fix(senscritique) (#3750)

bridges/SensCritiqueBridge.php

@@ -56,7 +56,8 @@ class SensCritiqueBridge extends BridgeAbstract
                         break;
                 }
                 $html = getSimpleHTMLDOM($uri);
-                $list = $html->find('ul.elpr-list', 0);
+                // This selector name looks like it's automatically generated
+                $list = $html->find('div.Universes__WrapperProducts-sc-1qa2w66-0.eVdcAv', 0);
 
                 $this->extractDataFromList($list);
             }
@@ -68,36 +69,13 @@ class SensCritiqueBridge extends BridgeAbstract
         if ($list === null) {
             returnClientError('Cannot extract data from list');
         }
-
-        foreach ($list->find('li') as $movie) {
+        foreach ($list->find('div[data-testid="product-list-item"]') as $movie) {
             $item = [];
-            $item['author'] = htmlspecialchars_decode($movie->find('.elco-title a', 0)->plaintext, ENT_QUOTES)
-            . ' '
-            . $movie->find('.elco-date', 0)->plaintext;
-
-            $item['title'] = $movie->find('.elco-title a', 0)->plaintext
-            . ' '
-            . $movie->find('.elco-date', 0)->plaintext;
-
-            $item['content'] = '';
-            $originalTitle = $movie->find('.elco-original-title', 0);
-            $description = $movie->find('.elco-description', 0);
-
-            if ($originalTitle) {
-                $item['content'] = '<em>' . $originalTitle->plaintext . '</em><br><br>';
-            }
-
-            $item['content'] .= $movie->find('.elco-baseline', 0)->plaintext
-            . '<br>'
-            . $movie->find('.elco-baseline', 1)->plaintext
-            . '<br><br>'
-            . ($description ? $description->plaintext : '')
-            . '<br><br>'
-            . trim($movie->find('.erra-ratings .erra-global', 0)->plaintext)
-            . ' / 10';
-
-            $item['id'] = $this->getURI() . ltrim($movie->find('.elco-title a', 0)->href, '/');
-            $item['uri'] = $this->getURI() . ltrim($movie->find('.elco-title a', 0)->href, '/');
+            $item['title'] = $movie->find('h2 a', 0)->plaintext;
+            // todo: fix image
+            $item['content'] = $movie->innertext;
+            $item['id'] = $this->getURI() . ltrim($movie->find('a', 0)->href, '/');
+            $item['uri'] = $this->getURI() . ltrim($movie->find('a', 0)->href, '/');
             $this->items[] = $item;
         }
     }

bridges/VkBridge.php

@@ -158,8 +158,8 @@ class VkBridge extends BridgeAbstract
                     $article_author_selector = 'div.article_snippet__author';
                     $article_thumb_selector = 'div.article_snippet__image';
                 }
-                $article_title = $article->find($article_title_selector, 0)->innertext;
-                $article_author = $article->find($article_author_selector, 0)->innertext;
+                $article_title = $article->find($article_title_selector, 0)->innertext ?? '';
+                $article_author = $article->find($article_author_selector, 0)->innertext ?? '';
                 $article_link = $article->getAttribute('href');
                 $article_img_element_style = $article->find($article_thumb_selector, 0)->getAttribute('style');
                 preg_match('/background-image: url\((.*)\)/', $article_img_element_style, $matches);

lib/FeedParser.php

@@ -2,6 +2,13 @@
 
 declare(strict_types=1);
 
+/**
+ * Very basic and naive feed parser that srapes out rss 0.91, 1.0, 2.0 and atom 1.0.
+ *
+ * Emit arrays meant to be used inside rss-bridge.
+ *
+ * The feed item structure is identical to that of FeedItem
+ */
 final class FeedParser
 {
     public function parseFeed(string $xmlString): array
@@ -200,6 +207,8 @@ final class FeedParser
             'content'       => null,
             'timestamp'     => null,
             'author'        => null,
+            'uid'           => null,
+            'categories'    => [],
             'enclosures'    => [],
         ];
         if (isset($feedItem->link)) {

lib/FormatAbstract.php

@@ -31,7 +31,10 @@ abstract class FormatAbstract
         $this->lastModified = $lastModified;
     }
 
-    public function setItems(array $items)
+    /**
+     * @param FeedItem[] $items
+     */
+    public function setItems(array $items): void
     {
         $this->items = $items;
     }

lib/url.php

@@ -7,7 +7,9 @@ final class UrlException extends \Exception
 }
 
 /**
- * Intentionally restrictive url parser
+ * Intentionally restrictive url parser.
+ *
+ * Only absolute http/https urls.
  */
 final class Url
 {
@@ -29,7 +31,7 @@ final class Url
 
         $parts = parse_url($url);
         if ($parts === false) {
-            throw new UrlException(sprintf('Invalid url %s', $url));
+            throw new UrlException(sprintf('Failed to parse_url(): %s', $url));
         }
 
         return (new self())
@@ -38,6 +40,7 @@ final class Url
             ->withPort($parts['port'] ?? 80)
             ->withPath($parts['path'] ?? '/')
             ->withQueryString($parts['query'] ?? null);
+            // todo: add fragment
     }
 
     public static function validate(string $url): bool