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

<?php

$http = new COM("Chilkat.Http");

//  Any string unlocks the component for the 1st 30-days.
$success = $http->UnlockComponent('Anything for 30-day trial');
if ($success != true) {
    print $http->lastErrorText() . "\n";
    exit;
}

//  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 = new COM("Chilkat.HtmlToXml");

//  Any string argument automatically begins the 30-day trial.
$success = $htmlToXml->UnlockComponent('30-day trial');
if ($success != true) {
    print 'HtmlToXml component unlock failed' . "\n";
    exit;
}

//  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 = new COM("Chilkat.Xml");
$xml->LoadXml($htmlToXml->toXml());

$success = $xml->SaveXml('out.xml');
if ($success != true) {
    print $xml->lastErrorText() . "\n";
    exit;
}

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

$formRoot = $xml->SearchForTag(null,'form');

if (is_null($formRoot)) {
    print 'No HTML form found!' . "\n";
    exit;
}

//  Show the form's name, method, and action:
print 'Form Name: ' . $formRoot->getAttrValue('name') . "\n";
print 'Form Method: ' . $formRoot->getAttrValue('method') . "\n";
print 'Form Action: ' . $formRoot->getAttrValue('action') . "\n";
print '----' . "\n";

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

$xmlNode = $formRoot->SearchForTag(null,'input');
while ((!(is_null($xmlNode)))) {

    //  print the input field's name, type, and current value:
    //  an empty input type indicates the default "text" type
    print 'Input Name: ' . $xmlNode->getAttrValue('name') . "\n";
    print 'Input Type: ' . $xmlNode->getAttrValue('type') . "\n";
    print 'Current Value: ' . $xmlNode->getAttrValue('value') . "\n";
    print '----' . "\n";

    $xmlTemp = $xmlNode;
    $xmlNode = $formRoot->SearchForTag($xmlNode,'input');

}

//  Iterate over "select" tags within the form:
$xmlNode = $formRoot->SearchForTag(null,'select');
while ((!(is_null($xmlNode)))) {

    print 'Select Name: ' . $xmlNode->getAttrValue('name') . "\n";

    $xmlTemp = $xmlNode;
    $xmlNode = $formRoot->SearchForTag($xmlNode,'select');

}

//  Iterate over "textarea" tags within the form:
$xmlNode = $formRoot->SearchForTag(null,'textarea');
while ((!(is_null($xmlNode)))) {

    print 'TextArea Name: ' . $xmlNode->getAttrValue('name') . "\n";

    $xmlTemp = $xmlNode;
    $xmlNode = $formRoot->SearchForTag($xmlNode,'textarea');

}


?>