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,
@" ", " ",
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;
}