ElasticSearch_仿京东搜索
仿京东搜索
目录- 仿京东搜索
- 1. 爬虫
- 1. 测试使用爬虫
- 2. 提取工具类
- 3. 编写实体类和业务层
- 1. 实体类
- 2. 业务层
- 4. 页面跳转
- 5. 前端
- 1. 爬虫
本博客内容根据狂神说整理
https://www.bilibili.com/video/BV17a4y1x7zq
1. 爬虫
首先明确数据从哪里来
- 数据库中获取
- 消息队列中获取
- 爬虫
- ......
爬取数据 : 获取请求返回的页面信息, 筛选出屋面想要的信息就可以了!
导入依赖 JSoup, 解析网页 ==> 爬电影, 音乐, 用tika
org.jsoup
jsoup
1.13.1
1. 测试使用爬虫
package com.wang.wangesjd.utils;
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.net.URL;
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
//获取请求 https://search.jd.com/Search?keyword=java
//前提: 需要联网, 而且不能获取到AJAX!
String url = "https://search.jd.com/Search?keyword=java";
//设置超时时间 30S
int timeOut = 30000;
//解析网页 ==> Document就是浏览器的Document对象
Document document = Jsoup.parse(new URL(url), timeOut);
//所有你在JS中可以使用的方法, 这里都能用!
Element element = document.getElementById("J_goodsList");
// System.out.println(element.html());
//获取所有的li元素
Elements elements = element.getElementsByTag("li");
//获取元素中的内容, 这里的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!
//JD 放在了这个class data-lazy-img
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();
System.out.println("===================================================");
System.out.println(img);
System.out.println(price);
System.out.println(title);
}
}
}
- 注意
- JD 貌似图片使用了反爬虫技术, 要获取的属性名和我们在前端调试时看到的不一样...
2. 提取工具类
package com.wang.wangesjd.utils;
import com.wang.wangesjd.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.net.URL;
import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.List;
public class HtmlParseUtil {
public static void main(String[] args) throws IOException {
//URL会将符号转义!
// HtmlParseUtil.parseJD("C%2B%2B").forEach(System.out::println);
//查询中文需要URL转码
// HtmlParseUtil.parseJD("心理学").forEach(System.out::println);
HtmlParseUtil.parseJD("C++").forEach(System.out::println);
}
public static List parseJD(String keywords) throws IOException {
//URL会对符号和汉字转码
//要先转码再拼接, 否则URL无法解析 (因为会将url中的符号也一起转码, 无法识别)
String urlKeywords = URLEncoder.encode(keywords, "UTF-8");
//获取请求 https://search.jd.com/Search?keyword=java
//前提: 需要联网, 而且不能获取到AJAX!
String url ="https://search.jd.com/Search?keyword=" + urlKeywords + "&enc=utf-8";
//设置超时时间 30S
int timeOut = 30000;
//解析网页 ==> Document就是浏览器的Document对象
Document document = Jsoup.parse(new URL(url), timeOut);
//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");
List goodsList = new ArrayList<>();
//获取元素中的内容, 这里的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!
