基于python + django + whoosh + jieba 分词器实现站内检索功能

pip install django-haystack
pip install whoosh
pip install jieba

pip install -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com   安装的库>

pip install -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com  django

pip install setuptools_scm

# django-admin startproject 项目名>
	django-admin startproject find

# python manage.py startapp APP名>
	python manage.py startapp searchshop

INSTALLED_APPS = [
	...
	'searchshop',
	...
]

class Shopp(models.Model):
    shop_name = models.TextField(max_length=200)
    shop_price = models.IntegerField(default=0)
    shop_dsc = models.CharField(max_length=200)

from .models import Shopp
admin.site.register(Shopp)

python manage.py makemigrations 
python manage.py migrate

 python manage.py createsuperuser

python manage.py runserver

INSTALLED_APPS = [
	...
	'haystack'
]

from haystack import indexes
from .models import Shopp # 之前创建的模型

# 修改此处，类名为模型类的名称+Index，比如模型类为GoodsInfo,则这里类名为GoodsInfoIndex(其实可以随便写)
class ArticlePostIndex(indexes.SearchIndex, indexes.Indexable):
    # text为索引字段
    # document = True，这代表haystack和搜索引擎将使用此字段的内容作为索引进行检索
    # use_template=True 指定根据表中的那些字段建立索引文件的说明放在一个文件中
    text = indexes.CharField(document=True, use_template=True)

    # 对那张表进行查询
    def get_model(self):  # 重载get_model方法，必须要有！
        # 返回这个model
        return Shopp

    # 建立索引的数据
    def index_queryset(self, using=None):
        # 这个方法返回什么内容，最终就会对那些方法建立索引，这里是对所有字段建立索引
        return self.get_model().objects.all()

python manage.py rebuild_index

from jieba.analyse import ChineseAnalyzer

 schema_fields[field_class.index_fieldname] = TEXT(
                    stored=True,
                    analyzer=StemmingAnalyzer(),
                    field_boost=field_class.boost,
                    sortable=True,
                )

schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=ChineseAnalyzer(),
                    field_boost=field_class.boost)

HAYSTACK_CONNECTIONS = {
    'default': {
        # 指定whoosh引擎 (之前创建的whoosh_cn_backend)
        'ENGINE': 'searchshop.whoosh_cn_backend.WhooshEngine',
        # 'ENGINE': 'jsapp.whoosh_cn_backend.WhooshEngine',      # whoosh_cn_backend是haystack的whoosh_backend.py改名的文件为了使用jieba分词
        # 索引文件路径
        'PATH': os.path.join(BASE_DIR, 'whoosh_index'),
    }
}
 # 添加此项，当数据库改变时，会自动更新索引，非常方便
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'

{{object.shop_name}}
{{object.shop_dsc}}
{{object.shop_price}}

{% load highlight %}
!DOCTYPE html>
html lang="en">
head>
    meta charset="UTF-8">
    title>商品列表/title>
    style>
        span.highlighted {
            color: red;
        }
    /style>
/head>
body>
    div class="search">
        form method="get" action="{% url 'shop:search' %}">
            input type="text" name="q" placeholder="a搜索商品">
            input type="submit" value="搜索">
        /form>
    /div>
    {% if shop_list and query %}
    ul>
        {% for question in shop_list %}
        li>
            {% highlight question.object.shop_name with query %}
            价格： {% highlight question.object.shop_price with query %}
            span class="post-author"> a> {% highlight question.object.shop_dsc with query %} /a>/span>
        /li>
        {% endfor %}
    /ul>
    {% else %}
    p>No polls are available./p>
    {% endif %}
/body>
/html>

from django.shortcuts import render
from django.http import HttpResponse
#Create your views here.
from .models import Shopp
from haystack.forms import  ModelSearchForm
from haystack.query import EmptySearchQuerySet
def index(request):
   shop_list = Shopp.objects.all()
   context = {
       'query': '',
       'shop_list': shop_list
   }
   return render(request, 'searchshop/index.html', context)

def search(request,  load_all=True, form_class=ModelSearchForm, searchqueryset=None):
   if request.GET.get('q'):
       form = form_class(request.GET, searchqueryset=searchqueryset, load_all=load_all)

       if form.is_valid():
           query = form.cleaned_data['q']
           results = form.search()
           context = {
               'query': query,
               'shop_list': results
           }
           return render(request, 'searchshop/index.html', context)
           # results = form.search()
       return HttpResponse(request.GET.get('q'))
   return HttpResponse('查询')

from . import views
app_name = 'shop'   # 重点是这一行
urlpatterns = [
   path('', views.index, name='index'),
   path('search', views.search, name='search'),
   #  path(r'search/$', views.search, name='search')
]

from django.urls import path, include

urlpatterns = [
   path('shop', include('searchshop.urls')),
   path('admin/', admin.site.urls),
]

python manage.py runserver