html2docx

import os import tempfile from html2docx import Html2Docx # Example HTML content with basic structure and an external image html_content = """ <h1>Hello World!</h1> <p>This is a paragraph with some <strong>bold</strong> and <em>italic</em> text.</p> <ul> <li>List Item 1</li> <li>List Item 2</li> </ul> <p style="text-align: center;">A centered paragraph.</p> <img src="https://www.python.org/static/community_logos/python-logo-only.png" width="100px" alt="Python Logo"> """ # Initialize the parser new_parser = Html2Docx() # Parse the HTML and get a python-docx Document object docx = new_parser.parse_html_section(html_content) # Save the document to a temporary file with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as temp_file: docx.save(temp_file.name) print(f"Generated DOCX saved to: {temp_file.name}") # To view the file, uncomment the following line (might not work on all OSs) # os.startfile(temp_file.name) # On Windows # import subprocess; subprocess.call(['open', temp_file.name]) # On macOS # In a real application, you might want to clean up the temp file after use # os.remove(temp_file.name)