tools/python/ocr_pdf.py

#!/usr/bin/env python3
"""OCR a scanned PDF using ocrmypdf (Tesseract backend)."""
import argparse, json, sys
from pathlib import Path

def ocr(input_path, output_path):
    import ocrmypdf
    
    if not output_path:
        output_path = str(Path(input_path).with_stem(Path(input_path).stem + '_ocr'))
    
    result = ocrmypdf.ocr(
        input_path, output_path,
        language='eng',
        skip_text=True,  # Skip pages that already have text
        deskew=True,
        optimize=1,
        progress_bar=False,
    )
    
    return output_path

def main():
    parser = argparse.ArgumentParser(description='OCR a PDF')
    parser.add_argument('--input', required=True)
    parser.add_argument('--output', required=True)
    args = parser.parse_args()
    try:
        result = ocr(args.input, args.output)
        print(json.dumps({"success": True, "output": result, "message": "OCR completed successfully"}))
    except Exception as e:
        print(json.dumps({"success": False, "output": "", "message": str(e)}))
        sys.exit(1)

if __name__ == '__main__':
    main()