private static void ConvertContentTo(HtmlNode node, WebPageContent webPageContent)
{
foreach (HtmlNode subnode in node.ChildNodes)
{
ConvertTo(subnode, webPageContent);
}
}
private static void ConvertTo(HtmlNode node, WebPageContent webPageContent)
{
string html;
switch (node.NodeType)
{
case HtmlNodeType.Document:
ConvertContentTo(node, webPageContent);
break;
case HtmlNodeType.Text:
// script and style must not be output
string parentName = node.ParentNode.Name;
if (parentName != "title")
break;
// get text
html = ((HtmlTextNode)node).Text;
// is it in fact a special closing node output as text?
if (HtmlNode.IsOverlappedClosingElement(html))
break;
webPageContent.Element = HtmlEntity.DeEntitize(html.Trim());
webPageContent.Line = node.Line;
webPageContent.LinePosition = node.LinePosition;
break;
case HtmlNodeType.Element:
if (node.HasChildNodes)
{
ConvertContentTo(node, webPageContent);
}
break;
}
}
public WebPageContent GetTitle()
{
var content = new WebPageContent();
ConvertTo(_crawledPage.HtmlDocument.DocumentNode, content);
return content;
}
