想把下面的中文部分提取出来,不知道怎么操作,请高手回答给出代码,谢了
<ul>
<li><span id='fld000000061' onclick='openFolder("000000061")'><img src='/images/pui-plus.gif' style='position: relative;top:-6px'/><img src='/images/ftv2folderclosed.gif'/></span><span onclick='jumpTo("00000006")' style='position: relative;top:-6px'>第一章 请卹事实</span></li>
<ul id='idoc000000061' style='display:none'>
 <li><span id='idoc000000062' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000006")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹事实</span></li>
<ul id='iblock000000062' style='display:none'>
</ul>
 <li><span id='idoc000000074' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000007")'  style='position: relative;top:-6px'>第二节 陆军伤亡请卹事实</span></li>
<ul id='iblock000000074' style='display:none'>
</ul>
 <li><span id='idoc000000106' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000010")'  style='position: relative;top:-6px'>第三节 空军伤亡请卹事实</span></li>
<ul id='iblock000000106' style='display:none'>
</ul>
 <li><span id='idoc000000138' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000013")'  style='position: relative;top:-6px'>第四节 人民守土伤亡请卹事实</span></li>
<ul id='iblock000000138' style='display:none'>
</ul>
</ul>
<li><span id='fld000000143' onclick='openFolder("000000143")'><img src='/images/pui-plus.gif' style='position: relative;top:-6px'/><img src='/images/ftv2folderclosed.gif'/></span><span onclick='jumpTo("00000014")' style='position: relative;top:-6px'>第二章 请卹手续</span></li>
<ul id='idoc000000143' style='display:none'>
 <li><span id='idoc000000142' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000014")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹手续</span></li>
<ul id='iblock000000142' style='display:none'>
</ul>
 <li><span id='idoc000000154' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000015")'  style='position: relative;top:-6px'>第二节 陆空军伤亡请卹手续</span></li>
<ul id='iblock000000154' style='display:none'>
</ul>
 <li><span id='idoc000000176' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000017")'  style='position: relative;top:-6px'>第三节 人民守土伤亡请卹手续</span></li>
<ul id='iblock000000176' style='display:none'>
</ul>
</ul>
<li><span id='fld000000185' onclick='openFolder("000000185")'><img src='/images/pui-plus.gif' style='position: relative;top:-6px'/><img src='/images/ftv2folderclosed.gif'/></span><span onclick='jumpTo("00000018")' style='position: relative;top:-6px'>第三章 办理抚卹手续</span></li>
<ul id='idoc000000185' style='display:none'>
 <li><span id='idoc000000182' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000018")'  style='position: relative;top:-6px'>第一节 各机关办理公务员抚卹手续</span></li>
<ul id='iblock000000182' style='display:none'>
</ul>
 <li><span id='idoc000000194' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000019")'  style='position: relative;top:-6px'>第二节 各机关办理陆空军抚卹手续</span></li>
<ul id='iblock000000194' style='display:none'>
</ul>
 <li><span id='idoc000000236' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000023")'  style='position: relative;top:-6px'>第三节 各机关办理人民守土伤亡抚卹手续</span></li>
<ul id='iblock000000236' style='display:none'>
</ul>
</ul>
<li><span id='fld000000257' onclick='openFolder("000000257")'><img src='/images/pui-plus.gif' style='position: relative;top:-6px'/><img src='/images/ftv2folderclosed.gif'/></span><span onclick='jumpTo("00000025")' style='position: relative;top:-6px'>第四章 卹金规定</span></li>
<ul id='idoc000000257' style='display:none'>
 <li><span id='idoc000000252' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000025")'  style='position: relative;top:-6px'>第一节 关于公务员卹金规定</span></li>
<ul id='iblock000000252' style='display:none'>
</ul>
 <li><span id='idoc000000284' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000028")'  style='position: relative;top:-6px'>第二节 关于陆军卹金规定</span></li>
<ul id='iblock000000284' style='display:none'>
</ul>
 <li><span id='idoc000000336' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000033")'  style='position: relative;top:-6px'>第三节 关于空军卹金规定</span></li>
<ul id='iblock000000336' style='display:none'>
</ul>
 <li><span id='idoc000000398' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif' ></img></span><span onclick='jumpTo("00000039")'  style='position: relative;top:-6px'>第四节 关于人民守土伤亡卹金规定</span></li>
<ul id='iblock000000398' style='display:none'>
</ul>
</ul>
<li><span id='fld000000419' onclick=''><img src='/images/pui-norm.gif' style='position: relative;top:-6px'></img><img src='/images/ftv2folderclosed.gif'/></span><span onclick='jumpTo("00000041")' style='position: relative;top:-6px'>委员长电慰抗战阵亡将士家属</span></li>
<ul id='idoc000000419' style='display:none'>
</ul>
</ul>

解决方案 »

  1.   

    至少有两个思路:
    1、解析HTML为DOM(用MSHTML之类的组件),遍历<span>节点,提取你想要的文本。
    2、不解析HTML,用正则表达式提取里面的双字节字符。
      

  2.   

