postcards_chuck_norris.py 文件源码

def _find_nouns(self, sentence):
        tokens = nltk.word_tokenize(sentence)
        tagged = nltk.pos_tag(tokens)
        nouns = [word for word, pos in tagged \
                 if (pos == 'NN' or pos == 'NNP' or pos == 'NNS' or pos == 'NNPS')]

        filter_keywords = ['chuck', 'norris', 'quot']
        filtered = [i for i in nouns if not any(f in i.lower() for f in filter_keywords)]
        return filtered