import re def remove_html_tags(text): """Remove HTML tags from text""" clean = re.compile('<.*?>') return re.sub(clean, '', text) def remove_url(text): """Remove URLs from text""" return re.sub(r'http\S+|www.\S+', '', text) def remove_digits(text): """Remove digits from text""" return re.sub(r'\d+', '', text) def remove_punc(text): """Remove punctuation from text""" return re.sub(r'[^\w\s]', '', text) def lower(text): return str.lower(text)