From 0e8112b9e8e8b9d278be78c24fe9b339a6cdf616 Mon Sep 17 00:00:00 2001
From: ORelio <ORelio@users.noreply.github.com>
Date: Fri, 29 Oct 2021 17:26:58 +0200
Subject: [PATCH] [DarkReading] Fix content extraction

Add article limit (main feed was broken due to too many articles)
Fix content extraction (html selector update)
Add support for article thumbnail
---
 bridges/DarkReadingBridge.php | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/bridges/DarkReadingBridge.php b/bridges/DarkReadingBridge.php
index 6ab83e9c8b3..da5fa4c764b 100644
--- a/bridges/DarkReadingBridge.php
+++ b/bridges/DarkReadingBridge.php
@@ -48,22 +48,25 @@ public function collectData(){
 		if ($feed_id != '000') {
 			$feed_url .= '?f_n=' . $feed_id . '&f_ln=' . $feed_name;
 		}
-		$this->collectExpandableDatas($feed_url);
+		$this->collectExpandableDatas($feed_url, 20);
 	}
 
 	protected function parseItem($newsItem){
 		$item = parent::parseItem($newsItem);
-		if (empty($item['content']))
-			return null; //ignore dummy articles
 		$article = getSimpleHTMLDOMCached($item['uri'])
 			or returnServerError('Could not request Dark Reading: ' . $item['uri']);
 		$item['content'] = $this->extractArticleContent($article);
 		$item['enclosures'] = array(); //remove author profile picture
+		$image = $article->find('meta[property="og:image"]', 0);
+		if (is_object($image)) {
+			$image = $image->content;
+			$item['enclosures'] = array($image);
+		}
 		return $item;
 	}
 
 	private function extractArticleContent($article){
-		$content = $article->find('div#article-main', 0)->innertext;
+		$content = $article->find('div.article-content', 0)->innertext;
 
 		foreach (array(
 			'<div class="divsplitter',
@@ -74,8 +77,6 @@ private function extractArticleContent($article){
 			$content = stripRecursiveHTMLSection($content, 'div', $div_start);
 		}
 
-		$content = stripWithDelimiters($content, '<h1 ', '</h1>');
-
 		return $content;
 	}
 }