function loadArticlesFromUrl($strNewsPageAbsoluteUrl, $max_articles_to_load = 10)
{
//fetch first page on ngb news
$html = file_get_html($strNewsPageAbsoluteUrl);
//list of all articles found on this page
$lstArticles = array();
$numArticles = 0;
// Find all news threads on first page
$threadInfoSelector = "ol#threads .threadbit";
//dom selector for basic thread infos
foreach ($html->find($threadInfoSelector) as $element) {
//check if this is a MOVED article and ignore it
if (strpos($element->class, "moved") !== FALSE) {
//skip this article, cause it was moved somewhere
continue;
}
//maximum number of articles to load each run
if ($numArticles >= $max_articles_to_load) {
break;
}
//get url to article
$strUrl = $element->find(".threadtitle .title")[0]->href;
//relative url here
$strUrl = 'https://ngb.to/' . $strUrl;
//absolute url now
//remove the session id from the url s=xxxxxx0000x0x0x00
$strUrl = preg_replace('/s=[a-zA-Z0-9]+/', '', $strUrl);
//create new news entry object
$objNews = new NewsEntry();
//try to load article details from this url
if ($objNews->loadFromUrl($strUrl) == TRUE) {
//remember date of last update/reply. we gotta fetch
//this here, not inside of loadFromUrl. other approach would have to go throug all pages to find last post date.
$strUpdated = $element->find(".threadlastpost dd")[1]->plaintext;
$objNews->setLastUpdateDate($strUpdated);
//get url to last comment on this article
$strLastPostUrl = $element->find(".threadlastpost a.lastpostdate")[0]->href;
//remove session id from last post url
$strLastPostUrl = preg_replace('/s=[a-zA-Z0-9]+/', '', $strLastPostUrl);
$objNews->setLastCommentUrl($strLastPostUrl);
$strLastCommentName = $element->find(".threadlastpost a.username strong")[0]->plaintext;
$strLastCommentUrl = $element->find(".threadlastpost a.username")[0]->href;
//remove session id from comment url
$strLastCommentUrl = preg_replace('/s=[a-zA-Z0-9]+/', '', $strLastCommentUrl);
//set author of the last comment. name and url to profile
$objNews->setLastCommentAuthor($strLastCommentName, $strLastCommentUrl);
//get number of comments
$strNumComments = $element->find("ul.threadstats a.understate")[0]->plaintext;
$objNews->setNumberOfComments($strNumComments);
//save the object to our list of articles.
$lstArticles[] = $objNews;
$numArticles++;
}
}
//eof foreach
//returns list of all articles fetched from the url passed to this function
return $lstArticles;
}
/**
* @see DatabaseObject::handleData()
*/
protected function handleData($data)
{
parent::handleData($data);
$this->user = new BASHUser($this->authorID);
}
