nltk实现对英文短文本的名词抽取

import nltk
import re
import csv
from xlwt import *
#nltk.download('punkt')

#对句子进行词汇分割和正规化，有些情况如aren‘t需要分割为are和n’t；或者i‘m要分割为i和’m。
#tokens_1=nltk.word_tokenize('what your')
#print(tokens_1)
import nltk
lowersetence='I would not doubt to see an upgrade to Tropical Harvey as soon as we have a closed low via hurricane hunters... PTC 09L 5pm Adv. should have it'.lower()
text = nltk.word_tokenize(lowersetence)
sentence=nltk.pos_tag(text)
#grammar = "NP:{<JJ|NN|NNS.*><POS|IN.*><NN|NNS.*>}"
grammar = r"""
            NP:{<JJ|NN><POS|IN>?<NN>+}
            PP:{<NN|NNS|NNP|NNPS>}

            """
cp = nltk.RegexpParser(grammar) #生成规则
result = cp.parse(sentence) #进行分块

substring=[]
finalstring=''
for subtree in result.subtrees():
    if ((subtree.label() == 'NP')|(subtree.label()=='PP')):
        substring.append(subtree)
for each in substring:
    length=len(each)
    #for i in (0,length-1):
        #print(each[i])
    for i in range(0,length):
        finalstring+=each[i][0]+' '
    finalstring+=', '
output=''
output+=finalstring
print(output)