1.pom文件
<?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>2.2.5.RELEASE</version>
<relativePath/> <!-- lookup parent from repository -->
</parent>
<groupId>com.zxj</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>
<!--自定义ES依赖版本与本地ES服务端版本一致-->
<elasticsearch.version>7.6.1</elasticsearch.version>
</properties>
<dependencies>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.10.2</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.60</version>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-elasticsearch</artifactId>
</dependency>
<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>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-devtools</artifactId>
<scope>runtime</scope>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-configuration-processor</artifactId>
<optional>true</optional>
</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>
静态资源素材:链接:https://pan.baidu.com/s/1VOErtTAtikR9MZCSO4062w
提取码:two0
application.properties:
server.port=9090
#关闭thymeleaf缓存
spring.thymeleaf.cache=false
IndexController .java
package com.zxj.controller;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
/**
* @author zxj
* @date 2020/5/28 13:05
*/
@Controller
public class IndexController {
@GetMapping({"/", "/index"})
public String index(){
return "index";
}
}
ElasticSearchConfig.java
package com.zxj.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;
/**
* @author zxj
* @date 2020/5/28 11:10
*/
@Configuration
public class ElasticSearchConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient restHighLevelClient = new RestHighLevelClient(
RestClient.builder(
new HttpHost("localhost", 9200, "http")
)
);
return restHighLevelClient;
}
}
实体类Content.java
package com.zxj.bean;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
/**
* @author zxj
* @date 2020/5/28 13:35
*/
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
private String title;
private String img;
private String price;
}
Html页面解析工具类HtmlParseUtil.java
package com.zxj.utils;
import com.zxj.bean.Content;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
/**
* @author zxj
* @date 2020/5/28 13:27
*/
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
parseJD("java").forEach(System.out :: println);
}
public static List<Content> parseJD(String keyword) throws IOException {
String url = "https://search.jd.com/Search?keyword=" + keyword;
Document document = Jsoup.parse(new URL(url), 30000);
Element element = document.getElementById("J_goodsList");
Elements elements = element.getElementsByTag("li");
List<Content> list = new ArrayList<>();
for (Element el : elements) {
//注意,此处图片有的网站是懒加载的,src属性获取不到想要的图片
String img = el.getElementsByTag("img").eq(0).attr("src");
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
list.add(new Content(title, img, price));
}
return list;
}
}
package com.zxj.service;
import com.alibaba.fastjson.JSON;
import com.sun.org.apache.xpath.internal.operations.Bool;
import com.zxj.bean.Content;
import com.zxj.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.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.elasticsearch.search.fetch.subphase.highlight.Highlighter;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
/**
* @author zxj
* @date 2020/5/28 13:45
*/
@Service
public class ContentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
//1.解析数据放入es中
public Boolean parseContent(String keyword) throws IOException {
List<Content> contents = HtmlParseUtil.parseJD(keyword);
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.搜索
public List<Map<String, Object>> search(String keyword, Integer pageNo, Integer pageSize) throws IOException {
if(pageNo <= 1){
pageNo = 1;
}
SearchRequest searchRequest = new SearchRequest("jd_goods");
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//分页
sourceBuilder.from(pageNo);
sourceBuilder.size(pageSize);
sourceBuilder.query(QueryBuilders.termQuery("title", keyword));
sourceBuilder.timeout(new TimeValue(10, TimeUnit.SECONDS));
//高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false);//多个高亮显示
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
sourceBuilder.highlighter(highlightBuilder);
searchRequest.source(sourceBuilder);
SearchResponse response = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String, Object>> list = new ArrayList<>();
for (SearchHit hit : response.getHits().getHits()) {
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField title = highlightFields.get("title");
//原来不高亮的查询结果
Map<String, Object> sourceAsMap = hit.getSourceAsMap();
//解析出高亮字段,将原来不高亮的字段替换掉
if(null != title){
Text[] fragments = title.fragments();
String newTitle = "";
for (Text fragment : fragments) {
newTitle += fragment;
}
//替换
sourceAsMap.put("title", newTitle);
}
list.add(sourceAsMap);
}
return list;
}
}
package com.zxj.controller;
import com.zxj.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;
/**
* @author zxj
* @date 2020/5/28 13:45
*/
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parse(@PathVariable("keyword") String keyword) throws IOException {
return contentService.parseContent(keyword);
}
@GetMapping("/search/{keyword}/{pageNo}/{pageSize}")
public List<Map<String, Object>> search(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") Integer pageNo,
@PathVariable("pageSize") Integer pageSize) throws IOException {
return contentService.search(keyword, pageNo, pageSize);
}
}
<!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 type="submit" @click.prevent="searchKey" 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="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: 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>
<!--前端使用Vue实现前后端分离-->
<script th:src="@{/js/axios.min.js}"></script>
<script th:src="@{/js/vue.min.js}"></script>
<script>
new Vue({
el: '#app',
data: {
keyword: '', //搜索条件
results: [] //搜索结果
},
methods: {
searchKey(){
var keyword = this.keyword;
console.log(keyword);
axios.get("search/" + keyword + "/1/10").then(response => {
console.log(response)
this.results = response.data;
})
}
}
})
</script>
</body>
</html>
启动项目,访问http://localhost:9090/parse/hadoop,http://localhost:9090/parse/java 去京东搜索页面抓取关键字数据信息,存入ES中
访问http://localhost:9090/,输入关键字,查询出高亮结果