java扒取网页，获取所需要内容列表展示

1.扒取原网页内容：

　　

2.本地展示效果

　　

3.代码

　　

    @ResponseBody
    public Map<String, Object> findGuoWuYaoWen(HttpServletRequest request, ModelMap model, String area,String city) {
        Map<String, Object> map = new HashMap<String, Object>();
        Map<String, Object> result = new HashMap<String, Object>();
        List<NationalNews> nationalList = new ArrayList<>();
        String title,newsUrl,time;
        
        Elements elements = getUrlElements();
        System.out.println("========================"+elements.toString());
        List<Element> subList = elements.subList(0, 9);
        for (Element element : subList) {
             String  title123 = element.text();
             title =title123.substring(0, title123.length()-10) ;
             newsUrl = element.select("a").attr("href");
             if(!newsUrl.contains("www")){
                 newsUrl="http://www.gov.cn"+newsUrl;     
             }
             time = title123.substring(title123.length()-10,title123.length());
                
             NationalNews nationalNews = new NationalNews(title, newsUrl, time);
             
             System.out.println(title+"=========================="+newsUrl+"=========================="+time);
             
             nationalList.add(nationalNews);
        }
        result.put("dataList", nationalList);
        return result;
    }

　　　private Elements getUrlElements() {
        System.out.println("=======================================抓取国家政府网内容任务开始了=======================================");
        String url = "http://www.gov.cn/pushinfo/v150203/index.htm";
        CloseableHttpClient httpClient = HttpClients.createDefault();
        Elements elementsByTag = null;
        
        try {
            HttpGet httpGet = new HttpGet(url);
            CloseableHttpResponse response = httpClient.execute(httpGet);
            try {
                HttpEntity entity = response.getEntity();
                //设置编码格式否则乱码
                String html = new String(EntityUtils.toString(entity).getBytes("iso8859-1"));
                
                 Document document = Jsoup.parse(html);
                 elementsByTag = document.getElementsByTag("li");
            }finally {     
                 response.close();
            }
        } catch (ClientProtocolException e1) {
            e1.printStackTrace();
        } catch (IOException e1) {
            e1.printStackTrace();
        }finally {
            // 关闭连接,释放资源
            try {
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        
        return elementsByTag;
    }