tor-spider/example.php

<?php
/**
 * Created by PhpStorm.
 * User: eric
 * Date: 12/23/16
 * Time: 4:19 PM
 */

require __DIR__ . '/vendor/autoload.php';
/*
if(false === is_dir(__DIR__ . '/images'))
{
    mkdir(__DIR__ . '/images');
}
*/

$client = new \Sikofitt\Tor\TorClient();

$resource = \GuzzleHttp\Psr7\StreamWrapper::getResource(new \GuzzleHttp\Psr7\Stream(fopen('http://4sy6ebszykvcv2n6.onion/', 'rb')));

/*$client->get('http://32b5oz2bbtn6gqj3.onion/index.php/Main_Page');

$images = $client->images();
$iterator = $images->getIterator();
while($iterator->valid()) {
    /*
     * $iterator->current(); is an array of
     * $result['fqd'] fully qualified domain uri - example.onion/path/filename.image
     * $result['src'] = the image src element, could be fqd or just /path/filename.image
     * $result['raw'] = the raw image data
     * $result['base64'] = base64 encoded raw data - file_put_contents(base64_decode(base64), file.image);
     * $result['html'] = the html of the page the image was retrieved from.
     */
  /*  foreach($iterator->current() as $key => $value)
    {
        file_put_contents(__DIR__ . '/images/' .
            pathinfo($value['src'], PATHINFO_FILENAME) . '.' .
            pathinfo($value['src'], PATHINFO_EXTENSION),
            $value['raw']);
    }
        $iterator->next();
}

*/

/*$client->get('http://4sy6ebszykvcv2n6.onion/');
$images = $client->images();
$html = $client->getHtml();
dump($html);
*/
//dump($resource);


    $j = stream_get_contents($resource);


fclose($resource);
dump($j);



/*
$iterator = $images->getIterator();
while($iterator->valid()) {
    foreach($iterator->current() as $key => $value)
    {
        file_put_contents(__DIR__ . '/images/' .
            pathinfo($value['src'], PATHINFO_FILENAME) . '.' .
            pathinfo($value['src'], PATHINFO_EXTENSION),
            $value['raw']);
    }
    $iterator->next();
}

$testArray = [
    'fqd' => null,
    'src' => null,
    'alt' => null,
    'base64' => null,
    'html' => null
];
$image = new \Sikofitt\Element\Image('https://www.google.com/file/robots.txt', $testArray);
dump($image);
//$images = $client->images();
//dump($images);
//$client->get('https://de.indymedia.org/index.shtml');
//foreach($images as $image) {
    //$image = new \Doctrine\Common\Collections\ArrayCollection();

  //  dump($image);
//}
//dump($result);

*/