Convert html to string c#

I have faced similar problem and found best solution . Below code works perfect for me.

  private string ConvertHtml_Totext(string source)
    {
     try
      {
      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 spaces because 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 that's 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,
             @"&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,
             @"&lt;","<",
             System.Text.RegularExpressions.RegexOptions.IgnoreCase);
    result = System.Text.RegularExpressions.Regex.Replace(result,
             @"&gt;",">",
             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);

    // for testing
    //System.Text.RegularExpressions.Regex.Replace(result,
    //       this.txtRegex.Text,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 in between
    // the escaped characters and remove redundant tabs in between line breaks
    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 multiple tabs following a line break 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 line breaks
    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";
    }

    // That's it.
    return result;
}
catch
{
    MessageBox.Show("Error");
    return source;
}

}

Escape characters such as \n and \r had to be removed first because they cause regexes to cease working as expected.

Moreover, to make the result string display correctly in the textbox, one might need to split it up and set textbox's Lines property instead of assigning to Text property.

this.txtResult.Lines = StripHTML(this.txtSource.Text).Split("\r".ToCharArray());

Source : https://www.codeproject.com/Articles/11902/Convert-HTML-to-Plain-Text-2

How do I convert HTML to normal text?

Below are several methods for converting, or saving, an HTML web page as a text document..
Click the File tab again, then click the Save as option..
In the Save as type drop-down list, select the Plain Text (*. txt) option. ... .
Click the Save button to save as a text document..

How do you convert HTML to plain text in C#?

You could convert HTML text to plain text by using the following HTMLToText method..
public partial class MainWindow : Window..
public MainWindow().
InitializeComponent();.
string html = "<p>Some text here</p>" +.
"< div > Some more<strong> text</ strong ></ div > ";.
p. Inlines. Add(html);.

How do I display HTML as plain text?

HTML <plaintext> Tag The <plaintext> tag tells the browser, that its content must be displayed as an ordinary text without formatting.

How do you do string in HTML?

You can create a String instance using plain text or HTML, for example both of these statements are valid: // From plain text var helloWorld = new HTMLString. String('Hello World'); // From HTML var helloWorldBold = new HTMLString.