https://www.linkedin.com/learning/level-up-advanced-python/html-to-markdown-converter

html2markdown.py

import re

# A closure to generate regex substitution functions
def conv_generator(html_pattern, md_replacement):
    """Generate a function that substitutes html_pattern with md_replacement"""
    html_pattern = re.compile(html_pattern)
    
    def sub_func(text):
        return html_pattern.sub(md_replacement, text)
    
    return sub_func

emphasis = conv_generator(r'<em>(.*?)</em>', r'*\1*')
paragraph = conv_generator(r'<p>(.*?)</p>', r'\1\n\n')
href = conv_generator(r'<a href="(.*?)">(.*?)</a>', r'[\2](\1)')
newline = conv_generator(r'\s+', ' ')

def html2markdown(html):
    '''Take in html text as input and return markdown'''
    result = newline(html)
    result = emphasis(result)
    result = paragraph(result)
    result = href(result)
    
    # remove any trailing newlines added by paragraphs
    result = result.strip() 
    
    return result