Created
October 1, 2015 14:52
-
-
Save karrikas/011a7a108d86dd026715 to your computer and use it in GitHub Desktop.
Find url from entire website
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
class urlfinder { | |
var $urls = array(); | |
var $visited = array(); | |
var $domain; | |
public function get ($url, $domain = '') { | |
if (in_array($url, $this->visited)) { | |
return; | |
} | |
$this->visited[] = $url; | |
if (!empty($domain)) { | |
$this->domain = $domain; | |
} | |
$doc = file_get_contents($url); | |
if (!preg_match_all('/<a [^>]*href=["|\']+([^"]+)["|\']+/', $doc, $res)) { | |
return; | |
} | |
foreach ($res[1] as $url) { | |
if (!preg_match('/^http[s]*:\/\//', $url)) { | |
$url = $this->domain . $url; | |
} | |
$subdomain = str_replace(array('http://', 'https://'), '', $this->domain); | |
if (preg_match('/^http[s]*:\/\/' . $subdomain . '/', $url)) { | |
$this->addUrl($url); | |
$this->get($url); | |
} | |
} | |
return $this->urls; | |
} | |
private function addUrl($url) { | |
foreach ($this->urls as $id => $values) { | |
if ($values['url'] == $url) { | |
$this->urls[$id]['count'] = $values['count'] + 1; | |
return; | |
} | |
} | |
$this->urls[] = array( | |
'url' => $url, | |
'count' => 1, | |
); | |
return; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment