/**
* This helper function can be used to get a valid uri from an url and return it.
*
* @param string $url
*
* @return mixed
*/
function getUri($url)
{
if (!empty($url)) {
// Sanitize URL first by removing unwanted chars
$url = preg_replace("/[\n\r]/", '', $url);
// Sanitize URL accourding to RFC1738 (perhaps use RFC3986?)
$entities = [' '];
$replacements = ['%20'];
$url = str_replace($entities, $replacements, $url);
// Check weither the domain is actually valid
if (getDomain($url) == false) {
return false;
}
$pslManager = new Pdp\PublicSuffixListManager();
$urlParser = new Pdp\Parser($pslManager->getList());
$urlData = $urlParser->parseUrl($url)->toArray();
$path = $urlData['path'] . (!empty($urlData['query']) ? '?' . $urlData['query'] : '');
// Set the path to root if empty (default)
if (empty($path)) {
$path = '/';
}
// Sanitize PATH accourding to RFC1738 (perhaps use RFC3986?)
$entities = [' '];
$replacements = ['%20'];
$path = str_replace($entities, $replacements, $path);
return $path;
} else {
return false;
}
}
/**
* This helper function can be used to get a valid domain.tld from an url and return it.
*
* @param string $url
*
* @return mixed
*/
function getDomain($url)
{
if (!empty($url)) {
// Sanitize URL first by removing unwanted chars
$url = preg_replace("/[\n\r]/", '', $url);
// Sanitize URL accourding to RFC1738 (perhaps use RFC3986?)
$entities = [' '];
$replacements = ['%20'];
$url = str_replace($entities, $replacements, $url);
// Check weither the URL is actually valid
if (!filter_var($url, FILTER_VALIDATE_URL) === true) {
return false;
}
$pslManager = new Pdp\PublicSuffixListManager();
$urlParser = new Pdp\Parser($pslManager->getList());
$urlData = $urlParser->parseUrl($url)->toArray();
if ($urlParser->isSuffixValid($urlData['registerableDomain']) === false) {
// Not a valid domain.
return false;
} else {
// Return valid domain
return $urlData['registerableDomain'];
}
} else {
return false;
}
}
/**
* This helper function can be used to get the url data.
*
* @param $url
*
* @return mixed
*
* @internal param string $str
*/
function getUrlData($url)
{
if (!empty($url)) {
$pslManager = new Pdp\PublicSuffixListManager();
$urlParser = new Pdp\Parser($pslManager->getList());
$urlData = $urlParser->parseUrl($url)->toArray();
return $urlData;
}
}
/**
* getBaseDomain
*
* Get domain name from a URL. This will check that the domain is valid for registering,
* preventing return of constructs like 'co.uk' as the domain. See https://publicsuffix.org/
*
* @param string $url URL
* @param boolean $includeSubdomain true to include include subdomains,
* default is false registerable domain only
* @param boolean $returnObject true to return Pdp\Uri\Url\Host object
* false returns domain as string
*
* @return Pdp\Uri\Url\Host|string|null domain, or null if domain is invalid
*/
public function getBaseDomain($url, $includeSubdomain = false, $returnObject = false)
{
$pslManager = new \Pdp\PublicSuffixListManager();
$parser = new \Pdp\Parser($pslManager->getList());
$url = mb_strtolower($url, 'UTF-8');
try {
// use php-domain-parser to give us just the domain
$pdp = $parser->parseUrl($url);
$host = $pdp->host->host;
} catch (\Exception $e) {
$this->events()->triggerEvent('core.exception', $e);
return null;
}
// check for exceptions, localhost and ip address (v4 & v6)
if (!empty($host)) {
// localhost exception
if ($host === 'localhost') {
return $returnObject ? $pdp->host : $host;
}
// Check for IPV6 URL (see http://www.ietf.org/rfc/rfc2732.txt)
// strip brackets before validating
if (substr($host, 0, 1) === '[' && substr($host, -1) === ']') {
$host = substr($host, 1, strlen($host) - 2);
}
// ip address exception
if (filter_var($host, FILTER_VALIDATE_IP)) {
return $returnObject ? new \Pdp\Uri\Url\Host(null, null, null, $host) : $host;
}
}
$host = $pdp->host->registerableDomain;
if (!empty($host) && $includeSubdomain) {
$host = $pdp->host->host;
}
return $returnObject ? $pdp->host : $host;
}
<p>Cette page permet de parser des urls et de ne ressortir que le nom de domaine !</p>
</div>
<?php
if (isset($_POST['urls'])) {
echo '<div class="row">';
echo '<div class="col-sm-12">';
echo '<p>Voilà les domaines extraits : </p>';
echo "<pre>";
$urls = explode("\n", $_POST['urls']);
foreach ($urls as $urlc) {
$urlc = trim($urlc);
if ($urlc == '') {
continue;
}
$pslManager = new Pdp\PublicSuffixListManager();
$parser = new Pdp\Parser($pslManager->getList());
$host = $urlc;
$url = $parser->parseUrl($host);
$newdomain = $url->host->registerableDomain;
echo $newdomain . "<br />";
}
echo "</pre>";
echo "</div>";
echo "</div>";
}
?>
{!! Form::open(array('url' => '/urlparse')) !!}
<div class="form-group">
{!! Form::textarea('urls', '', array('class' => 'form-control')) !!}
<br />
{!! Form::submit('Send') !!}
