1. import textract
  3. def strip_metadata(text):
  4. """
  5. Strips metadata from text blocks.
  7. Args:
  8. text (str): The text to strip metadata from.
  10. Returns:
  11. str: The text with metadata removed. Returns original text if an error occurs.
  12. """
  13. try:
  14. # Use textract to extract text, stripping metadata
  15. text = textract.process(text).decode('utf-8')
  16. return text
  17. except Exception as e:
  18. print(f"Error stripping metadata: {e}")
  19. return text # Return original text on error
  23. if __name__ == '__main__':
  24. # Example usage
  25. text_with_metadata = """
  26. This is a test document.
  27. Author: John Doe
  28. Date: 2023-10-27
  29. Title: Test Document
  30. """
  31. stripped_text = strip_metadata(text_with_metadata)
  32. print("Original text:\n", text_with_metadata)
  33. print("\nStripped text:\n", stripped_text)
  35. #Example with a file
  36. try:
  37. with open("test.pdf", "rb") as f:
  38. pdf_text = textract.process(f).decode('utf-8')
  39. stripped_pdf_text = strip_metadata(pdf_text)
  40. print("\nStripped PDF text:\n", stripped_pdf_text)
  41. except FileNotFoundError:
  42. print("test.pdf not found.")
  43. except Exception as e:
  44. print(f"Error processing PDF: {e}")

Add your comment