C# .Net使用正则表达式去除HTML标记和空格

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&nbsp;替换为空格

5.spaceReg :把一个以上的空格替换为一个空格.

public string RemoveHtml(string src)
{
    Regex htmlReg = new Regex(@"<[^>]+>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
    Regex htmlSpaceReg = new Regex("\\&nbsp\\;", 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();
}