1. Go to this page and download the library: Download slote/spider library. Choose the download type require.
2. Extract the ZIP file and open the index.php.
3. Add this code to the index.php.
<?php
require_once('vendor/autoload.php');
/* Start to develop here. Best regards https://php-download.com/ */
slote / spider example snippets
// ./index.php
r\Entity\Config;
use Mediashare\Spider\Entity\Url;
use Mediashare\Spider\Spider;
// Website Config
$config = new Config();
$config->setWebspider(true); // Crawl all website
$config->setPathRequires(['/Kernel/']); // Not crawl other path
$config->setPathExceptions(['/CodeSnippet/']); // Not crawl this path
// Modules
$config->setReportsDir(__DIR__.'/reports/'); // Reports path
$config->setModulesDir(__DIR__.'/modules/'); // Modules path
$config->enableDefaultModule(true); // Enable default SEO kernel modules
$config->removeModule('FileDownload'); // Disable Module
// Prompt Console / Dump
$config->setVerbose(true); // Prompt verbose output
$config->setJson(false); // Prompt json output
// Url
$url = new Url('https://mediashare.fr');
// Run Spider
$spider = new Spider($url, $config);
$result = $spider->run();
// ./modules/Href.php
namespace Mediashare\Modules;
class Href {
public $dom;
public function run() {
$links = [];
foreach($this->dom->filter('a') as $link) {
if (!empty($link)) {
$href = rtrim(ltrim($link->getAttribute('href')));
if ($href) {
if (isset($links[$href])) {
$links[$href]['counter']++;
} else {
$links[$href]['counter'] = 1;
}
}
}
}
return $links;
}
}
Loading please wait ...
Before you can download the PHP files, the dependencies should be resolved. This can take some minutes. Please be patient.