How do I convert HTML to RTF (Rich Text) in .NET without paying for a component? [closed]

Solution 1:

Actually there is a simple and free solution: use your browser, ok this is the trick I used:

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();

This could be slower than other methods but at least it's free and works!

Solution 2:

Check out this CodeProject article on XHTML2RTF.

Solution 3:

Expanding on Spartaco's answer I implimented the following which works GREAT!

    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

Solution 4:

It is not perfect of course, but here is the code I use to convert HTML to plain text.

(I was not the original author, I adapted it from code found on the web)

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,
                     @"&nbsp;", " ",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);

            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&bull;", " * ",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&lsaquo;", "<",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&rsaquo;", ">",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&trade;", "(tm)",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&frasl;", "/",
                     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,
                     @"&copy;", "(c)",
                     System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            result = System.Text.RegularExpressions.Regex.Replace(result,
                     @"&reg;", "(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;

    }

How do I convert HTML to RTF (Rich Text) in .NET without paying for a component? [closed]

Solution 1:

Solution 2:

Solution 3:

Solution 4:

Related

Recent Posts