Elasticsearch—jd实战

Elasticsearch—jd实战

此项目为了训练ElasticSearch的熟练度，通过爬虫获取jd的数据，完成数据库查询

本章资料： https://pan.baidu.com/s/1fu_KHu5VCBKorbgJgbvVwA 提取码：3ij8

一、创建Springboot项目

• 略

二、编写代码

1、导入依赖

•     <properties>
          <java.version>1.8</java.version>
          <elasticsearch.version>7.8.0</elasticsearch.version>
      </properties>
      <dependencies>
          <dependency>
              <groupId>org.springframework.boot</groupId>
              <artifactId>spring-boot-starter-data-elasticsearch</artifactId>
          </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>
          <!-- jsoup解析页面 -->
          <!-- 解析网页 爬视频可 研究tiko -->
          <dependency>
              <groupId>org.jsoup</groupId>
              <artifactId>jsoup</artifactId>
              <version>1.10.2</version>
          </dependency>
          <!-- fastjson -->
          <dependency>
              <groupId>com.alibaba</groupId>
              <artifactId>fastjson</artifactId>
              <version>1.2.70</version>
          </dependency>
      </dependencies>
  

2、导入前端素材

3、编写application.preperties配置文件

• #端口号
  server.port=8011
  #关闭网页缓存
  spring.thymeleaf.cache=false
  

4、编写IndexController、测试index

• @Controller
  public class IndexController {
         
  
      @GetMapping({
         "/", "index"})
      public String index(){
         
          return "index";
      }
  }
  

• 

5、编写爬虫

1. 分析京东搜索页面

   • http://search.jd.com/search?keyword=java
   • 
   • 审查页面元素
     • 页面列表id：J_goodsList
     • 
     • 

2. 爬取数据（获取请求返回的页面信息，筛选出可用的）

   • 创建HtmlParseUtil，并简单编写

   • public class HtmlParseUtil {
              
         public static void main(String[] args) throws IOException {
              
             /// 使用前需要联网
             // 请求url
             String url = "http://search.jd.com/search?keyword=java";
             // 1.解析网页(jsoup 解析返回的对象是浏览器Document对象)
             Document document = Jsoup.parse(new URL(url), 30000);
             // 使用document可以使用在js对document的所有操作
             // 2.获取元素（通过id）
             Element j_goodsList = document.getElementById("J_goodsList");
             // 3.获取J_goodsList ul 每一个 li
             Elements lis = j_goodsList.getElementsByTag("li");
             // 4.获取li下的 img、price、name
             for (Element li : lis) {
              
                 String img = li.getElementsByTag("img").eq(0).attr("src");// 获取li下 第一张图片
                 String name = li.getElementsByClass("p-name").eq(0).text();
                 String price = li.getElementsByClass("p-price").eq(0).text();
     
                 System.out.println("=======================");
                 System.out.println("img : " + img);
                 System.out.println("name : " + name);
                 System.out.println("price : " + price);
             }
         }
     }
     

   • 

   • 一般图片特别多的网站，所有的图片都是通过延迟加载的

   • // 打印标签内容
     Elements lis = j_goodsList.getElementsByTag("li");
     System.out.println(lis);
     

   • 打印所有li标签，发现img标签中并没有属性src的设置，只是data-lazy-ing设置图片加载的地址

   • 

3. 实现爬取JD数据

   1. 创建实体类

      • @Data
        @AllArgsConstructor
        @NoArgsConstructor
        public class Content implements Serializable {
                   
            private String name;
            private String img;
            private String price;
        }
        

   2. 封装工具栏

      • public class HtmlParseUtil {
                   
            public static void main(String[] args) throws IOException {
                   
                System.out.println(parseJD("java"));
            }
        
        
            public static List<Content> parseJD(String keyword) throws IOException {
                   
                /// 使用前需要联网
                // 请求url
                String url = "http://search.jd.com/search?keyword=" + keyword;
                // 1.解析网页(jsoup 解析返回的对象是浏览器Document对象)
                Document document = Jsoup.parse(new URL(url), 30000);
                // 使用document可以使用在js对document的所有操作
                // 2.获取元素（通过id）
                Element j_goodsList = document.getElementById("J_goodsList");
                //j_goodsList 如果这里为空   用下面这个方法
                //Document 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();
                // 3.获取J_goodsList ul 每一个 li
                Elements lis = j_goodsList.getElementsByTag("li");
                // System.out.println(lis);
                // 4.获取li下的 img、price、name
                // list存储所有li下的内容
                List<Content> contents = new ArrayList<Content>();
                for (Element li : lis) {
                   
                    // 由于网站图片使用懒加载，将src属性替换为data-lazy-img
                    String img = li.getElementsByTag("img").eq(0).attr("data-lazy-img");// 获取li下 第一张图片
                    String name = li.getElementsByClass("p-name").eq(0).text();
                    String price = li.getElementsByClass("p-price").eq(0).text();
                    // 封装为对象
                    Content content = new Content(name,img,price);
                    // 添加到list中
                    contents.add(content);
                }
                // System.out.println(contents);
                // 5.返回 list
                return contents;
            }
        }
        

      • 操作响应结果：

        • 

6、编写config

• @Configuration
  public class ElasticSearchConfig {
         
  
      @Bean
      public RestHighLevelClient restHighLevelClient(){
         
          RestHighLevelClient client = new RestHighLevelClient(
                  RestClient.builder(
                      new HttpHost("127.0.0.1", 9200, "http")
                  )
          );
          return client;
      }
  }
  

7、编写Service

• @Service
  public class ContentService {
         
  
      @Autowired
      private RestHighLevelClient client;
  
