第132天学习打卡（ElasticSearch 仿京东搜索 ）

Posted 2021-05-23 doudoutj

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！）

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;
@Component
public class HtmlParseUtil {
//    public static void main(String[] args) throws Exception {
//        new HtmlParseUtil().parseJD("java").forEach(System.out::println);
//
//    }
    public List<Content> parseJD(String keywords) throws Exception {

        String url = "https://search.jd.com/Search?keyword=" + keywords;

        Document document = Jsoup.parse(new URL(url), 30000);

        Element element = document.getElementById("J_goodsList");
        System.out.println(element.html());
        //获取所有的li元素
        Elements elements = document.getElementsByTag("li");
        ArrayList<Content> goodsList = new ArrayList<>();
        //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();
            Content content = new Content();
            content.setTitle(title);
            content.setPrice(price);
            content.setImg(img);
            goodsList.add(content);


        }
        return  goodsList;

    }
}

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
@Configuration  //相当于xml文件 r
public class ElasticSearchClientConfig {
    // spring <beans id = restHighLevelClient class = RestHighLevelClient>
    @Bean
    public RestHighLevelClient restHighLevelClient(){
        RestHighLevelClient client = new RestHighLevelClient(
                RestClient.builder(
                        new HttpHost("127.0.0.1", 9200, "http")));
        return client;


    }
}

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
@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.searchPageHighlightBuilder(keyword, pageNo, pageSize);




    }
}

IndexController.java

package com.kuang.controller;

import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;

@Controller
public class IndexController {
    @GetMapping({"/", "/index"})
    public String index(){
        return "index";
    }
}

pojo Content.java

package com.kuang.pojo;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;

@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
    private String title;
    private String img;
    private String price;
    //可以自己添加属性
}

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
@Service
public class ContentService {
    @Autowired //注入自己的类
    private RestHighLevelClient restHighLevelClient;
不能直接使用 @Autowired  需要spring容器
//    public static void main(String[] args) throws Exception {
//        new ContentService().parseContent("java");
//    }
    //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);
        //把查询的数据放入es中
        BulkRequest bulkRequest = new BulkRequest();
        bulkRequest.timeout("2m");
        for (int i = 0; i < contents.size(); i++) {
//            System.out.println(JSON.toJSONString(contents.get(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.获取这些数据 实现搜索功能
    public List<Map<String, Object>> searchPage(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);//从第几条数据开始（默认是从0开始）
        sourceBuilder.size(pageSize);
        //精准匹配
        TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
        sourceBuilder.query(termQueryBuilder);
        sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));

        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
        //解析结果
        ArrayList<Map<String, Object>> list = new ArrayList<>();
        for (SearchHit documentFields : searchResponse.getHits().getHits()) {
            list.add(documentFields.getSourceAsMap());

        }
        return list;


    }
    //3.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);//从第几条数据开始（默认是从0开始）
        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'>");
        highlightBuilder.postTags("</span>");
        sourceBuilder.highlighter(highlightBuilder);

        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.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);//将原来的字段用高亮字段替换掉

            }
            list.add(sourceAsMap);
        }
        return list;


    }




}

application.properties

server.port=9090
# 关闭thymeleaf的缓存
spring.thymeleaf.cache=false

新建一个文件夹，然后在这个文件夹里面使用cmd的命令 下载vue和axios

npm install vue
npm install axios

index.html

<!DOCTYPE html>
&
以上是关于第132天学习打卡（ElasticSearch  仿京东搜索 ）的主要内容，如果未能解决你的问题，请参考以下文章
 
 第128天学习打卡（ElasticSearch 初识elasticreach  及安装）
 第129天学习打卡（Elasticsearch  kibana安装   ES核心概念   IK分词器插件）
 第130天学习打卡（ElasticSearch   Rest风格说明   索引  文档   ）
 第131天学习打卡（ElastiSearch  集成SpringBoot）
 深度学习----------打卡第13天
 深度学习----------打卡第8天