utility method to strip html tags and entities

strip_html.py

import re

from django.utils.html import strip_tags

def strip_html_tags(text, strip_entities=True):
    """
    Args:
        text (str): text having html tags
        strip_entities (bool): If set to True html entities are also stripped

    Returns (str): Text without any html tags and entities
    """
    text = strip_tags(text)
    if strip_entities:
        text = re.sub(r'&([a-zA-Z]{4,5}|#[0-9]{2,4});', '', text)
    return text