//JD 放在了这个class data-lazy-img
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();
Content content = new Content();
content.setImg(img)
.setPrice(price)
.setTitle(title);
goodsList.add(content);
}
return goodsList;
}
}
- 注意
- URL解析时会转义符号和中文, 因此如果我们想传递中文或者符号的关键字, 需要先转义
- 不能将拼接后的url转义, 这样会导致URL中正常的符号也被转义, 导致无法识别, 正确的做法是先将被拼接的转义, 再拼接即可
3. 编写实体类和业务层
1. 实体类
package com.wang.wangesjd.pojo;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import lombok.experimental.Accessors;
@Data
@AllArgsConstructor
@NoArgsConstructor
@Accessors(chain = true)
public class Content {
private String img;
private String price;
private String title;
}
2. 业务层
这里有个小坑 ==> SpringBoot接管类, 如果是静态方法, 使用自动装载无法使用静态方法
package com.wang.wangesjd.service;
import com.alibaba.fastjson.JSON;
import com.wang.wangesjd.pojo.Content;
import com.wang.wangesjd.utils.HtmlParseUtil;
import org.elasticsearch.action.bulk.BulkRequest;
import org.elasticsearch.action.bulk.BulkResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.text.Text;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.common.xcontent.XContentType;
import org.elasticsearch.index.query.MatchQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.index.query.TermQueryBuilder;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.search.fetch.subphase.highlight.HighlightBuilder;
import org.elasticsearch.search.fetch.subphase.highlight.HighlightField;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
@Service
public class ContentService {
@Autowired
@Qualifier("restHighLevelClient")
private RestHighLevelClient rest;
@Autowired
private HtmlParseUtil htmlParseUtil;
//解析数据, 放入ES索引中
public Boolean parseContent(String keywords) throws IOException {
List contents = htmlParseUtil.parseJD(keywords);
//把查询的数据放入ES中
BulkRequest bulkRequest = new BulkRequest();
bulkRequest.timeout(TimeValue.timeValueMinutes(2L));
for (int i = 0; i < contents.size(); i++) {
bulkRequest.add(new IndexRequest("jd_goods")
.source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
}
BulkResponse bulk = rest.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
//获取这些数据(从ES索引中), 实现搜索功能
// public List> 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();
// //精准匹配
// MatchQueryBuilder matchQueryBuilder = QueryBuilders.matchQuery("title", keyword);
// sourceBuilder.query(matchQueryBuilder)
// .timeout(TimeValue.timeValueMinutes(1L));
// //分页
// sourceBuilder.from(pageNo)
// .size(pageSize);
// //执行搜索
// searchRequest.source(sourceBuilder);
// SearchResponse searchResponse = rest.search(searchRequest, RequestOptions.DEFAULT);
// //解析结果
// List> list = new ArrayList<>();
// for (SearchHit documentFields : searchResponse.getHits()) {
// list.add(documentFields.getSourceAsMap());
// }
// return list;
// }
//实现搜索高亮
public List> 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();
//精准匹配
MatchQueryBuilder matchQueryBuilder = QueryBuilders.matchQuery("title", keyword);
sourceBuilder.query(matchQueryBuilder)
.timeout(TimeValue.timeValueMinutes(1L));
//高亮
HighlightBuilder highlightBuilder = new HighlightBuilder();
//定义要高亮的标签和样式
highlightBuilder.field("title")
.preTags("")
.postTags("")
.requireFieldMatch(false); //是否需要高亮多个字段
sourceBuilder.highlighter(highlightBuilder);
//分页
sourceBuilder.from(pageNo)
.size(pageSize);
//执行搜索
searchRequest.source(sourceBuilder);
SearchResponse searchResponse = rest.search(searchRequest, RequestOptions.DEFAULT);
//解析结果
List> list = new ArrayList<>();
for (SearchHit documentFields : searchResponse.getHits()) {
//解析高亮的字段
Map highlightFields = documentFields.getHighlightFields();
HighlightField title = highlightFields.get("title");
Map sourceAsMap = documentFields.getSourceAsMap(); //这里是原来的结果(不含高亮)
if(title != null) {
Text[] fragments = title.fragments();
String highlightTitle = "";
for (Text text : fragments) {
highlightTitle += text;
}
//将高亮字段替换没有高亮的字段
sourceAsMap.put("title", highlightTitle);
}
list.add(sourceAsMap);
}
return list;
}
}
4. 页面跳转
package com.wang.wangesjd.controller;
import com.wang.wangesjd.service.ContentService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.PathVariable;
import org.springframework.web.bind.annotation.RestController;
import java.io.IOException;
import java.util.List;
import java.util.Map;
@RestController
public class ContentController {
@Autowired
private ContentService contentService;
@GetMapping("/parse/{keyword}")
public Boolean parse(@PathVariable String keyword) throws IOException {
return contentService.parseContent(keyword);
}
@GetMapping("/search/{keyword}/{pageNo}/{pageSize}")
public List> search(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") int pageNo,
@PathVariable("pageSize") int pageSize) throws IOException {
return contentService.searchPage(keyword, pageNo, pageSize);
}
}
使用RestFul风格
5. 前端
ES仿京东实战
- 注意
- 由于后端高亮传回来的是一个html, 我们需要解析, 不能单纯的双向绑定, 因此用 v-html