/// <Header>
/// 去除 HTML tag
/// </Header>
/// <param name="HTML">源</param>
/// <returns>结果</returns>
public static string StripHTML(string HTML) //google "StripHTML" 得到
{
string[] Regexs =
{
@"<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[] Replaces =
{
"",
"",
"",
"\"",
"&",
"<",
">",
" ",
"\xa1", //chr(161),
"\xa2", //chr(162),
"\xa3", //chr(163),
"\xa9", //chr(169),
"",
"\r\n",
""
};
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("\r\n", "");
return s;
}
}