樟树市建设局网站,西安哪家做网站好,西部数码 网站管理,合肥中科大网站开发项目搭建 1、启动ES#xff0c;和head-master#xff0c;用head-master建立索引 不建立也没事#xff0c;添加数据的时候会自动创建 2、导入SpringBoot需要的依赖 注意#xff1a;elasticsearch的版本要和自己本地的版本一致#xff01;所以还要在pom里面添加自定义版本…项目搭建 1、启动ES和head-master用head-master建立索引 不建立也没事添加数据的时候会自动创建 2、导入SpringBoot需要的依赖 注意elasticsearch的版本要和自己本地的版本一致所以还要在pom里面添加自定义版本 !--解析网页需要的依赖Jsoup-- dependencygroupIdorg.jsoup/groupIdartifactIdjsoup/artifactIdversion1.10.2/version /dependency !--阿里的JSon转换依赖-- dependencygroupIdcom.alibaba/groupIdartifactIdfastjson/artifactIdversion1.2.73/version /dependency !--ES启动依赖-- dependencygroupIdorg.springframework.boot/groupIdartifactIdspring-boot-starter-data-elasticsearch/artifactId /dependency !--thymeleaf模板依赖-- dependencygroupIdorg.springframework.boot/groupIdartifactIdspring-boot-starter-thymeleaf/artifactId /dependency dependencygroupIdorg.springframework.boot/groupIdartifactIdspring-boot-starter-web/artifactId /dependency !--lombok依赖-- dependencygroupIdorg.projectlombok/groupIdartifactIdlombok/artifactIdoptionaltrue/optional /dependency3、项目用到的静态资源修改过的 链接https://pan.baidu.com/s/1X1kwMHsDvML-0rBEJnUOdA提取码qjqy 4、添加SpringBoot配置(application.yml) #端口改为9090 server:port: 9090# 关闭 thymeleaf 的缓存 spring:thymeleaf:cache: false5、项目的整体结构 6、添加静态资源到项目中 7、SpringBoot中添加ES客户端配置类 ElasticSearchClientConfig.java package com.wu.config;Configuration public class ElasticSearchClientConfig {Beanpublic RestHighLevelClient restHighLevelClient() {RestHighLevelClient client new RestHighLevelClient(RestClient.builder(new HttpHost(127.0.0.1, 9200, http)));return client;} }Jsoup爬取京东数据 爬取数据 1、进入京东官网搜索java 2、按F12审查元素找到书籍所在位置 3、在utils包下建立HtmlParseUtil.java爬取测试 [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-hz6j9by4-1610955508957)(C:\Users\王东梁\AppData\Roaming\Typora\typora-user-images\image-20210118112732209.png)] //测试数据 public static void main(String[] args) throws IOException, InterruptedException {//获取请求String url https://search.jd.com/Search?keywordjava;// 解析网页 Jsou返回的Document就是浏览器的Docuement对象Document document Jsoup.parse(new URL(url), 30000);//获取id所有在js里面使用的方法在这里都可以使用Element element document.getElementById(J_goodsList);//获取所有的li元素Elements elements element.getElementsByTag(li);//用来计数int c 0;//获取元素中的内容 这里的el就是每一个li标签for (Element el : elements) {c;//这里有一点要注意直接attr使用src是爬不出来的因为京东使用了img懒加载String img el.getElementsByTag(img).eq(0).attr(data-lazy-img);//获取商品的价格并且只获取第一个text文本内容String price el.getElementsByClass(p-price).eq(0).text();String title el.getElementsByClass(p-name).eq(0).text();String shopName el.getElementsByClass(p-shop).eq(0).text();System.out.println();System.out.println(img);System.out.println(price);System.out.println(title);System.out.println(shopName);}System.out.println(c); }测试结果 获取结果没问题下面就把它封装成一个工具类 4、建立一个pojo实体类 实体类Content.java package com.wu.pojo;Data AllArgsConstructor NoArgsConstructor public class Content {private String img;private String price;private String title;private String shopName;//可以自己扩展属性 }工具类HtmlParseUtil.java package com.wu.utils;Component public class HtmlParseUtil {public ListContent parseJD(String keyword) throws IOException {ListContent list new ArrayList();String url https://search.jd.com/Search?keyword keyword;Document document Jsoup.parse(new URL(url), 30000);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 price el.getElementsByClass(p-price).eq(0).text();String title el.getElementsByClass(p-name).eq(0).text();String shopName el.getElementsByClass(p-shopnum).eq(0).text();list.add(new Content(img, price, title, shopName));}return list;} }[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Jpthiq6i-1610955508959)(C:\Users\王东梁\AppData\Roaming\Typora\typora-user-images\image-20210118115802010.png)] 5、业务层这里就不写接口了 ContentService.java 先写一个方法让爬取的数据添加到ES中 package com.wu.service;//业务编写 Service public class ContentService {//将客户端注入AutowiredQualifier(restHighLevelClient)private RestHighLevelClient client;//1、解析数据放到 es 中public boolean parseContent(String keyword) throws IOException {ListContent contents new HtmlParseUtil().parseJD(keyword);//把查询的数据放入 es 中BulkRequest request new BulkRequest();request.timeout(2m);for (int i 0; i contents.size(); i) {request.add(new IndexRequest(jd_goods).source(JSON.toJSONString(contents.get(i)), XContentType.JSON));}BulkResponse