using System.Text.RegularExpressions;
在进行数据采集,显示文章摘要,内容计数等情况下,需要清除源代码中的html标签,空格,style,script等标签.
注意下面代码的执行顺序:
1.styleReg:清除样式.如<style>.class{}</style>.全部替换为空.
2.scriptReg和styleReg同样的道理.
3.htmlReg :清除html标签的.输入为<div>aaa</div>,结果为:aaa
4.htmlSpaceReg :html空格 替换为空格
5.spaceReg :把一个以上的空格替换为一个空格
//移除HTML标记
public string RemoveHtml(string src)
{
Regex htmlReg = new Regex(@"<[^>]+>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
Regex htmlSpaceReg = new Regex("\\ \\;", RegexOptions.Compiled | RegexOptions.IgnoreCase);
Regex spaceReg = new Regex("\\s{2,}|\\ \\;", RegexOptions.Compiled | RegexOptions.IgnoreCase);
Regex styleReg = new Regex(@"<style(.*?)</style>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
Regex scriptReg = new Regex(@"<script(.*?)</script>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
src = styleReg.Replace(src, string.Empty);
src = scriptReg.Replace(src, string.Empty);
src = htmlReg.Replace(src, string.Empty);
src = htmlSpaceReg.Replace(src, " ");
src = spaceReg.Replace(src, " ");
return src.Trim();
}
想去掉除段落标记之外的所有html标记,只要页面的文字,好比是把代码贴到记事本的效果:
public static string DelHTML(string Htmlstring)//将HTML去除
{
#region
//删除脚本
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"-->", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<!--.*", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<A>.*</A>","");
//Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=\.[a-zA-Z]*\?[a-zA-Z]+=\d&\w=%[a-zA-Z]*|[A-Z0-9]","");
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(amp|#38);", "&", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(lt|#60);", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(gt|#62);", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&#(\d+);", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
//Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
#endregion
return Htmlstring;
}