第132天学习打卡（ElasticSearch 仿京东搜索 ）
在pom.xml中导入依赖
<!-- 引入fastjson-->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.75</version>
</dependency>
爬虫
数据问题？数据库获取，消息队列中获取，都可以成为数据源！ 爬虫！
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就可以了！）
1.
导入依赖pom.xml
<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.13.1</version>
</dependency>
utils HtmlParseUtil.java
package com.kuang.utils;
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
//前提：需要联网
String url = "https://search.jd.com/Search?keyword=java";
//解析网页 (Jsoup返回Document 对象就是浏览器Document 对象)
Document document = Jsoup.parse(new URL(url), 30000);
//所有你在js中可以使用的方法，这里都能使用
Element element = document.getElementById("J_goodsList");
System.out.println(element.html());
//获取所有的li元素
Elements elements = document.getElementsByTag("li");
//获取元素中的内容 这里el，就是每一个li标签了
for (Element el : elements) {
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();
System.out.println("=============================");
System.out.println(img);
System.out.println(price);
System.out.println(title);
}
}
}
对上面的代码进行封装
package com.kuang.utils;
import com.kuang.pojo.Content;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.stereotype.Component;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
config ElasticSearchClientConfig.java
package com.kuang.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;
//spring的两步骤
//1.找对象
//2.放到spring中待用
//3.如果是springboot 就先分析源码
controller
ContentController.java
package com.kuang.controller;
import com.kuang.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;
//请求编写
IndexController.java
package com.kuang.controller;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
pojo Content.java
package com.kuang.pojo;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
service ContentService.java
package com.kuang.service;
import com.alibaba.fastjson.JSON;
import com.kuang.pojo.Content;
import com.kuang.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.stereotype.Service;
import javax.naming.directory.SearchResult;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
//业务编写