[转载]清除文本中的Html标签 – Kevin Gao – 博客园.
以前做项目时,曾经遇到一个问题,就是要一段含html的文本中html的标签清除掉,并将清除后的文本显示在winform的Label上面。当时在网上搜寻了好久,终于找到了点资料,自己好好对照整理了下,现在分享给大家:
/// <summary> /// 清除文本中Html的标签 /// </summary> /// <param name="Content"></param> /// <returns></returns> private string ClearHtml(string Content) { Content = Zxj_ReplaceHtml("&#[^>]*;", "", Content); Content = Zxj_ReplaceHtml("</?marquee[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?object[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?param[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?embed[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?table[^>]*>", "", Content); Content = Zxj_ReplaceHtml(" ", "", Content); Content = Zxj_ReplaceHtml("</?tr[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?p[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?a[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?img[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?tbody[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?li[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?span[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?div[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?td[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?script[^>]*>", "", Content); Content = Zxj_ReplaceHtml("(javascript|jscript|vbscript|vbs):", "", Content); Content = Zxj_ReplaceHtml("on(mouse|exit|error|click|key)", "", Content); Content = Zxj_ReplaceHtml("<\\?xml[^>]*>", "", Content); Content = Zxj_ReplaceHtml("<\\/?[a-z]+:[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?font[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?b[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?u[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?i[^>]*>", "", Content); Content = Zxj_ReplaceHtml("</?strong[^>]*>", "", Content); string clearHtml = Content; return clearHtml; } } /// <summary> /// 清除文本中的Html标签 /// </summary> /// <param name="patrn">要替换的标签正则表达式</param> /// <param name="strRep">替换为的内容</param> /// <param name="content">要替换的内容</param> /// <returns></returns> private string Zxj_ReplaceHtml(string patrn, string strRep, string content) { if (string.IsNullOrEmpty(content)) { content = ""; } Regex rgEx = new Regex(patrn, RegexOptions.IgnoreCase); string strTxt = rgEx.Replace(content, strRep); return strTxt; }