public function testBuildPage() { $url = 'http://www.google.com/'; $client = new Client(array('url' => $url, 'data_config' => array('test' => '//h1[@id="test-heading"]'), 'builder' => new PageBuilderStub())); $page = $client->fetchPage(); $data = $page->getData(); $this->assertInstanceOf('PageScraper\\Page\\PageInterface', $page); $this->assertEquals($url, $page->getUrl()); $this->assertEquals('Testing H1', $data['test']); $this->assertInstanceOf('PageScraper\\Tests\\Stub\\PageBuilder', $client->getBuilder()); }
<?php libxml_use_internal_errors(true); include __DIR__ . '/../vendor/autoload.php'; use PageScraper\Client; // the most simpliest way to fetch the data is to use the Client $client = new Client(array('url' => 'https://news.ycombinator.com', 'data_config' => array('titles' => '//td[@class="title"]//a/text()', 'links' => '//td[@class="title"]//a/@href', 'side_links' => array('css' => '.title .comhead')))); // fetch the data, and get the Page object $page = $client->fetchPage(); // get the desired data $data = $page->getData(); // print the data echo '<pre>'; print_r($data); echo '</pre>';