fix(FeedParser): scrape out content from rss content:encoded (#4178)

* fix(FeedParser): parse content module from rss2 * refactor
RSS-Bridge · Jul 31, 2024 · b8a9f34 · b8a9f34
1 parent e55e9b8
commit b8a9f34
Show file tree

Hide file tree

Showing 5 changed files with 39 additions and 20 deletions.
diff --git a/README.md b/README.md
@@ -418,7 +418,16 @@ See `formats/PlaintextFormat.php` for an example.
 
 These commands require that you have installed the dev dependencies in `composer.json`.
 
+Run all tests:
+
     ./vendor/bin/phpunit
+
+Run a single test class:
+
+    ./vendor/bin/phpunit --filter UrlTest
+
+Run linter:
+
     ./vendor/bin/phpcs --standard=phpcs.xml --warning-severity=0 --extensions=php -p ./
 
 https://github.com/squizlabs/PHP_CodeSniffer/wiki

diff --git a/actions/DisplayAction.php b/actions/DisplayAction.php
@@ -112,15 +112,6 @@ private function createResponse(Request $request, BridgeAbstract $bridge, string
             $input = array_diff_key($requestArray, array_fill_keys($remove, ''));
             $bridge->setInput($input);
             $bridge->collectData();
-            $items = $bridge->getItems();
-            if (isset($items[0]) && is_array($items[0])) {
-                $feedItems = [];
-                foreach ($items as $item) {
-                    $feedItems[] = FeedItem::fromArray($item);
-                }
-                $items = $feedItems;
-            }
-            $feed = $bridge->getFeed();
         } catch (\Exception $e) {
             // Probably an exception inside a bridge
             if ($e instanceof HttpException) {
@@ -154,6 +145,16 @@ private function createResponse(Request $request, BridgeAbstract $bridge, string
             }
         }
 
+        $items = $bridge->getItems();
+        if (isset($items[0]) && is_array($items[0])) {
+            $feedItems = [];
+            foreach ($items as $item) {
+                $feedItems[] = FeedItem::fromArray($item);
+            }
+            $items = $feedItems;
+        }
+        $feed = $bridge->getFeed();
+
         $formatFactory = new FormatFactory();
         $format = $formatFactory->create($format);
 

diff --git a/lib/FeedItem.php b/lib/FeedItem.php
@@ -186,21 +186,26 @@ public function getContent(): ?string
     }
 
     /**
-     * @param string|object $content The item content as text or simple_html_dom object.
+     * @param string|array|\simple_html_dom|\simple_html_dom_node $content The item content
      */
     public function setContent($content)
     {
         $this->content = null;
+
         if (
             $content instanceof simple_html_dom
             || $content instanceof simple_html_dom_node
         ) {
             $content = (string) $content;
+        } elseif (is_array($content)) {
+            // Assuming this is the rss2.0 content module
+            $content = $content['encoded'] ?? '';
         }
+
         if (is_string($content)) {
             $this->content = $content;
         } else {
-            Debug::log(sprintf('Feed content must be a string but got %s', gettype($content)));
+            Debug::log(sprintf('Unable to convert feed content to string: %s', gettype($content)));
         }
     }
 

diff --git a/lib/FeedParser.php b/lib/FeedParser.php
@@ -167,8 +167,9 @@ public function parseRss2Item(\SimpleXMLElement $feedItem): array
         if (isset($namespaces['media'])) {
             $media = $feedItem->children($namespaces['media']);
         }
+
         foreach ($namespaces as $namespaceName => $namespaceUrl) {
-            if (in_array($namespaceName, ['', 'content', 'media'])) {
+            if (in_array($namespaceName, ['', 'media'])) {
                 continue;
             }
             $item[$namespaceName] = $this->parseModule($feedItem, $namespaceName, $namespaceUrl);

diff --git a/tests/FeedParserTest.php b/tests/FeedParserTest.php
@@ -8,6 +8,13 @@
 
 class FeedParserTest extends TestCase
 {
+    private \FeedParser $sut;
+
+    public function setUp(): void
+    {
+        $this->sut = new \FeedParser();
+    }
+
     public function testRss1()
     {
         $xml = <<<XML
@@ -37,8 +44,7 @@ public function testRss1()
         </rdf:RDF>
         XML;
 
-        $sut = new \FeedParser();
-        $feed = $sut->parseFeed($xml);
+        $feed = $this->sut->parseFeed($xml);
 
         $this->assertSame('hello feed', $feed['title']);
         $this->assertSame('http://meerkat.oreillynet.com', $feed['uri']);
@@ -74,8 +80,7 @@ public function testRss2()
         </rss>
         XML;
 
-        $sut = new \FeedParser();
-        $feed = $sut->parseFeed($xml);
+        $feed = $this->sut->parseFeed($xml);
 
         $this->assertSame('hello feed', $feed['title']);
         $this->assertSame('https://example.com/', $feed['uri']);
@@ -111,8 +116,7 @@ public function testAtom()
         </feed>
         XML;
 
-        $sut = new \FeedParser();
-        $feed = $sut->parseFeed($xml);
+        $feed = $this->sut->parseFeed($xml);
 
         $this->assertSame('hello feed', $feed['title']);
         $this->assertSame('https://example.com/1', $feed['uri']);
@@ -151,8 +155,7 @@ public function testAppleItunesModule()
         </rss>
         XML;
 
-        $sut = new \FeedParser();
-        $feed = $sut->parseFeed($xml);
+        $feed = $this->sut->parseFeed($xml);
         $expected = [
             'title' => '',
             'uri' => '',