Beispiel #1
0
        /// <summary>
        /// 清除文本中的HTML标记(保存换行符)
        /// </summary>
        /// <param name="str">待处理的字符串</param>
        /// <returns>string</returns>
        public static string ClearHtml2(this string HTML)
        {
            if (String.IsNullOrWhiteSpace(HTML))
            {
                return(String.Empty);
            }


            string[] Regexs =
            {
                @"</?([a-z]+)([^<]*)>",
                @"&(quot|#34);",
                @"&(amp|#38);",
                @"&(lt|#60);",
                @"&(gt|#62);",
                @"&(nbsp|#160);",
                @"&(iexcl|#161);",
                @"&(cent|#162);",
                @"&(pound|#163);",
                @"&(copy|#169);",
                @"&#(\d+);",
                @"-->",
                @"<!--.*\n",
                @"\[(\d+)?\]",
                @"\[E\:(\d+)?\|(\d+)?\|(\d+)?\]"
            };

            string[] Replaces =
            {
                String.Empty,
                "\"",
                "&",
                "<",
                ">",
                " ",
                "\xa1", //chr(161),
                "\xa2", //chr(162),
                "\xa3", //chr(163),
                "\xa9", //chr(169),
                String.Empty,
                "\r\n",
                String.Empty,
                string.Empty,
                string.Empty
            };

            string s = HTML;

            for (int i = 0, len = Regexs.Length; i < len; i++)
            {
                s = RegExt.CreateFromCache(Regexs[i], RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(s, Replaces[i]);
            }

            s.Replace("<", String.Empty);
            s.Replace(">", String.Empty);

            return(s);
        }
Beispiel #2
0
 /// <summary>
 /// 清除空格
 /// </summary>
 /// <param name="s"></param>
 /// <returns></returns>
 public static string TrimEmpty(this string s)
 {
     if (!string.IsNullOrWhiteSpace(s))
     {
         var reg = RegExt.CreateFromCache("\\s+", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
         return(s = reg.Replace(s, string.Empty));
     }
     return(s);
 }
Beispiel #3
0
        /// <summary>
        /// 是否是字母
        /// </summary>
        /// <param name="p"></param>
        /// <returns></returns>
        public static bool IsLetter(this string content)
        {
            Regex regex = RegExt.CreateFromCache(@"[^A-Za-z]+");

            if (regex.IsMatch(content))
            {
                return(false);
            }
            return(true);
        }
Beispiel #4
0
        /// <summary>
        /// 清除HTML标签中的Style属性
        /// </summary>
        /// <param name="HTML"></param>
        /// <returns></returns>
        public static string ClearHtmlStyle(this string HTML)
        {
            if (string.IsNullOrWhiteSpace(HTML))
            {
                return(string.Empty);
            }

            var re = RegExt.CreateFromCache("style\\=\".+?\"|style\\='.+?'", RegexOptions.IgnoreCase | RegexOptions.Multiline).Replace(HTML, string.Empty);

            return(re);
        }
Beispiel #5
0
        public static string ClearHtml3(this string HTML)
        {
            if (string.IsNullOrWhiteSpace(HTML))
            {
                return(string.Empty);
            }

            var reg     = RegExt.CreateFromCache(@"(?:\>)\w+(?:\<)", RegexOptions.Multiline | RegexOptions.IgnoreCase);
            var matches = reg.Matches(HTML);

            if (matches != null && matches.GetEnumerator().MoveNext())
            {
                var s = matches.OfType <Match>().ToArray().Select(i => i.Value);
                HTML = string.Join("", s);
            }
            HTML = HTML.Replace("<", string.Empty).Replace(">", string.Empty);
            return(HTML);
        }
Beispiel #6
0
        /// <summary>
        /// 清除文本中的HTML标记
        /// </summary>
        /// <param name="str">待处理的字符串</param>
        /// <returns>string</returns>
        public static string ClearHtml(this string HTML)
        {
            if (String.IsNullOrWhiteSpace(HTML))
            {
                return(String.Empty);
            }

            var regexdicts = new Dictionary <string, string>();

            regexdicts.Add(@"</?([a-z]+)([^<]*)>", String.Empty);
            regexdicts.Add(@"([\r\n])[\s]+", String.Empty);
            regexdicts.Add(@"&(quot|#34);", "\"");
            regexdicts.Add(@"&(amp|#38);", "&");
            regexdicts.Add(@"&(lt|#60);", "<");
            regexdicts.Add(@"&(gt|#62);", ">");
            regexdicts.Add(@"&(nbsp|#160);", " ");
            regexdicts.Add(@"&(iexcl|#161);", "\xa1");
            regexdicts.Add(@"&(cent|#162);", "\xa2");
            regexdicts.Add(@"&(pound|#163);", "\xa3");
            regexdicts.Add(@"&(copy|#169);", "\xa9");
            regexdicts.Add(@"&#(\d+);", String.Empty);
            regexdicts.Add(@"<!--.*-->", String.Empty);
            regexdicts.Add("<img[^>]*>", String.Empty);

            string s = HTML;

            foreach (var key in regexdicts.Keys)
            {
                s = RegExt.CreateFromCache(key, RegexOptions.IgnoreCase | RegexOptions.Multiline).Replace(s, regexdicts[key]);
            }

            s.Replace("<", String.Empty);
            s.Replace(">", String.Empty);
            s.Replace("\r\n", String.Empty);

            return(s);
        }