/** * Get all snippets for a given Yahoo SERP page. * @param SimpleHtmlDom $SHDObject * @return array */ protected function getPageSnippets($SHDObject) { $snippets = array(); foreach ($SHDObject->find('.aAbs') as $object) { $snippetText = $this->cleanText($object->innertext); $snippets[] = $this->fixRepeatedSpace($snippetText); } // fetch only organic results return $this->normalizeResult($snippets); }
/** * Get all snippets for a given Bing SERP. * @param SimpleHtmlDom $SHDObject * @return array */ protected function getPageSnippets($SHDObject) { $snippets = array(); // snippets in Bing's SERP are embedded into a <p> element child of b_caption foreach ($SHDObject->find('.b_caption p') as $object) { $snippetText = $this->cleanText($object->innertext); $snippets[] = $this->fixRepeatedSpace($snippetText); } // fetch only organic results return $this->normalizeResult($snippets); }
/** * Get all snippets for a given Google SERP. * @param SimpleHtmlDom $SHDObject * @return array */ protected function getPageSnippets($SHDObject) { $snippets = array(); // snippets in Google's SERP are embedded into a <span> element with class "st" foreach ($SHDObject->find('.st') as $object) { $snippetText = $this->cleanText($object->innertext); $snippets[] = $this->fixRepeatedSpace($snippetText); } // fetch only organic results return $this->normalizeResult($snippets); }
public function set() { $data = file_get_contents('http://www.kongregate.com/contests?haref=hp_devcontest'); $dom = new SimpleHtmlDom(); $dom->load($data); $tables = []; $temp = []; foreach ($dom->find('table.contests') as $element) { foreach ($element->find('tr.js-game-hover') as $tr) { $temp[] = trim($tr->plaintext); } $tables[] = $temp; $temp = ''; } $this->_DB->query('INSERT INTO contests (data, snap_date) VALUES (:data, :snap_date)'); $this->_DB->bind(['data' => json_encode($tables), 'snap_date' => date('Y-m-d H:i:s')]); $this->_DB->execute(); return $tables; }
public function pasteListAction() { $html = Redokes_Controller_Front::getInstance()->getParam('html', ''); $parentId = intval(Redokes_Controller_Front::getInstance()->getParam('parentId', 0)); $trackId = intval(Redokes_Controller_Front::getInstance()->getParam('trackId', 0)); if ($trackId) { // check what kind of content was sent if (preg_match('/<ul|<ol/i', $html)) { // html list // convert any ol to ul $html = str_replace('<ol', '<ul', $html); $html = str_replace('</ol', '</ul', $html); // load up the html into a dom object $dom = new SimpleHtmlDom($html); $ul = $dom->find('>ul', 0); $this->makeFromUl($ul, $trackId, $parentId); } else if (preg_match('/[\n\r]/', $html)) { // multi line $this->makeFromNewLines($html, $trackId, $parentId); } else { // assume single line $this->makeFromNewLines($html, $trackId, $parentId); } return; $track = new Navigation_Model_Track($trackId); $track->clearCache(); } }