ElastSearch整合SpringBoot模仿京东商城实现关键字高亮显示
Posted 梦与光同行
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了ElastSearch整合SpringBoot模仿京东商城实现关键字高亮显示相关的知识，希望对你有一定的参考价值。
前提:下载Elasticsearch服务并开启,使用SpringBoot集成Elasticsearch客户端
用到的技术:Springboot+Vue+Thymeleaf+Elasticsearch
效果如下
接下来上代码(不分前后顺序)
页面跳转controller
package com.wyh.controller;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
/**
* @program: SpringBoot_ElasticSearch
* @description: index页面跳转controller
* @author: 魏一鹤
* @createDate: 2022-04-19 23:09
**/
@Controller
public class IndexController
@GetMapping("/","/index")
public String index()
return "index";
接口数据请求controller
package com.wyh.controller;
import com.wyh.service.JDContentService;
import org.elasticsearch.client.RestHighLevelClient;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.PathVariable;
import org.springframework.web.bind.annotation.RestController;
import javax.annotation.Resource;
import java.io.IOException;
import java.util.List;
import java.util.Map;
/**
* @program: SpringBoot_ElasticSearch_JD
* @description: 京东商品控制器
* @author: 魏一鹤
* @createDate: 2022-04-20 00:48
**/
//前端请求编写
@RestController
public class JDContentController
@Autowired
private JDContentService jdContentService;
//测试es批量添加京东数据 restful风格
@GetMapping("/parse/keyword")
public boolean parse(@PathVariable("keyword") String keyword) throws IOException
return jdContentService.parseContent(keyword);
//测试查询
@GetMapping("/search/keyword/pageNo/pageSize")
public List<Map<String,Object>> search(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") int pageNo,
@PathVariable("pageSize")int pageSize) throws IOException
return jdContentService.searchPageHighLight(keyword,pageNo,pageSize);
京东商品实体
package com.wyh.entity;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import org.springframework.stereotype.Component;
/**
* @program: SpringBoot_ElasticSearch_JD
* @description: JD内容实体
* @author: 魏一鹤
* @createDate: 2022-04-20 00:37
**/
@Data
@AllArgsConstructor
@NoArgsConstructor
@Component
public class JDContent
private String title;
private String img;
private String price;
//可以自定义继续加属性
京东商品service
package com.wyh.service;
import com.alibaba.fastjson.JSON;
import com.wyh.entity.JDContent;
import com.wyh.utils.htmlParseUtil;
import org.elasticsearch.action.bulk.BulkRequest;
import org.elasticsearch.action.bulk.BulkResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.text.Text;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.common.xcontent.XContentType;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.index.query.TermQueryBuilder;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.search.fetch.subphase.highlight.HighlightBuilder;
import org.elasticsearch.search.fetch.subphase.highlight.HighlightField;
import org.springframework.stereotype.Service;
import javax.annotation.Resource;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
/**
* @program: SpringBoot_ElasticSearch_JD
* @description: 京东商品服务接口
* @author: 魏一鹤
* @createDate: 2022-04-20 00:47
**/
//业务编写
@Service
public class JDContentService
//注入bean
@Resource
private RestHighLevelClient client;
//1 解析数据 放入es索引库
public boolean parseContent(String keywords) throws IOException
ArrayList<JDContent> jdContents = new HtmlParseUtil().parseJD(keywords);
//把查询并且解析好的数据批量插入到es库
BulkRequest bulkRequest = new BulkRequest();
//过期时间2分钟
bulkRequest.timeout("2m");
//批量插入数据
for (int i = 0; i < jdContents.size(); i++)
bulkRequest.add(new IndexRequest("jd_goods")
//这里就不给id赋值了 随时生成
.source(JSON.toJSONString(jdContents.get(i)),XContentType.JSON)
);
//执行批量插入请求
BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT);
//没有返回失败就是成功
return !bulk.isFragment();
//2 获取这些数据 实现搜索功能
public List<Map<String,Object>> searchPage(String keyword,int pageNo,int pageSize) throws IOException
//当前页数第一条
if(pageNo<=1)
pageNo=1;
//条件搜索
SearchRequest searchRequest = new SearchRequest("jd_goods");
//构建查询
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
//查询条件
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
//分页
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
//精准匹配关键字
SearchSourceBuilder query = searchSourceBuilder.query(termQueryBuilder);
//超时时间
searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
//执行搜索
searchRequest.source(searchSourceBuilder);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
//创建map 用于返回
ArrayList<Map<String,Object>> arrayList = new ArrayList();
//解析结果
for (SearchHit document : searchResponse.getHits().getHits())
arrayList.add(document.getSourceAsMap());
