空闲时间实现了一个ES搜索demo(数据是用爬虫京东的数据)
前端thymeleaf+vue
项目结构如图:
(源码地址:https://gitee.com/zhu_can_admin/elaticsearch.git)
pom文件(注意es版本必须跟你本地版本一致,springboot版本3以上)
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-parent</artifactId>
<version>2.3.5.RELEASE</version>
<relativePath/> <!-- lookup parent from repository -->
</parent>
<groupId>com.example</groupId>
<artifactId>es-jd</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>es-jd</name>
<description>Demo project for Spring Boot</description>
<properties>
<java.version>1.8</java.version>
<elasticsearch.version>7.6.2</elasticsearch.version>
</properties>
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-thymeleaf</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<!--es客户端-->
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>elasticsearch-rest-high-level-client</artifactId>
<version>7.6.2</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.66</version>
</dependency>
<!--解析网页jsoup-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.10.2</version>
</dependency>
<!--springboot的elasticsearch服务-->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-elasticsearch</artifactId>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-test</artifactId>
<scope>test</scope>
<exclusions>
<exclusion>
<groupId>org.junit.vintage</groupId>
<artifactId>junit-vintage-engine</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-maven-plugin</artifactId>
</plugin>
</plugins>
</build>
</project>
yml文件
server:
port: 9090
spring:
thymeleaf:
cache: false
config
@Configuration
public class ElasticSearchClientConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(new HttpHost("127.0.0.1",9200,"http"))
);
return client;
}
}
utils
@Component
public class HtmlParesUtil {
public List<Content> paresJD(String keywords)throws Exception {
String url = "https://search.jd.com/Search?keyword="+keywords;
Document document = Jsoup.parse(new URL(url), 30000);
Element element = document.getElementById("J_goodsList");
Elements elements = element.getElementsByTag("li");
ArrayList<Content> goodList = new ArrayList<>();
elements.stream().forEach(item->{
String img = item.getElementsByTag("img").eq(0).attr("data-lazy-img");
String price = item.getElementsByClass("p-price").eq(0).text();
String title = item.getElementsByClass("p-name").eq(0).text();
Content content = new Content(title, img, price);
goodList.add(content);
});
return goodList;
}
public static void main(String[] args) throws Exception {
new HtmlParesUtil().paresJD("java").forEach(System.out::println);
}
}
entity
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
private String title;
private String img;
private String price;
}
service
@Service
public class ContentService {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient client;
//将京东商城爬到的数据存到es
public Boolean parseContent(String keywords) throws Exception {
List<Content> contents = new HtmlParesUtil().paresJD(keywords);
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("2m");
for (int i = 0; i < contents.size(); i++) {
bulkRequest.add(new IndexRequest("jd_goods").source(JSONObject.toJSONString(contents.get(i)), XContentType.JSON));
}
BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
//精确搜索
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 sourceBuilder = new SearchSourceBuilder();
//分页
sourceBuilder.from(pageNo);
sourceBuilder.size(pageSize);
//精准匹配
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
sourceBuilder.query(termQueryBuilder);
sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
//执行搜索
searchRequest.source(sourceBuilder);
SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT);
//返回结果
ArrayList<Map<String,Object>> list = new ArrayList<>();
for (SearchHit hit : search.getHits().getHits()) {
list.add(hit.getSourceAsMap());
}
return list;
}
//高亮搜索
public List<Map<String,Object>> searchHighPage(String keyword,int pageNo,int pageSize) throws IOException {
if (pageNo <= 1) {
pageNo = 1;
}
//条件搜索
SearchRequest searchRequest = new SearchRequest("jd_goods");
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//分页
sourceBuilder.from(pageNo);
sourceBuilder.size(pageSize);
//高亮搜索
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false);// tltie字段里面相同的字段出现多个高亮 关闭
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
sourceBuilder.highlighter(highlightBuilder);
//精准匹配
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
sourceBuilder.query(termQueryBuilder);
sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
//执行搜索
searchRequest.source(sourceBuilder);
SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT);
//返回结果
ArrayList<Map<String, Object>> list = new ArrayList<>();
for (SearchHit hit : search.getHits().getHits()) {
//高亮部分
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = hit.getSourceAsMap(); //搜索结果
if (title != null) {
Text[] fragments = title.fragments();
String newTitle = "";
for (Text fragment : fragments) {
newTitle += fragment;
}
//高亮字段替换原来字段
sourceAsMap.put("title", newTitle);
}
list.add(sourceAsMap);
}
return list;
}
}
controller
@Controller
public class IndexController {
@GetMapping({"/","/index"})
public String index(){
return "index";
}
}
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parse(@PathVariable("keyword")String keyword) throws Exception {
return contentService.parseContent(keyword);
}
@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.searchHighPage(keyword,pageNo,pageSize);
}
}
在es新建索引jd_goods
测试一下结果
@SpringBootTest(classes = EsJdApplication.class)
class EsJdApplicationTests {
@Autowired
private ContentService contentService;
//通过爬虫将数据爬到es数据库
@Test
void contextLoads() throws Exception {
contentService.parseContent("java");
}
//高亮查询
@Test
void contextLoads2() throws Exception {
List<Map<String, Object>> java = contentService.searchHighPage("java", 1, 20);
for (Map<String, Object> stringObjectMap : java) {
System.out.println(stringObjectMap);
}
}
}
结合前端
<!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 type="text" v-model="keyword" autocomplete="off" value="dd" id="mq"
class="s-combobox-input" aria-haspopup="true">
</div>
</div>
<button type="submit" @click.prevent="searchKey" id="searchbtn">搜索</button>
</div>
</fieldset>
</form>
<ul class="relKeyTop">
<li><a>Java</a></li>
<li><a>前端</a></li>
<li><a>Linux</a></li>
<li><a>大数据</a></li>
<li><a>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="result in results">
<div class="product-iWrap">
<!--商品封面-->
<div class="productImg-wrap">
<a class="productImg">
<img :src="result.img">
</a>
</div>
<!--价格-->
<p class="productPrice">
<em>{{result.price}}</em>
</p>
<!--标题-->
<p class="productTitle">
<a v-html="result.title"> </a>
</p>
<!-- 店铺名 -->
<div class="productShop">
<span>店铺: ES_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/axios.min.js}"></script>
<script th:src="@{/js/vue.min.js}"></script>
<script>
new Vue({
el: '#app',
data:{
keyword:'',
results:[]
},
methods:{
searchKey(){
var keyword = this.keyword;
axios.get('search/'+keyword+"/1/10").then(response=>{
console.log(response.data);
this.results = response.data;
})
}
}
})
</script>
</body>
</html>