ElasticSearch篇——实现京东搜索(含爬虫操作/解析数据到ES/精准查询/对接前端/高亮查询）一篇文章带你速通~~~~~~~~_elasticsearch加爬虫搜集

话不多说，兄弟们坐好。马上开冲！

爬取解析数据

1、项目导入jsoup依赖

<!--解析网页-->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.15.4</version>
</dependency>

2、编写工具类解析网页

package com.guohui.util;
 
import com.guohui.po.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);
    }
 
    //抽成方法
    public List<Content> parseJD(String keywords) throws Exception {
        //获取请求:这里注意ajax异步请求是获取不到的
        String url = "https://search.jd.com/Search?keyword=" + keywords;
 
        //解析网页(Jsoup返回Document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，这里都能用
        Element element = document.getElementById("J_goodsList");
        //获取所有的li元素
        Elements elements = element.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) {
            //关于这种图片特别多的网站，所有的图片都是延迟加载的
            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.setImg(img);
            content.setPrice(price);
            goodsList.add(content);
        }
        return goodsList;
    }
}

编写业务层

业务层代码希望大家能够认真阅读！

import com.alibaba.fastjson2.JSON;
import com.guohui.po.Content;
import com.guohui.service.ContentService;
import com.guohui.util.HtmlParseUtil;
import lombok.extern.slf4j.Slf4j;
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 java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
 
@Service
@Slf4j
public class ContentServiceImpl implements ContentService {
 
    @Autowired
    private HtmlParseUtil htmlParseUtil;
 
    @Autowired
    private RestHighLevelClient restHighLevelClient;
 
    /**
     * @Author xgh
     * @Description 解析数据放入ES
     * @Date 2023/7/23 16:09
     * @Return
     **/
    @Override
    public boolean parseContent(String keyWorld) throws Exception {
        //调用封装的解析页面的工具类，获得页面上的li集合
        List<Content> contents = htmlParseUtil.parseJD(keyWorld);
        log.info("解析的数据为：{}", contents.toString());
 
        //批量添加文档
        BulkRequest bulkRequest = new BulkRequest();
        for (int i = 0; i < contents.size(); i++) {
            log.info("数据为：{}", contents.get(i));
            bulkRequest.add(new IndexRequest("jd_goods")
                    .source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
        }
 
        //批量执行请求
        BulkResponse responses = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
        return !responses.hasFailures();
    }
 
    /**
     * @Author xgh
     * @Description 获取数据后搜索数据
     * @Date 2023/7/23 16:39
     * @Return
     **/
    @Override
    public List<Map<String, Object>> searchData(String keyWord, int pageNo, int pageSize) throws IOException {
        //分页的判断
        if (pageNo <= 1) {
            pageNo = 1;
        }
 
        //创建查询的请求
        SearchRequest searchRequest = new SearchRequest("jd_goods");
 
        //构建查询条件
        SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
 
        //通过工具来构建构建查询条件
        TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyWord);
        //调用query方法实现精准查询
        searchSourceBuilder.query(termQueryBuilder);
 
        //分页
        searchSourceBuilder.from(pageNo);
        searchSourceBuilder.size(pageSize);
 
        //设置查询的超时时间
        searchSourceBuilder.timeout(new TimeValue(66, TimeUnit.SECONDS));
 
        //封装搜索
        searchRequest.source(searchSourceBuilder);
 
        //调用客户端来查询
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
 
        //解析查询的结果
        List<Map<String, Object>> mapList = new ArrayList<>();
        for (SearchHit documentFields : searchResponse.getHits().getHits()) {
            //调用getSourceAsMap方法将查询出的结果转换成map，然后将map添加到List集合中！
            mapList.add(documentFields.getSourceAsMap());
        }
        return mapList;
    }
 
    /**
    * @Author xgh
    * @Description 高亮查询
    * @Date 2023/7/23 17:13
    * @Return
    **/
    @Override
    public List<Map<String, Object>> searchDataHighLight(String keyWord, int pageNo, int pageSize) throws IOException {
        //分页的判断
        if (pageNo <= 1) {
            pageNo = 1;
        }
 
