ES集成SpringBoot
1.导包
<dependency> <groupId>org.elasticsearch.client</groupId> <artifactId>elasticsearch-rest-high-level-client</artifactId> <version>7.15.2</version> </dependency>
2.写代码
//构建springboot项目可以直接勾选NoSQL选项中的ES,在官网初始化中复制这个代码 //注入到Bean中就可以调用测试了！！！搞定！1.构建项目导包。2.注入。3使用 @Configuration public class ElasticsearchConfig { @Bean public RestHighLevelClient restHighLevelClient(){ RestHighLevelClient client = new RestHighLevelClient( RestClient.builder( //new HttpHost("localhost", 9200, "http"), //不是集群构建一个就行了 new HttpHost("localhost", 9200, "http"))); return client; } }
3.测试
@Qualifier("restHighLevelClient")
@Autowired
private RestHighLevelClient client;
@Test
void createIndex() throws IOException {
//测试API
//索引创建 Request
CreateIndexRequest dlb_index = new CreateIndexRequest("dlb_index");
// 执行请求 获得响应
CreateIndexResponse createIndexResponse = client.indices()
.create(dlb_index, RequestOptions.DEFAULT);
System.out.println("createIndexResponse = " + createIndexResponse);
//创建索引完成，put
//删除测试
DeleteIndexRequest request = new DeleteIndexRequest("dlb_index");
AcknowledgedResponse delete = client.indices().delete(request, RequestOptions.DEFAULT);
//获取索引测试
GetIndexRequest request = new GetIndexRequest("dlb_index");
boolean exists = client.indices().exists(request,RequestOptions.DEFAULT);
}
2.文档操作
//添加文档 @Test void addDoc() throws IOException { User u1 = new User("大萝卜", 10); IndexRequest req = new IndexRequest("dlb_index"); //put test/_doc/1 req.id("1"); //超时设置 req.timeout(TimeValue.timeValueSeconds(1)); req.timeout("1s"); //将数据放到请求 json 引入fastJson req.source(JSON.toJSONString(u1), XContentType.JSON); //客户端发送请求 ,获取响应结果 IndexResponse index = client.index(req, RequestOptions.DEFAULT); System.out.println("index = " + index.toString()); System.out.println("index = " + index.status());//CREATED 首次状态 /** PUT /test1/type1/1 { "name": "大萝卜", "uage" : 30 } */ }
@Test//判断文档（这个条数据）是否存在 GetRequest void pdDoc() throws IOException { GetRequest request = new GetRequest("dlb_index","1"); //不获取返回的_source上下文，效率更高 request.fetchSourceContext(new FetchSourceContext(false)); boolean exists = client.exists(request, RequestOptions.DEFAULT); System.out.println("exists = " + exists); }
@Test//获取文档信息（本行数据） void getDoc() throws IOException { GetRequest request = new GetRequest("dlb_index","1"); GetResponse documentFields = client.get(request, RequestOptions.DEFAULT); //打印文档内容 //map转字符串：{"age":10,"name":"大萝卜"} System.out.println(documentFields.getSourceAsString()); //这个地方就是kibana右侧显示的巴拉巴拉 System.out.println("documentFields = " + documentFields); }
@Test//更新文档信息（修改本行数据） void upDataDoc() throws IOException { UpdateRequest request = new UpdateRequest("dlb_index","1"); request.timeout("1s"); User user = new User("啊哈哈",33); request.doc(JSON.toJSONString(user),XContentType.JSON); UpdateResponse update = client.update(request, RequestOptions.DEFAULT); System.out.println(update.status()); }
@Test//删除文档记录 void deleteDoc() throws IOException { DeleteRequest deleteRequest = new DeleteRequest("dlb_index","1"); deleteRequest.timeout("1s"); DeleteResponse delete = client.delete(deleteRequest, RequestOptions.DEFAULT); System.out.println(delete.status()); }
@Test//批量导入数据，本质像循环 void bigData() throws IOException { BulkRequest bulkRequest = new BulkRequest(); bulkRequest.timeout("10s"); ArrayList<User> list = new ArrayList<>(); list.add(new User("大萝卜",18)); list.add(new User("大萝卜",18)); for (int i = 0; i < list.size(); i++) { bulkRequest.add(new IndexRequest("dlb_index") .id(i+1+"")//不写id就会生成随机id .source(JSON.toJSONString(list.get(i)),XContentType.JSON)); } BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT); boolean b = bulk.hasFailures();//成功返回false System.out.println(bulk.status());//OK }
@Test//查询 void cz() throws IOException {
//建造者模式 SearchRequest searchRequest = new SearchRequest("dlb_index"); //构建搜索对象---->指挥 SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder(); //设置搜索条件---->工人 TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("age", "18"); searchSourceBuilder.query(termQueryBuilder);//----->生产产品 searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS)); //放进请求中 searchRequest.source(searchSourceBuilder); //发送请求 SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT); System.out.println(JSON.toJSONString(search.getHits())); System.out.println("------------------"); SearchHits hits = search.getHits(); SearchHit[] hits1 = hits.getHits(); for (SearchHit documentFields : hits1) { System.out.println(documentFields.getSourceAsMap()); } }
4.案例
pojo实体类未写出 Crawler、user
1.爬取数据准备
<!--导包--> <!--电影音乐用tika包--> <!-- 解析网页包--https://mvnrepository.com/artifact/org.jsoup/jsoup --> <dependency> <groupId>org.jsoup</groupId> <artifactId>jsoup</artifactId> <version>1.14.3</version> </dependency>
2.工具类爬取方法
public List<Crawler> getData(String url) throws Exception { ArrayList<Crawler> list = new ArrayList<>(); //前提：联网 ， AJAX 不能获取需要模拟浏览器 //获取请求 if ("".equals(url)){ url="https://XXXX.com/tag/win11-zhuti/"; } //解析网页 , 返回的是前端页面 url不支持中文 Document document = Jsoup.parse(new URL(url), 3000); Element elementById = document.getElementById("post-list"); Elements li = elementById.getElementsByTag("li"); for (Element el : li) { String img = el.getElementsByTag("img").eq(0).attr("src"); String name = el.getElementsByClass("post-info").eq(0).text(); if (!"".equals(img)&&!"".equals(name)){ list.add(new Crawler(img,name)); System.out.println(img); System.out.println("name:"+name); } } return list; }
3.导入数据和查询数据
@Service public class HtmlService { @Autowired private RestHighLevelClient restHighLevelClient; //插入到查询引擎中 public Boolean parseHtml(String url) throws Exception { List<Crawler> list = new HtmlUtils().getData(url); BulkRequest bulkRequest = new BulkRequest(); bulkRequest.timeout("3m"); for (int i = 0; i < list.size(); i++) { bulkRequest.add( new IndexRequest("mf") //这里没有设置id,可以参考上篇批量添加 .source(JSON.toJSONString(list.get(i)),XContentType.JSON)); } BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT); return !bulk.hasFailures(); } //查询、参数1：查询谁。参数2：从第几页开始。参数3：每页大小 public ArrayList<Map<String,Object>> searchPage(String keyword,int page,int pageSize) { if (page<=1){ page=1; } //查询连接 SearchRequest mf = new SearchRequest("mf"); //条件建造者 SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder(); //分页 searchSourceBuilder.from(page); searchSourceBuilder.size(pageSize); //查询条件组装 MatchQueryBuilder ztName = QueryBuilders.matchQuery("ztName", keyword); searchSourceBuilder.query(ztName); searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS)); //设置高亮 HighlightBuilder highlightBuilder = new HighlightBuilder(); highlightBuilder.field("ztName");//哪个字段是高亮 highlightBuilder.requireFieldMatch(false);//查出的一句话中只有一个词是高亮的 highlightBuilder.preTags("<p style='color:red'>");//怎么亮起来 highlightBuilder.postTags("</p>"); searchSourceBuilder.highlighter(highlightBuilder); //把组装好的条件放到请求中 mf.source(searchSourceBuilder); //执行请求，返回结果 SearchResponse search = null; try { search = restHighLevelClient.search(mf, RequestOptions.DEFAULT); } catch (IOException e) { System.out.println("连接异常"); e.printStackTrace(); return null; } ArrayList<Map<String,Object>> list = new ArrayList<>(); for (SearchHit hit : search.getHits().getHits()) { Map<String, Object> map = hit.getSourceAsMap();//原来的结果 //解析高亮字段 Map<String, HighlightField> hmap = hit.getHighlightFields(); HighlightField name = hmap.get("ztName");//从hit里面查找出高亮的字段 if (name!=null){ String a=""; Text[] fragments = name.fragments();// System.err.println("fragments = " + fragments[0]); for (Text text : fragments) { a+=text; } System.err.println(a); map.put("ztName",a);//替换原来的 } System.out.println(map); list.add(map); } return list; }
