Convert html to docx
Dependencies: python-docx & bs4
pip install htmldocx
Add strings of html to an existing docx.Document object
from docx import Document
from htmldocx import HtmlToDocx
document = Document()
new_parser = HtmlToDocx()
# do stuff to document
html = '<h1>Hello world</h1>'
new_parser.add_html_to_document(html, document)
# do more stuff to document
document.save('your_file_name')
Convert files directly
from htmldocx import HtmlToDocx
new_parser = HtmlToDocx()
new_parser.parse_html_file(input_html_file_path, output_docx_file_path)
Convert files from a string
from htmldocx import HtmlToDocx
new_parser = HtmlToDocx()
docx = new_parser.parse_html_string(input_html_file_string)