Skip to content

Instantly share code, notes, and snippets.

@niilante
Forked from andreaselia/ScrapeFunko.php
Created November 19, 2017 17:00
Show Gist options
  • Star 1 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save niilante/acd46cfb4e15dd3bdcdf63478d85c738 to your computer and use it in GitHub Desktop.
Save niilante/acd46cfb4e15dd3bdcdf63478d85c738 to your computer and use it in GitHub Desktop.
<?php
namespace App\Console\Commands;
use Illuminate\Console\Command;
class ScrapeFunko extends Command
{
/**
* The name and signature of the console command.
*
* @var string
*/
protected $signature = 'scrape:funko';
/**
* The console command description.
*
* @var string
*/
protected $description = 'Funko POP! Vinyl Scraper';
/**
* The list of funko collection slugs.
*
* @var array
*/
protected $collections = [
'animation',
'disney',
'games',
'heroes',
'marvel',
'monster-high',
'movies',
'pets',
'rocks',
'sports',
'star-wars',
'television',
'the-vault',
'the-vote',
'ufc',
];
/**
* Create a new command instance.
*
* @return void
*/
public function __construct()
{
parent::__construct();
}
/**
* Execute the console command.
*
* @return mixed
*/
public function handle()
{
foreach ($collections as $collection) {
$this->scrape($collection);
}
}
/**
* For scraping data for the specified collection.
*
* @param string $collection
* @return boolean
*/
public static function scrape($collection)
{
$crawler = Goutte::request('GET', env('FUNKO_POP_URL').'/'.$collection);
$pages = ($crawler->filter('footer .pagination li')->count() > 0)
? $crawler->filter('footer .pagination li:nth-last-child(2)')->text()
: 0
;
for ($i = 0; $i < $pages + 1; $i++) {
if ($i != 0) {
$crawler = Goutte::request('GET', env('FUNKO_POP_URL').'/'.$collection.'?page='.$i);
}
$crawler->filter('.product-item')->each(function ($node) {
$sku = explode('#', $node->filter('.product-sku')->text())[1];
$title = trim($node->filter('.title a')->text());
print_r($sku.', '.$title);
});
}
return true;
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment