simple keywords nltk

simple_keywors.py

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

nltk.download('stopwords')
nltk.download('punkt')

punctuations = ['(',')',';',':','[',']',',']
stop_words = stopwords.words('portuguese')

tokens = set(word_tokenize(text_from_pdf.lower(), language='portuguese'))
token_keywords = [
      word.encode('ascii', 'ignore').decode('ascii') 
      for word in tokens if not word in stop_words and not word in punctuations
]
keywords = ' '.join(token_keywords)