数据源:用爬虫获取。
1.导入依赖jsoup(解析网页)
<dependency>
<artifactId>elasticsearch</artifactId>
<groupId>org.elasticsearch</groupId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.elasticsearch.plugin</groupId>
<artifactId>transport-netty4-client</artifactId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>transport</artifactId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>elasticsearch-rest-high-level-client</artifactId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>elasticsearch-rest-client</artifactId>
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.15.3</version>
</dependency>
2.京东页面现在有反爬虫机制,需要cookie绕过安全验证界面
需要找到cookie中,thor键对应的值
封装工具类
pojo层
service层
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient client;
public Boolean parseJD(String keyword) throws Exception{
List<Content> contents = new HtmlParseUtil().parseJd(keyword);
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout("100s");
for (int i = 0; i < contents.size(); i++) {
bulkRequest.add(
new IndexRequest("jdgoods")
.source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
}
BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
public List<Map<String,Object>> search(String keyWord,int pageno,int pageSize) throws IOException {
SearchRequest searchRequest = new SearchRequest("jdgoods");
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
MatchQueryBuilder matchQueryBuilder = QueryBuilders.matchQuery("title", keyWord);
searchSourceBuilder.query(matchQueryBuilder);
searchSourceBuilder.from(pageno);
searchSourceBuilder.size(pageSize);
searchRequest.source(searchSourceBuilder);
//构建高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");//构建高亮字段
highlightBuilder.requireFieldMatch();//是否多个字段高亮
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
searchSourceBuilder.highlighter(highlightBuilder);
SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String,Object>> list = new ArrayList();
for (SearchHit hit : search.getHits().getHits()) {
//解析高亮字段,就是把原来结果集中的普通字段替换掉
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = hit.getSourceAsMap();//原来的结果集
StringBuilder n_title = new StringBuilder();
if (title!=null){
Text[] fragments = title.fragments();//取出字段
for (Text fragment : fragments) {
n_title.append(fragment);
}
sourceAsMap.put("title",n_title);
}
list.add(sourceAsMap);
}
return list;
}
controller
@RestController
public class IndexController {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient client;
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parase(@PathVariable("keyword") String keyword) throws Exception {
Boolean aBoolean = contentService.parseJD(keyword);
return aBoolean;
}
@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.search(keyword,pageNo,pageSize);
}
}
html
<!DOCTYPE html>
<html xmlns:th="http://www.thymeleaf.org">
<head>
<meta charset="utf-8"/>
<title>ES仿京东实战</title>
<link rel="stylesheet" th:href="@{/css/style.css}"/>
<script th:src="@{/js/jquery.min.js}"></script>
</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" @click.prevent="searchKey" id="searchbtn">搜索</button>
</div>
</fieldset>
</form>
<ul class="relKeyTop">
<li><a>Java</a ></li>
<li><a>前端</a ></li>
<li><a>Linux</a ></li>
<li><a>大数据</a ></li>
<li><a>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> this is test </li>
<li> Java </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>店铺: ZXWJava </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>
<script th:src="@{/js/axios.min.js}"></script>
<script th:src="@{/js/vue.min.js}"></script>
<script>
new Vue({
el: '#app',
data: {
keyword: '',//搜索关键字
results: [] //搜索结果
},
methods: {
searchKey(){
var keyword = this.keyword;
axios.get('search/'+keyword+"/2/10").then(
response=>{
this.results = response.data;
}
)
}
}
})
</script>
</body>
</html>
成品展示