java使用Document类解析html

今天工作中用到了解析html获取其中的标签内容，在此记录一下：
先感谢两个帖子：
引用：
https://www.cnblogs.com/blog5277/p/6704288.html
https://blog.csdn.net/zhanglei500038/article/details/74858395
接下来是我的应用：

<DIV class="navbar navbar-inverse navbar-fixed-top">
  <DIV class="navbar-inner">
    <DIV class="container-fluid">
      <a class="brand lnk-file-title" STYLE="text-decoration: none; width: 200px" TITLE=" ">&nbsp;</a>
      <a id="btnPrint" STYLE="margin:0px;padding:10px;" href="javascript:;" onClick="printDoc()">
        <img src="./1281e94387f5efb28be502f828edc032.files/print.png">
      </a>
      <DIV class="changePage">
        <a class="pageUp" href="javascript:;" onClick="slidePage(0)"></a>
        <a class="pageDown" href="javascript:;" onClick="slidePage(1)"></a>
        <SPAN STYLE="padding:0px 10px 0px 10px">Page:</SPAN>
        <INPUT class="activePage" type="text" Value="1" onBlur="changePage(this.value)" onkeyup="this.value=this.value.replace(/[^0-9]/g,'')" onafterpaste="this.value=this.value.replace(/[^0-9]/g,'')">
        <SPAN class="totalPage"></SPAN>
      </DIV>
    </DIV>
  </DIV>
</DIV>
<DIV id="printArea" STYLE="display:none"></DIV>
<DIV class="container-fluid container-fluid-content">
  <DIV class="row-fluid">
    <DIV class="span12 docArea">
      <DIV class="word-page" STYLE="width:921px;height:1275px" data-loaded="true">
        <DIV class="word-content">
          <embed src="1281e94387f5efb28be502f828edc032.files/1.svg" width="100%" height="100%" type="image/svg+xml"></embed>
        </DIV>
      </DIV>
      <DIV class="word-page" STYLE="width:921px;height:1275px" data-loaded="true">
        <DIV class="word-content">
          <embed src="1281e94387f5efb28be502f828edc032.files/2.svg" width="100%" height="100%" type="image/svg+xml"></embed>
        </DIV>
      </DIV>
      <DIV class="word-page" STYLE="width:921px;height:1275px" data-loaded="true">
        <DIV class="word-content">
          <embed src="1281e94387f5efb28be502f828edc032.files/3.svg" width="100%" height="100%" type="image/svg+xml"></embed>
        </DIV>
      </DIV>
      <DIV class="word-page" STYLE="width:921px;height:1275px" data-loaded="true">
        <DIV class="word-content">
          <embed src="1281e94387f5efb28be502f828edc032.files/4.svg" width="100%" height="100%" type="image/svg+xml"></embed>
        </DIV>
      </DIV>
      <DIV class="word-page" STYLE="width:921px;height:1275px" data-loaded="true">
        <DIV class="word-content">
          <embed src="1281e94387f5efb28be502f828edc032.files/5.svg" width="100%" height="100%" type="image/svg+xml"></embed>
        </DIV>
      </DIV>
      <DIV class="word-page" STYLE="width:921px;height:1275px">
        <DIV class="word-content"></DIV>
      </DIV>
    </DIV>
  </DIV>
</DIV>

我是要拿取embed标签中的src的内容：
对上面两个帖子进行整合：

public static List<String> match(String source, String element, String attr) {
    List<String> result = new ArrayList<String>();
    String reg = "<" + element + "[^<>]*?\\s" + attr + "=['\"]?(.*?)['\"]?\\s.*?>";
    Matcher m = Pattern.compile(reg).matcher(source);
    while (m.find()) {
        String r = m.group(1);
        result.add(r);
    }
    return result;
}
 public static void main(String[] args) throws MalformedURLException, IOException {
	Document doc= Jsoup.parse(new URL("http://docv.hdkt100.com/2018/11/1281e94387f5efb28be502f828edc032.html"),100000);
	String html = doc.toString();
   // String source = "<a title=中国体育报 href=''>aaa</a><a title='北京日报' href=''>bbb</a>";
    List<String> list = match(html, "embed", "src");
    System.out.println(list);
}

其中用到的jar包：

	<dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.10.2</version>
        </dependency>