    看不懂楼上的,遍历<span>能给代码么?
      

  3.   


    string test = @"<ul> 
    <li> <span id='fld000000061' onclick='openFolder(""000000061"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000006"")' style='position: relative;top:-6px'>第一章 请卹事实 </span> </li> 
    <ul id='idoc000000061' style='display:none'> 
    <li> <span id='idoc000000062' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000006"")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹事实 </span> </li> 
    <ul id='iblock000000062' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000074' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000007"")'  style='position: relative;top:-6px'>第二节 陆军伤亡请卹事实 </span> </li> 
    <ul id='iblock000000074' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000106' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000010"")'  style='position: relative;top:-6px'>第三节 空军伤亡请卹事实 </span> </li> 
    <ul id='iblock000000106' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000138' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000013"")'  style='position: relative;top:-6px'>第四节 人民守土伤亡请卹事实 </span> </li> 
    <ul id='iblock000000138' style='display:none'> 
    </ul> 
    </ul> 
    <li> <span id='fld000000143' onclick='openFolder(""000000143"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000014"")' style='position: relative;top:-6px'>第二章 请卹手续 </span> </li> 
    <ul id='idoc000000143' style='display:none'> 
    <li> <span id='idoc000000142' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000014"")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹手续 </span> </li> 
    <ul id='iblock000000142' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000154' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000015"")'  style='position: relative;top:-6px'>第二节 陆空军伤亡请卹手续 </span> </li> 
    <ul id='iblock000000154' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000176' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000017"")'  style='position: relative;top:-6px'>第三节 人民守土伤亡请卹手续 </span> </li> 
    <ul id='iblock000000176' style='display:none'> 
    </ul> 
    </ul> 
    <li> <span id='fld000000185' onclick='openFolder(""000000185"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000018"")' style='position: relative;top:-6px'>第三章 办理抚卹手续 </span> </li> 
    <ul id='idoc000000185' style='display:none'> 
    <li> <span id='idoc000000182' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000018"")'  style='position: relative;top:-6px'>第一节 各机关办理公务员抚卹手续 </span> </li> 
    <ul id='iblock000000182' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000194' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000019"")'  style='position: relative;top:-6px'>第二节 各机关办理陆空军抚卹手续 </span> </li> 
    <ul id='iblock000000194' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000236' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000023"")'  style='position: relative;top:-6px'>第三节 各机关办理人民守土伤亡抚卹手续 </span> </li> 
    <ul id='iblock000000236' style='display:none'> 
    </ul> 
    </ul> 
    <li> <span id='fld000000257' onclick='openFolder(""000000257"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000025"")' style='position: relative;top:-6px'>第四章 卹金规定 </span> </li> 
    <ul id='idoc000000257' style='display:none'> 
    <li> <span id='idoc000000252' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000025"")'  style='position: relative;top:-6px'>第一节 关于公务员卹金规定 </span> </li> 
    <ul id='iblock000000252' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000284' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000028"")'  style='position: relative;top:-6px'>第二节 关于陆军卹金规定 </span> </li> 
    <ul id='iblock000000284' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000336' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000033"")'  style='position: relative;top:-6px'>第三节 关于空军卹金规定 </span> </li> 
    <ul id='iblock000000336' style='display:none'> 
    </ul> 
    <li> <span id='idoc000000398' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000039"")'  style='position: relative;top:-6px'>第四节 关于人民守土伤亡卹金规定 </span> </li> 
    <ul id='iblock000000398' style='display:none'> 
    </ul> 
    </ul> 
    <li> <span id='fld000000419' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000041"")' style='position: relative;top:-6px'>委员长电慰抗战阵亡将士家属 </span> </li> 
    <ul id='idoc000000419' style='display:none'> 
    </ul> 
    </ul>";
            Regex re = new Regex(@"<span .* onclick='jumpto\(""(\d+)""\)'.*>(.*)</span>", RegexOptions.IgnoreCase);
            MatchCollection matches = re.Matches(test);
            foreach (Match m in matches)
            {
                Response.Write(m.Groups[1].Value);
                Response.Write("\t");
                Response.Write(m.Groups[2].Value);
                Response.Write("\n");
            }
    输出的是
    00000006 第一章 请卹事实 
    00000006 第一节 公务员伤亡及退职请卹事实 
    00000007 第二节 陆军伤亡请卹事实 
    00000010 第三节 空军伤亡请卹事实 
    00000013 第四节 人民守土伤亡请卹事实 
    00000014 第二章 请卹手续 
    00000014 第一节 公务员伤亡及退职请卹手续 
    00000015 第二节 陆空军伤亡请卹手续 
    00000017 第三节 人民守土伤亡请卹手续 
    00000018 第三章 办理抚卹手续 
    00000018 第一节 各机关办理公务员抚卹手续 
    00000019 第二节 各机关办理陆空军抚卹手续 
    00000023 第三节 各机关办理人民守土伤亡抚卹手续 
    00000025 第四章 卹金规定 
    00000025 第一节 关于公务员卹金规定 
    00000028 第二节 关于陆军卹金规定 
    00000033 第三节 关于空军卹金规定 
    00000039 第四节 关于人民守土伤亡卹金规定 
    00000041 委员长电慰抗战阵亡将士家属前面是跳转参数,后面是相关目录
      

  4.   


