java正则表达式，如何剔除HTML注释

下面这段html代码，我想剔除所有的标签、脚本、注释，只留下实际的文字内容，使用的java方法也贴出来了，可结果却不尽人意，剔除结果是剩下了几个字，经研究，发现是regEx_o = "<\\!--.*-->"导致的，由于<body></body>的前后都有<!---->注释，导致整个body都被截掉了，尝试这样写regEx_o = "<\\!--[^(*-->*)]-->";还是会存在问题，所有正能请教高人了！
HTML页面的内容：

<html xmlns:v="urn:schemas-microsoft-com:vml"

xmlns:o="urn:schemas-microsoft-com:office:office"

xmlns:w="urn:schemas-microsoft-com:office:word"

xmlns:m="http://schemas.microsoft.com/office/2004/12/omml"

xmlns="http://www.w3.org/TR/REC-html40">



<head>

<meta http-equiv=Content-Type content="text/html; charset=gb2312">

<meta name=ProgId content=Word.Document>

<meta name=Generator content="Microsoft Word 12">

<meta name=Originator content="Microsoft Word 12">

<link rel=File-List href="54-01-01_3_2.files/filelist.xml">

<link rel=Edit-Time-Data href="54-01-01_3_2.files/editdata.mso">

<!--[if !mso]>

<style>

v\:* {behavior:url(#default#VML);}

o\:* {behavior:url(#default#VML);}

w\:* {behavior:url(#default#VML);}

.shape {behavior:url(#default#VML);}

</style>

<![endif]-->

<title>气发〔2001〕×号</title>

<!--[if gte mso 9]><xml>

 <o:DocumentProperties>

  <o:Author>admin</o:Author>

 </o:DocumentProperties>

</xml><![endif]-->

<link rel=themeData href="54-01-01_3_2.files/themedata.thmx">

<link rel=colorSchemeMapping href="54-01-01_3_2.files/colorschememapping.xml">

<!--[if gte mso 9]><xml>

 <w:WordDocument>

</xml><![endif]-->

<style>

<!--

 /* Font Definitions */

div.Section1

	{page:Section1;}

-->

</style>

<!--[if gte mso 10]>

<style>

 /* Style Definitions */

</style>

<![endif]--><!--[if gte mso 9]><xml>

 </o:shapelayout></xml><![endif]-->

</head>



<body lang=ZH-CN style='tab-interval:21.0pt;text-justify-trim:punctuation'>



<div class=Section1 style='layout-grid:30.8pt -.2pt;mso-layout-grid-char-alt:

-849'>



<p class=MsoNormal style='line-height:28.3pt;mso-line-height-rule:exactly'><!--[if gte vml 1]><v:line

 id="_x0000_s1029" style='position:absolute;left:0;text-align:left;z-index:-3;

 visibility:visible;mso-position-vertical-relative:page' from="-20.95pt,783.3pt"

 to="460.95pt,783.3pt" strokecolor="red" strokeweight="4.5pt">

 <v:stroke linestyle="thinThick"/>

</v:line><![endif]-->



</span><![endif]><!--[if gte vml 1]><v:line id="_x0000_s1027" style='position:absolute;

 left:0;text-align:left;z-index:-5;visibility:visible;

 mso-position-vertical-relative:page' from="-20.75pt,140.6pt" to="461.15pt,140.6pt"

 strokecolor="red" strokeweight="4.5pt">

 <v:stroke linestyle="thickThin"/>

</v:line><![endif]--><![if !vml]><span style='mso-ignore:vglayout;position:

absolute;z-index:-5;left:0px;margin-left:-31px;margin-top:184px;width:649px;

height:7px'><img width=649 height=7 src="54-01-01_3_2.files/image002.gif"

v:shapes="_x0000_s1027"></span><![endif]></p>



</span><![endif]></p>



<p class=MsoNormal align=center style='text-align:center;line-height:35.0pt;

mso-line-height-rule:exactly;layout-grid-mode:char'><span style='font-size:

22.0pt;mso-bidi-font-size:10.0pt;font-family:方正小标宋简体;mso-bidi-font-weight:bold'>质量检验工作改革方案的通知<span

lang=EN-US><o:p></o:p></span></span></p>



<p class=MsoNormal style='text-indent:31.6pt;mso-char-indent-count:2.0;

line-height:25.0pt;mso-line-height-rule:exactly'><span style='mso-bidi-font-size:

16.0pt;font-family:仿宋_GB2312;mso-bidi-font-family:宋体;color:black;mso-font-kerning:

