Jsoup 解析html

Jsoup解析线上html文件 

/**
     * 根据url地址获取元素
     * 
     * @param url
     *            要爬虫的url地址
     * @return 返回需要继续的元素值
     * 
     *         这里解析的为的 xy 网页上的应用信息 内容 ul 标签中
     * 
     */
    public Elements getHtmlRescoureByurl(String url) {
        Connection con = Jsoup.connect(url).timeout(5000); 
        try {
            con.header("Connection", "keep-alive");
            con.header("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8");
            con.header("User-Agent",
                    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.89 Safari/537.36");

            Document doc = con.get();
            Elements divs = doc.getElementsByTag("div");

            Element div = null;
            for (Element element : divs) {
                if (element.attr("class").equals("seventyfive")) {
                    div = element;
                    break;
                }
            }
            if (div != null) {
                Elements uls = div.getElementsByTag("ul");
                if (uls.size() > 0) {
                    Element ul = uls.get(0);
                    return ul.getElementsByTag("li");
                }
            }
        } catch (IOException e) {
            System.out.println(e.getMessage());
        }
        return null;
    }

    
    /**
     *    解析返回的xml内容
     * @param lis
     * @return
     */
    public List<Object[]> parElement(Elements lis , int type) {
        List<Object[]> list = new ArrayList<Object[]>();
        int i = 0;
        String defaulttime = new SimpleDateFormat("yyyy-MM-dd").format(new Date());
        
        for (Element li : lis) {
            String icon = li.getElementsByAttributeValue("class", "xy_img").attr("src"); // icon图标
            Elements als = li.getElementsByTag("a");
            String appname = als.get(2).text();                                             // appname
            String downloaded = li.getElementsByAttributeValue("class","edloaded").text();  // 下载次数
            String app_size = li.getElementById("app_size_" + i).text();
            String size = app_size.split("\|").length > 0? app_size.split("\|")[0]:"";                                         // 软件大小
            String updatetime = app_size.split("\|").length > 1? app_size.split("\|")[1]:defaulttime;                                     // 更新日期
            String itunesid = als.get(3).attr("id");                                         // itunesid
            String version = als.get(3).attr("version");                                     // 版本号
            String bundleid = als.get(3).attr("bid");                                         // bundleid
            String ipaurl = als.get(3).attr("resurl");
            ipaurl = getFromBase64(ipaurl);                                                    //  ipa下载地址
            i++;
            
            //   ipa 下载地址为空   appname太长  更时间为空
            //  参数顺序   itunesid,appname,icon,version,bundleid,size,downloaded,ipaurl,updatetime  
            Object[] params = new Object[]{itunesid,appname,icon,version,bundleid,size,downloaded,type,ipaurl,updatetime};
            list.add(params);
        }
        return list;
    }


// post 请求
  
    public void testJsop(){
        try {
            Connection conn = Jsoup.connect("https://passport.jd.com/new/login.aspx");
            conn.data("loginname","test1");
            conn.data("loginpwd","test1");
            Document doc = conn.post(); 
　　　　　　　　 // Document doc = con.ignoreContentType(true).get();       
            System.out.println(doc);
        } catch (IOException e) {          
            e.printStackTrace();
        }
    }

需要jar jsoup