// 拼接规格
String b1 = b1s.get(i);
String b2 = b2s.get(i);
String area = b1 + "室" + b2 + "厅";
// 去掉空格再截取,或者中间人
String str = brokers.get(i);
String trim = str.trim();
String broker = trim.split(" ")[1];
// 给对象赋值
WebHouse house = new WebHouse();
house.setTitle(title);
house.setPrice(price);
house.setArea(area);
house.setBroker(broker);
// 添加到集合
list.add(house);
}
System.out.println(list);
page.putField("house", list);
}
@Override
public Site getSite() {
return site;
}
public static void main(String[] args) {
Spider.create(new House())
.addUrl("https://bj.zu.anjuke.com/?t=1&from=0&comm_exist=on&kw=3%E5%B1%85%E5%AE%A4")
.addPipeline(new Pipeline() {
@Override
public void process(ResultItems resultItems, Task task) {
WebHouse house = resultItems.get("house");
}
})
.thread(5)
.run();
}
}
Java
##### 4.3、同步到es
* 同步之前,需要在实体类加上 `@Document` 注解,以及要查询的字段指定分词器和类型 [![house](https://img-blog.csdnimg.cn/img_convert/808e0b0bae975ae71d1a1626f8dd875b.png)](https://assets.llhnp.com/usr/images/web_house/house.png)
* 使用es提供的同步接口
package com.llh.repository;
import com.llh.domain.WebHouse;
import org.springframework.data.repository.CrudRepository;
import org.springframework.stereotype.Repository;
/**
- User: sunjunfu
- DateTime: 2023/9/23 9:56
*/
@Repository
public interface WebHouseRepository extends CrudRepository<WebHouse,Integer> {
}
Java
* 在测试类调用爬取的数据同步到es
@Test
public void test3(){
Spider.create(new House())
.addUrl(“https://bj.zu.anjuke.com/?t=1&from=0&comm_exist=on&kw=3%E5%B1%85%E5%AE%A4”)
.addPipeline(new Pipeline() {
@Override
public void process(ResultItems resultItems, Task task) {
List house = resultItems.get(“house”);
// 存入数据库
webHouseService.saveBatch(house);
// 全量同步到es
webHouseRepository.saveAll(house);
}
})
.thread(5)
.run();
}
Java
##### 4.4、编写测试接口
* WebHouseController.java
package com.llh.controller;
import cn.hutool.core.collection.CollUtil;
import cn.hutool.core.util.StrUtil;
import com.llh.domain.WebHouse;
import com.llh.form.HouseForm;
import com.llh.repository.WebHouseRepository;
import com.llh.service.WebHouseService;
import com.llh.utils.Result;
import org.elasticsearch.index.query.BoolQueryBuilder;
import org.elasticsearch.index.query.MatchQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.fetch.subphase.highlight.HighlightBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.domain.PageRequest;
import org.springframework.data.domain.Pageable;
import org.springframework.data.elasticsearch.core.ElasticsearchRestTemplate;
import org.springframework.data.elasticsearch.core.SearchHit;
import org.springframework.data.elasticsearch.core.SearchHits;
import org.springframework.data.elasticsearch.core.query.NativeSearchQuery;
import org.springframework.data.elasticsearch.core.query.NativeSearchQueryBuilder;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import javax.annotation.PostConstruct;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
/**
-
User: sunjunfu
-
DateTime: 2023/9/23 10:19
*/
@RestController
@RequestMapping(“/house”)
public class WebHouseController {
@Autowired
WebHouseService webHouseService;@Autowired
WebHouseRepository webHouseRepository;@Autowired
ElasticsearchRestTemplate elasticsearchRestTemplate;// 初始化 同步到es
@PostConstruct
public void init(){
List houses = webHouseService.list();
webHouseRepository.saveAll(houses);
}@RequestMapping(“/list”)