  
      // 1、解析数据放入 es 索引中
      public Boolean parseContent(String keyword) throws IOException {
         
          // 获取内容
          List<Content> contents = HtmlParseUtil.parseJD(keyword);
          // 内容放入 es 中
          BulkRequest request = new BulkRequest();
          request.timeout("2m"); // 可更具实际业务是指
          for (int i = 0; i < contents.size(); i++) {
         
              request.add(
                      new IndexRequest("jd_goods")
                              .id(""+(i+1))
                              .source(JSON.toJSONString(contents.get(i)), XContentType.JSON)
              );
          }
          BulkResponse responses = client.bulk(request, RequestOptions.DEFAULT);
          return !responses.hasFailures();
      }
  
      // 2、根据keyword分页查询结果
      public List<Map<String, Object>> search(String keyword, Integer pageIndex, Integer pageSize) throws IOException {
         
          if (pageIndex < 0){
         
              pageIndex = 0;
          }
  
          //高级查询-请求对象
          SearchRequest request = new SearchRequest("jd_goods");
          // 构建查询的请求体
          SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
          // 构建精确查询请求——>通过keyword查字段name
          TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("name", keyword);
          //把精确查询请求放入请求体
          searchSourceBuilder.query(termQueryBuilder);
          searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));// 60s
          // 分页
          searchSourceBuilder.from(pageIndex);
          searchSourceBuilder.size(pageSize);
  
          // 高亮
          HighlightBuilder highlightBuilder = new HighlightBuilder();
          highlightBuilder.field("name");
          highlightBuilder.preTags("");
          highlightBuilder.postTags("");
          searchSourceBuilder.highlighter(highlightBuilder);
  
          request.source(searchSourceBuilder);
          SearchResponse searchResponse = client.search(request, RequestOptions.DEFAULT);
          // 解析结果 ==========
          SearchHits hits = searchResponse.getHits();
          List<Map<String, Object>> results = new ArrayList<>();
          for (SearchHit documentFields : hits.getHits()) {
         
              // 使用新的字段值（高亮），覆盖旧的字段值
              Map<String, Object> sourceAsMap = documentFields.getSourceAsMap();
              // 高亮字段
              Map<String, HighlightField> highlightFields = documentFields.getHighlightFields();
              HighlightField name = highlightFields.get("name");
              // 替换
              if (name != null){
         
                  Text[] fragments = name.fragments();
                  StringBuilder new_name = new StringBuilder();
                  for (Text text : fragments) {
         
                      new_name.append(text);
                  }
                  sourceAsMap.put("name",new_name.toString());
              }
              results.add(sourceAsMap);
          }
          return results;
      }
  }
  

8、编写Controller

• @RestController
  public class ContentController {
         
  
      @Autowired
      private ContentService contentService;
  
      @GetMapping("/parse/{keyword}")
      public Boolean parse(@PathVariable("keyword") String keyword) throws IOException {
         
          return contentService.parseContent(keyword);
      }
  
      @GetMapping("/search/{keyword}/{pageIndex}/{pageSize}")
      public List<Map<String, Object>> parse(@PathVariable("keyword") String keyword,
                                             @PathVariable("pageIndex") Integer pageIndex,
                                             @PathVariable("pageSize") Integer pageSize) throws IOException {
         
          return contentService.search(keyword,pageIndex,pageSize);
      }
  }
  

9、测试结果

• 
• 
• 

三、前后端分离(简单使用vue)

1、下载并引入Vue.min.js和axios.js

1. 如果安装了nodejs，可以按如下步骤，没有自行下载

2. 自行创建一个文件夹打开命令行执行以下代码

3. npm install vue
   npm install axios
   

4. 

5. 

2、在页面引入资源

1. <script th:src="@{/js/vue.min.js}">script>
   <script th:src="@{/js/axios.min.js}">script>	
   

2. 前端全代码如下：

   • 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 ">
     
             
             <div id="header" class=" header-list-app">
                 <div class="headerLayout">
                     <div class="headerCon ">
                         
                         <h1 id="mallLogo">
                             <img th:src="@{/images/jdlogo.png}" alt="">
                         h1>
     
                         <div class="header-extra">
     
                             
                             <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>狂神说Javaa>li>
                                     <li><a>狂神说前端a>li>
                                     <li><a>狂神说Linuxa>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>
     
             
             <div id="content">
                 <div class="main">
                     
                     <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>
     
                     
                     <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>
     
                     
                     <div class="view grid-nosku">
     
                         <div class="product" v-for="result in results">
                             <div class="product-iWrap">
                                 
                                 <div class="productImg-wrap">
                                     <a class="productImg">
                                         <img :src="result.img">
                                     a>
                                 div>
                                 
                                 <p class="productPrice">
                                     <em>{
             {result.price}}em>
                                 p>
                                 
                                 <p class="productTitle">
                                     <a v-html="result.name"> a>
                                 p>
                                 
                                 <div class="productShop">
                                     <span>店铺： 狂神说Java span>
                                 div>
                                 
                                 <p class="productStatus">
                                     <span>月成交<em>999笔em>span>
                                     <span>评价 <a>3a>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: '',
                 results:[]
             },
             methods:{
                
                 searchKey(){
                
                     let keyword=this.keyword;
                     console.log(keyword);
                     ///search/{keyword}/{pageNum}/{pageSize}
                     axios.get('search/'+keyword+"/1/20").then(response=>{
                
                         console.log(response);
                         this.results=response.data;
                     });
                 }
             }
     
         })
     script>
     
     body>
     html>
     

四、最终测试结果

•