KeywordsHandler.py 文件源码

def extract_keyword(self):
        sents = []
        comm_list = self.dao.get_hotel_comments()
        # ???????????????
        for comm in comm_list:
            sents.extend(normal.get_sentences(comm[2]))
        print "length of sentences:%d"%len(sents)
        # ??????????
        pos_sents = []
        for sent in sents:
            pos_sents.append(pseg.cut(sent))
        print "length of pos_sents:%d"%len(pos_sents)
        # ?????,?????
        print "counting"
        noun_dict = {}
        for pos_sent in pos_sents:
            for key,type in pos_sent:
                if type == "n":
                    if key not in noun_dict:
                        noun_dict[key] = 1
                    else:
                        noun_dict[key] = noun_dict[key] + 1
        a = sorted(noun_dict.iteritems(),key=lambda asd:asd[1],reverse=True)
        return a