自由色彩,无限魅力:www.zyml.net
提取HTML代码中文字的C#函数
上一篇 /
下一篇 2008-02-04 15:34:36
查看( 7 ) /
评论( 0 )
/// <summary>
/// 去除HTML标记
/// </summary>
/// <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*(([""'])([url=file://\\[""]\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s[/url]*)?>",
@"([\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
,RegexOptions.IgnoreCase );
strOutput = regex.Replace(strOutput,aryRep);
}
strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace("\r\n","");
return strOutput;
论坛模式
推荐
收藏
分享给好友
推荐到圈子
管理
TAG: