springboot集成ElasticSearch笔记
https://www.elastic.co/cn/downloads/elasticsearch
elasticSearch官方下载
https://www.bilibili.com/video/BV17a4y1x7zq?p=12
借鉴狂神视频教学
https://www.elastic.co/guide/cn/index.html
https://www.elastic.co/guide/cn/elasticsearch/guide/current/index.html
官方文档地址
https://www.elastic.co/guide/en/elasticsearch/client/index.html
JAVA REST Client已过期
现在先用JAVA REST Client学习
导入依赖
<repositories>
<repository>
<id>es-snapshotsid>
<name>elasticsearch snapshot reponame>
<url>https://snapshots.elastic.co/maven/url>
repository>
repositories>
<dependency>
<groupId>org.elasticsearch.clientgroupId>
<artifactId>elasticsearch-rest-high-level-clientartifactId>
<version>7.17.2version>
dependency>
找到原生的依赖
Initialization
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("localhost", 9200, "http"),
new HttpHost("localhost", 9201, "http")));
client.close();
配置的基本问题，要保证导入的依赖和es版本一致
config类
package com.speoki.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 //xml文件
public class ElasticSearchClientConfig {
@Bean
public RestHighLevelClient restHighLevelCliClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("localhost",9200,"http")));
return client;
}
}
源码在外部库看
构建有三个类RestClientBuilder,RestHighLevelClient高级客户端，RestClient普通的客户端
索引的API操作
Autowired自动装配config类，@Qualifier名字指定包
测试类测试
package com.speoki;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.client.indices.CreateIndexRequest;
import org.elasticsearch.client.indices.CreateIndexResponse;
import org.junit.jupiter.api.Test;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.boot.test.context.SpringBootTest;
import java.io.IOException;
@SpringBootTest
class SpeokiEsApiApplicationTests {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient client;
//这里的名字要和方法名一致,不一致的话要用Qualifier
//测试索引的创建 request
@Test
void testCreateIndex() throws IOException {
//创建索引请求
CreateIndexRequest request = new CreateIndexRequest("speoki_index");
//客户端执行创建请求,请求后获得响应
CreateIndexResponse response = client.indices().create(request, RequestOptions.DEFAULT);
System.out.println(response);
}
}
删除索引的时候返回
acknowledged:"true"
package com.speoki;
import org.elasticsearch.action.admin.indices.delete.DeleteIndexRequest;
import org.elasticsearch.action.support.master.AcknowledgedResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.client.indices.CreateIndexRequest;
import org.elasticsearch.client.indices.CreateIndexResponse;
import org.elasticsearch.client.indices.GetIndexRequest;
import org.junit.jupiter.api.Test;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.boot.test.context.SpringBootTest;
import java.io.IOException;
@SpringBootTest
class SpeokiEsApiApplicationTests {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient client;
//这里的名字要和方法名一致,不一致的话要用Qualifier
//测试索引的创建 request put speoki_index
@Test
void testCreateIndex() throws IOException {
//创建索引请求
CreateIndexRequest request = new CreateIndexRequest("speoki_index");
//客户端执行创建请求,请求后获得响应
CreateIndexResponse response = client.indices().create(request, RequestOptions.DEFAULT);
System.out.println(response);
}
//测试获取索引
@Test
void testExistsIndex() throws IOException {
GetIndexRequest request = new GetIndexRequest("speoki_index");
boolean exists = client.indices().exists(request, RequestOptions.DEFAULT);
System.out.println(exists);
}
//删除索引
@Test
void deleteIndex() throws IOException {
DeleteIndexRequest request = new DeleteIndexRequest("speoki_index");
AcknowledgedResponse delete = client.indices().delete(request, RequestOptions.DEFAULT);
System.out.println(delete);
System.out.println(delete.isAcknowledged());
}
}
文档的API操作
@Test
//测试添加文档
void testAddDocument() throws IOException {
//创建对象
User user = new User();
//创建请求
IndexRequest request = new IndexRequest("speoki_index");
//规则 put/speoki_index/_doc/1
request.id("1");
request.timeout(TimeValue.timeValueSeconds(1));
request.timeout("1s");
//将我们的数据放入请求 json
IndexRequest source = request.source(JSON.toJSONString(user), XContentType.JSON);
//客户端发送请求,获取响应结果
IndexResponse index = client.index(request, RequestOptions.DEFAULT);
System.out.println(index.toString());
System.out.println(index.status());//对应命令返回的状态
}
//获取文档，查看是否存在 get /index/_doc/1
@Test
void testDocExists() throws IOException {
GetRequest getRequest = new GetRequest("speoki_index", "1");
//不获取_source的上下文了
getRequest.fetchSourceContext(new FetchSourceContext(false));
getRequest.storedFields("_none_");
boolean exists=client.exists(getRequest,RequestOptions.DEFAULT);
System.out.println(exists);
}
//获取文档的信息
@Test
void testGetDoc() throws IOException {
GetRequest getRequest = new GetRequest("speoki_index", "1");
GetResponse getResponse = client.get(getRequest, RequestOptions.DEFAULT);
System.out.println(getResponse.getSourceAsString());
//打印文档的内容
System.out.println(getResponse);
}
//更新文档的信息
@Test
void testUpdateDoc() throws IOException {
UpdateRequest updateRequest = new UpdateRequest("speoki_index","1");
updateRequest.timeout("1s");
User user = new User("狂神说JAVA",18);
updateRequest.doc(JSON.toJSONString(user),XContentType.JSON);
UpdateResponse update = client.update(updateRequest, RequestOptions.DEFAULT);
System.out.println(update);
System.out.println(update.status());
}
//删除文档记录
@Test
void testDelete00Request() throws IOException {
DeleteRequest request = new DeleteRequest("speoki_index", "1");
request.timeout("1s");
DeleteResponse delete = client.delete(request, RequestOptions.DEFAULT);
System.out.println(delete);
System.out.println(delete.status());
}
//批量插入数据
//SearchRequest搜索请求
//SearchSourceBuilder条件构造
//HighlightBuilder构建高亮
//精确查询 TermQueryBuilder
//MatchAllQueryBuilder
//xxxQueryBuilder 对应我们刚刚看到的索引名
@Test
void testBulkRequest() throws IOException {
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("10s");
ArrayList<User> userList = new ArrayList<>();
userList.add(new User("speoki1",3) );
userList.add(new User("speoki2",3) );
userList.add(new User("speoki3",3) );
userList.add(new User("speoki4",3) );
userList.add(new User("speoki5",3) );
//批处理请求
for (int i = 0; i <userList.size() ; i++) {
bulkRequest.add(new IndexRequest("speoki_index").id(""+(i+1)).source(JSON.toJSONString(userList.get(i)),XContentType.JSON));
}
BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT);
System.out.println(bulk.hasFailures());
//返回false代表成功
}
//查询
@Test
void testSearch() throws IOException {
SearchRequest searchRequest = new SearchRequest("speoki_index");
///真实项目应该放在一个utils类中 SearchRequest searchRequest = new SearchRequest(ESConst.ES_INDEX);
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//构建搜索条件 QueryBuilder qb = new QueryBuilder();
//使用工具类
TermQueryBuilder tqb = QueryBuilders.termQuery("name", "speoki1");
// MatchAllQueryBuilder matchAllQueryBuilder = QueryBuilders.matchAllQuery();
sourceBuilder.query(tqb);
//设置分页
// sourceBuilder.from();
// sourceBuilder.size();
// 有默认的
sourceBuilder.timeout(new TimeValue(60,TimeUnit.SECONDS));
searchRequest.source(sourceBuilder);
SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT);
System.out.println(search);
System.out.println("======================");
System.out.println(JSON.toJSONString(search.getHits()));
System.out.println("=====================");
for (SearchHit hit : search.getHits().getHits()) {
