public function testScraping()
{
$this->assertFileExists($this->htmlPage);
$html = file_get_contents($this->htmlPage);
// Crawler need root url, however the initial page is loaded from $htmlPage variable
$this->crawler = new Crawler('', 'http://hiring-tests.s3-website-eu-west-1.amazonaws.com');
// Load html
$this->crawler->addHtmlContent($html);
$client = new \Goutte\Client();
$scraper = new \App\Scraper($client);
$scraper->setXpath('.product');
// Set crawler directly
$scraper->setCrawler($this->crawler);
// Page is null as we bypass this by setting the crawler on the above line
$results = $scraper->scrapePage("");
$this->assertEquals(json_encode($this->_getExpectedResults()), json_encode($results));
}
<?php
namespace App;
require "../vendor/autoload.php";
$page = 'http://hiring-tests.s3-website-eu-west-1.amazonaws.com/2015_Developer_Scrape/5_products.html';
$client = new \Goutte\Client();
$scraper = new \App\Scraper($client);
$scraper->setXpath('.product');
print_r(json_encode($scraper->scrapePage($page), JSON_PRETTY_PRINT));
print "\n";