bulk client.bulk(request, RequestOptions.DEFAULT);return !bulk.hasFailures();} }6、在Controller包下建立 ContentController.java package com.wu.controller;//请求编写 RestController public class ContentController {Autowiredprivate ContentService contentService;GetMapping(/parse/{keyword})public Boolean parse(PathVariable(keyword) String keyword) throws IOException {return contentService.parseContent(keyword);} }7、启动SpringBoot项目访问它爬取数据添加到ES中 http://127.0.0.1:9090/parse/java 实现搜索功能 [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-xZLCRWps-1610955508961)(C:\Users\王东梁\AppData\Roaming\Typora\typora-user-images\image-20210118131856663.png)] 1、在ContentService.java添加 //2、获取这些数据实现基本的搜索功能 public ListMapString, Object searchPage(String keyword, int pageNo, int pageSize) throws IOException {if (pageNo 1) {pageNo 1;}if (pageSize 1) {pageSize 1;}//条件搜索SearchRequest searchRequest new SearchRequest(jd_goods);SearchSourceBuilder sourceBuilder new SearchSourceBuilder();//分页sourceBuilder.from(pageNo).size(pageSize);//精准匹配TermQueryBuilder termQuery QueryBuilders.termQuery(title, keyword);sourceBuilder.query(termQuery);sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));//执行搜索SearchRequest source searchRequest.source(sourceBuilder);SearchResponse searchResponse client.search(searchRequest, RequestOptions.DEFAULT);//解析结果ListMapString, Object list new ArrayList();for (SearchHit documentFields : searchResponse.getHits().getHits()) {list.add(documentFields.getSourceAsMap());}return list; }2、在ContentController添加搜索请求 GetMapping(/search/{keyword}/{pageNo}/{pageSize}) public ListMapString, Object search(PathVariable(keyword) String keyword,PathVariable(pageNo) int pageNo,PathVariable(pageSize) int pageSize) throws IOException {ListMapString, Object list contentService.searchPage(keyword, pageNo, pageSize);return list; }3、访问http://127.0.0.1:9090/search/java/1/10 欧克爬取和搜索都没问题下面要做的就是和前端交互了 和前端交互 1、前端接收数据 index.html 1、用vue接收数据 scriptnew Vue({el: #app,data: {keyword: , //搜索的关键字results: [] //搜索的结果},methods: {searchKey() {var keyword this.keywordaxios.get(search/ keyword /1/210).then(response {this.results response.data;//绑定数据})}}}) /script2、用vue给前端传递数据 2、访问 127.0.0.1:9090 并且搜索java 欧克完美 实现关键字高亮 1、改ContentService.java里面的搜索功能就行 //3、获取这些数据实现基本的搜索高亮功能 public ListMapString, Object searchPagehighlighter(String keyword, int pageNo, int pageSize) throws IOException {if (pageNo 1) {pageNo 1;}if (pageSize 1) {pageSize 1;}//条件搜索SearchRequest searchRequest new SearchRequest(jd_goods);SearchSourceBuilder sourceBuilder new SearchSourceBuilder();//分页sourceBuilder.from(pageNo).size(pageSize);//精准匹配TermQueryBuilder termQuery QueryBuilders.termQuery(title, keyword);// 高 亮 HighlightBuilder highlightBuilder new HighlightBuilder(); //获取高亮构造器highlightBuilder.field(title); //需要高亮的字段highlightBuilder.requireFieldMatch(false);//不需要多个字段高亮highlightBuilder.preTags(span stylecolor:red); //前缀highlightBuilder.postTags(/span); //后缀sourceBuilder.highlighter(highlightBuilder); //把高亮构造器放入sourceBuilder中sourceBuilder.query(termQuery);sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));//执行搜索SearchRequest source searchRequest.source(sourceBuilder);SearchResponse searchResponse client.search(searchRequest, RequestOptions.DEFAULT);//解析结果ListMapString, Object list new ArrayList();for (SearchHit hit : searchResponse.getHits().getHits()) {MapString, HighlightField highlightFields hit.getHighlightFields();//获取高亮字段HighlightField title highlightFields.get(title); //得到我们需要高亮的字段MapString, Object sourceAsMap hit.getSourceAsMap();//原来的返回的结果//解析高亮的字段if (title ! null) {Text[] fragments title.fragments();String new_title ;for (Text text : fragments) {new_title text;}sourceAsMap.put(title, new_title); //高亮字段替换掉原来的内容即可}list.add(sourceAsMap);}return list; }2、改变Controller里面的搜索请求 GetMapping(/search/{keyword}/{pageNo}/{pageSize}) public ListMapString, Object search(PathVariable(keyword) String keyword,PathVariable(pageNo) int pageNo,PathVariable(pageSize) int pageSize) throws IOException {ListMapString, Object list contentService.searchPagehighlighter(keyword, pageNo, pageSize);return list; }3、发现问题 需要高亮的字段前缀和后缀都有了但是这不是我们想要的结果 4、解决问题 这里Vue给了我们很方便的解决办法 5、完美