如何在不使用组件的情况下将HTML转换为RTF（Rich Text）？
是否有一个免费的第三方或.NET类将HTML转换为RTF（用于启用富文本格式的Windows窗体控件）？
“免费”的要求来自于我只在一个原型上工作，只需加载BrowserControl，并在需要的时候呈现HTML（即使速度很慢），并且Developer Express将要发布自己的尽快控制。
我不想学习手写RTF，而且我已经知道HTML，所以我认为这是快速获得一些可certificate代码的最快方法。
其实有一个简单和免费的解决scheme：使用您的浏览器，好吧，这是我用过的把戏：
var webBrowser = new WebBrowser(); webBrowser.CreateControl(); // only if needed webBrowser.DocumentText = *yourhtmlstring*; while (_webBrowser.DocumentText != *yourhtmlstring*) Application.DoEvents(); webBrowser.Document.ExecCommand("SelectAll", false, null); webBrowser.Document.ExecCommand("Copy", false, null); *yourRichTextControl*.Paste(); 这可能比其他方法慢，但至less它是免费的，工作！
看看这个CodeProject文章XHTML2RTF 。
扩大对Spartaco的答复，我实现了以下伟大的作品！
Using reportWebBrowser As New WebBrowser reportWebBrowser.CreateControl() reportWebBrowser.DocumentText = sbHTMLDoc.ToString While reportWebBrowser.DocumentText <> sbHTMLDoc.ToString Application.DoEvents() End While reportWebBrowser.Document.ExecCommand("SelectAll", False, Nothing) reportWebBrowser.Document.ExecCommand("Copy", False, Nothing) Using reportRichTextBox As New RichTextBox reportRichTextBox.Paste() reportRichTextBox.SaveFile(DocumentFileName) End Using End Using
这当然不是完美的，但这里是我用来将HTML转换为纯文本的代码。
（我不是原作者，我是从网上find的代码改编的）
public static string ConvertHtmlToText(string source) { string result; // Remove HTML Development formatting // Replace line breaks with space // because browsers inserts space result = source.Replace("\r", " "); // Replace line breaks with space // because browsers inserts space result = result.Replace("\n", " "); // Remove step-formatting result = result.Replace("\t", string.Empty); // Remove repeating speces becuase browsers ignore them result = System.Text.RegularExpressions.Regex.Replace(result, @"( )+", " "); // Remove the header (prepare first by clearing attributes) result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*head([^>])*>", "<head>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*head( )*>)", "</head>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, "(<head>).*(</head>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase); // remove all scripts (prepare first by clearing attributes) result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*script([^>])*>", "<script>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*script( )*>)", "</script>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); //result = System.Text.RegularExpressions.Regex.Replace(result, // @"(<script>)([^(<script>\.</script>)])*(</script>)", // string.Empty, // System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"(<script>).*(</script>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase); // remove all styles (prepare first by clearing attributes) result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*style([^>])*>", "<style>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*style( )*>)", "</style>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, "(<style>).*(</style>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase); // insert tabs in spaces of <td> tags result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*td([^>])*>", "\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // insert line breaks in places of <BR> and <LI> tags result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*br( )*>", "\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*li( )*>", "\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // insert line paragraphs (double line breaks) in place // if <P>, <DIV> and <TR> tags result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*div([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*tr([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*p([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove remaining tags like <a>, links, images, // comments etc - anything thats enclosed inside < > result = System.Text.RegularExpressions.Regex.Replace(result, @"<[^>]*>", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase); // replace special characters: result = System.Text.RegularExpressions.Regex.Replace(result, @" ", " ", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"•", " * ", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"‹", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"›", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"™", "(tm)", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"⁄", "/", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"<", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @">", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"©", "(c)", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, @"®", "(r)", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove all others. More can be added, see // http://hotwired.lycos.com/webmonkey/reference/special_characters/ result = System.Text.RegularExpressions.Regex.Replace(result, @"&(.{2,6});", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase); // make line breaking consistent result = result.Replace("\n", "\r"); // Remove extra line breaks and tabs: // replace over 2 breaks with 2 and over 4 tabs with 4. // Prepare first to remove any whitespaces inbetween // the escaped characters and remove redundant tabs inbetween linebreaks result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)( )+(\r)", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, "(\t)( )+(\t)", "\t\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, "(\t)( )+(\r)", "\t\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)( )+(\t)", "\r\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove redundant tabs result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+(\r)", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove multible tabs followind a linebreak with just one tab result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+", "\r\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Initial replacement target string for linebreaks string breaks = "\r\r\r"; // Initial replacement target string for tabs string tabs = "\t\t\t\t\t"; for (int index = 0; index < result.Length; index++) { result = result.Replace(breaks, "\r\r"); result = result.Replace(tabs, "\t\t\t\t"); breaks = breaks + "\r"; tabs = tabs + "\t"; } // Thats it. return result; }
也许你需要的是一个编辑HTML的控件 ？
