快速入门Java爬虫、全文搜索引擎Elasticsearch，分析实战项目：仿京东搜索（二）
hi大家好，今天我把上周的内容继续讲完！！
接着上次的部分，今天我们分享的是Elaticsearch全文搜索引擎，Elasticsearch是基于Lucene做了一些封装和增强。
首先我们先介绍一下Elasticsearch，简称es是一个开源的高扩展的分布式全文搜索引擎，它可以近乎实时的存储、检索数据；本身它扩展性很好，可以扩展到上百台服务器，处理PB级别(大数据时代)的数据。es也使用java开发并使用Lucene作为其核心来实现所有索引和搜索的功能，但是它的目的是通过简单的Restful API 来隐藏Luncene的复杂性，从而让全文搜索变得简单。
首先大家先去下载好Elaticsearch，访问 Elasticsearch 官网 下载安装包Download Elasticsearch | Elastic
https://www.elastic.co/cn/downloads/elasticsearch得到下载的文件后，在bin目录下打开cmd，start elasticsearch，再用浏览器打开9200端口，出现以下界面代表运行成功。
在这里进行一些小扩展，这里我们可以使用一些扩展插件如head和Kibana，Kibana是一个针对Elasticsearch的开源分析及及可视化平台，用来搜索、查看交互存储在Elasticsearch索引中的数据。简单的来说，这些扩展插件是可以用来帮助我们具体学习Elaticsearch的，毕竟是可视化。
如果大家想具体了解Elaticesearch的功能，可以去看官网的开发文档，像里面的·IK分词器、高亮都是需要掌握的。
我今天是展示项目所以不多说，首先我们需要把上篇文章的爬虫包装成一个类，方便我们调用，毕竟我们在使用es前必须保证里面有数据才对。
项目的所有文件都如图所示， yaml文件我配置的端口是8081；在用之前得保证你有相关的jsoup和es得maven依赖，上周已经提供。以下是上周的爬虫类utils下的jsoupService
package com.liu.utils;
import com.liu.pojo.goodJD;
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.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
@Component
public class jsouputils {
// public static void main(String[] args) throws Exception {
https://search.jd.com/Search?keyword=java
// new jsouputils().parsJD("java").forEach(System.out::println);
// }
public List<goodJD> parsJD(String keywords) throws Exception {
String url ="https://search.jd.com/Search?keyword="+keywords;
Document document = Jsoup.parse(new URL(url), 900000000);
Element element = document.getElementById("J_goodsList");
Elements elements = element.getElementsByTag("li");
ArrayList<goodJD> goodJDlist = new ArrayList<>();
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();
String shopnum = el.getElementsByClass("p-shop").eq(0).text();
goodJD goodJD = new goodJD();
goodJD.setTitle(title);
goodJD.setImg(img);
goodJD.setPrice(price);
goodJD.setShopnum(shopnum);
goodJDlist.add(goodJD);
}
return goodJDlist;
}
}
接下来我们需要在config目录下加一个ESconfig类，目的是为了连接上我们的ES，127.0.0.1：9200代表本地路径加端口。具体代码如下所示：
package com.liu.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
public class ESconfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("127.0.0.1", 9200, "http")));
return client;
}
}
接下来就是最难的service层了，具体代码如下：
package com.liu.service;
import com.alibaba.fastjson.JSON;
import com.liu.pojo.goodJD;
import com.liu.utils.jsouputils;
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.QueryBuilder;
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 javax.swing.text.Highlighter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
@Service
public class JsoupService {
@Autowired
private RestHighLevelClient restHighLevelClient;
public Boolean parseContent(String keywords) throws Exception {
List<goodJD> goodJDS = new jsouputils().parsJD(keywords);
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("2m");
for (int i = 0; i < goodJDS.size(); i++) {
bulkRequest.add((new IndexRequest("jd_good")
.source(JSON.toJSONString(goodJDS.get(i)), XContentType.JSON)
));
}
BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
public List<Map<String,Object>> seachPage(String keywords,
int pageNo,
int pageSize) throws IOException {
if(pageNo<=1){
pageNo=1;
}
SearchRequest searchRequest = new SearchRequest("jd_good");
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keywords);
