# encoding=utf-8
import json
import jieba
from sys import argv
from collections import defaultdict
path = argv[1]
objs = map(lambda s: json.loads(s), open(path).readlines())
res = defaultdict(list)
for idx, obj in enumerate(objs):
for word in set(jieba.cut_for_search(obj['title'])):
res[word].append(idx)
while True:
try:
key = raw_input('请输入查询关键词:').decode('utf-8')
for x in map(lambda i: '%d:%s' % (i, objs[i]['title']), res.get(key, [])):
print x
except:
pass
jieba分词python建立倒排索引
最新推荐文章于 2023-05-07 15:48:03 发布