Whoosh：Python 的轻量级搜索工具

# -*- coding: utf-8 -*-
import os
from whoosh.index import create_in
from whoosh.fields import *
from jieba.analyse import ChineseAnalyzer
import JSON
# 创建schema, stored为True表示能够被检索
schema = Schema(title=TEXT(stored=True, analyzer=ChineseAnalyzer()),
 dynasty=ID(stored=True),
 poet=ID(stored=True),
 content=TEXT(stored=True, analyzer=ChineseAnalyzer())
 )

# 解析poem.csv文件
with open('poem.csv', 'r', encoding='utf-8') as f:
 texts = [_.strip().split(',') for _ in f.readlines() if len(_.strip().split(',')) == 4]
# 存储schema信息至indexdir目录
indexdir = 'indexdir/'
if not os.path.exists(indexdir):
 os.mkdir(indexdir)
ix = create_in(indexdir, schema)
# 按照schema定义信息，增加需要建立索引的文档
writer = ix.writer()
for i in range(1, len(texts)):
 title, dynasty, poet, content = texts[i]
 writer.add_document(title=title, dynasty=dynasty, poet=poet, content=content)
writer.commit()

# 创建一个检索器
searcher = ix.searcher()
# 检索content中出现'明月'的文档
results = searcher.find("content", "明月")
print('一共发现%d份文档。' % len(results))
for i in range(min(10, len(results))):
 print(json.dumps(results[i].fields(), ensure_ascii=False))

一共发现44份文档。
前10份文档如下：
{"content": "床前明月光，疑是地上霜。举头望明月，低头思故乡。", "dynasty": "唐代", "poet": "李白 ", "title": "静夜思"}
{"content": "边草，边草，边草尽来兵老。山南山北雪晴，千里万里月明。明月，明月，胡笳一声愁绝。", "dynasty": "唐代", "poet": "戴叔伦 ", "title": "调笑令·边草"}
{"content": "独坐幽篁里，弹琴复长啸。深林人不知，明月来相照。", "dynasty": "唐代", "poet": "王维 ", "title": "竹里馆"}
{"content": "汉江明月照归人，万里秋风一叶身。休把客衣轻浣濯，此中犹有帝京尘。", "dynasty": "明代", "poet": "边贡 ", "title": "重赠吴国宾"}
{"content": "秦时明月汉时关，万里长征人未还。但使龙城飞将在，不教胡马度阴山。", "dynasty": "唐代", "poet": "王昌龄 ", "title": "出塞二首·其一"}
{"content": "京口瓜洲一水间，钟山只隔数重山。春风又绿江南岸，明月何时照我还？", "dynasty": "宋代", "poet": "王安石 ", "title": "泊船瓜洲"}
{"content": "四顾山光接水光，凭栏十里芰荷香。清风明月无人管，并作南楼一味凉。", "dynasty": "宋代", "poet": "黄庭坚 ", "title": "鄂州南楼书事"}
{"content": "青山隐隐水迢迢，秋尽江南草未凋。二十四桥明月夜，玉人何处教吹箫？", "dynasty": "唐代", "poet": "杜牧 ", "title": "寄扬州韩绰判官"}
{"content": "露气寒光集，微阳下楚丘。猿啼洞庭树，人在木兰舟。广泽生明月，苍山夹乱流。云中君不见，竟夕自悲秋。", "dynasty": "唐代", "poet": "马戴 ", "title": "楚江怀古三首·其一"}
{"content": "海上生明月，天涯共此时。情人怨遥夜，竟夕起相思。灭烛怜光满，披衣觉露滋。不堪盈手赠，