ElasticSearch(三)实战操作
1、项目结果
从网页中爬取title、price、img,然后存储到es中,并进行搜索vue渲染出来。
2、创建项目
1、创建SpringBoot项目
将es版本修改成我们自己对应的版本号:
<elasticsearch.version>7.6.1</elasticsearch.version>
在application.properties配置文件中添加:
server.port=8888
spring.thymeleaf.cache=false
下载前端,部署到我们的项目resources下,
我的gitee仓库地址:https://gitee.com/he-ze__-an/elastic-search
添加依赖:
<!--解析网页jsoup-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.13.1</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>2.0.19</version>
</dependency>
编写配置,创建config包,编写ElasticSearchClientConfig.java,连接我们的es
package com.heze.config;
import org.apache.http.HttpHost;
import org.elasticsearch.client.RestClient;
import org.elasticsearch.client.RestHighLevelClient;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
//1.找对象
//2.放到spring中待用
@Configuration
public class ElasticSearchClientConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("127.0.0.1", 9200, "http")
)
);
return client;
}
}
3、爬虫
创建utils包,编写HtmlParseUtil.java,实现从网站获取资源:title,img,price
创建pojo包,编写Content.java,包含上面三个属性
package com.heze.utils;
import com.heze.pojo.Content;
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;
/**
* @author 何泽
* @version 1.0
*/
@Component
public class HtmlParseUtil {
public List<Content> parseJD(String keywords) throws IOException {
// 获取请求 https://search.jd.com/Search?keyword=java
String url = "https://search.jd.com/Search?keyword=" + keywords;
//解析网页 (Jsoup返回的Document就是浏览器Document对象)
Document document = Jsoup.parse(new URL(url), 30000);
// 所有你在js中可以使用的方法,这里都能用
Element elementById = document.getElementById("J_goodsList");
// 获取所有的li元素
Elements elements = elementById.getElementsByTag("li");
ArrayList<Content> goodsList = new ArrayList<>();
// 获取元素中的内容
for (Element el : elements) {
String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
Content content = new Content();
content.setImg(img);
content.setPrice(price);
content.setTitle(title);
goodsList.add(content);
}
return goodsList;
}
}
得到结果:
4、存放入es中,以及从中搜索出来
创建service文件夹,创建ContentService.java,下面调用我们注入的restHighLevelClient,实现搜索,高亮
package com.heze.service;
import com.alibaba.fastjson.JSON;
import com.heze.pojo.Content;
import com.heze.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.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import javax.naming.directory.SearchResult;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
@Service
public class ContentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
// 1.解析数据放在 es 索引中
public Boolean parseContent(String keywords) throws IOException {
List<Content> contents = new HtmlParseUtil().parseJD(keywords);
// 把查询的数据放入 es 中
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("2m");
for (int i = 0; i < contents.size(); i++) {
bulkRequest.add(new IndexRequest("jd_goods")
.source(JSON.toJSONString(contents.get(i)), XContentType.JSON)
);
}
BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
// 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 {
if (pageNo <= 1){
pageNo = 1;
}
//条件搜索
SearchRequest searchRequest = new SearchRequest("jd_goods");
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
// 分页
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
// 高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false); //关闭多个高亮
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
searchSourceBuilder.highlighter(highlightBuilder);
// 精准匹配
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
searchSourceBuilder.query(termQueryBuilder);
searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
// 执行搜索
searchRequest.source(searchSourceBuilder);
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
// 解析结果
ArrayList<Map<String, Object>> list = new ArrayList<>();
for (SearchHit documentFields : searchResponse.getHits().getHits()) {
Map<String, HighlightField> highlightFields = documentFields.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = documentFields.getSourceAsMap();
// 解析高亮的字段
if (title != null){
Text[] fragments = title.fragments();
String name = "";
