rtfparse

import pathlib from rtfparse.parser import Rtf_Parser from rtfparse.renderers.de_encapsulate_html import De_encapsulate_HTML import os import tempfile # Create a dummy RTF file for demonstration # In a real scenario, you would read an existing RTF file. rtf_content = r"{\rtf1\ansi\deff0 This is some {\b bold} text and a line break.\par This is a new line.}" temp_rtf_file = pathlib.Path(tempfile.gettempdir()) / "dummy_example.rtf" temp_html_file = pathlib.Path(tempfile.gettempdir()) / "extracted_example.html" try: # Write dummy RTF content to a temporary file with open(temp_rtf_file, "w", encoding="ascii") as f: f.write(rtf_content) print(f"Created temporary RTF file: {temp_rtf_file}") # Programmatic usage: Parse the RTF file parser = Rtf_Parser(rtf_path=temp_rtf_file) parsed_document = parser.parse_file() # Render the parsed RTF to extract HTML content renderer = De_encapsulate_HTML() with open(temp_html_file, mode="w", encoding="utf-8") as html_file: renderer.render(parsed_document, html_file) print(f"RTF parsed and HTML extracted to: {temp_html_file}") # Display the extracted HTML content with open(temp_html_file, "r", encoding="utf-8") as f: print("\nExtracted HTML content:") print(f.read()) except Exception as e: print(f"An error occurred: {e}") finally: # Clean up temporary files if temp_rtf_file.exists(): os.remove(temp_rtf_file) print(f"Cleaned up {temp_rtf_file}") if temp_html_file.exists(): os.remove(temp_html_file) print(f"Cleaned up {temp_html_file}")