1. 项目搭建
1.1 elasticSearch依赖版本
首先修改Spring Boot版本为2.2.5
1.2 application.properties文件
server.port=9090
# 关闭thymeleaf的缓存
spring.thymeleaf.cache=false
1.3 导入静态资源
1.4 创建首页映射
package com.rgh.controller;
@Controller
public class IndexController {
@GetMapping({"/","/index"})
public String index(){
return "index";
}
}
1.5 访问首页
2. 数据爬取
爬取京东的数据
2.1 导入jsoup依赖
用来解析网页
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.10.2</version>
</dependency>
package com.rgh.util;
@Component
public class HtmlParseUtil {
public List<Content> parseJD(String keywords) throws Exception {
//获取请求
String url = "https://search.jd.com/Search?keyword="+keywords;
//解析网页。(Jsoup返回Document就是浏览器Document对象)
Document document = Jsoup.parse(new URL(url), 30000);
//所有你在js中可以使用的方法，这里都能用
Element element = document.getElementById("J_goodsList");
//获取所有的li元素
Elements elements = element.getElementsByTag("li");
ArrayList<Content> goodsList = new ArrayList<>();
//获取元素中的内容，这里el 就是每一个li标签了
for(Element el : elements){
//关于这种图片特别多的网站，所有的图片都是延迟加载的
String img = el.getElementsByTag("img").eq(0).attr("source-data-lazy-img");
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
Content content = new Content();
content.setTitle(title);
content.setImg(img);
content.setPrice(price);
goodsList.add(content);
}
return goodsList;
}
}
2.2 创建对应的实体类
package com.rgh.pojo;
@Data
@NoArgsConstructor
@AllArgsConstructor
public class Content {
private String title;
private String img;
private String price;
}
2.3 创建配置类
package com.rgh.config;
@Configuration
public class ElasticSearchClientConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client = new RestHighLevelClient(
RestClient.builder(
new HttpHost("127.0.0.1",9200,"http")
)
);
return client;
}
}
2.4 业务编写
导入解析JSON的依赖
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.62</version>
</dependency>
前提:在es中创建一个jd_goods的索引
解析数据放入es索引中
package com.rgh.service;
@Service
public class ContentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
public Boolean parseContent(String keywords) throws Exception {
List<Content> contents = new HtmlParseUtil().parseJD(keywords);
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();
}
2.5 请求编写
package com.rgh.controller;
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parse(@PathVariable("keyword") String keyword) throws Exception{
return contentService.parseContent(keyword);
}
3. 实现搜索功能
3.1 分页+搜索+高亮业务编写
package com.rgh.service;
@Service
public class ContentService {
@Autowired
private RestHighLevelClient restHighLevelClient;
//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));
//高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.field("title");
highlightBuilder.requireFieldMatch(false);//多个高亮显示
highlightBuilder.preTags("<span style= 'color:red'>");
highlightBuilder.postTags("</span>");
sourceBuilder.highlighter(highlightBuilder);
//执行搜索
searchRequest.source(sourceBuilder);
SearchResponse search = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
//解析结果
ArrayList<Map<String,Object>> list = new ArrayList<>();
for(SearchHit hit : search.getHits().getHits()){
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField title1 = highlightFields.get("title");
Map<String, Object> sourceAsMap = hit.getSourceAsMap();//原来的结果
//解析高亮的字段，将原来的字段换为我们高亮的字段即可
if(title1 != null){
Text[] fragments = title1.fragments();
String n_title = "";
for (Text text : fragments) {
n_title += text;
}
sourceAsMap.put("title",n_title);
}
list.add(sourceAsMap);
}
return list;
}
}
3.2 请求编写
package com.rgh.controller;
@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") int pageNo,
@PathVariable("pageSize") int pageSize) throws IOException {
return contentService.searchPage(keyword,pageNo,pageSize);
}
}
4. 前端请求
4.1 引入js文件
<script th:src="@{/js/axios.min.js}"></script>
<script th:src="@{/js/vue.min.js}"></script>
4.2 Vue
4.3 页面响应成功
参考：B站狂神说Java
网友评论