a python script to clean an input of html and return just text

clean_html.py

class ParseHTML(HTMLParser):
    def __init__(self):
        super().__init__()
        self.reset()
        self.strict = False
        self.convert_charrefs = True
        self.text = StringIO()

    def handle_data(self, d):
        self.text.write(d)

    def get_data(self):
        return self.text.getvalue()


def strip_tags(html):
    # convert entities to utf-8
    parser = HTMLParser()
    html = parser.unescape(html)

    s = ParseHTML()
    s.feed(html)
    return s.get_data()