获取html中的全部中文文本
/// <summary> /// 获取文本中的全部中文文本 /// </summary> /// <param name="oriText"></param> /// <returns></returns> public static string GetChineseWord(string oriText) { string x = @"[\u4E00-\u9FFF]+"; MatchCollection Matches = Regex.Matches (oriText, x, RegexOptions.IgnoreCase); StringBuilder sb = new StringBuilder(); foreach (Match NextMatch in Matches) { sb.Append(NextMatch.Value); } return sb.ToString(); }