【百度云搜寻，搜各种材料:http://www.lqkweb.com】
【搜网盘，搜各种材料:http://www.swpan.cn】
elasticsearch(搜索引擎)提供了主动补全接口
官网阐明：https://www.elastic.co/guide/...
1、创立搜寻主动补全字段suggest
主动补全须要用到一个字段名称为suggest类型为Completion类型的一个字段
所以咱们须要用将后面的elasticsearch-dsl操作elasticsearch(搜索引擎)减少suggest类型为Completion
留神：因为elasticsearch-dsl源码问题，设置字段为Completion类型指定分词器时会报错，所以咱们须要重写CustomAnalyzer类
只有Completion类型才是，其余类型不必，其余类型间接指定分词器即可
#!/usr/bin/env pythonfrom datetime import datetimefrom elasticsearch_dsl import DocType, Date, Nested, Boolean, \ analyzer, InnerObjectWrapper, Completion, Keyword, Text, Integer# 更多字段类型见第三百六十四节elasticsearch(搜索引擎)的mapping映射治理from elasticsearch_dsl.analysis import CustomAnalyzer as _CustomAnalyzer #导入CustomAnalyzer类from elasticsearch_dsl.connections import connections # 导入连贯elasticsearch(搜索引擎)服务器办法connections.create_connection(hosts=['127.0.0.1'])class CustomAnalyzer(_CustomAnalyzer): # 自定义CustomAnalyzer类，来重写CustomAnalyzer类 def get_analysis_definition(self): return {}ik_analyzer = CustomAnalyzer("ik_max_word", filter=["lowercase"]) # 实例化重写的CustomAnalyzer类传入分词器和大小写转，将大写转换成小写class lagouType(DocType): # 自定义一个类来继承DocType类 suggest = Completion(analyzer=ik_analyzer) # Text类型须要分词，所以须要晓得中文分词器，ik_max_wordwei为中文分词器 title = Text(analyzer="ik_max_word") # 设置，字段名称=字段类型，Text为字符串类型并且能够分词建设倒排索引 description = Text(analyzer="ik_max_word") keywords = Text(analyzer="ik_max_word") url = Keyword() # 设置，字段名称=字段类型，Keyword为一般字符串类型，不分词 riqi = Date() # 设置，字段名称=字段类型，Date日期类型 class Meta: # Meta是固定写法 index = "lagou" # 设置索引名称(相当于数据库名称) doc_type = 'biao' # 设置表名称if __name__ == "__main__": # 判断在本代码文件执行才执行外面的办法，其余页面调用的则不执行外面的办法 lagouType.init() # 生成elasticsearch(搜索引擎)的索引，表，字段等信息# 应用办法阐明：# 在要要操作elasticsearch(搜索引擎)的页面，导入此模块# lagou = lagouType() #实例化类# lagou.title = '值' #要写入字段=值# lagou.description = '值'# lagou.keywords = '值'# lagou.url = '值'# lagou.riqi = '值'# lagou.save() #将数据写入elasticsearch(搜索引擎)2、搜寻主动补全字段suggest写入数据
搜寻主动补全字段suggest接管的要搜寻的字段分词数据，详情见上面的自定义分词函数
elasticsearch-dsl操作elasticsearch(搜索引擎)
#!/usr/bin/env python# -*- coding:utf8 -*-#!/usr/bin/env pythonfrom datetime import datetimefrom elasticsearch_dsl import DocType, Date, Nested, Boolean, \ analyzer, InnerObjectWrapper, Completion, Keyword, Text, Integerfrom elasticsearch_dsl.connections import connections # 导入连贯elasticsearch(搜索引擎)服务器办法# 更多字段类型见第三百六十四节elasticsearch(搜索引擎)的mapping映射治理from elasticsearch_dsl.analysis import CustomAnalyzer as _CustomAnalyzer #导入CustomAnalyzer类connections.create_connection(hosts=['127.0.0.1'])class CustomAnalyzer(_CustomAnalyzer): # 自定义CustomAnalyzer类，来重写CustomAnalyzer类 def get_analysis_definition(self): return {}ik_analyzer = CustomAnalyzer("ik_max_word", filter=["lowercase"]) # 实例化重写的CustomAnalyzer类传入分词器和大小写转，将大写转换成小写class lagouType(DocType): # 自定义一个类来继承DocType类 suggest = Completion(analyzer=ik_analyzer) # Text类型须要分词，所以须要晓得中文分词器，ik_max_wordwei为中文分词器 title = Text(analyzer="ik_max_word") # 设置，字段名称=字段类型，Text为字符串类型并且能够分词建设倒排索引 description = Text(analyzer="ik_max_word") keywords = Text(analyzer="ik_max_word") url = Keyword() # 设置，字段名称=字段类型，Keyword为一般字符串类型，不分词 riqi = Date() # 设置，字段名称=字段类型，Date日期类型 class Meta: # Meta是固定写法 index = "lagou" # 设置索引名称(相当于数据库名称) doc_type = 'biao' # 设置表名称def gen_suggest(index, info_tuple): # 依据字符串生成搜寻倡议数组 """ 此函数次要用于,连贯elasticsearch(搜索引擎)，应用ik_max_word分词器，将传入的字符串进行分词，返回分词后的后果 此函数须要两个参数： 第一个参数：要调用elasticsearch(搜索引擎)分词的索引index，个别是（索引操作类._doc_type.index） 第二个参数：是一个元组，元祖的元素也是元组，元素元祖里有两个值一个是要分词的字符串，第二个是分词的权重，多个分词传多个元祖如下 书写格局： gen_suggest(lagouType._doc_type.index, (('字符串', 10),('字符串', 8))) """ es = connections.create_connection(lagouType._doc_type.using) # 连贯elasticsearch(搜索引擎)，应用操作搜索引擎的类上面的_doc_type.using连贯 used_words = set() suggests = [] for text, weight in info_tuple: if text: # 调用es的analyze接口分析字符串， words = es.indices.analyze(index=index, analyzer="ik_max_word", params={'filter':["lowercase"]}, body=text) anylyzed_words = set([r["token"] for r in words["tokens"] if len(r["token"])>1]) new_words = anylyzed_words - used_words else: new_words = set() if new_words: suggests.append({"input":list(new_words), "weight":weight}) # 返回分词后的列表，外面是字典， # 如：[{'input': ['录音', '广告'], 'weight': 10}, {'input': ['新能源', '汽车',], 'weight': 8}] return suggestsif __name__ == "__main__": # 判断在本代码文件执行才执行外面的办法，其余页面调用的则不执行外面的办法 lagouType.init() # 生成elasticsearch(搜索引擎)的索引，表，字段等信息# 应用办法阐明：# 在要要操作elasticsearch(搜索引擎)的页面，导入此模块# lagou = lagouType() #实例化类# lagou.title = '值' #要写入字段=值# lagou.description = '值'# lagou.keywords = '值'# lagou.url = '值'# lagou.riqi = '值'# lagou.save() #将数据写入elasticsearch(搜索引擎)suggest字段写入数据
# -*- coding: utf-8 -*-# Define here the models for your scraped items## See documentation in:# http://doc.scrapy.org/en/latest/topics/items.html# items.py,文件是专门用于，接管爬虫获取到的数据信息的，就相当于是容器文件import scrapyfrom scrapy.loader.processors import MapCompose, TakeFirstfrom scrapy.loader import ItemLoader # 导入ItemLoader类也就加载items容器类填充数据from adc.models.elasticsearch_orm import lagouType, gen_suggest # 导入elasticsearch操作模块class LagouItemLoader(ItemLoader): # 自定义Loader继承ItemLoader类，在爬虫页面调用这个类填充数据到Item类 default_output_processor = TakeFirst() # 默认利用ItemLoader类，加载items容器类填充数据，是列表类型，能够通过TakeFirst()办法，获取到列表里的内容def tianjia(value): # 自定义数据预处理函数 return value # 将解决后的数据返给Itemclass LagouItem(scrapy.Item): # 设置爬虫获取到的信息容器类 title = scrapy.Field( # 接管爬虫获取到的title信息 input_processor=MapCompose(tianjia), # 将数据预处理函数名称传入MapCompose办法里解决，数据预处理函数的形式参数value会主动接管字段title ) description = scrapy.Field() keywords = scrapy.Field() url = scrapy.Field() riqi = scrapy.Field() def save_to_es(self): lagou = lagouType() # 实例化elasticsearch(搜索引擎对象) lagou.title = self['title'] # 字段名称=值 lagou.description = self['description'] lagou.keywords = self['keywords'] lagou.url = self['url'] lagou.riqi = self['riqi'] # 将title和keywords数据传入分词函数，进行分词组合后返回写入搜寻倡议字段suggest lagou.suggest = gen_suggest(lagouType._doc_type.index, ((lagou.title, 10),(lagou.keywords, 8))) lagou.save() # 将数据写入elasticsearch(搜索引擎对象) return写入elasticsearch(搜索引擎)后的状况
{ "_index": "lagou", "_type": "biao", "_id": "AV5MDu0NXJs9MkF5tFxW", "_version": 1, "_score": 1, "_source": { "title": "LED光催化灭蚊灯广告录音_广告录音网-火红广告录音_叫卖录音下载_语音广告制作", "keywords": "各类小商品,广告录音,叫卖录音,火红广告录音", "url": "http://www.luyin.org/post/2486.html", "suggest": [ { "input": [ "广告" , "火红" , "制作" , "叫卖" , "灭蚊灯" , "语音" , "下载" , "led" , "录音" , "灭蚊" , "光催化" , "催化" ], "weight": 10 } , { "input": [ "小商品" , "广告" , "各类" , "火红" , "叫卖" , "商品" , "小商" , "录音" ], "weight": 8 } ], "riqi": "2017-09-04T16:43:20", "description": "LED光催化灭蚊灯广告录音 是广告录音网-火红广告录音中一篇对于 各类小商品 的文章，欢迎您浏览和评论,业余叫卖录音-广告录音-语音广告制作" }}
