From 0de2db853f139e6f7c11dcd4cf402e72660d20ef Mon Sep 17 00:00:00 2001
From: Corentin Garcia <corenting@gmail.com>
Date: Wed, 30 Jun 2021 12:14:25 +0200
Subject: [PATCH] [NYTBridge] Fix article parsing (#2106)

Co-authored-by: podiki <podiki@users.noreply.github.com>
---
 bridges/NYTBridge.php | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/bridges/NYTBridge.php b/bridges/NYTBridge.php
index 687d0889..15fded3a 100644
--- a/bridges/NYTBridge.php
+++ b/bridges/NYTBridge.php
@@ -4,22 +4,33 @@ class NYTBridge extends FeedExpander {
 	const MAINTAINER = 'IceWreck';
 	const NAME = 'New York Times Bridge';
 	const URI = 'https://www.nytimes.com/';
-	const CACHE_TIMEOUT = 3600;
+	const CACHE_TIMEOUT = 900; // 15 minutes
 	const DESCRIPTION = 'RSS feed for the New York Times';
 
 	public function collectData(){
-		$this->collectExpandableDatas('https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml', 15);
+		$this->collectExpandableDatas('https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml', 40);
 	}
 
 	protected function parseItem($newsItem){
 		$item = parent::parseItem($newsItem);
+		$article = '';
+
 		// $articlePage gets the entire page's contents
 		$articlePage = getSimpleHTMLDOM($newsItem->link);
+
+		// handle subtitle
+		$subtitle = $articlePage->find('p.css-w6ymp8', 0);
+		if ($subtitle != null) {
+			$article .= '<strong>' . $subtitle->plaintext . '</strong>';
+		}
+
 		// figure contain's the main article image
-		$article = $articlePage->find('figure', 0);
-		// p > css-exrw3m has the actual article
-		foreach($articlePage->find('p.css-exrw3m') as $element)
-			$article = $article . $element;
+		$article .= $articlePage->find('figure', 0) . '<br />';
+
+		// section.meteredContent has the actual article
+		foreach($articlePage->find('section.meteredContent p') as $element)
+			$article .= '' . $element . '';
+
 		$item['content'] = $article;
 		return $item;
 	}