HTML Removal 類別庫(移除Html標籤)

HTML Removal 類別庫(移除Html標籤)

using System;

using System.Collections.Generic;

using System.Linq;

using System.Web;



/// <summary>

/// HtmlRemoval 的摘要描述

/// </summary>

using System;

using System.Text.RegularExpressions;



/// <summary>

/// Methods to remove HTML from strings.

/// </summary>

public static class HtmlRemoval

{

    /// <summary>

    /// Remove HTML from string with Regex.

    /// </summary>

    public static string StripTagsRegex(string source)

    {

        return Regex.Replace(source, "<.*?>", string.Empty);

    }



    /// <summary>

    /// Compiled regular expression for performance.

    /// </summary>

    static Regex _htmlRegex = new Regex("<.*?>", RegexOptions.Compiled);



    /// <summary>

    /// Remove HTML from string with compiled Regex.

    /// </summary>

    public static string StripTagsRegexCompiled(string source)

    {

        return _htmlRegex.Replace(source, string.Empty);

    }



    /// <summary>

    /// Remove HTML tags from string using char array.

    /// </summary>

    public static string StripTagsCharArray(string source)

    {

        char[] array = new char[source.Length];

        int arrayIndex = 0;

        bool inside = false;



        for (int i = 0; i < source.Length; i++)

        {

            char let = source[i];

            if (let == '<')

            {

                inside = true;

                continue;

            }

            if (let == '>')

            {

                inside = false;

                continue;

            }

            if (!inside)

            {

                array[arrayIndex] = let;

                arrayIndex++;

            }

        }

        return new string(array, 0, arrayIndex);

    }



    /// <summary>

    /// 尋找及取代 Visual C#.NET 中的 XML 檔案中的特殊字元

    /// </summary>

    /// <param name="source"></param>

    /// <returns></returns>

    public static string StripTagsRestore(string source)

    {

        string Rsource = source;

        try

        {

            Rsource = Rsource.Replace("&amp;", "&");

            Rsource = Rsource.Replace("&lt;", "<");

            Rsource = Rsource.Replace("&gt;", ">");

            Rsource = Rsource.Replace("&quto;", "\"");

            Rsource = Rsource.Replace("&apos;", "'");

        }

        catch (System.Exception)

        {

            //throw;

        }

        return Rsource;

    }

}

參考來源：不知名網友(年代久遠已追溯不到來源)