array( 'name'=>'Novel URL', 'patterns'=>'http:\/\/www.novelupdates.com\/.*', 'required'=>true ) )); private $seriesTitle=''; public function collectData(){ $thread = parse_url($this->getInput('n')) or $this->returnClientError('This URL seems malformed, please check it.'); if($thread['host'] !== 'www.novelupdates.com') $this->returnClientError('NovelUpdates URL only.'); if(strpos($thread['path'], 'series/') === FALSE) $this->returnClientError('You must specify the novel URL.'); $url = $this->uri.$thread['path'].''; $fullhtml = $this->getSimpleHTMLDOM($url) or $this->returnServerError("Could not request NovelUpdates, novel not found"); $this->seriesTitle = $fullhtml->find('h4.seriestitle', 0)->plaintext; // dirty fix for nasty simpledom bug: https://github.com/sebsauvage/rss-bridge/issues/259 // forcefully removes tbody $html = $fullhtml->find('table#myTable', 0)->innertext; $html = stristr($html, ''); //strip thead $html = stristr($html, ''); //remove tbody $html = str_get_html(stristr($html, '', true)); //remove last tbody and get back as an array foreach($html->find('tr') as $element){ $item = array(); $item['uri'] = $element->find('td', 2)->find('a', 0)->href; $item['title'] = $element->find('td', 2)->find('a', 0)->plaintext; $item['team'] = $element->find('td', 1)->innertext; $item['timestamp'] = strtotime($element->find('td', 0)->plaintext); $item['content'] = ''.$this->seriesTitle.' - '.$item['title'].' by '.$item['team'].'
'.$fullhtml->find('div.seriesimg', 0)->innertext.''; $this->items[] = $item; } } public function getName(){ return (!empty($this->seriesTitle) ? $this->seriesTitle.' - ' : '') .'Novel Updates'; } public function getCacheDuration(){ return 21600; // 6 hours } }