public static function getFeedStructureFromXML($oRssFeed, $sXMLString, $sStopAt)
{
// called when parsing rss feeds, tries to convert a mixed xml string into a structured object
$oParsedFeed = self::oXMLStringToFeedObject($sXMLString);
// go through each feed item and save into our system
foreach ($oParsedFeed->aoItems as $oDataOnlyFeedItem) {
$oFeedItem = new FeedItem();
$oFeedItem->title = $oDataOnlyFeedItem->title;
$oFeedItem->url = $oDataOnlyFeedItem->url;
$oFeedItem->guid = $oDataOnlyFeedItem->guid;
$oFeedItem->pubDate = $oDataOnlyFeedItem->pubDate;
$oFeedItem->feed_id = $oRssFeed->id;
/*
if ($oParsedFeed->bPic) {
$oFeedItem->thumb = $oDataOnlyFeedItem->thumb;
}
*/
$oFeedItem->save();
// schedule crunching our scraping thumb..
if (!$oParsedFeed->bPic) {
// schedule for image scrape
Feeds::scheduleFeedItemImageScrape($oFeedItem->id);
} else {
// we have a thumbnail but need to make sure it's the correct size
Feeds::scheduleThumbCrunch($oFeedItem->sPicURL, $oFeedItem->id);
}
$oFeedItem->save();
}
return $oParsedFeed;
}
public static function scrapeThumbFromFeedItem($iFeedItemId)
{
try {
$oFeedItem = FeedItem::find($iFeedItemId);
$sUrlToHit = $oFeedItem->url;
////echo "scrape: ", $sUrlToHit, "<br/>";
$page_content = @file_get_contents($sUrlToHit);
if (!empty($page_content)) {
$dom_obj = new DOMDocument();
libxml_use_internal_errors(true);
$dom_obj->loadHTML($page_content);
$meta_val = null;
foreach ($dom_obj->getElementsByTagName('meta') as $meta) {
if ($meta->getAttribute('property') == 'og:image') {
$meta_val = $meta->getAttribute('content');
break;
}
}
if (isset($meta_val)) {
self::storeThumbForFeedItem($oFeedItem, $meta_val);
} else {
$oFeedItem->thumb = '';
$oFeedItem->save();
}
}
} catch (Exception $e) {
}
}
