scriptotek / colligator-backend

use Symfony\Component\DomCrawler\Crawler;

class FluxScraper extends Scraper implements ScraperInterface

{

    public function recognizes($url)

    {

        return strpos($url, 'flux.no');

    }

    public function scrape(Crawler $crawler)

    {

        $texts = $crawler->filter('.productPageBody > p')->each(function (Crawler $node) {

            return $node->text();

        });

        $text = implode('\n\n', $texts);

        return $this->returnResult($text, 'Flux forlag');

    }

}

use Symfony\Component\DomCrawler\Crawler;

class LocScraper extends Scraper implements ScraperInterface

{

    public function recognizes($url)

    {

        return strpos($url, 'loc.gov');

    }

    public function scrape(Crawler $crawler)

    {

        $text = $crawler->filter('body')->first()->text();

        $texts = preg_split("/\r\n|\n\n/", $text);

        $text = $this->getLongestText($texts);

        return $this->returnResult($text, 'Library of Congress');

    }

}