org.springframework.boot spring-boot-starter-data-elasticsearch org.springframework.boot spring-boot-starter-thymeleaf org.springframework.boot spring-boot-starter-web org.jsoup jsoup 1.11.2 org.springframework.boot spring-boot-devtools runtime true org.springframework.boot spring-boot-devtools runtime true org.springframework.boot spring-boot-configuration-processor true org.projectlombok lombok true org.springframework.boot spring-boot-starter-test test com.alibaba fastjson 1.2.74
项目结构：
server.port=9090 spring.thymeleaf.cache=false
编写控制层
@Controller
public class IndexController {
@RequestMapping({"/","/index"})
public String index(){
return "index";
}
}
访问页面测试
新建工具类和实体类，工具类用于爬取网页的数据，实体类用于存储爬取到的数据。
@Data
@NoArgsConstructor
@AllArgsConstructor
public class PaperContent {
private String img;
private String price;
private String title;
}
首先我们需要查看网页的前台结构
编写爬取网页的工具类，对比网页前端的网页结构来编写代码
public ListparseHtmlElement(String keyWord) throws Exception { List paperContents=new ArrayList<>(); //keyword用于需要查询的关键字 String url="http://search.jd.com/Search?keyword="+keyWord; document document = Jsoup.parse(new URL(url), 30000); //根据id获取文档 Element element = document.getElementById("J_goodsList"); // System.out.println(element); //获取标签 Elements elements = element.getElementsByTag("li"); // System.out.println(elements); //获取元素内容，这里el就是就是标签 for (Element el:elements) { PaperContent paperContent=new PaperContent(); //获取li标签中的图片信息 //图片是通过懒加载的，并不是直接通过src来获取的 String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img"); //获取li标签中的价格信息 String price = el.getElementsByClass("p-price").eq(0).text(); //获取li标签中的书名信息 String title = el.getElementsByClass("p-name").eq(0).text(); System.out.println("==============================="); System.out.println(img); System.out.println(price); System.out.println(title); paperContent.setImg(img); paperContent.setPrice(price); paperContent.setTitle(title); paperContents.add(paperContent); } return paperContents; }
测试:
public static void main(String[] args) throws Exception {
new PageParse().parseHtmlElement("java").forEach(System.out::println);
}
后台查看是否爬取到数据：
编写配置类，连接本地Elasticsearch
@Configuration
public class ElasticSearchConfig {
@Bean
public RestHighLevelClient restHighLevelClient(){
RestHighLevelClient client=new RestHighLevelClient(
RestClient.builder(new HttpHost("127.0.0.1",9200,"http"))
);
return client;
}
}
编写Service层，将爬取到的数据放入ElasticSearch中前提是索引存在。
@Autowired
private RestHighLevelClient restHighLevelClient;
//解析数据放到elasticSearch
public Boolean parseContent(String keyword) throws Exception {
//查询到的数据
List paperContents = new PageParse().parseHtmlElement(keyword);
BulkRequest bulkRequest=new BulkRequest();
bulkRequest.timeout("2m");
//将查询到的数据放入容器中
for (int i = 0; i < paperContents.size(); i++) {
bulkRequest.add(new IndexRequest("jd_commodity")
.source(JSON.toJSONString(paperContents.get(i)), XContentType.JSON));
}
//将请求中大哥数据放入ElasticSearch(批量插入)
BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
return !bulk.hasFailures();
}
编写controller层，与前端结合
@RequestMapping("/parse/{keyword}")
public Boolean pushElk(@PathVariable("keyword") String keyword) throws Exception {
return jdService.parseContent(keyword);
}
访问地址运行测试：
查看elasticsearch是否已经存在数据
//从elasticSearch中获取数据并且高亮显示
public List> getContent(String keyword,int pageNo,int pageSize) throws IOException {
if (pageNo<=1){
pageNo=1;
}
//条件搜索
SearchRequest searchRequest=new SearchRequest("jd_commodity");
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
//分页
searchSourceBuilder.from(pageNo);
searchSourceBuilder.size(pageSize);
//精准查询
TermQueryBuilder termQueryBuilder= QueryBuilders.termQuery("title",keyword);
searchSourceBuilder.query(termQueryBuilder);
searchSourceBuilder.timeout(new Timevalue(60, TimeUnit.SECONDS));
searchRequest.source(searchSourceBuilder);
SearchResponse searchs = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
//解析结果
List> list=new ArrayList<>();
for (SearchHit hit:searchs.getHits().getHits()) {
list.add(hit.getSourceAsMap());
}
return list;
}
contoller层调用方法
@RequestMapping("/parse/{keyword}/{pageNo}/{pageSize}")
public List> getElk(@PathVariable("keyword") String keyword,
@PathVariable("pageNo") int pageNo,
@PathVariable("pageSize") int pageSize) throws IOException {
return jdService.getContent(keyword, pageNo, pageSize);
}
访问设置的地址访问
与前端结合：
（html代码）
ElasticSearch仿京东实战
测试：
可以检索出相关数据
高亮：设置高亮字段，替换原来的字段
向读取内容的方法中添加以下代码，
测试：
完成。
