def word_analysis(str): en = regexp_tokenize(str, "([A-Za-z]+),https") T = list(Text(en)) texts = remove_special_characters(str) noun = Hannanum().nouns(texts) noun.extend(T) print(noun) count = Counter(noun) noun_list = count.most_common(30) print(count) index = 0 count_ = [] for v in noun_list: if len(v[0]) >= 1: index = index + 1 count_.append(v) if index >= 10: break return count_