html-for-docx

from docx import Document from html4docx import HtmlToDocx from io import BytesIO # Example 1: Add HTML to an existing Document object and save document = Document() # Or load an existing .docx: Document('template.docx') parser = HtmlToDocx() html_string = '<h1>Hello world</h1><p>This is a <strong>paragraph</strong> with some <em>formatting</em>.</p>' parser.add_html_to_document(html_string, document) document.save('output.docx') print("Saved 'output.docx' with basic HTML content.") # Example 2: Convert an HTML string directly to a BytesIO object (in-memory) buffer = BytesIO() parser_in_memory = HtmlToDocx() html_string_2 = '<p style="color: blue;">This text is blue.</p>' parser_in_memory.add_html_to_document(html_string_2, buffer) # To read from the buffer again, reset its position buffer.seek(0) print(f"Generated DOCX in memory, size: {len(buffer.getvalue())} bytes.") # Example 3: Convert an HTML file directly # Create a dummy HTML file for demonstration with open('input.html', 'w', encoding='utf-8') as f: f.write('<h2>Content from file</h2><p>This was converted from an HTML file.</p>') file_parser = HtmlToDocx() file_parser.parse_html_file('input.html', 'output_from_file.docx') print("Saved 'output_from_file.docx' from 'input.html'.")