含html标记的文本处理方法

    /// <summary>
    /// 去除给定内容中的html标记，只保留图片标记
    /// </summary>
    /// <param name="strHtml">给定内容</param>
    protected string getContent(string strHtml)
    {
        string str = string.Empty;
        //str = Regex.Replace(strHtml, "<.+?>", "", RegexOptions.IgnoreCase);//一个去掉所有HTML标记
        //str = Regex.Replace(strHtml, "/<(?!img).*?>/g", " ", RegexOptions.IgnoreCase);//这是保留Img和<br>
        //str = Regex.Replace(strHtml, "<(?!/?br|/?img)[^<>]*>", "", RegexOptions.IgnoreCase);//保留Img和<Br>
        str = Regex.Replace(strHtml, "<(?!/?img)[^<>]*>", "", RegexOptions.IgnoreCase);//保留Img
        //改Img为[图片]
        str = Regex.Replace(str, "<?img[^<>]*>", "[图片]", RegexOptions.IgnoreCase);

        //空格符
        string strEmpty = " ";
        int intEmpy = strEmpty.Length;
        str = str.Trim();
        //去除所有空格符
        while (str.IndexOf(strEmpty) != -1)
        {
            str = str.Remove(str.IndexOf(strEmpty), intEmpy);
        }

        return str;
    }