在网页中定位表单元素的一个复杂问题是该页面可能包含框架,并且任何框架中都可能存在表单。基本上,您必须遍历所有帧和每个帧中的表单。将表单作为 IHTMLFormElement 获取后,使用 Cryer 的函数获取表单元素名称。
您提供的示例链接没有任何框架,并且您在获取表单元素列表时应该没有问题,除非您尝试按名称获取表单,因为它没有分配名称。使用以下过程获取表单元素名称和值没有问题
procedure GetForms(doc1: IHTMLDocument2; var sl: TStringList);
var
i, j, n: integer;
docForm: IHTMLFormElement;
slt: TStringList;
s: string;
begin
if doc1 = nil then
begin
ShowMessage('doc1 is empty [GetForms]');
Exit;
end;
slt := TStringList.Create;
n := NumberOfForms(doc1);
sl.Add('Forms: ' + IntToStr(n));
for i := 0 to n - 1 do
begin
docForm := GetFormByNumber(doc1, i);
sl.Add('Form Name: ' + docForm.Name);
slt.Clear;
slt := GetFormFieldNames(docForm);
for j := 0 to slt.Count - 1 do
begin
s := GetFieldValue(docForm, slt[j]);
sl.Add('Field Name: ' + slt[j] + ' value: "' + s + '"');
end;
end;
sl.Add('');
slt.Free;
end;
Cryer 的框架集导航示例不适用于所有网站,请参阅http://support.microsoft.com/support/kb/articles/Q196/3/40.ASP。以下函数在我尝试过的所有站点上成功地将框架提取为 IHTMLDocument2
function GetFrameByNumber(Doc:IHTMLDocument2; n:integer):IHTMLDocument2;
var
Container: IOleContainer;
Enumerator: ActiveX.IEnumUnknown;
Unknown: IUnknown;
Browser: IWebBrowser2;
Fetched: Longint;
NewDoc: IHTMLDocument2;
i : integer;
begin
// We cannot use the document's frames collection here, because
// it does not work in every case (i.e. Documents from a foreign domain).
// From: http://support.microsoft.com/support/kb/articles/Q196/3/40.ASP
i := 0;
if (Supports(Doc, IOleContainer, Container)) and
(Container.EnumObjects(OLECONTF_EMBEDDINGS, Enumerator) = S_OK) then
begin
while Enumerator.Next(1, Unknown, @Fetched) = S_OK do
begin
if (Supports(Unknown, IWebBrowser2, Browser)) and
(Supports(Browser.Document, IHTMLDocument2, NewDoc)) then
begin
// Here, NewDoc is an IHTMLDocument2 that you can query for
// all the links, text edits, etc.
if i=n then
begin
Result := NewDoc;
Exit;
end;
i := i+1;
end;
end;
end;
end;
这是我如何使用 GetForms 和 GetFrameByNumber 的示例
// from the TForm1 declaration
{ Public declarations }
wdoc: IHTMLDocument2;
procedure TForm1.btnAnalyzeClick(Sender: TObject);
begin
wdoc := WebBrowser.Document as IHTMLDocument2;
GetDoc(wdoc);
end;
procedure TForm1.GetDoc(doc1: IHTMLDocument2);
var
i, n: integer;
doc2: IHTMLDocument2;
frame_dispatch: IDispatch;
frame_win: IHTMLWindow2;
ole_index: olevariant;
sl: TStringList;
begin
if doc1 = nil then
begin
ShowMessage('Web doc is empty');
Exit;
end;
Form2.Memo1.Lines.Clear;
sl := TStringList.Create;
n := doc1.frames.length;
sl.Add('Frames: ' + IntToStr(n));
// check each frame for the data
if n = 0 then
GetForms(doc1, sl)
else
for i := 0 to n - 1 do
begin
sl.Add('--Frame: ' + IntToStr(i));
ole_index := i;
frame_dispatch := doc1.Frames.Item(ole_index);
if frame_dispatch <> nil then
begin
frame_win := frame_dispatch as IHTMLWindow2;
doc2 := frame_win.document;
// sl.Add(doc2.body.outerHTML);
GetForms(doc2,sl);
GetDoc(doc2);
end;
end;
// Form2 just contains a TMemo
Form2.Memo1.Lines.AddStrings(sl);
Form2.Show;
sl.Free;
end;
您的示例中的逻辑是错误的,1.当网页上只有 1 个表单时,永远不会提取表单元素列表,2.除非找到“theid”中的标签,否则重复循环将导致访问冲突
这是您为成功提取表单元素而精简的示例。
var
i : integer;
nforms : integer;
document : IHTMLDocument2;
theForm : IHTMLFormElement;
fields : TStringList;
theform1 : integer;
num : integer;
theid : string;
begin
fields := TStringList.Create;
theid := 'xx';
// original code follows
i := -1;
// nforms := NumberOfForms(webbrowser1.document as IHTMLDocument2);
// document := webbrowser1.document as IHTMLDocument2;
// if nforms = 1 then
// begin
// theForm := GetFormByNumber(webbrowser1.document as IHTMLDocument2, 0);
// theform1 := 0;
// end
// else
begin
// repeat
begin
inc(i);
theForm := GetFormByNumber(webbrowser1.document as IHTMLDocument2,
i);
fields := GetFormFieldNames(theForm);
num := fields.IndexOf(theid);
theform1 := i;
end;
// until (num <> -1);
end;
// end of original code
Memo1.Lines.Text := fields.Text;
fields.Free;
end;