爬取数据，es搜索渲染实战

实战

爬虫

爬取数据：获取请求返回的页面信息，筛选出我们想要的数据

java中jsoup包

只能爬取网页，爬取电影，音乐用tika包

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.14.3</version>
</dependency>

爬数据工具类

@Component
public class ParseJdUtils {
    public List<Good> parseGoods(String keywords) throws Exception {
        String url = "https://search.jd.com/Search?enc=utf-8&keyword=" + keywords;
        Document document = Jsoup.parse(new URL(url), 30000);
        Element element = document.getElementById("J_goodsList");
        Elements elements = element.getElementsByTag("li");
        List<Good> list = new ArrayList<>();
        for (Element el : elements) {
            String img = el.getElementsByClass("p-img").get(0).getElementsByTag("img").attr("data-lazy-img");
            String price = el.getElementsByClass("p-price").get(0).text();
            String title = el.getElementsByClass("p-name").get(0).text();
            Good good = new Good();
            good.setTitle(title);
            good.setImg(img);
            good.setPrice(price);
            list.add(good);
        }
        return list;
    }
}

service爬取数据放入es

@Override
public boolean addGood(String keywords) throws Exception {
    List<Good> goods = parseJdUtils.parseGoods(keywords);
    BulkRequest bulkRequest = new BulkRequest("jd_good");
    bulkRequest.timeout("2m");
    for (int i = 0; i < goods.size(); i++) {
        Good good = goods.get(i);
        bulkRequest.add(new IndexRequest().id((i + 1) + "").source(JSONObject.toJSONString(good), XContentType.JSON));
    }
    BulkResponse bulk = restHighLevelClient.bulk(bulkRequest, RequestOptions.DEFAULT);
    return !bulk.hasFailures();
}

搜索和高亮搜索

@Override
public List<Map<String, Object>> search(String keywords, int pageNo, int pageSize) throws IOException {
    //搜索请求
    SearchRequest searchRequest = new SearchRequest("jd_good");

    //搜索条件
    SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
    TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("title", "java");
    sourceBuilder.query(termQueryBuilder);
    sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));

    //高亮
    HighlightBuilder highlightBuilder = new HighlightBuilder();
    highlightBuilder.field("title");//高亮字段
    highlightBuilder.requireFieldMatch(false);//多个高亮显示关闭
    highlightBuilder.preTags("<span style='color:red'>");//高亮标签和样式前缀
    highlightBuilder.postTags("</span>");//高亮猴准
    sourceBuilder.highlighter(highlightBuilder);

    //分页
    sourceBuilder.from((pageNo - 1) * pageSize);//从第几条开始=size*（pageNo-1）
    sourceBuilder.size(pageSize);

    searchRequest.source(sourceBuilder);
    SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
    List<Map<String, Object>> result = new ArrayList<>();


    //1.非高亮展示
    /*for (SearchHit hit : searchResponse.getHits().getHits()) {
        result.add(hit.getSourceAsMap());
    }*/

    //2.高亮
    for (SearchHit hit : searchResponse.getHits().getHits()) {
        Map<String, HighlightField> highlightFields = hit.getHighlightFields();
        HighlightField title = highlightFields.get("title");
        Map<String, Object> sourceAsMap = hit.getSourceAsMap();
        if (title != null) {
            Text[] fragments = title.fragments();
            StringBuilder newTitle = new StringBuilder();
            for (Text fragment : fragments) {
                newTitle.append(fragment);
            }
            sourceAsMap.put("title", newTitle.toString());
        }
        result.add(sourceAsMap);

    }

    return result;
}