Unterseiten einer Homepage ermitteln

[Bummi]

vielleich hilft Dir der Codefetzen aus unserer Codebase?

Delphi-Quellcode:

procedure TCrawlingThread.WBDocumentComplete(Sender: TObject ;const pDisp:IDispatch;var  URL: OLEVariant);
var
  i:Integer;
  ElementCollection: IHTMLElementCollection;
  HtmlElement: IHTMLElement;
  AnchorString: string;
  sl:TStringList;
begin
  try
  if Assigned((FWB.Document as IHTMLDocument2).body) then
    begin
      sl:=TStringList.Create;
      try
      sl.Text := ((FWB.Document as IHTMLDocument2).body as IHTMLBodyElement).createTextRange.text;
      sl.SaveToFile(IncludeTrailingBackSlash(FFilePath) + FGuid);
      finally
      sl.Free;
      end;
    end;
  ElementCollection:= (FWB.Document as IHTMLDocument2).all;
  For i := 0 To ElementCollection.length - 1 do
      begin
            HtmlElement := ElementCollection.item(I, '') as IHTMLElement;
            if HTMLElement.tagName = 'A' then
            begin
              AnchorString := (HtmlElement as IHTMLAnchorElement).href;
              FCollectedLinks.Add(AnsiLowerCase(AnchorString));
              end;
      end;
  FCanTerminate := true;

  except
  on E:Exception do FError := E.Message;
  end;
end;

[Die Muhkuh]

Lustig wird's dann bei Flash-Seiten oder welche, die den Content per JavaScript nachladen und diesen auch nur per JS austauschen.