From 212c56fde580887d84f0030a0910f4d884ffd1fe Mon Sep 17 00:00:00 2001
From: Paul Prechtel <Mynacol@users.noreply.github.com>
Date: Thu, 20 Apr 2023 23:02:08 +0200
Subject: [PATCH] [HeiseBridge] Handle heise+ articles better (#3358)

- Stop parsing paywalled heise+ articles, as they had garbage content
  and anyways not the full article.
- Link to archive.today to access the full article without account.
  (Automatically getting the full article from archive.ph was not feasible
  b/c of captchas and problems extracting the actual content)
---
 bridges/HeiseBridge.php | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/bridges/HeiseBridge.php b/bridges/HeiseBridge.php
index d89710f9..0e57ee85 100644
--- a/bridges/HeiseBridge.php
+++ b/bridges/HeiseBridge.php
@@ -118,12 +118,22 @@ class HeiseBridge extends FeedExpander
     protected function parseItem($feedItem)
     {
         $item = parent::parseItem($feedItem);
-        $item['uri'] = explode('?', $item['uri'])[0] . '?seite=all';
 
+        // strip rss parameter
+        $item['uri'] = explode('?', $item['uri'])[0];
+
+        // ignore TechStage articles
         if (strpos($item['uri'], 'https://www.heise.de') !== 0) {
             return $item;
         }
 
+        // abort on heise+ articles and link to archive.ph for full-text content
+        if (str_starts_with($item['title'], 'heise+ |')) {
+            $item['uri'] = 'https://archive.ph/?run=1&url=' . urlencode($item['uri']);
+            return $item;
+        }
+
+        $item['uri'] .= '?seite=all';
         $article = getSimpleHTMLDOMCached($item['uri']);
 
         if ($article) {