springboot整合es实战

springboot整合es实战

在做springboot和elasticsearch整合实战时，elasticsearch服务我用的docker容器，由于是第一次整合遇到许多bug。再次做记录。

1.elasticsearch的服务的跨域问题
解决链接

2.elasticsearch-head创建索引响应406
解决链接

3.由于版本的原因在es6.x需要在往索引增加Document时添加type字段
参考

4.es-head的github地址，告诉我们怎么开启es-head的服务
链接

下面时相关实战：
一、ES数据来源，我选择通过爬虫爬取数据，存到es中

@Component
public class HtmlParseUtil {
    public List<Content> parseJD(String keywords)throws Exception{
        //1.获取请求
        String url = "https://search.jd.com/Search?keyword="+keywords;
        //2.解析网页(Jsoup返回Document就是浏览器的Document对象)
        Document document = Jsoup.parse(new URL(url), 30000);
        Element ele = document.getElementById("J_goodsList");
        //System.out.println(ele);
        List<Content> list = new ArrayList<>();
        //获取所有的li标签
        Elements tag_lis = ele.getElementsByTag("li");
        //获取元素中的内容,这里每个element就是li标签
        for(Element element:tag_lis){
            String img = element.getElementsByTag("img").eq(0).attr("src");
            String price = element.getElementsByClass("p-price").eq(0).text();
            String title = element.getElementsByClass("p-name").eq(0).text();
            //封装对象
            Content content = new Content();
            content.setTitle(title);
            content.setImg(img);
            content.setPrice(price);
            list.add(content);
        }
        return list;
    }
}

通过上面的工具类能取京东爬取关键字商品的信息(图片url、title、price)，前提是要导入相关依赖。
以杜蕾斯为关键字，测试效果：
二.es的配置(原生)

@Configuration
public class ElasticSearchClientConfig {
    @Bean
    public RestHighLevelClient restHighLevelClient(){
        return new RestHighLevelClient(
                RestClient.builder(
                        new HttpHost("192.168.1.101", 9200,"http")));
    }
}

三.service层

@Service
public class ContentService {

    @Autowired
    private RestHighLevelClient restHighLevelClient;
    @Autowired
    private HtmlParseUtil htmlParseUtil;

    //1.解析数据放入es索引中
    public Boolean parseContent(String keywords) throws Exception{
        List<Content> contents = htmlParseUtil.parseJD(keywords);
        //把查询出来的数据放入es里面
        BulkRequest bulkRequest = new BulkRequest();
        bulkRequest.timeout("2m");

        for(int i=0;i<contents.size();i++){
            System.out.println(contents.get(i));
            bulkRequest.add(
                    new IndexRequest("jd_goods_2",keywords+"")
                    .source(JSON.toJSONString(contents.get(i)), XContentType.JSON));
        }
        BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
        return !bulk.hasFailures();
    }

    //2.获取这些数据实现搜索功能
    public List<Map<String,Object>> searchPage(String keyword, int pageNo, int pageSize) throws IOException {
        if(pageNo<=1){
            pageNo = 1;
        }
        //条件搜索
        SearchRequest searchRequest = new SearchRequest("jd_goods");
        //资源构造器(封装查询条件)
        SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();

        //分页
        sourceBuilder.from(pageNo);
        sourceBuilder.size(pageSize);

        //精准匹配
        TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", keyword);
        sourceBuilder.query(termQueryBuilder);
        sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));

        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);

        //解析结果
        List<Map<String,Object>> list = new ArrayList<>();
        for(SearchHit documentFields:searchResponse.getHits().getHits()){
            list.add(documentFields.getSourceAsMap());
        }
        return list;
    }
}

四.controller层

@Controller
public class ContentController {
    @Autowired
    private ContentService contentService;

    //从京东爬取关键字信息(title、price、src)存放到es中
    @GetMapping("/parse/{keyword}")
    @ResponseBody
    public Boolean parse(@PathVariable String keyword) throws Exception{
        return contentService.parseContent(keyword);
    }

    //从es中查询相关的信息 参数一：关键字 参数二：页码 参数三：显示条数
    @GetMapping("/search/{keyword}/{pageNo}/{pageSize}")
    @ResponseBody
    public List<Map<String,Object>> search(@PathVariable("keyword")String keyword,
                                           @PathVariable("pageNo")int pageNo,
                                           @PathVariable("pageSize")int pageSize) throws IOException {
        if(pageNo==0){
            pageNo=1;
        }
        if(pageSize==0){
            pageSize=5;
        }
        return contentService.searchPage(keyword,pageNo,pageSize);
    }

    @GetMapping("/parse/add2es")
    public String test(String keyword){
        System.out.println(keyword);
        return "redirect:/parse/"+keyword;
    }
}

效果：