Strip the HTML and get raw page content

StripHtml

private static String StripHtml(String source)
{
	List<Char> array = new List<Char>(source.Length);
	Boolean inside = false;
	Boolean dquotes = false;
	Boolean squotes = false;

	///1) look for tags or things that need to be fully removed (entire containing contents) and remove them
	source = source.Replace("&nbsp;", "").Replace("Â", "").Replace("<br>", " ").Replace("<br />", " ");
	String lowersource = source.ToLower();
	Int32 scriptindex = lowersource.IndexOf("<script");
	while (scriptindex > 0)
	{
		Int32 scriptendindex = lowersource.IndexOf("</script>", scriptindex) + "</script>".Length;
		lowersource = lowersource.Remove(scriptindex, scriptendindex - scriptindex);
		source = source.Remove(scriptindex, scriptendindex - scriptindex);

		scriptindex = lowersource.IndexOf("<script");
	}

	///really cheesy way for now to remove most of the extra spacing
	source = source.Replace(Environment.NewLine, "").Replace("  ", "");

	///2) search entire contents for < and > tags outside of quotes and remove those pieces
	foreach (Char c in source)
	{                
	switch (c)
		{
			case '\r':
			case '\n':
			case '\t':
				continue;
			case '\'':
				if (inside && !dquotes)
				{
					if (squotes)
						squotes = false;
					else
						squotes = true;
					continue;
				}
				break;
			case '"':
				if (inside && !squotes)
				{
					if (dquotes)
						dquotes = false;
					else
						dquotes = true;
					continue;
				}
				break;
			case '>':
				if (dquotes || squotes) ///if we're within the inside and we are in quotes then we have to keep going
					continue;
				inside = false;
				continue;
			case '<':
				if (dquotes || squotes) ///if we're in quotes then we have to keep going
					continue;
				inside = true;
				continue;
		}
	   
		if (!inside)
		{
			array.Add(c);
		}
	}

	return new String(array.ToArray()).Trim();
}