Clean HTML

clean_html.py

def clean_html(html):
    """ Remove HTML markup from the given string. """
    # remove inline JavaScript / CSS
    x = re.sub(r'(?is)<(script|style).*?>.*?(</\1>)', '', html.strip())
    # remove html comments. must be done before removing regular tags since comments can contain '>' characters.
    x = re.sub(r'(?s)<!--(.*?)-->[\n]?', '', x)
    # remove the remaining tags
    x = re.sub(r'(?s)<.*?>', ' ', x)                                                                                                          
    # remove html entities
    x = remove_entities(x)
    # clean up whitespace
    x = re.sub(r'[ ]+', ' ', x)
    return x