Jsoup解析网页html

Jsoup解析网页html

解析网页demo:

利用Jsoup获取截图中的数据信息：

html代码片段：

  <!-- 当前基金档案\计算\定投\开户 start -->
             <div class="wrapper">
               <div class="wrapper_min">
                 <div class="merchandiseDetail">
                   <div class="fundDetail-header">
                     <div class="fundDetail-tit">
                       <div style="float: left">兴全社会责任混合
                         <span>(</span>
                         <span class="ui-num">340007</span></div>)</div>
                     <div class="fundDetail-tools">
                       <a class="jijinba" href="http://guba.eastmoney.com/list,of340007.html">基金吧</a>
                       <!-- 未自选 start -->
                       <a class="addSel" id="addSel" href="javascript:;" target="_self">加自选</a>
                       <!-- 未自选 end -->
                       <a class="addCom" id="addCom" href="javascript:;" target="_self" onclick="common.addCompare()">加对比</a>
                       <a class="addDownApp" href="http://fundact.eastmoney.com/app/">手机版天天基金下载</a></div>
                   </div>
                   <div class="fundDetail-main">
                     <!-- 档案 start -->
                     <div class="fundInfoItem">
                       <!--开放式基金收益率模块-->
                       <div class="dataOfFund">
                         <dl class="dataItem01">
                           <dt>
                             <p>
                               <span>
                                 <span class="sp01">净值估算</span></span>
                               <span id="gz_gztime">(17-12-20 15:00)</span>
                               <span class="infoTips">
                                 <span class="tipsBubble" style="display: none;">净值估算每个交易日9：30-15：00盘中实时更新（QDII基金为海外交易时段），是按照基金持仓、指数走势和基金过往业绩估算，估算数据并不代表真实净值，仅供参考，请以基金管理人披露净值为准。</span></span>
                             </p>
                           </dt>
                           <dd class="dataNums">
                             <dl class="floatleft">
                               <span class="ui-font-large ui-color-green ui-num" id="gz_gsz">3.7576</span></dl>
                             <dl id="gz_icon" class="gzdown"></dl>
                             <dl class="floatleft fundZdf">
                               <span class="ui-font-middle ui-color-green ui-num" id="gz_gszze">0.0594</span>
                               <span class="ui-font-middle ui-color-green ui-num" id="gz_gszzl">-1.56%</span></dl>
                           </dd>
                           <dd>
                             <span>近1月：</span>
                             <span class="ui-font-middle ui-color-green ui-num">-4.62%</span></dd>
                           <dd>
                             <span>近1年：</span>
                             <span class="ui-font-middle ui-color-red ui-num">44.20%</span></dd>
                         </dl>
                         <span class="dataOfFund-line"></span>
                         <dl class="dataItem02">
                           <dt>
                             <p>
                               <span class="ui-color-blue">
                                 <span class="sp01">
                                   <a href="http://fund.eastmoney.com/f10/jjjz_340007.html">单位净值</a></span>(</span>2017-12-19)</p>
                           </dt>
                           <dd class="dataNums">
                             <span class="ui-font-large ui-color-red ui-num">3.8170</span>
                             <span class="ui-font-middle ui-color-red ui-num">1.41%</span></dd>
                           <dd>
                             <span>近3月：</span>
                             <span class="ui-font-middle ui-color-red ui-num">13.47%</span></dd>
                           <dd>
                             <span>近3年：</span>
                             <span class="ui-font-middle ui-color-red ui-num">113.48%</span></dd>
                         </dl>
                         <span class="dataOfFund-line"></span>
                         <dl class="dataItem03">
                           <dt>
                             <p>
                               <span class="ui-color-blue">
                                 <span class="sp01">
                                   <a href="http://fund.eastmoney.com/f10/jjjz_340007.html">累计净值</a></span>
                               </span>
                             </p>
                           </dt>
                           <dd class="dataNums">
                             <span class="ui-font-large ui-color-red ui-num">4.0070</span></dd>
                           <dd>
                             <span>近6月：</span>
                             <span class="ui-font-middle ui-color-red ui-num">25.35%</span></dd>
                           <dd>
                             <span>成立来：</span>
                             <span class="ui-font-middle ui-color-red ui-num">332.92%</span></dd>
                         </dl>
                       </div>
                       <div class="infoOfFund">
                         <div class="infoOfFund-line"></div>
                         <table>
                           <tr>
                             <td>基金类型：
                               <a href="http://fund.eastmoney.com/HH_jzzzl.html#os_0;isall_0;ft_;pt_3">混合型</a>&nbsp;&nbsp;|&nbsp;&nbsp;中高风险</td>
                             <td>
                               <a href="http://fund.eastmoney.com/f10/gmbd_340007.html">基金规模</a>：76.83亿元（2017-09-30）</td>
                             <td>基金经理：
                               <a href="http://fund.eastmoney.com/f10/jjjl_340007.html">傅鹏博</a></td>
                           </tr>
                           <tr>
                             <td>
                               <span class="letterSpace01">成 立 日</span>：2008-04-30</td>
                             <td>
                               <span class="letterSpace01">管 理 人</span>：
                               <a href="http://fund.eastmoney.com/company/80036742.html">兴全基金</a></td>
                             <td>
                               <a class="floatleft" href="http://fund.eastmoney.com/f10/jjpj_340007.html">基金评级</a>
                               <span class="floatleft">：</span>
                               <div class="jjpj4"></div>
                             </td>
                           </tr>
                         </table>
                       </div>
                     </div>
                     <!-- 档案 end -->

