search_engine.py 文件源码

def result_by_time(self, sentence):
        seg_list = jieba.lcut(sentence, cut_all=False)
        n, cleaned_dict = self.clean_list(seg_list)
        time_scores = {}
        for term in cleaned_dict.keys():
            r = self.fetch_from_db(term)
            if r is None:
                continue
            docs = r[2].split('\n')
            for doc in docs:
                docid, date_time, tf, ld = doc.split('\t')
                if docid in time_scores:
                    continue
                news_datetime = datetime.strptime(date_time, "%Y-%m-%d %H:%M:%S")
                now_datetime = datetime.now()
                td = now_datetime - news_datetime
                docid = int(docid)
                td = (timedelta.total_seconds(td) / 3600) # hour
                time_scores[docid] = td
        time_scores = sorted(time_scores.items(), key = operator.itemgetter(1))
        if len(time_scores) == 0:
            return 0, []
        else:
            return 1, time_scores