Extract HTML Form Information

Download an HTML page, parse the HTML, and extract information for the 1st form on the page.

Download Chilkat XML ActiveX

Download Chilkat HTML-to-XML ActiveX (also includes HTML-to-PlainText conversion)

Download Chilkat HTTP ActiveX

uses
    Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
    Dialogs, StdCtrls,
    CHILKATXMLLib_TLB,
    HTMLTOXMLLib_TLB,
    CHILKATHTTPLib_TLB,
    OleCtrls;

...

procedure TForm1.Button1Click(Sender: TObject);
var
http: TChilkatHttp;
success: Integer;
html: String;
htmlToXml: THtmlToXml;
xml: CHILKATXMLLib_TLB.IChilkatXml;
formRoot: CHILKATXMLLib_TLB.IChilkatXml;
xmlTemp: CHILKATXMLLib_TLB.IChilkatXml;
xmlNode: CHILKATXMLLib_TLB.IChilkatXml;

begin
http := TChilkatHttp.Create(Self);

//  Any string unlocks the component for the 1st 30-days.
success := http.UnlockComponent('Anything for 30-day trial');
if (success <> 1) then
  begin
    ShowMessage(http.LastErrorText);

  end;

//  Send the HTTP GET and return the content in a string.

html := http.QuickGetStr('http://www.nature.com/register/');

//  Convert the HTML to XML for parsing...
htmlToXml := THtmlToXml.Create(Self);

//  Any string argument automatically begins the 30-day trial.
success := htmlToXml.UnlockComponent('30-day trial');
if (success <> 1) then
  begin
    ShowMessage('HtmlToXml component unlock failed');

  end;

//  Indicate the charset of the output XML we'll want.
//  The charset of the original HTML page can be anything.
//  Chilkat will convert and handle it properly...
htmlToXml.XmlCharset := 'utf-8';

//  Set the HTML:
htmlToXml.Html := html;

//  Convert and load into an XML object:
xml := TChilkatXml.Create(Self).ControlInterface;
xml.LoadXml(htmlToXml.ToXml());

success := xml.SaveXml('out.xml');
if (success <> 1) then
  begin
    ShowMessage(xml.LastErrorText);

  end;
//  Find the first form tag and navigate to it:

formRoot := xml.SearchForTag(nil,'form');

if (formRoot = nil ) then
  begin
    ShowMessage('No HTML form found!');

  end;

//  Show the form's name, method, and action:
Memo1.Lines.Add('Form Name: ' + formRoot.GetAttrValue('name'));
Memo1.Lines.Add('Form Method: ' + formRoot.GetAttrValue('method'));
Memo1.Lines.Add('Form Action: ' + formRoot.GetAttrValue('action'));
Memo1.Lines.Add('----');

//  Iterate over "input" tags within the form:

xmlNode := formRoot.SearchForTag(nil,'input');
while (not (xmlNode = nil )) do
  begin

    //  print the input field's name, type, and current value:
    //  an empty input type indicates the default "text" type
    Memo1.Lines.Add('Input Name: ' + xmlNode.GetAttrValue('name'));
    Memo1.Lines.Add('Input Type: ' + xmlNode.GetAttrValue('type'));
    Memo1.Lines.Add('Current Value: ' + xmlNode.GetAttrValue('value'));
    Memo1.Lines.Add('----');

    xmlTemp := xmlNode;
    xmlNode := formRoot.SearchForTag(xmlNode,'input');

  end;

//  Iterate over "select" tags within the form:
xmlNode := formRoot.SearchForTag(nil,'select');
while (not (xmlNode = nil )) do
  begin

    Memo1.Lines.Add('Select Name: ' + xmlNode.GetAttrValue('name'));

    xmlTemp := xmlNode;
    xmlNode := formRoot.SearchForTag(xmlNode,'select');

  end;

//  Iterate over "textarea" tags within the form:
xmlNode := formRoot.SearchForTag(nil,'textarea');
while (not (xmlNode = nil )) do
  begin

    Memo1.Lines.Add('TextArea Name: ' + xmlNode.GetAttrValue('name'));

    xmlTemp := xmlNode;
    xmlNode := formRoot.SearchForTag(xmlNode,'textarea');

  end;


end;