c# 正则html标签剔除方法的实现代码
本文导语: 方法1: public string checkStr(string html) { System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressi...
方法1:
public string checkStr(string html)
{
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"
", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //过滤标记
html = regex2.Replace(html, ""); //过滤href=javascript: () 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("", "");
html = html.Replace("", "");
return html;
}
方法2:
#region 过滤掉 html代码
public static string StripHTML(string strHtml)
{
string [] aryReg ={
@"]*?>.*?",
@"",
@"([rn])[s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"(d+);",
@"-->",
@"