        //创建查询的请求
        SearchRequest searchRequest = new SearchRequest("jd_goods");
 
        //构建查询条件
        SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
 
        //通过工具来构建构建查询条件
        TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyWord);
        //调用query方法实现精准查询
        searchSourceBuilder.query(termQueryBuilder);
 
        //配置高亮！！！！！！
        HighlightBuilder highlightBuilder = new HighlightBuilder();
        //当存在多个相同的字段的时候，关闭多个高亮，只高亮一个地方即可
        highlightBuilder.requireFieldMatch(false);
 
        //设置高亮的字段
        highlightBuilder.field("title");
        //设置高亮的颜色
        highlightBuilder.preTags("<span style='color=red'>");
        highlightBuilder.postTags("</span>");
        searchSourceBuilder.highlighter(highlightBuilder);
 
        //分页
        searchSourceBuilder.from(pageNo);
        searchSourceBuilder.size(pageSize);
 
        //设置查询的超时时间
        searchSourceBuilder.timeout(new TimeValue(66, TimeUnit.SECONDS));
 
        //封装搜索
        searchRequest.source(searchSourceBuilder);
 
        //调用客户端来查询
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
 
        //解析查询的结果
        List<Map<String, Object>> mapList = new ArrayList<>();
        for (SearchHit documentFields : searchResponse.getHits().getHits()) {
            //解析高亮的字段
            Map<String, HighlightField> highlightFields = documentFields.getHighlightFields();
            HighlightField title = highlightFields.get("title");
            Map<String, Object> sourceAsMap = documentFields.getSourceAsMap(); //这是原来的查询结果
            //将高亮的字段把原来结果的字段替换掉即可！！！！！！
            if (title != null){
                Text[] fragments = title.fragments();
                String new_title = "";
                for (Text text : fragments) {
                    new_title += text;
                }
                //将高亮的字段替换掉原来的字段
                sourceAsMap.put("title",new_title);
            }
            mapList.add(sourceAsMap);
        }
        return mapList;
    }
 
 
}

编写API层

import com.guohui.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 ContentApi {
    @Autowired
    private ContentService contentService;
 
    /**
    * @Author xgh
    * @Description 解析页面数据，存储到ES中
    * @Date 2023/7/23 16:58
    * @Return
    **/
    @GetMapping("/parse/{keyWord}")
    public Boolean parse(@PathVariable("keyWord") String keyWord) throws Exception {
 
        return contentService.parseContent(keyWord);
    }
 
    /**
    * @Author xgh
    * @Description 查询ES数据
    * @Date 2023/7/23 16:58
    * @Return
    **/
    @GetMapping("/search/{keyWord}/{pageNo}/{pageSize}")
    public List<Map<String,Object>> searchData(@PathVariable("keyWord") String keyWord,
                                               @PathVariable("pageNo") int pageNo,
                                               @PathVariable("pageSize") int pageSize) throws IOException {
        return contentService.searchData(keyWord,pageNo,pageSize);
    }
 
    /**
     * @Author xgh
     * @Description 高亮查询ES数据
     * @Date 2023/7/23 16:58
     * @Return
     **/
    @GetMapping("/searchHigh/{keyWord}/{pageNo}/{pageSize}")
    public List<Map<String,Object>> searchDataHighLight(@PathVariable("keyWord") String keyWord,
                                               @PathVariable("pageNo") int pageNo,
                                               @PathVariable("pageSize") int pageSize) throws IOException {
        return contentService.searchDataHighLight(keyWord,pageNo,pageSize);
    }
}
 

调用API响应结果

1、调用爬取数据并存储到ES的方法

观察ES的head可视化工具中是否存入了跟ES相关的数据

2、直接查询数据

3、调用高亮查询

最后需要前端通过下面的标签将html语言进行解析即可！！！！！！

至此，关于ES中爬取页面数据实现文章检索功能已经介绍完毕，详细的使用希望大家能够认真阅读各个层的代码，注释也很详细的哈！

后续还会持续的更新，希望打大家可以继续关注~