110,547
社区成员
发帖
与我相关
我的任务
分享请发表友善的回复…
发表回复
jimil 2014-05-23
- 打赏
- 举报
我想你的目的，应该2楼已经给出了方法，只不过这些正则你得自己完成，然后replace加上你需要插入的内容。
self001 2014-05-23
- 打赏
- 举报
是的，不过插入了相关的字符串后得替换回来。不能插入在html中。。
self001 2014-05-21
- 打赏
- 举报
谢谢大家，可能是理解错了。不只是要排除html，还要插入内容，内容不能插 入在html标签内，是这个意思。。
蝶恋花雨 2014-05-21
- 打赏
- 举报
#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);
System.Text.RegularExpressions.Regex regex10 = new System.Text.RegularExpressions.Regex(@" ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex11 = new System.Text.RegularExpressions.Regex(@">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex12 = 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 = regex10.Replace(html, "");//过滤空格
html = regex11.Replace(html, "");
html = regex12.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
return html;
}
#endregion
#region//过滤简单的HTML代码去
/// <summary>
/// 过滤简单的HTML代码去 图片空格。之类
/// </summary>
public static string Subfilter(string html)
{
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@" ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //过滤frameset
html = regex2.Replace(html, ""); //过滤frameset
html = regex3.Replace(html, ""); //过滤frameset
html = regex4.Replace(html, "");
html = regex5.Replace(html, "");//过滤空格
html = regex6.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
return html;
}
#endregion
#region//去除HTML标记用于过滤掉FckEditor中的HTML标记
/// <param name="strHtml">包括HTML的源码 </param>
/// <returns>已经去除后的文字</returns>
public static string StripHTML(string strHtml)
{
string[] aryReg ={
@"<script[^>]*?>.*?</script>",
@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>",
@"([\r\n])[\s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(\d+);",
@"-->",
@"<!--.*\n"
};
string[] aryRep = {
"",
"",
"",
"\"",
"&",
"<",
">",
" ",
"\xa1",//chr(161),
"\xa2",//chr(162),
"\xa3",//chr(163),
"\xa9",//chr(169),
"",
"\r\n",
""
};
string newReg = aryReg[0];
string strOutput = strHtml;
for (int i = 0; i < aryReg.Length; i++)
{
Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput, aryRep[i]);
}
strOutput.Replace("<", "");
strOutput.Replace(">", "");
strOutput.Replace("\r\n", "");
strOutput.Replace(" ", " ");
return strOutput;
}
#endregion
exception92 2014-05-21
- 打赏
- 举报
去掉 html 标签？？使用replace方法。
bwangel 2014-05-20
- 打赏
- 举报
var htmlStr = "<body> <div>aaa </div></body>";
var result = Regex.Replace("<[^>]*>", "");
zhouxiulu 2014-05-20
- 打赏
- 举报
你说什么排除HTML啊?是不要HTML中的各个标签吗?如果是这个的话用Replace就可以了
