/// <summary>
/// Конвертировать HTML в текст.
/// </summary>
/// <param name="node"></param>
/// <param name="outText"></param>
/// <param name="documentFactory">Фабрика документов.</param>
public static void ConvertHtmlToText(IHtmlNode node, TextWriter outText, IHtmlDocumentFactory documentFactory)
{
if (documentFactory == null)
{
throw new ArgumentNullException(nameof(documentFactory));
}
switch (node)
{
case IHtmlCommentNode _:
// don't output comments
break;
case IHtmlTextNode tn:
// script and style must not be output
string parentName = tn.ParentNode.Name;
if ((parentName == "script") || (parentName == "style"))
{
break;
}
// get text
var html = tn.Text;
// is it in fact a special closing node output as text?
if (documentFactory.IsOverlappedClosingElement(html))
{
break;
}
// check the text is meaningful and not a bunch of whitespaces
if (html.Trim().Length > 0)
{
outText.Write(documentFactory.DeEntitize(html));
}
break;
default:
switch (node.Name)
{
case "p":
// treat paragraphs as crlf
outText.WriteLine();
break;
}
if (node.HasChildNodes)
{
ConvertContentTo(node, outText, documentFactory);
}
break;
}
}
