/// <summary>
/// 清除html中的标记，只留下文字。
/// </summary>
/// <param name="HTML"></param>
/// <returns></returns>
public string ClearHTMLTags(string HTML)
{
if (string.IsNullOrEmpty(HTML)) return "";
string[] Regexs ={
@"<script[^>]*?>.*?</script>",
@"<(/s*)?!?((w+:)?w+)(w+(s*=?s*(([""'])(file://[%22%22'tbnr]%7c[%5e/7])*?7|w+)|.{0})|s)*?(/s*)?>",
//@"([
])[s]+",//换行
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(d+);",
@"-->",
@"<!--.*
"
};
string[] Replaces ={
"",
"",
//"",//换行
""",
"&",
"<",
">",
" ",
"xa1", //chr(161),
"xa2", //chr(162),
"xa3", //chr(163),
"xa9", //chr(169),
"",
"
",
""
};
string s = HTML;
for (int i = 0; i < Regexs.Length; i++)
{
s = new Regex(Regexs[i], RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(s, Replaces[i]);
}
//s.Replace("<", "");
//s.Replace(">", "");
//s.Replace("
", "");
return s;
}