for (Text text : fragments) {
name += text;
}
sourceAsMap.put("title", name); // 高亮字段替换掉原来的内容即可
}
list.add(sourceAsMap);
}
return list;
}
}
5、使用vue进行渲染
到前端看一下搜索情况:
创建controller包,编写ContentController.java,实现搜索显示结果:
package com.heze.controller;
import com.heze.service.ContentService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.PathVariable;
import org.springframework.web.bind.annotation.RestController;
import java.io.IOException;
import java.util.List;
import java.util.Map;
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keywords}")
public Boolean parse(@PathVariable("keywords") String keywords) throws IOException {
return contentService.parseContent(keywords);
}
@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 contentService.searchPage(keyword, pageNo, pageSize);
}
}
在随便一个文件中创建vue项目,npm install vue
| npm install axios
然后将axios.min.js文件和vue.min.js放在项目resources文件下,做前后端分离
在页面中添加异步访问,实现渲染数据
<!DOCTYPE html>
<html xmlns:th="http://www.thymeleaf.org">
<head>
<meta charset="utf-8"/>
<title>狂神说Java-ES仿京东实战</title>
<link rel="stylesheet" th:href="@{/css/style.css}"/>
</head>
<body class="pg">
<div class="page" id="app">
<div id="mallPage" class=" mallist tmall- page-not-market ">
<!-- 头部搜索 -->
<div id="header" class=" header-list-app">
<div class="headerLayout">
<div class="headerCon ">
<!-- Logo-->
<h1 id="mallLogo">
<img th:src="@{/images/jdlogo.png}" alt="">
</h1>
<div class="header-extra">
<!--搜索-->
<div id="mallSearch" class="mall-search">
<form name="searchTop" class="mallSearch-form clearfix">
<fieldset>
<legend>天猫搜索</legend>
<div class="mallSearch-input clearfix">
<div class="s-combobox" id="s-combobox-685">
<div class="s-combobox-input-wrap">
<input v-model="keyword" type="text" autocomplete="off" value="dd" id="mq"
class="s-combobox-input" aria-haspopup="true">
</div>
</div>
<button @click.prevent="searchPage" type="submit" id="searchbtn">搜索</button>
</div>
</fieldset>
</form>
<ul class="relKeyTop">
<li><a>狂神说Java</a></li>
<li><a>狂神说前端</a></li>
<li><a>狂神说Linux</a></li>
<li><a>狂神说大数据</a></li>
<li><a>狂神聊理财</a></li>
</ul>
</div>
</div>
</div>
</div>
</div>
<!-- 商品详情页面 -->
<div id="content">
<div class="main">
<!-- 品牌分类 -->
<form class="navAttrsForm">
<div class="attrs j_NavAttrs" style="display:block">
<div class="brandAttr j_nav_brand">
<div class="j_Brand attr">
<div class="attrKey">
品牌
</div>
<div class="attrValues">
<ul class="av-collapse row-2">
<li><a href="#"> 狂神说 </a></li>
<li><a href="#"> Java </a></li>
</ul>
</div>
</div>
</div>
</div>
</form>
<!-- 排序规则 -->
<div class="filter clearfix">
<a class="fSort fSort-cur">综合<i class="f-ico-arrow-d"></i></a>
<a class="fSort">人气<i class="f-ico-arrow-d"></i></a>
<a class="fSort">新品<i class="f-ico-arrow-d"></i></a>
<a class="fSort">销量<i class="f-ico-arrow-d"></i></a>
<a class="fSort">价格<i class="f-ico-triangle-mt"></i><i class="f-ico-triangle-mb"></i></a>
</div>
<!-- 商品详情 -->
<div class="view grid-nosku">
<div class="product" v-for="item in results">
<div class="product-iWrap">
<!--商品封面-->
<div class="productImg-wrap">
<a class="productImg">
<img :src="item.img">
</a>
</div>
<!--价格-->
<p class="productPrice">
<em>{
{
item.price}}</em>
</p>
<!--标题-->
<p class="productTitle">
<a v-html="item.title"></a>
</p>
<!-- 店铺名 -->
<div class="productShop">
<span>店铺: 狂神说Java </span>
</div>
<!-- 成交信息 -->
<p class="productStatus">
<span>月成交<em>999笔</em></span>
<span>评价 <a>3</a></span>
</p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<script th:src="@{/js/vue.min.js}"></script>
<script th:src="@{/js/axios.min.js}"></script>
<script>
new Vue({
el:'#app',
data:{
keyword:'', //搜索关键字
results:[], //搜索结果
},
methods:{
searchPage(){
var keyword = this.keyword;
console.log(keyword)
axios.get("/search/"+keyword+"/1/10").then(res=>{
console.log(res.data)
this.results = res.data;
})
}
}
})
</script>
</body>
</html>
得到结果:
总结:就是配置类连接es,从网站扒下三个数据然后存入es,再然后从es中search数据,通过vue渲染出来即可。可以将es当成一个索引库(或者叫数据库),存放内容,然后我们从中获取,crud中的内容,实现我们的搜索功能,暂时还没有具体的感觉,但是理论上说,应该是比mysql这种数据库快很多。