用Django实现搜寻的主动补全性能阐明
1.将搜寻框绑定一个事件，每输出一个字触发这个事件，获取到输入框里的内容，用ajax将输出的词申请到Django的逻辑处理函数。
2.在逻辑处理函数里，将申请词用elasticsearch(搜索引擎)的fuzzy含糊查问，查问suggest字段里存在申请词的数据，将查问到的数据增加到主动补全
html代码：
<!DOCTYPE html ><html xmlns="http://www.w3.org/1999/xhtml">{#引入动态文件门路#}{% load staticfiles %}<head><meta http-equiv="X-UA-Compatible" content="IE=emulateIE7" /><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /><title>lcv-search 搜索引擎</title><link href="{% static 'css/style.css'%}" rel="stylesheet" type="text/css" /><link href="{% static 'css/index.css'%}" rel="stylesheet" type="text/css" /></head><body><div id="container"> <div id="bd"> <div id="main"> <h1 class="title"> <div class="logo large"></div> </h1> <div class="nav ue-clear"> <ul class="searchList"> <li class="searchItem current" data-type="article">文章</li> <li class="searchItem" data-type="question">问答</li> <li class="searchItem" data-type="job">职位</li> </ul> </div> <div class="inputArea"> {% csrf_token %} <input type="text" class="searchInput" /> <input type="button" class="searchButton" onclick="add_search()" /> <ul class="dataList"> <li>如何学好设计</li> <li>界面设计</li> <li>UI设计培训要多少钱</li> <li>设计师学习</li> <li>哪里有好的网站</li> </ul> </div> <div class="historyArea"> <p class="history"> <label>热门搜寻：</label> </p> <p class="history mysearch"> <label>我的搜寻：</label> <span class="all-search"> <a href="javascript:;">专一界面设计网站</a> <a href="javascript:;">用户体验</a> <a href="javascript:;">互联网</a> <a href="javascript:;">资费套餐</a> </span> </p> </div> </div><!-- End of main --> </div><!--End of bd--> <div class="foot"> <div class="wrap"> <div class="copyright">Copyright ©uimaker.com 版权所有 E-mail:admin@uimaker.com</div> </div> </div></div></body><script type="text/javascript" src="{% static 'js/jquery.js'%}"></script><script type="text/javascript" src="{% static 'js/global.js'%}"></script><script type="text/javascript"> var suggest_url = "/suggest/" var search_url = "/search/" $('.searchList').on('click', '.searchItem', function(){ $('.searchList .searchItem').removeClass('current'); $(this).addClass('current'); }); function removeByValue(arr, val) { for(var i=0; i<arr.length; i++) { if(arr[i] == val) { arr.splice(i, 1); break; } } } // 搜寻倡议 $(function(){ $('.searchInput').bind(' input propertychange ',function(){ var searchText = $(this).val(); var tmpHtml = "" $.ajax({ cache: false, type: 'get', dataType:'json', url:suggest_url+"?s="+searchText+"&s_type="+$(".searchItem.current").attr('data-type'), async: true, success: function(data) { for (var i=0;i<data.length;i++){ tmpHtml += '<li><a href="'+search_url+'?q='+data[i]+'">'+data[i]+'</a></li>' } $(".dataList").html("") $(".dataList").append(tmpHtml); if (data.length == 0){ $('.dataList').hide() }else { $('.dataList').show() } } }); } ); }) hideElement($('.dataList'), $('.searchInput'));</script><script> var searchArr; //定义一个search的，判断浏览器有无数据存储（搜寻历史） if(localStorage.search){ //如果有，转换成 