nltk.tokenize.punkt() 这个class能将text拆分成句子，但是会保留标点符号，比如括号之类的
import nltk.data
text =
'''
... Punkt knows that the periods in Mr. Smith and Johann S. Bach
... do not mark sentence boundaries. And sometimes sentences
... can start with non-capitalized words. i is a good variable
... name.
... '''
sent_detector = nltk.data.load(
'tokenizers/punkt/english.pickle')
print(
'\n-----\n'.join(sent_detector.tokenize(text.strip())))
'''
...Punkt knows that the periods in Mr. Smith and Johann S. Bach
do not mark sentence boundaries.
-----
'''
