PHP code example of rafaelglikis / sinama

1. Go to this page and download the library: Download rafaelglikis/sinama 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/ */

rafaelglikis / sinama example snippets


use  Sinama\Client;
$client = new Client();


// Go to the motherfuckingwebsite.com website
$crawler = $client->request('GET', 'https://motherfuckingwebsite.com/');


use  Sinama\Client;
use GuzzleHttp\Client as GuzzleClient;

$client = new Client(new GuzzleClient([
    'timeout' => 60
]));
$crawler = $client->request('GET', 'https://github.com/trending');


$link = $crawler->selectLink('PHP')->link();
$crawler = $client->click($link);
echo $crawler->getUri()."\n";


$crawler->filter('h3 > a')->each(function ($node) {
    print trim($node->text())."\n";
});


$crawler = $client->request('GET', 'https://github.com/trending');
echo '<html>';
echo '<head>';
echo '<title>'.$crawler->findTitle().'</title>';
echo '<head>';
echo '<body>';
echo '<h1>'.$crawler->findTitle().'</h1>';
echo '<p>Main Image: '.$crawler->findMainImage().'</p>';
echo $crawler->findMainContent();
echo '<pre>';
echo 'Links: ';
print_r($crawler->findLinks());
echo 'Emails: ';
print_r($crawler->findEmails());
echo 'Images: ';
print_r($crawler->findImages());
echo '</pre>';
echo '</body>';
echo '</html>';


$crawler = $client->request('GET', 'https://www.google.com/');
$form = $crawler->selectButton('Google Search')->form();
$crawler = $client->submit($form, ['q' => 'rafaelglikis/sinama']);
$crawler->filter('h3 > a')->each(function ($node) {
    print trim($node->text())."\n";
});


use Sinama\Crawler;
use Sinama\Spider as BaseSpider;

class Spider extends BaseSpider
{
    public function parse(Crawler $crawler)
    {
        $crawler->filter('div.read-more > a')->each(function (Crawler $node) {
            $this->scrape($node->attr('href'));
        });

        $crawler->filter('div.blog-pagination > a')->each(function ($node) {
            $this->follow($node->attr('href'));
        });
    }

    public function scrape($url)
    {
        echo "*************************************************** ".$url."\n";
        $crawler = $this->client->request('GET', $url);
        echo "Title: " . $crawler->findTitle() . "\n";
        echo "Main Image: " . $crawler->findMainImage()."\n";
        echo "Main Content: \n" . $crawler->findMainContent()."\n";
        echo "Emails: \n";
        print_r($crawler->findEmails());
        echo "Links: \n";
        print_r($crawler->findLinks());
    }

    public function getStartUrls(): array
    {
        return [
            'https://blog.scrapinghub.com'
        ];
    }
}

$spider = new Spider([
    'start_urls' => [ 'https://blog.scrapinghub.com' ],
    'max_depth' => 2,
    'verbose' => true
]);
$spider->run();