2020-04-09
/// <summary>
/// 将html文本转化为 文本内容方法TextNoHTML
/// </summary>
/// <param name="Htmlstring">HTML文本值</param>
/// <returns></returns>
public static string TextNoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([/r/n])[/s]+", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "/", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "/xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "/xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "/xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "/xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(/d+);", "", RegexOptions.IgnoreCase);
//替换掉 < 和 > 标记
Htmlstring = Htmlstring.Replace("<", "");
Htmlstring = Htmlstring.Replace(">", "");
Htmlstring = Htmlstring.Replace("\r\n", "");
Htmlstring = Htmlstring.Replace("\r", "");
Htmlstring = Htmlstring.Replace("\n", "");
//返回去掉html标记的字符串
return Htmlstring;
}在检索时忽然发现比预想的数据多，搜索的是python，然后出来的几条数据和python风马牛不相及，查看了下源码，发现html标签里有个样式叫python。
解决方法，加了个字段，存放去掉html标签的数据，检索时检索这个字段。