1、依赖
<!--解析网页-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.10.2</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.75</version>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-elasticsearch</artifactId>
<!-- 自定义es版本依赖 否则会出bug-->
<version>7.6.1</version>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-thymeleaf</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-devtools</artifactId>
<scope>runtime</scope>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-configuration-processor</artifactId>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-test</artifactId>
<scope>test</scope>
</dependency>
2、后端
(1)配置类
//集成es 配置
@Configuration
public class ESConfig {
@Bean
public RestHighLevelClient client(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("localhost", 9200, "http")
));
return client;
}
}
(2)实体类
@Data
@NoArgsConstructor
@AllArgsConstructor
public class Content {
//商品标题
private String title;
//商品的图片
private String img;
//商品的价格
private String price;
}
(3)爬取数据工具类
当前京东首页数据自动跳转到登录页,已无法实现效果,可换一个网站
@Component
public class HtmlParseUtil {
public List<Content> goods(String keyword) throws IOException {
//获取请求
String url= "https://search.jd.com/Search?keyword="+keyword+"&enc=utf-8";
//解析网页
Document document = Jsoup.parse(new URL(url), 30000);
Element element = document.getElementById("J_goodsList");
//获取所有的li元素
Elements li = element.getElementsByTag("li");
ArrayList<Content> goodsList = new ArrayList<>();
for (Element el : li) {
//获取每一个li标签下所有的img标签下的第一个元素,属性为src
String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
//获取每一个li标签下所有的p-price标签下的第一个元素,并转换为文档
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
// 封装获取的数据
Content content = new Content();
content.setTitle(title);
content.setImg(img);
content.setPrice(price);
//将封装的好的对象放入list集合
goodsList.add(content);
}
return goodsList;
}
}
(4)service
@Service
public class ContentService {
@Resource
private RestHighLevelClient client;
public Boolean parseContent(String keywords) throws IOException {
//获取爬取的数据
List<Content> contentList = new HtmlParseUtil().goods(keywords);
//创建批量请求
BulkRequest bulkRequest = new BulkRequest();
//设置超时时间
bulkRequest.timeout("100s");
//通过for循环依次插入
for (int i = 0; i < contentList.size(); i++) {
bulkRequest.add(
new IndexRequest("jd_goods")
.source(JSON.toJSONString(contentList.get(i)), XContentType.JSON)
);
}
// 通过客户端发送请求
BulkResponse bulk = client.bulk(bulkRequest, RequestOptions.DEFAULT);
// 获得状态码
return !bulk.hasFailures();
}
public List<Map<String,Object>> goodsHighLight(String keyword,int pageNo,int pageSize) throws IOException {
SearchRequest searchRequest = new SearchRequest("jd_goods");
//构建搜索条件
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//分页
sourceBuilder.from(pageNo);
sourceBuilder.size(pageSize);
//精准查询
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
//查询器
sourceBuilder.query(termQueryBuilder);
//设置超时时间
sourceBuilder.timeout(new TimeValue(160, TimeUnit.SECONDS));
//设置高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
//设置高亮的字段
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false); //是否多个高亮显示
//高亮的样式
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
//将高亮设置放入构建器中
sourceBuilder.highlighter(highlightBuilder);
//执行搜索
searchRequest.source(sourceBuilder);
//客户端发送请求
SearchResponse search = client.search(searchRequest, RequestOptions.DEFAULT);
ArrayList<Map<String,Object>> list = new ArrayList<>();
//将所有符合条件的循环输出
for (SearchHit hit : search.getHits().getHits()) {
//取出高亮集合
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
//取出高亮中key值为title的
HighlightField title = highlightFields.get("title");
Map<String, Object> sourceAsMap = hit.getSourceAsMap();
//如果高亮字段不为空 ,就将原来的字段替换为高亮字段
if (title!=null){
Text[] fragments = title.fragments();
String n_title="";
for (Text fragment : fragments) {
n_title+=fragment;
}
sourceAsMap.put("title",n_title); //高亮字段替换原来的内容即可
}
list.add(sourceAsMap);
}
return list;
}
}
(5)controller
@Controller
public class IndexController {
@GetMapping("/")
public String index(){
return "index";
}
}
@RestController
public class ContentController {
@Autowired
ContentService service;
@RequestMapping("/goods/{keyword}")
public Boolean goods(@PathVariable("keyword") String keyword) throws IOException {
Boolean aBoolean = service.parseContent(keyword);
return aBoolean;
}
@GetMapping("/page/{keyword}/{pageNo}/{pageSize}")
public List<Map<String,Object>> page(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") int pageNo,
@PathVariable("pageSize") int pageSize) throws IOException {
List<Map<String, Object>> goods = service.goodsHighLight(keyword, pageNo, pageSize);
System.out.println(goods.toString());
return goods;
}
}
3、前端
<!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 v-html="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>
<script src="../static/js/vue.min.js"></script>
<script src="../static/js/axios.min.js"></script>
<script>
new Vue({
el: '#app',
data: {
keyword:'',
results:[] //返回的结果
},
methods: {
searchKey: function(){
var a =this.keyword;
console.log(a);
axios.get('page/'+a+"/1/30").then(function (response) {
console.log(response.data);
this.results=response.data;
console.log(response.data.title)
})
}
}
})
</script>
</body>
</html>