ocrmypdf

import ocrmypdf from ocrmypdf import OcrOptions import os # Create dummy input.pdf for demonstration with open('input.pdf', 'wb') as f: f.write(b'%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj 2 0 obj<</Type/Pages/Count 1/Kids[3 0 R]>>endobj 3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Contents 4 0 R>>endobj 4 0 obj<</Length 11>>stream\nBT /F1 12 Tf 72 712 Td (Hello World)Tj ET\nendstream\nendobj\nxref\n0 5\n0000000000 65535 f\n0000000009 00000 n\n0000000055 00000 n\n0000000109 00000 n\n0000000171 00000 n\ntrailer<</Size 5/Root 1 0 R>>startxref\n200\n%%EOF') # The recommended way to call ocrmypdf.ocr() is to construct an OcrOptions object. # This provides type hints and validation. (v17.0.0+) options = OcrOptions( input_file='input.pdf', output_file='output_ocr.pdf', deskew=True, languages=['eng'], # Example: use environment variable for Tesseract path if needed for CI/local testing # tesseract_path=os.environ.get('TESSERACT_PATH', None) ) try: ocrmypdf.ocr(options) print("OCR processing complete. Output saved to output_ocr.pdf") except ocrmypdf.exceptions.BadArgs as e: print(f"Error with OCRmyPDF arguments: {e}") except ocrmypdf.exceptions.InputFileError as e: print(f"Error with input file: {e}") except Exception as e: print(f"An unexpected error occurred: {e}") finally: # Clean up dummy files if os.path.exists('input.pdf'): os.remove('input.pdf') if os.path.exists('output_ocr.pdf'): os.remove('output_ocr.pdf')