京东案例

京东案例

1、导入页面

2、创建jd_goods索引

3、编写业务逻辑

爬取数据

    public static List<Content> parseJD(String keywords) throws IOException {

        String url = "https://search.jd.com/Search?keyword="+keywords;
        //解析网页
        Document document = Jsoup.parse(new URL(url), 30000);
        //所有你在js中可以使用的方法，这都有
        Element element = document.getElementById("J_goodsList");
        //获取所有的li元素
        Elements elements = element.getElementsByTag("li");
        //获取元素中的内容，这里el就是每一个li标签了
        ArrayList<Content> goodsList = new ArrayList<>();
        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 content = new Content();
            content.setImg(img);
            content.setPrice(price);
            content.setTitle(title);
            goodsList.add(content);
        }
        return goodsList;
    }

    @Override
    public Boolean parseContent(String keywords) throws IOException {
        List<Content> contentList = HtmlParseUtil.parseJD(keywords);
        //吧查询到的数据放入es中
        BulkRequest bulkRequest = new BulkRequest();
        bulkRequest.timeout("2m");

        for (int i=0;i<contentList.size();i++){
            ObjectMapper mapper = new ObjectMapper();
            if (contentList.get(i).getImg()==""||contentList.get(i).getImg()==null){
                continue;
            }
            String content = mapper.writeValueAsString(contentList.get(i));
            bulkRequest.add(
                    new IndexRequest("jd_goods")
                    .source(content, XContentType.JSON));
        }
        BulkResponse bulkResponse = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
        System.out.println(bulkResponse.status());
        return !bulkResponse.hasFailures();
    }

查询的接口

    @Override
    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");
        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
        ArrayList<Map<String,Object>> list = new ArrayList<>();
        for (SearchHit documentFields:searchResponse.getHits().getHits()){
            list.add(documentFields.getSourceAsMap());
        }
        return list;
    }

高亮查询接口

    @Override
    public List<Map<String, Object>> highLightSearch(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();
        //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));

        //高亮
        HighlightBuilder highlightBuilder = new HighlightBuilder();
        highlightBuilder.field("title");
        highlightBuilder.requireFieldMatch(false); //多个高亮显示
        highlightBuilder.preTags("<span style='color:red'>");
        highlightBuilder.postTags("</span>");
        sourceBuilder.highlighter(highlightBuilder);

        //执行搜索
        searchRequest.source(sourceBuilder);
        SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
        //解析结果
        ArrayList<Map<String,Object>> list = new ArrayList<>();
        for (SearchHit documentFields:searchResponse.getHits().getHits()){

            Map<String, HighlightField> highlightFields = documentFields.getHighlightFields();//获取高亮部分title
            HighlightField title = highlightFields.get("title"); //获取title内容
            Map<String, Object> sourceAsMap = documentFields.getSourceAsMap();//原来的结果
            //解析高亮的字段，将原来的字段换成我们高亮的字段即可
            if (title!=null){
                Text[] fragments = title.fragments();//提取高亮内容
                String n_title = "";
                for (Text text:fragments){ //
                    n_title += text; //将高亮部分替换给n_title
                }
                sourceAsMap.put("title", n_title); //高亮的字段替换原来的内容
            }

            list.add(sourceAsMap);
        }
        return list;
    }