[TldrTechBridge] Fix duplicate entries and empty sections (#4466)

SqrtMinusOne · web-flow · commit f270cd35e71a · 2025-03-05T19:36:41.000+01:00
diff --git a/bridges/TldrTechBridge.php b/bridges/TldrTechBridge.php
@@ -57,6 +57,9 @@ public function collectData()
                 continue;
             }
             $itemUrl = Url::fromString(self::URI . ltrim($child->href, '/'));
+            if ($itemUrl == $locationUrl) {
+                continue;
+            }
             $this->extractItem($itemUrl);
             if (count($this->items) >= $limit) {
                 break;
@@ -125,6 +128,11 @@ private function extractContent($url)
                 }
             }
         }
+        foreach ($content->find('section') as $section) {
+            if (count($section->children()) == 0) {
+                $content->removeChild($section);
+            }
+        }
         $title = $content->find('h2', 0);
         return [$content->innertext, $title->plaintext];
     }

Original file line number	Diff line number	Diff line change
`@@ -57,6 +57,9 @@ public function collectData()`
`57`	`57`	`continue;`
`58`	`58`	`}`
`59`	`59`	`$itemUrl = Url::fromString(self::URI . ltrim($child->href, '/'));`
	`60`	`+ if ($itemUrl == $locationUrl) {`
	`61`	`+ continue;`
	`62`	`+ }`
`60`	`63`	`$this->extractItem($itemUrl);`
`61`	`64`	`if (count($this->items) >= $limit) {`
`62`	`65`	`break;`
`@@ -125,6 +128,11 @@ private function extractContent($url)`
`125`	`128`	`}`
`126`	`129`	`}`
`127`	`130`	`}`
	`131`	`+ foreach ($content->find('section') as $section) {`
	`132`	`+ if (count($section->children()) == 0) {`
	`133`	`+ $content->removeChild($section);`
	`134`	`+ }`
	`135`	`+ }`
`128`	`136`	`$title = $content->find('h2', 0);`
`129`	`137`	`return [$content->innertext, $title->plaintext];`
`130`	`138`	`}`