1.依次安装以下包:
pip install django-haystack
pip install whoosh
pip install jieba
2.修改settings.py文件:
- 添加应用
INSTALLED_APPS = (
...
'haystack',
)
添加搜索引擎
HAYSTACK_CONNECTIONS = {
'default': {
'ENGINE': 'haystack.backends.whoosh_cn_backend.WhooshEngine',
'PATH': os.path.join(BASE_DIR, 'whoosh_index'),
}
}
#自动生成索引
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
3.在应用目录下建立search_indexes.py文件:
#!/usr/bin/env python
# coding=utf-8
from haystack import indexes
from .models import HeroInfo
class HeroInfoIndex(indexes.SearchIndex,indexes.Indexable):
text = indexes.CharField(document=True, use_template=True)
def get_model(self):
# 哪个表,这里查找英雄表
return HeroInfo
def index_queryset(self, using=None):
# 基于哪些数据进行检索
return self.get_model().objects.all()
4.在目录“templates/search/indexes/应用名称/”下创建“模型类名称_text.txt”文件,
(此例应用名称为:booktest,文本文件为:heroinfo_text.txt):
这里列出了要对哪些列的内容进行检索(注意字段是CharField类型的才可以)
# 我们在models.py中创建的HeroInfo,hname和hcontent是CharField类型
class HeroInfo(models.Model):
hname = models.CharField('名字',max_length=20)
hgender = models.BooleanField(default=True)
isDelete = models.BooleanField(default=False)
hcontent = models.CharField('英雄介绍',max_length=1000)
hbook = models.ForeignKey('BookInfo',verbose_name='所属图书',on_delete=models.CASCADE)
# /templates/search/indexes/booktest/heroinfo_text.txt
# heroinfo_text.txt中:
{{object.hname}}
{{object.hcontent}}
5.在目录“templates/search/”下建立检索的结果页面search.html:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>检索的结果页面</title>
</head>
<body>
搜索的关键词:{{query}}
{% if query %}
<h3>搜索结果如下:</h3>
{% if not page.object_list|length == 0 %}
<table border="1">
<tr>
<th width="50%">姓名</th>
<th width="50%">英雄介绍</th>
</tr>
{% for result in page.object_list %}
<tr>
<th width="50%"><a href="/search/{{ result.object.id }}/">{{ result.object.hname }}</a></th>
<th width="80%"><a href="/search/{{ result.object.id }}/">{{ result.object.hcontent }}</a></th>
</tr>
{% endfor %}
</table>
{{page}}
共{{page.object_list|length}}条数据
{% if page.has_previous or page.has_next %}
<div>
{% if page.has_previous %}<a href="?q={{ query }}&page={{ page.previous_page_number }}">{% endif %}« 上一页{% if page.has_previous %}</a>{% endif %}
|
{% if page.has_next %}<a href="?q={{ query }}&page={{ page.next_page_number }}">{% endif %}下一页 »{% if page.has_next %}</a>{% endif %}
</div>
{% endif %}
{% elif page.object_list|length == 0 %}
<p>啥也没找到啊</p>
{% endif %}
{% else %}
未输入关键词,请<a href="/search_index/">返回查询页</a>
{% endif %}
</body>
</html>
在目录“templates”下建立搜索输入内容界面search_index.html:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<form method='get' action="/search/" target="_blank">
<input type="text" name="q" placeholder="请输入至少两个字">
<input type="submit" value="查询">
</form>
</body>
</html>
6.设置视图views.py文件:
from django.shortcuts import render
from django.http import HttpResponse
from .models import *
# 搜索输入内容界面视图
def search_index(request):
return render(request,'search_index.html')
# 这个是点击查询结果后显示的页面
def search_result(request,id):
result = HeroInfo.objects.filter(pk=id)
li = []
for i in result:
li.append('英雄id:'+id)
li.append('<br>')
li.append('<br>')
li.append('英雄姓名:'+i.hname)
li.append('<br>')
li.append('<br>')
li.append('英雄介绍:'+i.hcontent)
li.append('<br>')
li.append('<br>')
li.append('<a href="/search_index/">返回查询首页</a>')
return HttpResponse(li)
7.建立ChineseAnalyzer.py文件:
- 保存在haystack的安装文件夹下,路径大致如“.....Lib/site-packages/haystack/backends”
# encoding: utf-8
import jieba
from whoosh.analysis import Tokenizer, Token
class ChineseTokenizer(Tokenizer):
def __call__(self, value, positions=False, chars=False,
keeporiginal=False, removestops=True,
start_pos=0, start_char=0, mode='', **kwargs):
t = Token(positions, chars, removestops=removestops, mode=mode,
**kwargs)
seglist = jieba.cut(value, cut_all=True)
for w in seglist:
t.original = t.text = w
t.boost = 1.0
if positions:
t.pos = start_pos + value.find(w)
if chars:
t.startchar = start_char + value.find(w)
t.endchar = start_char + value.find(w) + len(w)
yield t
def ChineseAnalyzer():
return ChineseTokenizer()
8.在以上目录里复制whoosh_backend.py文件,改名为whoosh_cn_backend.py:
先导入:from .ChineseAnalyzer import ChineseAnalyzer
然后查找
analyzer=StemmingAnalyzer()
改为
analyzer=ChineseAnalyzer()
9.生成索引:
- 初始化索引数据
python manage.py rebuild_index
10.启动服务:
python manage.py runserver