return arrayList;
//3 实现搜索高亮的功能
public List<Map<String,Object>> searchPageHighLight(String keyword,int pageNo,int pageSize) throws IOException
//当前页数第一条
if(pageNo<=1)
pageNo=1;
//条件搜索
SearchRequest searchRequest = new SearchRequest("jd_goods");
//构建查询
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
//查询条件
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
//分页
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
//精准匹配关键字
SearchSourceBuilder query = searchSourceBuilder.query(termQueryBuilder);
//超时时间
searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
//高亮显示
HighlightBuilder highlightBuilder = new HighlightBuilder();
//让标题高亮
highlightBuilder.field("title");
//高亮的前缀
highlightBuilder.preTags("<span style='color:red'>");
//高亮的后缀
highlightBuilder.postTags("</span>");
//关闭多个高亮
highlightBuilder.requireFieldMatch(false);
searchSourceBuilder.highlighter(highlightBuilder);
//执行搜索
searchRequest.source(searchSourceBuilder);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
//创建map 用于返回
ArrayList<Map<String,Object>> arrayList = new ArrayList();
//解析结果
for (SearchHit document : searchResponse.getHits().getHits())
//获取高亮的字段
Map<String, HighlightField> highlightFields = document.getHighlightFields();
HighlightField title = highlightFields.get("title");
//原来的结果
Map<String, Object> sourceAsMap = document.getSourceAsMap();
//解析高亮的字段,将原来的字段换成高亮的字段即可
//如果高亮字段存在
if(title!=null)
Text[] fragments = title.fragments();
//新标题
String newTitle="";
for (Text fragment : fragments)
newTitle+=fragment;
//高亮字段替换原来的字段内容即可
sourceAsMap.put("title",newTitle);
arrayList.add(sourceAsMap);
return arrayList;
解析页面工具包
package com.wyh.utils;
import com.wyh.entity.JDContent;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.stereotype.Component;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
/**
* @program: SpringBoot_ElasticSearch_JD
* @description: jsoup解析网页
* @author: 魏一鹤
* @createDate: 2022-04-19 23:53
**/
@Component
public class HtmlParseUtil
//public static void main(String[] args) throws IOException
// //ArrayList<JDContent> jdContents = parseJD("你好");
// //for (JDContent jdContent : jdContents)
// // System.out.println(jdContent);
// //
// 获取请求 前提需要联网
// //String url="https://search.jd.com/Search?keyword=java";
// 解析网页 jsoup返回的document对象就是浏览器document对象
// 所有在js中可以使用的方法,这里都能使用 比如document.getElementById()
// //Document document = Jsoup.parse(new URL(url), 30000);
// 获取我们想要的数据
// //Element element = document.getElementById("J_goodsList");
// //System.out.println(element.html());
// 获取全部的li元素
// //Elements elements = element.getElementsByTag("li");
// //System.out.println(elements);
// 获取元素中的内容
// //for (Element el : elements)
// // //图片
// // //为什么明明可以看到图片的src但是就是获取不到呢
// // //这里面用到一个懒加载机制 真正的图片是放在source-data-lazy-img(data-lazy-img)中的
// // String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
// // //价格
// // String price = el.getElementsByClass("p-price").eq(0).text();
// // //标题
// // String title = el.getElementsByClass("p-name").eq(0).text();
// // System.out.println("-------------------------------");
// // System.out.println(img);
// // System.out.println(price);
// // System.out.println(title);
// //
// //
//
//解析京东请求
public ArrayList<JDContent> parseJD(String keywords) throws IOException
//获取请求 前提需要联网
String url="https://search.jd.com/Search?keyword="+keywords;
//解析网页 jsoup返回的document对象就是浏览器document对象
//所有在js中可以使用的方法,这里都能使用 比如document.getElementById()
Document document = Jsoup.parse(new URL(url), 30000);
//获取我们想要的数据
Element element = document.getElementById("J_goodsList");
System.out.println(element.html());
//获取全部的li元素
Elements elements = element.getElementsByTag("li");
//京东实体对象集合
ArrayList<JDContent> jdContents = new ArrayList<>();
//获取元素中的内容
for (Element el : elements)
//图片
//为什么明明可以看到图片的src但是就是获取不到呢
//这里面用到一个懒加载机制 真正的图片是放在source-data-lazy-img(data-lazy-img)中的
String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
//价格
String price = el.getElementsByClass("p-price").eq(0).text();
//标题
String title = el.getElementsByClass("p-name").eq(0).text();
System.out.println("-------------------------------");
System.out.println(img);
System.out.println(price);
System.out.println(title);
//创建京东实体对象
JDContent jdContent = new JDContent();
jdContent.setImg(img);
jdContent.setTitle(title);
jdContent.setPrice(price);
//把全部属性放进集合里面
jdContents.add(jdContent);
return jdContents;
springboot整合系列
SpringBoot系列八：SpringBoot整合消息服务（SpringBoot 整合 ActiveMQSpringBoot 整合 RabbitMQSpringBoot 整合 Kafka）
[SpringBoot系列]SpringBoot如何整合SSMP