System.out.println(hit.getSourceAsMap());
}
}
//查询
京东实战
server.port=9090
spring.thymeleaf.cache=false
#关闭thymeleaf的缓存
@Controller
public class IndexController {
@GetMapping({"/","/index"})
public String index(){
return "index";
}
}
数据问题
爬取数据：获取请求返回的页面信息，筛选出我们想要的数据
jsoup包
<dependency>
<groupId>org.jsoupgroupId>
<artifactId>jsoupartifactId>
<version>1.10.2version>
dependency>
<dependency>
<groupId>com.alibabagroupId>
<artifactId>fastjsonartifactId>
<version>1.2.70version>
dependency>
<dependency>
<groupId>org.springframework.bootgroupId>
<artifactId>spring-boot-devtoolsartifactId>
<scope>runtimescope>
<optional>trueoptional>
dependency>
京东页面结构
爬虫的写法
package com.speoki.util;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import java.io.IOException;
import java.net.URL;
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
//获取请求 https://search.jd.com/Search?keyword=java
//记得联网 ajax不能获取，模拟浏览器
String url = AConst.AURL;
//解析网页 Jsoup返回Document就是浏览器Document对象
Document parse = Jsoup.parse(new URL(url), 30000);
//所有你在js中可以使用的方法这里都可以使用
Element element = parse.getElementById("J_goodsList");
System.out.println(element.html());
}
}
获取所有的li标签内的内容
这里没有src。。。。
打印一下
图片是懒加载的
package com.speoki.util;
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;
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
//获取请求 https://search.jd.com/Search?keyword=java
//记得联网 ajax不能获取，模拟浏览器
String url = AConst.AURL;
//解析网页 Jsoup返回Document就是浏览器Document对象
Document parse = Jsoup.parse(new URL(url), 30000);
//所有你在js中可以使用的方法这里都可以使用
Element element = parse.getElementById("J_goodsList");
// System.out.println(element.html());
//爬取页面，获取请求返回的信息。筛选出需要的数据
//获取所有的li标签下的内容
Elements li = element.getElementsByTag("li");
//打印所有li标签下的信息
for (Element e : li) {
// System.out.println(e);
//获取图片地址
//关于这种图片特别多的网站，所有的图片都是延迟加载的
//source-data-lazy-img
//data-lazy-img
String img = e.getElementsByTag("img").eq(0).attr("data-lazy-img");
//获取商品价格p-price
String price = e.getElementsByClass("p-price").eq(0).text();
//获取商品名字p-name
String title=e.getElementsByClass("p-name").eq(0).text();
System.out.println("==================");
System.out.println(img);
System.out.println(price);
System.out.println(title);
}
}
}
====================
public static void main(String[] args) throws IOException {
new HtmlParseUtil().parseJD("并发").forEach(System.out::println);
//首先调用方法，然后将得到的对象输出 forEach(System.out::println)
}
public ArrayList<Content> parseJD(String keywords) throws IOException {
//获取请求 https://search.jd.com/Search?keyword=java
//记得联网 ajax不能获取，模拟浏览器
// String url = AConst.AURL;
//解析网页 Jsoup返回Document就是浏览器Document对象
Document parse = Jsoup.parse(new URL("https://search.jd.com/Search?keyword="+keywords), 30000);
//所有你在js中可以使用的方法这里都可以使用
Element element = parse.getElementById("J_goodsList");
// System.out.println(element.html());
//爬取页面，获取请求返回的信息。筛选出需要的数据
//获取所有的li标签下的内容
ArrayList<Content> goodsList = new ArrayList<>();
Elements li = element.getElementsByTag("li");
//打印所有li标签下的信息
for (Element e : li) {
// System.out.println(e);
//获取图片地址
//关于这种图片特别多的网站，所有的图片都是延迟加载的
//source-data-lazy-img
//data-lazy-img
String img = e.getElementsByTag("img").eq(0).attr("data-lazy-img");
//获取商品价格p-price
String price = e.getElementsByClass("p-price").eq(0).text();
//获取商品名字p-name
String title=e.getElementsByClass("p-name").eq(0).text();
System.out.println("==================");
System.out.println(img);
System.out.println(price);
System.out.println(title);
Content content = new Content();
content.setTitle(title);
content.setImg(img);
content.setPrice(price);
goodsList.add(content);
}
return goodsList;
}
}
URL不支持中文需要设置
npm显示理想树解决方法
\
