asp.net 如何查找html某一标记里面的内容呢？

q704174307 2008-11-29 10:35:04

如题，我在CS文件里面，用string str取出了某张html文件的源代码
那么我想利用js的getElementsByTagName原理，才取出str的某些节点内容
可以怎么实现呢
用CS或者JS写都行

...全文

195 17 打赏收藏转发到动态举报

写回复

用AI写文章

17 条回复

切换为时间正序

请发表友善的回复…

发表回复

q704174307 2008-11-29

打赏
举报

顶上去

q704174307 2008-11-29

打赏
举报

我有一个想法，就是能不能把html换成xml，这样会不会容易一点

q704174307 2008-11-29

打赏
举报

楼上的。你要想到一件事
就是说
div里面可以嵌套div
比如
<div id=1>
<div></div>
</div>

mengxj85 2008-11-29

打赏
举报

前几天收藏的几种方法
------------
C# code
public class Reg
{
#region/// 过滤html,js,css代码
/// <summary>
/// 过滤html,js,css代码
/// </summary>
/// <param name="html">参数传入</param>
/// <returns></returns>
public static string CheckStr(string html)
{
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" no[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //过滤<script></script>标记
html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性
html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件
html = regex4.Replace(html, ""); //过滤iframe
html = regex5.Replace(html, ""); //过滤frameset
html = regex6.Replace(html, ""); //过滤frameset
html = regex7.Replace(html, ""); //过滤frameset
html = regex8.Replace(html, ""); //过滤frameset
html = regex9.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
return html;
}
#endregion
#region /// 过滤p /p代码
/// <summary>
/// 过滤p /p代码
/// </summary>
/// <param name="html">参数传入</param>
/// <returns></returns>
public static string InputStr(string html)
{
html = html.Replace(@"\<img[^\>]+\>", "");
html = html.Replace(@"<p>", "");
html = html.Replace(@"</p>", "");
return html;
}
#endregion

/// <summary>
/// 截取字符串
/// </summary>
/// <param name="str"></param>
/// <param name="length"></param>
/// <returns></returns>
protected string GetLength(string str, int length)
{
string strR = str;
if (str.Length > length)
{
strR = str.Substring(0, length) + "...";
}
return strR;
}

}

-----------------------------
直接replace也行

using System.Text.RegularExpressions;

string html = "test start <iframe src=''> </iframe> end";
html = Regex.Replace(html, @" <iframe.+? </iframe>", "", RegexOptions.IgnoreCase);//IgnoreCase即不限制大小写
--------------------
C# code

///<summary>
///替换html中的特殊字符
///</summary>
///<param name="theString">需要进行替换的文本。</param>
///<returns>替换完的文本。</returns>
public string HtmlEncode(string theString)
{
theString = theString.Replace(">", ">");
theString = theString.Replace("<", "<");
theString = theString.Replace(" ", " ");
theString = theString.Replace(" ", " ");
theString = theString.Replace("\"", """);
theString = theString.Replace("\'", "'");
theString = theString.Replace("\n", "<br/> ");
return theString;
}

------------------

q704174307 2008-11-29

打赏
举报

啊，大家帮帮我啊，着急用啊
我在这个节骨眼上总转不过

lxl_sprots 2008-11-29

打赏
举报

帮你顶一下。。。

q704174307 2008-11-29

打赏
举报



<body>

<div>

<div class="left">

  <div class="spic"><img src="images/1_01.gif" /></div>

  <div>

    <ul>

      <li><strong>主　　办:</strong><em>中国元素网</em></li>

      <li><strong>主　　编:</strong><em>中国元素网</em></li>

      <li><strong>编　　辑:</strong><em>中国元素网</em></li>

      <li><strong>设计总监:</strong><em>中国元素网</em></li>

      <li><strong>设　　计:</strong><em>中国元素网<br />中国元素网</em></li>

      <li><strong>技术支持:</strong><em>中国元素网</em></li>

    </ul>

    <dl>

      <dt>联系方式：</dt>

      <dd>[内容合作]　0754-00000000</dd>

      <dd>[广告投放]　0754-00000000</dd>

    </dl>

  </div>

</div>

<div class="center"></div>

<div class="right">

  <div class="directory">

    <h1>目录</h1>

    <label>Directory</label>

    <em>Vol/01</em>

  </div>

  <div class="dc">

    <dl>

      <dd class="pic"><a href="#"><img src="images/1_02.gif" /></a></dd>

      <dd class="title"><a href="#">饮食新闻</a></dd>

      <dd class="des">介绍饮料界新闻 信息</dd>

    </dl>

  </div>

  <div class="dc">

    <dl>

      <dd class="pic"><a href="#"><img src="images/1_02.gif" /></a></dd>

      <dd class="title"><a href="#">饮食新闻</a></dd>

      <dd class="des">介绍饮料界新闻 信息</dd>

    </dl>

  </div>

  <div class="dc">

    <dl>

      <dd class="pic"><a href="#"><img src="images/1_02.gif" /></a></dd>

      <dd class="title"><a href="#">饮食新闻</a></dd>

      <dd class="des">介绍饮料界新闻 信息</dd>

    </dl>

  </div>

  <div class="dc" id="2">

    <dl>

      <dd class="pic"><a href="#"><img src="images/1_02.gif" /></a></dd>

      <dd class="title"><a href="#">饮食新闻</a></dd>

      <dd class="des">介绍饮料界新闻 信息</dd>

    </dl>

  </div>

  <div class="dc" id="1">

    <dl>

      <dd class="pic"><a href="#"><img src="images/1_02.gif" /></a></dd>

      <dd class="title"><a href="#">饮食新闻</a></dd>

      <dd class="des">介绍饮料界新闻 信息</dd>

    </dl>

  </div>

  </div>

</div>

</body>

</html>