elasticsearch学习五：小项目实战

学习目标：项目实战elasticsearch

数据是爬虫jd页面数据同步elasticsearch

 1. elasticsearch 配置类

public class ElasticSearchClientConfig {

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

1. 实体类

@Data
@NoArgsConstructor
@AllArgsConstructor
@Builder
public class Content {
    private String img;
    private String price;
    private String title;
}

2. 爬虫数据代码

public class HtmlParseUtil {
    public List parse(String keyWord)throws Exception{
        String url = "https://search.jd.com/Search?keyword="+ keyWord;
        //解析网页
        Document document = Jsoup.parse(new URL(url), 30000);
        //js中可以使用的方法
        Element element = document.getElementById("J_goodsList");
        ArrayList contentList = new ArrayList<>();
        //获取元素中的内容
        Elements elements = element.getElementsByTag("li");
        for (Element el : elements) {
            String img = el.getElementsByTag("img").eq(0).attr("src");
            String price = el.getElementsByClass("p-price").eq(0).text();
            String title = el.getElementsByClass("p-name").eq(0).text();
            Content build = Content.builder()
                    .img(img)
                    .price(price)
                    .title(title)
                    .build();
            contentList.add(build);
        }
        return contentList;
    }
}

3.业务层

    @Autowired
    private RestHighLevelClient restHighLevelClient;

    public Boolean parse(String keyWords) throws Exception {
        HtmlParseUtil htmlParseUtil = new HtmlParseUtil();
        //把查询的数据放入到es中
        BulkRequest bulkRequest = new BulkRequest();
        List contents = htmlParseUtil.parse(keyWords);
        for (int i = 0; i < contents.size(); i++) {
             bulkRequest.add(
                     new IndexRequest("goods")
                     .id(""+(i+1))
                     .source(JSON.toJSONString(contents.get(i)), XContentType.JSON)
             );
        }
        BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
        return !bulk.hasFailures();
    }
}

5. Controller层

@RestController
public class ContentController {

    @Autowired
    private ContentService contentService;

    @RequestMapping("/parse")
    public Boolean parse(String keyWords) throws Exception {
        return contentService.parse(keyWords);
    }
}

6.测试结果

7.es查询数据

  public List> searchGoods(String keyWords,int pageNo,int pageSize) 
   throws IOException {
        //创建搜索条件
        SearchRequest searchRequest = new SearchRequest("goods");
        SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
        //分页
        sourceBuilder.from(pageNo);
        sourceBuilder.size(pageSize);
        //精确匹配
        TermQueryBuilder queryBuilder = QueryBuilders.termQuery("title", keyWords);
        sourceBuilder.query(queryBuilder);
        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
        //解析结果
        ArrayList> list = new ArrayList<>();
        for (SearchHit searchHit : searchResponse.getHits().getHits()) {
            list.add(searchHit.getSourceAsMap());
        }
        return list;
    }

8.访问测试

@RequestMapping("/searchGoods")
    public List> searchGoods(@RequestParam("keyWords")String keyWords,
                                                @RequestParam("pageNo")int pageNo,
                                                @RequestParam("pageSize")int pageSize) throws IOException {
        return contentService.searchGoods(keyWords,pageNo,pageSize);
    }

9.实现高亮效果

 

 public List> searchHigth(String keyWords,int pageNo,int pageSize) throws IOException {
        //创建搜索条件
        SearchRequest searchRequest = new SearchRequest("goods");
        SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
        //分页
        sourceBuilder.from(pageNo);
        sourceBuilder.size(pageSize);
        //高亮
        HighlightBuilder highlightBuilder = new HighlightBuilder();
        highlightBuilder.field("title");
        //多个高亮显示
        highlightBuilder.requireFieldMatch(false);
        highlightBuilder.preTags("");
        highlightBuilder.postTags("");
        //精确匹配
        TermQueryBuilder queryBuilder = QueryBuilders.termQuery("title", keyWords);
        sourceBuilder.query(queryBuilder);
        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
        //解析结果
        ArrayList> list = new ArrayList<>();
        for (SearchHit searchHit : searchResponse.getHits().getHits()) {
            Map highlightFields = searchHit.getHighlightFields();
            HighlightField title = highlightFields.get("title");
            Map sourceAsMap = searchHit.getSourceAsMap();
            //解析高亮的字段，将原来的字段换为我们高亮的字段
            if (title != null){
                Text[] fragments = title.fragments();
                String nTitle = "";
                for (Text text : fragments) {
                    nTitle += text;
                }
                sourceAsMap.put("title",nTitle);
            }
            list.add(sourceAsMap);
        }
        return list;
    }