public string DealHtml(string str)
{
//str = Regex.Replace(str, @"<(img)[^>]*>|</(img)>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<(table|tbody|tr|td|th)[^>]*>|</(table|tbody|tr|td|th)>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<(div|blockquote|fieldset|legend)[^>]*>|</(div|blockquote|fieldset|legend)>", "", RegexOptions.IgnoreCase);
//str = Regex.Replace(str, @"<(font|i|u|h[1-9]|s)[^>]*>|</(font|i|u|h[1-9]|s)>", "", RegexOptions.IgnoreCase);
//str = Regex.Replace(str, @"<(style|strong)[^>]*>|</(style|strong)>", "", RegexOptions.IgnoreCase);
//str = Regex.Replace(str, @"<a[^>]*>|</a>", "", RegexOptions.IgnoreCase);
//str = Regex.Replace(str, @"<(meta|iframe|frame|span|tbody|layer)[^>]*>|</(iframe|frame|meta|span|tbody|layer)>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<br[^>]*", "", RegexOptions.IgnoreCase);
str = str.Replace("<br>", "");
return str;
}
【正则表达式过滤html的标签对】相关文章：
★ python使用正则表达式分析网页中的图片并进行替换的方法