1.Jsoup获取数据
<!--jsoup-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
</dependency>
import com.mine.esjd.pojo.Content;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class HtmlParseUtil {
public static void main(String[] args) throws Exception {
parseJD("java").forEach(System.out::println);
}
/**
* parseJD
*
* @return
*/
public static List<Content> parseJD(String keyword) {
List<Content> list = new ArrayList<>();
String url = "https://search.jd.com/Search?keyword=" + keyword;
//Document document = Jsoup.parse(new URL(url), 30000);
Document document = null;
try {
document = Jsoup.connect(url).userAgent("Mozilla/5.0 (Windows NT 5.1; zh-CN) AppleWebKit/535.12 (KHTML, like Gecko) Chrome/22.0.1229.79 Safari/535.12").timeout(30000).get();
} catch (IOException e) {
e.printStackTrace();
}
if (document == null) {
return list;
}
Element element = document.getElementById("J_goodsList");
Elements elements = element.getElementsByTag("li");
for (Element el : elements) {
String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
String pricce = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
list.add(new Content(title, pricce, img));
}
return list;
}
}
2.添加数据至ES
<!-- lombok -->
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
</dependency>
<!-- fastjson -->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
</dependency>
<!-- elasticsearch -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-elasticsearch</artifactId>
</dependency>
<!--thymeleaf -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-thymeleaf</artifactId>
</dependency>
<!-- web -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<!--jsoup-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
</dependency>
<!--hutool-->
<dependency>
<groupId>cn.hutool</groupId>
<artifactId>hutool-all</artifactId>
</dependency>
@Configuration
public class ESConfig {
@Bean
public RestHighLevelClient restHighLevelClient() {
return new RestHighLevelClient(RestClient.builder(new HttpHost("127.0.0.1", 9200, "http")));
}
}
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Content {
private String title;
private String price;
private String img;
}
public interface ContentService {
/**
* 添加数据至ES
*
* @param keyword
* @return
*/
public boolean parse(String keyword);
}
@Service
public class ContentServiceImpl implements ContentService {
Snowflake snowflake = IdUtil.getSnowflake(1, 1);
@Autowired
private RestHighLevelClient restHighLevelClient;
@Override
public boolean parse(String keyword) {
List<Content> contents = HtmlParseUtil.parseJD(keyword);
BulkRequest request = new BulkRequest();
request.timeout("30s");
for (int i = 0; i < contents.size(); i++) {
request.add(new IndexRequest("jd_goods").id(snowflake.nextIdStr()).source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
}
try {
BulkResponse response = restHighLevelClient.bulk(request, RequestOptions.DEFAULT);
return !response.hasFailures();
} catch (IOException e) {
e.printStackTrace();
}
return false;
}
}
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parse(@PathVariable("keyword") String keyword) {
return contentService.parse(keyword);
}
}
- 访问http://localhost:9090/parse/{yourword}
3.搜索结果
<!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>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><a href="#"> </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：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 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() {
var keyword = this.keyword;
console.log(keyword);
axios.get('search/' + keyword + '/1/30').then(response=>{
this.results=response.data;
console.log(this.results);
});
}
}
})
</script>
</body>
</html>
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/search/{keyword}/{pageNo}/{pageSize}")
public List<Map<String, Object>> search(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") Integer pageNo,
@PathVariable("pageSize") Integer pageSize
) {
return contentService.search(keyword, pageNo, pageSize);
}
}
public interface ContentService {
/**
* 从ES查询数据
*
* @param keyword
* @param pageNo
* @param pageSize
* @return
*/
public List<Map<String, Object>> search(String keyword, Integer pageNo, Integer pageSize);
}
@Service
public class ContentServiceImpl implements ContentService {
Snowflake snowflake = IdUtil.getSnowflake(1, 1);
@Autowired
private RestHighLevelClient restHighLevelClient;
@Override
public List<Map<String, Object>> search(String keyword, Integer pageNo, Integer pageSize) {
List<Map<String, Object>> list = new ArrayList<>();
SearchRequest searchRequest = new SearchRequest("jd_goods");
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//分页
sourceBuilder.from((pageNo - 1) * pageSize);
sourceBuilder.size(pageSize);
//精准查询
//TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
//match查询
MatchQueryBuilder matchQueryBuilder = QueryBuilders.matchQuery("title", keyword);
sourceBuilder.query(matchQueryBuilder);
sourceBuilder.timeout(TimeValue.timeValueSeconds(30));
//高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.preTags("<span style='color:red'>");
highlightBuilder.postTags("</span>");
highlightBuilder.field("title");
sourceBuilder.highlighter(highlightBuilder);
//执行搜索
searchRequest.source(sourceBuilder);
try {
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
for (SearchHit searchHit : searchResponse.getHits().getHits()) {
//高亮置换
Map<String, HighlightField> highlightFields = searchHit.getHighlightFields();
Text[] fragments = highlightFields.get("title").fragments();
String highlightTitle = "";
if (null != fragments && fragments.length > 0) {
for (int i = 0; i < fragments.length; i++) {
highlightTitle += fragments[i];
}
}
Map<String, Object> asMap = searchHit.getSourceAsMap();
if (StrUtil.isNotEmpty(highlightTitle)) {
asMap.put("title", highlightTitle);
}
list.add(asMap);
}
} catch (IOException e) {
e.printStackTrace();
}
return list;
}
}
- 测试结果
