NLTK是NLP一个工具包，下面介绍具体用法
    1、分词、断句

    1. from nltk.tokenize import word_tokenize,sent_tokenize
    3. #分词
    4. sentence="Hello Mr. Smith, how are you doing today? "
    5. print(word_tokenize(sentence))
    6. #['Hello', 'Mr.', 'Smith', ',', 'how', 'are', 'you', 'doing', 'today', '?']
    8. #断句
    9. paragraph="Hello Mr. Smith, how are you doing today?\
    10. The weather is great, and Python is awesome.\
    11. The sky is pinkish-blue. You shouldn't eat cardboard."
    12. print(sent_tokenize(paragraph))
    13. #['Hello Mr. Smith, how are you doing today?', 
    14. #    'The weather is great, and Python is awesome.',
    15. #    'The sky is pinkish-blue.', "You shouldn't eat cardboard."]

    2、停用词

    1. from nltk.corpus import stopwords
    3. print(stopwords.words('english'))
    4. #['i', 'me', 'my', 'myself',......"won't", 'wouldn', "wouldn't"]