searchSourceBuilder.query(termQueryBuilder);
searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
searchRequest.source(searchSourceBuilder);
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String,Object>>list = new ArrayList<>();
for (SearchHit documentFields : searchResponse.getHits()) {
list.add(documentFields.getSourceAsMap());
}
return list;
}
public List<Map<String,Object>> seachPagehighlighter(String keywords,
int pageNo,
int pageSize) throws IOException {
if(pageNo<=1){
pageNo=1;
}
SearchRequest searchRequest = new SearchRequest("jd_good");
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
TermQueryBuilder termQueryBuilder =
QueryBuilders.termQuery("title", keywords);
searchSourceBuilder.query(termQueryBuilder);
searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false);
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
searchSourceBuilder.highlighter(highlightBuilder);
searchRequest.source(searchSourceBuilder);
SearchResponse searchResponse =
restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String,Object>>list = new ArrayList<>();
for (SearchHit documentFields : searchResponse.getHits()) {
Map<String, HighlightField> highlightFields =
documentFields.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = documentFields.getSourceAsMap();
if(title!=null){
Text[] fragments = title.fragments();
String ntitle="";
for (Text text : fragments) {
ntitle +=text;
}
sourceAsMap.put("title",ntitle);
}
list.add(sourceAsMap);
}
return list;
}
}
对应service层我来进行一下简单的分析，
BulkRequest是插入多个数据时候使用，连接2分钟
高亮操作：
接着是controllerr层
JsoupController类：
package com.liu.controller;
import com.liu.service.JsoupService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.CrossOrigin;
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 JsoupController {
@Autowired
private JsoupService jsoupService;
@CrossOrigin
@GetMapping("/parse/{keywords}")
public Boolean parse(@PathVariable String keywords) throws Exception {
return jsoupService.parseContent(keywords);
}
@CrossOrigin
@GetMapping("/search/{keywords}/{pageNo}/{pageSize}")
public List<Map<String,Object>> search(
@PathVariable String keywords,
@PathVariable int pageNo,
@PathVariable int pageSize) throws IOException {
return jsoupService.seachPagehighlighter(keywords,pageNo,pageSize);
}
}
indexjion类：
package com.liu.controller;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
@Controller
public class indexjion {
@GetMapping({"/", "/index"})
public String toindex(){
return "index";
}
}
前端界面
index.html：
<!DOCTYPE html>
<html xmlns:th="http://www.thymeleaf.org">
<head>
<meta charset="utf-8"/>
<title>Java-ES仿京东实战</title>
<link rel="stylesheet" th:href="@{/css/style.css}"/>
</head>
<body class="pg">
<div class="page" id="app">
<div id="mallPage" class=" mallist tmall- page-not-market ">
<!-- 头部搜索 -->
<div id="header" class=" header-list-app">
<div class="headerLayout">
<div class="headerCon ">
<!-- Logo-->
<h1 id="mallLogo">
<img th:src="@{/images/jdlogo.png}" alt="">
</h1>
<div class="header-extra">
<!--搜索-->
<div id="mallSearch" class="mall-search">
<form name="searchTop" class="mallSearch-form clearfix">
<fieldset>
<legend>京东搜索</legend>
<div class="mallSearch-input clearfix">
<div class="s-combobox" id="s-combobox-685">
<div class="s-combobox-input-wrap">
<input v-model="keyword" type="text" autocomplete="off" value="dd" id="mq"
