path.exists():
+        logging.error(f"File not found: {pdf_path}")
+        return
+    try:
+        images = pdf2image.convert_from_path(pdf_path=str(pdf_path))
+    except Exception as e:
+        logging.error(f"Failed to convert PDF: {e}")
+        return
+    save_images(
+        images=images,
+        save_dir=pdf_path.parent,
+        base_name=pdf_path.stem,
+    )
+
+
+if __name__ == "__main__":
+    main()