/// <summary>
/// Gets only the cdata (inner text) for the html page returning it as a list.
/// </summary>
/// <param name="webResponseText"></param>
/// <param name="filter">Optional filter, pass in null to skip</param>
/// <param name="cdata"></param>
/// <returns></returns>
public static bool TryGetCdata(string webResponseText, Func <string, bool> filter, out string[] cdata)
{
cdata = null;
if (string.IsNullOrWhiteSpace(webResponseText))
{
return(false);
}
var ms = new MemoryStream(Encoding.UTF8.GetBytes(webResponseText));
var antlrHtml = AspNetParseTree.InvokeParse(ms);
if (antlrHtml == null)
{
return(false);
}
var innerText = antlrHtml.CharData;
if (innerText.Count <= 0)
{
return(false);
}
cdata = antlrHtml.CharData.ToArray();
if (filter != null)
{
cdata = cdata.Where(filter).ToArray();
}
return(cdata.Length > 0);
}
public static HtmlParseResults InvokeParse(Stream stream)
{
var input = new AntlrInputStream(stream);
var lexer = new HTMLLexer(input);
var tokens = new CommonTokenStream(lexer);
var parser = new HTMLParser(tokens);
var tree = parser.htmlDocument();
var walker = new ParseTreeWalker();
var loader = new AspNetParseTree();
walker.Walk(loader, tree);
return(loader.Results);
}