java实现代码：

/**
 * Project Name:wlpc
 * File Name:XyzqTask.java
 * Package Name:com.xyzq.wlpc.task
 * Date:2017年12月20日下午1:48:16
 * Copyright (c) 2017 All Rights Reserved.
 *
*/
  import java.io.IOException;;import net.sf.json.JSONObject;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;/**
 * ClassName:XyzqTask
 * Function: TODO
 * Reason:   TODO
 * Date:     2017年12月20日 下午1:48:16
 * @author   lizm
 * @since    JDK 1.6
 *
 */
public class XyzqTask extends BaseTask {

    private void getHtml(){
        String url = "";
        url = Pub.getPropertiesValue("wlpc", "wlpc.web.url");
        try {
            Document doc = Jsoup.connect(url).get();
            //class等于fundDetail-tit的div标签
            Elements fundDetail_tit = doc.select("div.fundDetail-tit");
            for (Element element : fundDetail_tit){
                //特殊字符'(',使用 \\( 或 [(]
                System.out.println("fundDetail_tit>>>>:"+element.text().split("\\(")[0]);
                //获取div下的第一个span的class为ui-num的值
                Document elementDoc = Jsoup.parse(element.toString());
                Element elm = elementDoc.select("span.ui-num").first();
                System.out.println("elm>>>>:"+elm.text());
            }
            //id等于gz_gztime的span标签
            Elements gz_gztime = doc.select("span#gz_gztime");
            for (Element element : gz_gztime){
                System.out.println("gz_gztime>>>>:"+element.text().replace("(", "").replace(")", ""));
            }
            //id等于gz_gsz的span标签
            Elements gz_gsz = doc.select("span#gz_gsz");
            for (Element element : gz_gsz){
                System.out.println("gz_gsz>>>>:"+element.text());
            }
            //id等于gz_gszze的span标签
            Elements gz_gszze = doc.select("span#gz_gszze");
            for (Element element : gz_gszze){
                System.out.println("gz_gszze>>>>:"+element.text());
            }

            //id等于gz_gszzl的span标签
            Elements gz_gszzl = doc.select("span#gz_gszzl");
            for (Element element : gz_gszzl){
                System.out.println("gz_gszzl>>>>:"+element.text());
            }
            //class等于dataItem02的dl标签
            Elements dataItem02 = doc.select("dl.dataItem02");
            for (Element element : dataItem02){
                Document elementDoc = Jsoup.parse(element.toString());
                Element elm1 = elementDoc.getElementsByTag("p").first();
                System.out.println("elm>>>>:"+elm1.text().replace("单位净值 (", "").replace(")", ""));
                Element elm_dd = elementDoc.select("dd.dataNums").first();
                Document doc_dd = Jsoup.parse(elm_dd.toString());
                Element elm_dd_span1 = doc_dd.getElementsByTag("span").first();
                System.out.println("elm_dd_span1>>>:"+elm_dd_span1.text());
                Element elm_dd_span2 = doc_dd.getElementsByTag("span").last();
                System.out.println("elm_dd_span2>>>:"+elm_dd_span2.text());
            }
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        XyzqTask client = new XyzqTask();
        client.getHtml();
    }
}
 

输出结果：

fundDetail_tit>>>>:兴全社会责任混合
elm>>>>:340007
gz_gztime>>>>:17-12-21 15:00
gz_gsz>>>>:3.8583
gz_gszze>>>>:+0.0933
gz_gszzl>>>>:+2.48%
elm>>>>:2017-12-20
elm_dd_span1>>>:3.7650
elm_dd_span2>>>:-1.36%