                Regex reg = new Regex("<span.*>(?<text>.*)</span>");
                string str = @"<span onclick='jumpTo(""00000006"")' style='position: relative;top:-6px'>第一章请卹事实 </span> </li>
    <ul id='idoc000000061' style='display:none'>
    <li> <span id='idoc000000062' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000006"")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹事实 </span> </li>
    <ul id='iblock000000062' style='display:none'>
    </ul>
    <li> <span id='idoc000000074' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000007"")'  style='position: relative;top:-6px'>第二节 陆军伤亡请卹事实 </span> </li>
    <ul id='iblock000000074' style='display:none'>
    </ul>
    <li> <span id='idoc000000106' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000010"")'  style='position: relative;top:-6px'>第三节 空军伤亡请卹事实 </span> </li>
    <ul id='iblock000000106' style='display:none'>
    </ul>
    <li> <span id='idoc000000138' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000013"")'  style='position: relative;top:-6px'>第四节 人民守土伤亡请卹事实 </span> </li>
    <ul id='iblock000000138' style='display:none'>
    </ul>
    </ul>
    <li> <span id='fld000000143' onclick='openFolder(""000000143"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000014"")' style='position: relative;top:-6px'>第二章请卹手续 </span> </li>
    <ul id='idoc000000143' style='display:none'>
    <li> <span id='idoc000000142' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000014"")'  style='position: relative;top:-6px'>第一节 公务员伤亡及退职请卹手续 </span> </li>
    <ul id='iblock000000142' style='display:none'>
    </ul>
    <li> <span id='idoc000000154' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000015"")'  style='position: relative;top:-6px'>第二节 陆空军伤亡请卹手续 </span> </li>
    <ul id='iblock000000154' style='display:none'>
    </ul>
    <li> <span id='idoc000000176' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000017"")'  style='position: relative;top:-6px'>第三节 人民守土伤亡请卹手续 </span> </li>
    <ul id='iblock000000176' style='display:none'>
    </ul>
    </ul>
    <li> <span id='fld000000185' onclick='openFolder(""000000185"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000018"")' style='position: relative;top:-6px'>第三章办理抚卹手续 </span> </li>
    <ul id='idoc000000185' style='display:none'>
    <li> <span id='idoc000000182' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000018"")'  style='position: relative;top:-6px'>第一节 各机关办理公务员抚卹手续 </span> </li>
    <ul id='iblock000000182' style='display:none'>
    </ul>
    <li> <span id='idoc000000194' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000019"")'  style='position: relative;top:-6px'>第二节 各机关办理陆空军抚卹手续 </span> </li>
    <ul id='iblock000000194' style='display:none'>
    </ul>
    <li> <span id='idoc000000236' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000023"")'  style='position: relative;top:-6px'>第三节 各机关办理人民守土伤亡抚卹手续 </span> </li>
    <ul id='iblock000000236' style='display:none'>
    </ul>
    </ul>
    <li> <span id='fld000000257' onclick='openFolder(""000000257"")'> <img src='/images/pui-plus.gif' style='position: relative;top:-6px'/> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000025"")' style='position: relative;top:-6px'>第四章卹金规定 </span> </li>
    <ul id='idoc000000257' style='display:none'>
    <li> <span id='idoc000000252' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000025"")'  style='position: relative;top:-6px'>第一节 关于公务员卹金规定 </span> </li>
    <ul id='iblock000000252' style='display:none'>
    </ul>
    <li> <span id='idoc000000284' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000028"")'  style='position: relative;top:-6px'>第二节 关于陆军卹金规定 </span> </li>
    <ul id='iblock000000284' style='display:none'>
    </ul>
    <li> <span id='idoc000000336' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000033"")'  style='position: relative;top:-6px'>第三节 关于空军卹金规定 </span> </li>
    <ul id='iblock000000336' style='display:none'>
    </ul>
    <li> <span id='idoc000000398' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif' > </img> </span> <span onclick='jumpTo(""00000039"")'  style='position: relative;top:-6px'>第四节 关于人民守土伤亡卹金规定 </span> </li>
    <ul id='iblock000000398' style='display:none'>
    </ul>
    </ul>
    <li> <span id='fld000000419' onclick=''> <img src='/images/pui-norm.gif' style='position: relative;top:-6px'> </img> <img src='/images/ftv2folderclosed.gif'/> </span> <span onclick='jumpTo(""00000041"")' style='position: relative;top:-6px'>委员长电慰抗战阵亡将士家属 </span> </li>
    <ul id='idoc000000419' style='display:none'>
    </ul>
    </ul> ";
                List<string> list = new List<string>();
                Match match = reg.Match(str);
                while (match.Success)
                {
                    list.Add(match.Groups["text"].Value);
                    match = match.NextMatch();
                }
      

  5.   


    请参考
    http://www.timandes.com/post/21/
    。至于DOM怎么操作,请参考MSDN。