调用下面的方法屏蔽所有html标签提取文本_html忽略标签取文本-优快云博客

本文介绍了一个用于移除字符串中HTML标签和特殊字符的C#方法。该方法通过正则表达式来清理HTML标签、脚本、注释及特殊字符实体等，确保输出的文本干净且安全。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

 
 public  
 static  
 string  
 NoHTML( 
 string  
 Htmlstring) 
 //替换HTML标记 
 
    
 { 
 
    
 string  
 pattern =  
 "http://([^\\s]+)\".+?span.+?\\[(.+?)\\].+?>(.+?)<" 
 ; 
 
    
 Regex reg =  
 new  
 Regex(pattern, RegexOptions.IgnoreCase); 
 
    
 //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); 
 
    
 Htmlstring = Regex.Replace(Htmlstring,  
 @"<img[^>]*>;" 
 , 
 "" 
 , RegexOptions.IgnoreCase); 
 
    
 Htmlstring.Replace( 
 "<" 
 , 
 "" 
 ); 
 
    
 Htmlstring.Replace( 
 ">" 
 , 
 "" 
 ); 
 
    
 Htmlstring.Replace( 
 "\r\n" 
 , 
 "" 
 ); 
 
    
 Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim(); 
 
    
 return  
 Htmlstring; 
 
    
 } 