文章目录
- 8.1、项目搭建
- 8.2、Jsoup爬虫
- 8.3、业务编写
- 8.4、前后端交互
- 8.5、关键字高亮实现
8.1、项目搭建
导入fastjson包
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.62</version>
</dependency>
导入页面及静态资源
资源链接:https://pan.baidu.com/s/1hw1mL87BBF62GsZH7DhcpA 提取码:7k7k
编写IndexControler测试
@Controller
public class IndexController {
@RequestMapping({"/","/index"})
public String string(){
return "index";
}
}
启动
8.2、Jsoup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Jsoup依赖包
<!--解析网页-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.13.1</version>
</dependency>
2、编写一个封装对象的实体类
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
private String img;
private String title;
private String price;
// 可以自己添加属性
}
3、爬取
package com.chen.util;
import com.chen.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.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
@Component
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
new HtmlParseUtil().parseJD("java").forEach(System.out::println);
}
public List<Content> parseJD(String keywords) throws IOException {
// 获得请求 https://search.jd.com/Search?keyword=java
// 前提:需要联网
String url = "https://search.jd.com/Search?keyword="+keywords;
// 解析网页 Jsoup返回Document就是浏览器的Document对象
Document document = Jsoup.parse(new URL(url), 30000);
// 所有在js中可以使用的方法,这里都可以用
Element element= document.getElementById("J_goodsList");
System.out.println(element);
// 获取所有的li元素
Elements elements = element.getElementsByTag("li");
ArrayList<Content> goodList = new ArrayList<>();
// 获取元素中的内容
for (Element el : elements) {
// 如果通过src获取不到图片的话,有可能所有图片都是延迟加载的!
// 我们attr的属性可能需要通过data-lazy-img去获取
String img = el.getElementsByTag("img").eq(0).attr("src");
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
Content content = new Content();
content.setImg(img);
content.setTitle(title);
content.setPrice(price);
goodList.add(content);
}
return goodList;
}
}
4、运行测试
8.3、业务编写
1、新建立一个config包,编写ElasticSearchConfig
@Configuration
public class ElasticSearchConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("127.0.0.1", 9200, "http")));
return client;
}
}
2、将数据放入es中
- 编写ContentService
@Service
public class ContentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
// 1、解析数据放入es 索引中
public Boolean parseContent(String keywords) throws IOException {
List<Content> contents = new HtmlParseUtil().parseJD(keywords);
// 把查询到的数据放入 es 中
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("2m");
for (int i = 0; i < contents.size(); 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();
}
}
- 编写ContentController
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keywords}")
public boolean parse(@PathVariable("keywords") String keywords) throws IOException {
return contentService.parseContent(keywords);
}
}
- 启动
2、获取这些数据实现搜索功能
- 给ContentService 中添加方法
/**
*
* @param keyword 关键字
* @param pageNo 标识从第几行开始
* @param pageSize 页面大小
* @return
*/
// 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);
sourceBuilder.size(pageSize);
// 精准匹配
TermQueryBuilder title = QueryBuilders.termQuery("title", keyword);
sourceBuilder.query(title);
sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
// 执行搜索
searchRequest.source(sourceBuilder);
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String,Object>> list = new ArrayList<>();
// 执行结果
for (SearchHit hit : searchResponse.getHits().getHits()) {
list.add(hit.getSourceAsMap());
}
return list;
}
- 给ContentController添加接口
@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.searchPage(keyword,pageNo,pageSize);
}
- 启动访问测试
8.4、前后端交互
1、新建文件夹并在文件夹下执行命令行下载vue
npm init
npm install vue
npm install axios
文件夹下的到:
2、将js文件导入项目中
3、修改index.html
<!DOCTYPE html>
<html xmlns:th="http://www.thymeleaf.org">
<head>
<meta charset="utf-8"/>
<title>狂神说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>天猫搜索</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 type="submit" id="searchbtn" @click.prevent="searchKey">搜索</button>
</div>
</fieldset>
</form>
<ul class="relKeyTop">
<li><a>狂神说Java</a></li>
<li><a>狂神说前端</a></li>
<li><a>狂神说Linux</a></li>
<li><a>狂神说大数据</a></li>
<li><a>狂神聊理财</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="#"> 狂神说 </a></li>
<li><a href="#"> Java </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><b>¥</b>{{result.price}}</em>
</p>
<!--标题-->
<p class="productTitle">
<a> {{result.title}} </a>
</p>
<!-- 店铺名 -->
<div class="productShop">
<span>店铺: 狂神说Java </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>
</div>
</div>
</div>
<!-- 前端使用Vue,实现前后端分离 -->
<script th:src="@{/js/axios.min.js}"></script>
<script th:src="@{/js/vue.min.js}"></script>
<script>
new Vue({
el: "#app",
data: {
keyword: '', // 搜索的关键字
results: [] // 搜索的结果
},
methods: {
searchKey(){
var keyword = this.keyword;
console.log(keyword);
// 对接后端的接口
axios.get('search/'+keyword+'/1/10').then(response=>
{
console.log(response);
this.results = response.data; // 绑定数据
})
}
}
})
</script>
</body>
</html>
4、测试效果
注意:
如果在代码没有问题的情况下出现问题,可以先将项目clean一下,然后重启!
8.5、关键字高亮实现
1、给ContentService 中添加方法
// 2、获取这些数据实现搜索功能
public List<Map<String,Object>> searchPageHighlight(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);
sourceBuilder.size(pageSize);
// 精准匹配
TermQueryBuilder title = QueryBuilders.termQuery("title", keyword);
sourceBuilder.query(title);
sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));
// 高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
// 是否多个高亮显示 这里选否
highlightBuilder.requireFieldMatch(false);
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);
ArrayList<Map<String,Object>> list = new ArrayList<>();
// 解析结果
for (SearchHit hit : searchResponse.getHits().getHits()) {
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField highlightTitle = highlightFields.get("title");
// 原来的结果
Map<String, Object> sourceAsMap = hit.getSourceAsMap();
// 解析高亮的字段 将原来的字段换为我们高亮的字段即可
// 注意这里是highlightTitle,不要错用为上面的title
if (highlightTitle != null){
Text[] fragments = highlightTitle.fragments();
String n_title = "";
for (Text text : fragments) {
n_title += text;
}
// 将原来的字段换为我们高亮的字段即可
sourceAsMap.put("title",n_title);
}
list.add(sourceAsMap);
}
return list;
}
2、给ContentController添加接口
@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.searchPageHighlight(keyword,pageNo,pageSize);
}
3、修改index.html (将title的绑定改为v-html)
<!--标题-->
<p class="productTitle">
<a v-html="result.title"></a>
</p>
4、效果