Strip HTML : HTML « Network « C# / C Sharp

Strip HTML
 


using System;
using System.Collections.Generic;
using System.Text;

namespace natol.GoogleReaderAPI
{
    public static class Util
    {
        public static string StripHTML(string source)
        {

            try
            {

                string result;

                // Remove HTML Development formatting
                result = source.Replace("\r", " ");        // Replace line breaks with space because browsers inserts space
                result = result.Replace("\n", " ");        // Replace line breaks with space because browsers inserts space
                result = result.Replace("\t", string.Empty);    // Remove step-formatting
                result = System.Text.RegularExpressions.Regex.Replace(result, @"( )+", " ");    // Remove repeating speces becuase browsers ignore them

                // 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);

                // for testng
                //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 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);
                result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+(\r)", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);    // Remove redundant tabs
                result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+", "\r\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase);        // Remove multible tabs followind a linebreak with just one tab
                string breaks = "\r\r\r";        // Initial replacement target string for linebreaks
                string tabs = "\t\t\t\t\t";        // Initial replacement target string for tabs
                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;

            }
            catch
            {
                return source;
            }

        }
    }
}
Related examples in the same category

1.	Get Links From HTML
2.	Parses the value information from any INPUT tag in an HTML string where the name="" attribute matched the tagID parameter
3.	Html Utilities
4.	Convert HTML To Text
5.	Converts a FontUnit to a size for the HTML FONT tag
6.	Remove tags from a html string
7.	Sanitize any potentially dangerous tags from the provided raw HTML input using a whitelist based approach
8.	Get Type As Html
9.	HTML-encodes a string and returns the encoded string.
10.	Strips all HTML tags from the specified string.
11.	Removes the HTML whitespace.
12.	Array To Html Breaked String
13.	Show Html Page in String with Process