class="s-combobox-input" aria-haspopup="true">
</div>
</div>
<button @click.prevent="searchkey" type="submit" id="searchbtn">搜索</button>
</div>
</fieldset>
</form>
<ul class="relKeyTop">
<li><a>java</a></li>
<li><a>Vue</a></li>
<li><a>Rdeis</a></li>
<li><a>Docker</a></li>
<li><a>spring</a></li>
</ul>
</div>
</div>
</div>
</div>
</div>
<!-- 商品详情页面 -->
<div id="content">
<div class="main">
<!-- 品牌分类 -->
<form class="navAttrsForm">
<div class="attrs j_NavAttrs" style="display:block">
<div class="brandAttr j_nav_brand">
<div class="j_Brand attr">
<div class="attrKey">
品牌
</div>
<div class="attrValues">
<ul class="av-collapse row-2">
<li><a href="#"> 实惠 </a></li>
<li><a href="#"> 人人 </a></li>
</ul>
</div>
</div>
</div>
</div>
</form>
<!-- 排序规则 -->
<div class="filter clearfix">
<a class="fSort fSort-cur">综合<i class="f-ico-arrow-d"></i></a>
<a class="fSort">人气<i class="f-ico-arrow-d"></i></a>
<a class="fSort">新品<i class="f-ico-arrow-d"></i></a>
<a class="fSort">销量<i class="f-ico-arrow-d"></i></a>
<a class="fSort">价格<i class="f-ico-triangle-mt"></i><i class="f-ico-triangle-mb"></i></a>
</div>
<!-- 商品详情 -->
<div class="view grid-nosku">
<div class="product" v-for="result in results">
<div class="product-iWrap">
<!--商品封面-->
<div class="productImg-wrap">
<a class="productImg">
<img :src="result.img">
</a>
</div>
<!--价格-->
<p class="productPrice">
<em>{{result.price}}</em>
</p>
<!--标题-->
<p class="productTitle">
<a v-html="result.title"></a>
</p>
<!-- 店铺名 -->
<div class="productShop">
<span>{{result.shopnum}}</span>
</div>
<!-- 成交信息 -->
<p class="productStatus">
<span>月成交<em>999笔</em></span>
<span>评价 <a>3</a></span>
</p>
</div>
</div>
</div>
<div class="filter clearfix" >
<a class="fSort fSort-cur"><button @click.prevent="pageone" type="submit" >1</button ><i class="f-ico-arrow-d"></i></a>
<a class="fSort" ><button @click.prevent="pagetwo" type="submit" >2</button ><i class="f-ico-arrow-d"></i></a>
<a class="fSort"><button @click.prevent="pagethree" type="submit" >3</button ><i class="f-ico-arrow-d"></i></a>
<a class="fSort">4<i class="f-ico-arrow-d"></i></a>
<a class="fSort">5<i class="f-ico-triangle-mt"></i><i class="f-ico-triangle-mb"></i></a>
</div>
</div>
</div>
</div>
</div>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/vue.min.js"></script>
<script src="https://unpkg.com/axios/dist/axios.min.js"></script>
<!--<script th:src="@{/js/vue.min.js}"></script>-->
<!--<script th:src="@{/js/axios.min.js}"></script>-->
<script>
new Vue({
el: '#app',
data: {
keyword: '',
results: []
},
methods: {
searchkey: function (){
var keyword= this.keyword;
axios.get('search/'+keyword+"/1/10").then(response=>{
console.log(response.data);
this.results=response.data;
})
},
pageone :function (){
var keyword= this.keyword;
axios.get('search/'+keyword+"/1/10").then(response=>{
console.log(response.data);
this.results=response.data;
})
},
pagetwo :function (){
var keyword= this.keyword;
axios.get('search/'+keyword+"/2/10").then(response=>{
console.log(response.data);
this.results=response.data;
})
},
pagethree :function (){
var keyword= this.keyword;
axios.get('search/'+keyword+"/3/10").then(response=>{
console.log(response.data);
this.results=response.data;
})
}
}
})
</script>
</body>
</html>最终实现结果：
首页：
输入java之后：（爬虫爬的java数据！！！）
可以按下一页调节：