C# 將html文本轉化為 文本內容方法TextNoHTML

不記得在哪看過這個，挺實用的

/// <summary>
/// 將html文本轉化為 文本內容方法TextNoHTML
/// </summary>
/// <param name="Htmlstring">HTML文本值</param>
/// <returns></returns>
public string TextNoHTML(string Htmlstring)
{
    //刪除腳本   
    Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
    //刪除HTML   
    Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"([/r/n])[/s]+", "", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "/", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", "   ", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "/xa1", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "/xa2", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "/xa3", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "/xa9", RegexOptions.IgnoreCase);
    Htmlstring = Regex.Replace(Htmlstring, @"&#(/d+);", "", RegexOptions.IgnoreCase);
    //替換掉 < 和 > 標記
    Htmlstring = Htmlstring.Replace("<", "");
    Htmlstring = Htmlstring.Replace(">", "");
    Htmlstring = Htmlstring.Replace("\r\n", "");
    Htmlstring = Htmlstring.Replace("\r", "");
    Htmlstring = Htmlstring.Replace("\n", "");
    //返回去掉html標記的字符串
    return Htmlstring;
}

/// <summary>  
/// 獲取Img的路徑  
/// </summary>  
/// <param name="htmlText">Html字符串文本</param>  
/// <returns>以數組形式返回圖片路徑</returns>  
public static string[] GetHtmlImageUrlList(string htmlText)
{
    Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);
    //新建一個matches的MatchCollection對象 保存 匹配對象個數(img標簽)  
    MatchCollection matches = regImg.Matches(htmlText);
    int i = 0;
    string[] sUrlList = new string[matches.Count];
    //遍歷所有的img標簽對象  
    foreach (Match match in matches)
    {
        //獲取所有Img的路徑src,並保存到數組中  
        sUrlList[i++] = match.Groups["imgUrl"].Value;
    }
    return sUrlList;
}