registerXPathNamespace("dc", "http://purl.org/dc/elements/1.1/"); $rssHeaderContent = $rssContent->channel[0]; $this->debugMessage("RSS content is ===========\n".var_export($rssHeaderContent, true)."==========="); $this->load_RSS_2_0_feed_data($rssHeaderContent); foreach($rssContent->item as $item) { $this->debugMessage("parsing item ".var_export($item, true)); $this->items[] = $this->parseRSSItem($item); } } protected function parseRSSItem($newsItem) { $namespaces = $newsItem->getNameSpaces(true); $dc = $newsItem->children($namespaces['dc']); $rdf = $newsItem->children($namespaces['rdf']); $item = array(); $item['title'] = trim($newsItem->title); $this->debugMessage("browsing Oatmeal item ".var_export($newsItem, true)); $item['uri']=(string) $newsItem->attributes($namespaces['rdf'])->about; // now load that uri from cache $this->debugMessage("now loading page ".$item['uri']); $articlePage = str_get_html($this->get_cached($item['uri'])); $content = $articlePage->find('#comic', 0); if($content==null) { $content = $articlePage->find('#blog'); } $item['content'] = $content->innertext; $this->debugMessage("dc content is ".var_export($dc, true)); $item['author'] = (string) $dc->creator; $item['timestamp'] = DateTime::createFromFormat(DateTime::ISO8601, $dc->date)->getTimestamp(); $this->debugMessage("writtem by ".$item['author']." on ".$item['timestamp']); return $item; } public function getCacheDuration(){ return 7200; // 2h hours } }