clean text from html tags

clean_html.py

import re

def cleanhtml(raw_html):
    
    #Some HTML texts can also contain entities that are not enclosed in brackets, such as '&nsbm'. If that is the case, then you might want to write the regex as
    CLEANR = re.compile('<.*?>|&([a-z0-9]+|#[0-9]{1,6}|#x[0-9a-f]{1,6});')

    # as per recommendation from @freylis, compile once only
    CLEANR = re.compile('<.*?>') 
    cleantext = re.sub(CLEANR, '', raw_html)
    return cleantext