refactor: FeedExpander::parseItem() descendants (#3744)

This commit is contained in:
Dag 2023-10-13 00:25:34 +02:00 committed by GitHub
parent 9bda9e246a
commit 382648fc22
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
46 changed files with 314 additions and 281 deletions

View file

@ -52,18 +52,15 @@ class TheGuardianBridge extends FeedExpander
public function collectData()
{
$feed = $this->getInput('feed');
$feedURL = 'https://feeds.theguardian.com/theguardian/' . $feed;
$this->collectExpandableDatas($feedURL, 10);
$url = 'https://feeds.theguardian.com/theguardian/' . $feed;
$this->collectExpandableDatas($url, 10);
}
protected function parseItem($newsItem)
protected function parseItem($item)
{
$item = parent::parseItem($newsItem);
$item = parent::parseItem($item);
// --- Recovering the article ---
// $articlePage gets the entire page's contents
$articlePage = getSimpleHTMLDOM($newsItem->link);
$articlePage = getSimpleHTMLDOM($item['uri']);
// figure contain's the main article image
$article = $articlePage->find('figure', 0);
// content__article-body has the actual article