数组的模式寄存到searchArr的数组里（localStorage以字符串的模式存储，所以要把它转换成数组的模式） searchArr= localStorage.search.split(",") }else{ //如果没有，则定义searchArr为一个空的数组 searchArr = []; } //把存储的数据显示进去作为搜寻历史 MapSearchArr(); function add_search(){ var val = $(".searchInput").val(); if (val.length>=2){ //点击搜寻按钮时，去重 KillRepeat(val); //去重后把数组存储到浏览器localStorage localStorage.search = searchArr; //而后再把搜寻内容显示进去 MapSearchArr(); } window.location.href=search_url+'?q='+val+"&s_type="+$(".searchItem.current").attr('data-type') } function MapSearchArr(){ var tmpHtml = ""; var arrLen = 0 if (searchArr.length >= 5){ arrLen = 5 }else { arrLen = searchArr.length } for (var i=0;i<arrLen;i++){ tmpHtml += '<a href="'+search_url+'?q='+searchArr[i]+'">'+searchArr[i]+'</a>' } $(".mysearch .all-search").html(tmpHtml); } //去重 function KillRepeat(val){ var kill = 0; for (var i=0;i<searchArr.length;i++){ if(val===searchArr[i]){ kill ++; } } if(kill<1){ searchArr.unshift(val); }else { removeByValue(searchArr, val) searchArr.unshift(val) } }</script></html>Django路由映射
"""pachong URL ConfigurationThe `urlpatterns` list routes URLs to views. For more information please see: https://docs.djangoproject.com/en/1.10/topics/http/urls/Examples:Function views 1. Add an import: from my_app import views 2. Add a URL to urlpatterns: url(r'^/pre>, views.home, name='home')Class-based views 1. Add an import: from other_app.views import Home 2. Add a URL to urlpatterns: url(r'^/pre>, Home.as_view(), name='home')Including another URLconf 1. Import the include() function: from django.conf.urls import url, include 2. Add a URL to urlpatterns: url(r'^blog/', include('blog.urls'))"""from django.conf.urls import urlfrom django.contrib import adminfrom app1 import viewsurlpatterns = [ url(r'^admin/', admin.site.urls), url(r'^/pre>, views.indexluoji), url(r'^index/', views.indexluoji), url(r'^suggest//pre>, views.suggestluoji,name="suggest"), # 搜寻字段补全申请]Django动态文件配置
# Static files (CSS, JavaScript, Images)# https://docs.djangoproject.com/en/1.10/howto/static-files/#配置动态文件前缀STATIC_URL = '/static/'#配置动态文件目录STATICFILES_DIRS = [ os.path.join(BASE_DIR, 'static')]备注：搜寻主动补全fuzzy查问
#搜寻主动补全fuzzy查问POST lagou/biao/_search?pretty{ "suggest":{ #字段名称 "my_suggest":{ #自定义变量 "text":"广告", #搜索词 "completion":{ "field":"suggest", #搜寻字段 "fuzzy":{ "fuzziness":1 #编辑间隔 } } } }, "_source":"title"}Django逻辑解决文件
from django.shortcuts import render# Create your views here.from django.shortcuts import render,HttpResponsefrom django.views.generic.base import Viewfrom app1.models import lagouType #导入操作elasticsearch(搜索引擎)类import jsondef indexluoji(request): print(request.method) # 获取用户申请的门路 return render(request, 'index.html')def suggestluoji(request): # 搜寻主动补全逻辑解决 key_words = request.GET.get('s', '') # 获取到申请词 re_datas = [] if key_words: s = lagouType.search() # 实例化elasticsearch(搜索引擎)类的search查问 s = s.suggest('my_suggest', key_words, completion={ "field": "suggest", "fuzzy": { "fuzziness": 2 }, "size": 5 }) suggestions = s.execute_suggest() for match in suggestions.my_suggest[0].options: source = match._source re_datas.append(source["title"]) return HttpResponse(json.dumps(re_datas), content_type="application/json")最终实现