added article categories for GolemBridge (#3377)

* added article categories for GolemBridge

* tabs are bad, spaces good

* fixed duplicate categories on multi-page articles
This commit is contained in:
Tone 2023-05-08 16:21:03 +02:00 committed by GitHub
parent ec091fb747
commit a1b6bca581
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 0 deletions

View File

@ -88,6 +88,14 @@ class GolemBridge extends FeedExpander
$item['author'] = $author->plaintext;
}
$categories = $articlePage->find('ul.tags__list li');
foreach ($categories as $category) {
$trimmedcategories[] = trim(html_entity_decode($category->plaintext));
}
if (isset($trimmedcategories)) {
$item['categories'] = array_unique($trimmedcategories);
}
$item['content'] .= $this->extractContent($articlePage);
// next page