0pt'>为适应精细化天气预报服务工作需求，开展精细化的天气预报质量检验工作，完善预报业务质量考核体系，有效促进天气预报准确率的提高，我司决定对现行中短期天气预报质量检验工作进行改革。主要改革内容为：<span

lang=EN-US>12</span>小时降水量预报用语严格按照<span lang=EN-US>12</span>小时降水量分级标准，<span

lang=EN-US>24</span>小时时效的检验使用<span lang=EN-US>2</span>段<span lang=EN-US>12</span>小时的预报质量检验结果。现行的由<span

lang=EN-US>2</span>段<span lang=EN-US>12</span>小时预报合成为<span lang=EN-US>24</span>小时预报进行质量检验的方法暂且保留。<span

lang=EN-US><o:p></o:p></span></span></p>





<p class=MsoNormal style='line-height:21.5pt;mso-line-height-rule:exactly;

layout-grid-mode:char'><!--[if gte vml 1]><v:shape id="文本框_x0020_2" o:spid="_x0000_s1030"

 type="#_x0000_t202" style='position:absolute;left:0;text-align:left;

 margin-left:182.2pt;margin-top:16.15pt;width:272.75pt;height:34.7pt;z-index:5;

 visibility:visible;mso-width-relative:margin;mso-height-relative:margin'

 o:gfxdata="UEsDBBQABgAIAAAAIQC2gziS/gAAAOE

" stroked="f" strokecolor="white">

 <v:fill opacity="0"/>

 <v:textbox style='mso-next-textbox:#文本框_x0020_2'>

  <![if !mso]>

  <table cellpadding=0 cellspacing=0 width="100%">

   <tr>

    <td><![endif]>

    <div>

    <p class=MsoNormal align=center style='text-align:center'><span

    style='font-family:仿宋_GB2312;mso-ascii-font-family:"Times New Roman"'>预报司</span></p>

    </div>

    <![if !mso]></td>

   </tr>

  </table>

  <![endif]></v:textbox>

</v:shape><![endif]--><![if !vml]><span style='mso-ignore:vglayout'>



<table cellpadding=0 cellspacing=0 align=left>

 <tr>

  <td width=242 height=21></td>

 </tr>

 <tr>

  <td></td>

  <td><img width=369 height=51 src="54-01-01_3_2.files/image003.gif"

  alt="文本框: 预报司" v:shapes="文本框_x0020_2"></td>

 </tr>

</table>



</span><![endif]>



<p class=MsoNormal align=right style='margin-right:63.15pt;mso-para-margin-right:

4.0gd;text-align:right;line-height:30.0pt;mso-line-height-rule:exactly;

layout-grid-mode:char'><span lang=EN-US style='font-family:仿宋_GB2312;

letter-spacing:-.3pt'>2012</span><span style='font-family:仿宋_GB2312;letter-spacing:

-.3pt'>年<span lang=EN-US>11</span>月<span lang=EN-US>29</span>日<span lang=EN-US><o:p></o:p></span></span></p>



</div>



</body>



</html>

我使用的java方法：

public static String stripHtml(String HTMLStr) {

       String htmlStr = HTMLStr;  

       String textStr = "";  

       java.util.regex.Pattern p_script;  

       java.util.regex.Matcher m_script;  

       java.util.regex.Pattern p_style;  

       java.util.regex.Matcher m_style;  

       java.util.regex.Pattern p_html;  

       java.util.regex.Matcher m_html;  

       java.util.regex.Pattern p_o;  

       java.util.regex.Matcher m_o;  

       try {  

           

           String regEx_o = " ";//空格

           p_o = Pattern.compile(regEx_o, Pattern.CASE_INSENSITIVE);

           m_o = p_o.matcher(htmlStr);

           htmlStr = m_o.replaceAll(" ");

         

           regEx_o = "<\\/p>";//换行符

           p_o = Pattern.compile(regEx_o, Pattern.CASE_INSENSITIVE);

           m_o = p_o.matcher(htmlStr);

           htmlStr = m_o.replaceAll("</p>;newline;");

  

           regEx_o = "<\\!--.*-->";//html注释

           p_o = Pattern.compile(regEx_o, Pattern.CASE_INSENSITIVE);

           m_o = p_o.matcher(htmlStr);

           htmlStr = m_o.replaceAll("");





           String regEx_script = "<[//s]*?script[^>]*?>[//s//S]*?<[//s]*?///[//s]*?script[//s]*?>";  //脚本

           p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);  

           m_script = p_script.matcher(htmlStr);  

           htmlStr = m_script.replaceAll("");   



           String regEx_style = "<[//s]*?style[^>]*?>[//s//S]*?<[//s]*?///[//s]*?style[//s]*?>";   //样式

           p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);  

           m_style = p_style.matcher(htmlStr);  

           htmlStr = m_style.replaceAll("");

           

           regEx_o = " ";//空格

           p_o = Pattern.compile(regEx_o, Pattern.CASE_INSENSITIVE);

           m_o = p_o.matcher(htmlStr);

           htmlStr = m_o.replaceAll(" ");

           

           regEx_o = "<\\/p>";//换行符

           p_o = Pattern.compile(regEx_o, Pattern.CASE_INSENSITIVE);

           m_o = p_o.matcher(htmlStr);

           htmlStr = m_o.replaceAll("</p>;newline;");





           String regEx_html = "<[^>]+>"; //其他html标签

           p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);  

           m_html = p_html.matcher(htmlStr);  

           htmlStr = m_html.replaceAll("");  



           textStr = htmlStr.replaceAll(" ", "");  

           textStr = textStr.replaceAll(";newline;","\n");

       } catch (Exception e)  {  

           System.err.println("Html2Text: " + e.getMessage());

       }

      return textStr;

   }