基于ElasticSearch的实战-仿京东搜素
1、创建springboot项目，添加相关依赖
2、导入相关Maven依赖
<?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>
<groupId>com.fu</groupId>
<artifactId>es-jd</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>es-jd</name>
<description>es-jd</description>
<properties>
<java.version>1.8</java.version>
<!--定义es版本依赖，保证和本地一致，我的本地es版本为7.6.2，
注意这里也要和SpringBoot版本对相应，不同的SpringBoot版本对应不同的es版本，否则会不兼容，已踩过坑！！！ -->
<elasticsearch.version>7.6.2</elasticsearch.version>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
<spring-boot.version>2.3.7.RELEASE</spring-boot.version>
</properties>
<dependencies>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.83</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>
<dependencyManagement>
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-dependencies</artifactId>
<version>${spring-boot.version}</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-maven-plugin</artifactId>
<version>2.3.7.RELEASE</version>
<configuration>
<mainClass>com.fu.EsJdApplication</mainClass>
</configuration>
<executions>
<execution>
<id>repackage</id>
<goals>
<goal>repackage</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
3、编写代码
package com.fu.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;
@Configuration
public class ElasticSearchClientConfig {
@Bean
public RestHighLevelClient restHighLevelClient() {
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("localhost", 9200, "http")));
return client;
}
}
package com.fu.controller;
import com.fu.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/{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.searchPage(keyword, pageNo, pageSize);
return contentService.searchPageHighlightBuilder(keyword, pageNo, pageSize);
}
}
package com.fu.controller;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
@Controller
public class IndexController {
@GetMapping({"/","/index"})
public String index(){
return "index";
}
}
package com.fu.service;
import com.alibaba.fastjson.JSON;
import com.fu.entity.Content;
import com.fu.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.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;
@Service
public class ContentService {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient Client;
// 1.解析数据放入 es索引中
public Boolean parseContent(String keywords) throws Exception {
List<Content> contents = new HtmlParseUtil().parseJD(keywords);
//把查询到的数据放入es索引库中
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("5m");
for (int i = 0; i < contents.size(); i++) {
bulkRequest.add(
new IndexRequest("jd_goods")
.source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
}
BulkResponse bulk = Client.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
// 2.获取这些数据实现搜索高亮功能
public List<Map<String, Object>> searchPageHighlightBuilder(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));
//高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false); //多个高亮显示
highlightBuilder.preTags("<span style='color:red'>");//设置前缀
highlightBuilder.postTags("</span>"); //设置后缀
sourceBuilder.highlighter(highlightBuilder);
//执行搜索
searchRequest.source(sourceBuilder);
SearchResponse searchResponse = Client.search(searchRequest, RequestOptions.DEFAULT);
//解析结果
ArrayList<Map<String, Object>> list = new ArrayList<>();
for (SearchHit hit : searchResponse.getHits().getHits()) {
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = hit.getSourceAsMap(); //原来的结果!
//解析高亮的字段，将原来的字段换为我们高亮的字段即可!
if (title != null) {
Text[] fragments = title.fragments();
String n_title = "";
for (Text text : fragments) {
n_title += text;
sourceAsMap.put("title", n_title); //高亮字段替换掉原来的内容即可!
}
list.add(sourceAsMap);
}
}
return list;
}
}
package com.fu.utils;
import com.fu.entity.Content;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
public class HtmlParseUtil {
public List<Content> parseJD(String keywords) throws Exception {
//获取请求 https://search.jd.com/Search?keyword=java
String url = "https://search.jd.com/Search?keyword="+keywords+"&enc=utf-8";
//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);
// System.out.println(document.html());
//获取商品列表
Element j_goodsList = document.getElementById("J_goodsList");
//获取所有的li元素
Elements elements = document.getElementsByTag("li");
//创建一个集合存储商品内容
List<Content> contents = new ArrayList<>();
//获取元素中的内容
for (Element el : elements ){
//由于图片是延迟加载
//date-lazy-img
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();
// String commit = el.getElementsByClass("p-commit").eq(0).text();
String commit = "10万+";
String shopnum = el.getElementsByClass("p-shop").eq(0).text();
contents.add(new Content(img,price,title,commit,shopnum));
}
return contents;
}
}
package com.fu.entity;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
private String img; //图片
private String price; //价格
private String title; //标题
private String commit; //评价数量
private String shopnum; //商品编号
}
