longest_word.py

from nltk.tokenize import RegexpTokenizer
tokenizer = RegexpTokenizer(r'\w+')
tokens = tokenizer.tokenize(text)
tokens = [i.lower() for i in tokens]

## Uncomment and remove the ")" to get length of longest word
print("Longest word in text: " + max(tokens, key=len) )# + " is " + str(len(max(tokens, key=len))) + " characters long")

## Longest real word
tokens = [y for y in tokens if y != "cutterigsloop"]
print("Longest real word in text: " + max(tokens, key=len) + " is " + str(len(max(tokens, key=len))) + " characters long")