public Result list(WebHouse house){// 高亮 HighlightBuilder.Field[] highFiles = new HighlightBuilder.Field[1]; // 将title字段高亮显示 highFiles[0] = new HighlightBuilder.Field("title") .preTags("<font style='color: red'>") .postTags("</font>"); // 分页( es 中 0 代表第一页) Pageable page = PageRequest.of(house.getPageNum()-1,house.getPageSize()); // 组合查询 BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery(); if(StrUtil.isNotBlank(house.getTitle())){ // 模糊查询 MatchQueryBuilder matchQuery = QueryBuilders.matchQuery("title", house.getTitle()); // 同时满足条件 boolQueryBuilder.must(matchQuery); } // 构建查询条件 NativeSearchQuery query = new NativeSearchQueryBuilder() .withQuery(boolQueryBuilder) .withPageable(page) .withHighlightFields(highFiles) .build(); // 查询数据 SearchHits<WebHouse> search = elasticsearchRestTemplate.search(query, WebHouse.class); // 获取总条数 long totalHits = search.getTotalHits(); List<WebHouse> list = new ArrayList<>(); for (SearchHit<WebHouse> houseSearchHit : search) { // 获取数据对象 WebHouse webHouse = houseSearchHit.getContent(); // 获取高亮的属性 Map<String, List<String>> highlightFields = houseSearchHit.getHighlightFields(); // 获取title字段的数据 List<String> title = highlightFields.get("title"); if(CollUtil.isNotEmpty(title)){ // 将高亮后的数据覆盖 webHouse.setTitle(title.get(0)); } // 存入集合 list.add(webHouse); } // 将总条数和数据封装到对象 HouseForm houseForm = new HouseForm(totalHits, list); return Result.success(houseForm);
}
}
Java
### 5、前端页面
##### 5.1、编写展示页面
* ListView.vue
<el-form-item>
<el-button type="primary" @click="onSubmit">查询</el-button>
</el-form-item>
</el-form>
<el-table
:data="tableData"
border
style="width: 100%;">
<el-table-column
prop="id"
label="编号"
width="180">
</el-table-column>
<el-table-column
prop="title"
label="标题"
width="180">
<template v-slot="scope">
<span v-html="scope.row.title"></span>
</template>
</el-table-column>
<el-table-column
prop="price"
label="价格/月"
width="180">
</el-table-column>
<el-table-column
prop="area"
label="规格"
width="180">
</el-table-column>
<el-table-column
prop="broker"
label="中间人"
width="180">
</el-table-column>
</el-table>
<el-pagination
background
layout="prev, pager, next"
:page-size="formInline.pageSize"
:total="total"
@current-change="page">
</el-pagination>
**自我介绍一下,小编13年上海交大毕业,曾经在小公司待过,也去过华为、OPPO等大厂,18年进入阿里一直到现在。**
**深知大多数大数据工程师,想要提升技能,往往是自己摸索成长或者是报班学习,但对于培训机构动则几千的学费,着实压力不小。自己不成体系的自学效果低效又漫长,而且极易碰到天花板技术停滞不前!**
**因此收集整理了一份《2024年大数据全套学习资料》,初衷也很简单,就是希望能够帮助到想自学提升又不知道该从何学起的朋友。**
![img](https://img-blog.csdnimg.cn/img_convert/31254d24b8f8b340cc5b20907b2e8242.png)
![img](https://img-blog.csdnimg.cn/img_convert/1f170d26ceaaff73201671444bafd4f6.png)
![img](https://img-blog.csdnimg.cn/img_convert/19b82ac0158f34e94b2a68ccd5338493.png)
![img](https://img-blog.csdnimg.cn/img_convert/6fa8cf5446db6fd8acabb791190b7c06.png)
![img](https://img-blog.csdnimg.cn/img_convert/53ae244a05afdd82a560aa56b88a9ef4.png)
**既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上大数据开发知识点,真正体系化!**
**由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新**
**如果你觉得这些内容对你有帮助,可以添加VX:vip204888 (备注大数据获取)**
![img](https://img-blog.csdnimg.cn/img_convert/9bde04873e83326df9dc063c85f01d44.png)
**一个人可以走的很快,但一群人才能走的更远。不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎扫码加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!**
**既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上大数据开发知识点,真正体系化!**
**由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新**
**如果你觉得这些内容对你有帮助,可以添加VX:vip204888 (备注大数据获取)**
[外链图片转存中...(img-oIH17VvA-1712957386024)]
**一个人可以走的很快,但一群人才能走的更远。不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎扫码加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!**