In article <44401b57$1@newsgroups.borland.com>, sjohnson@caelix.com
says...
> Hi,
>
> I'm using TIdHTTP to get a web site. The Get method returns all of the data
> and HTML formating codes. Is there a component that will strip the formating
> HTML codes and return just the data?
>
Very easy to parse text from HTML using IHTMLDocument2.
uses ...,mshtml, ActiveX, ComObj;
procedure TForm1.Button1Click(Sender: TObject);
var
IDoc: IHTMLDocument2;
sHTMLFile: String;
v: Variant;
begin
sHTMLFile := idHTTP1.Get('http://www.mysite.com');
Idoc:=CreateComObject(Class_HTMLDOcument) as IHTMLDocument2;
try
IDoc.designMode:='on';
while IDoc.readyState<>'complete' do
Application.ProcessMessages;
v:=VarArrayCreate([0,0],VarVariant);
v[0]:= sHTMLFile;
IDoc.write(PSafeArray(System.TVarData(v).VArray));
IDoc.designMode:='off';
while IDoc.readyState<>'complete' do
Application.ProcessMessages;
Memo1.Lines.Text := IDoc.body.innerText;
finally
IDoc := nil;
end;
end;
