ContentExtractor: fix handling of data-srcset

The extractor was incorrectly setting the value of data-srcset into the src attribute, however srcset does not use the same format leading to loading error with incorrect paths. Now data-srcset sets the value of srcset which will let the browser to use paths of either src or srcset attributes. Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
j0k3r · Jan 19, 2021 · 20d6250 · 20d6250
1 parent 987aa6c
commit 20d6250
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 4 deletions.
diff --git a/src/Extractor/ContentExtractor.php b/src/Extractor/ContentExtractor.php
@@ -607,16 +607,23 @@ function ($element, $currentEntity) {
                     continue;
                 }
 
-                $src = null;
+                $attributes = [];
                 foreach ($this->config['src_lazy_load_attributes'] as $attribute) {
                     if ($e->hasAttribute($attribute)) {
-                        $src = $e->getAttribute($attribute);
+                        $key = 'src';
+                        if ('data-srcset' === $attribute) {
+                            $key = 'srcset';
+                        }
+                        $attributes[$key] = $e->getAttribute($attribute);
                         $e->removeAttribute($attribute);
                     }
                 }
 
-                if (null !== $src) {
-                    $e->setAttribute('src', $src);
+                foreach (['src', 'srcset'] as $attr) {
+                    if (\array_key_exists($attr, $attributes)
+                        && null !== $attributes[$attr]) {
+                        $e->setAttribute($attr, $attributes[$attr]);
+                    }
                 }
             }
 

diff --git a/tests/Extractor/ContentExtractorTest.php b/tests/Extractor/ContentExtractorTest.php
@@ -756,6 +756,11 @@ public function dataForlazyLoad(): array
                 '<div>' . str_repeat('this is the best part of the show', 10) . '<img src="data:image/gif;base64,R0lGODlhAQABAAAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==" data-toto-src="http://0.0.0.0/big_image.jpg"/></div>',
                 '<img src="http://0.0.0.0/big_image.jpg"',
             ],
+            // test with img attribute data-srcset
+            [
+                '<div>' . str_repeat('this is the best part of the show', 10) . '<img data-src="http://0.0.0.0/src.jpg" data-srcset="http://0.0.0.0/srcset1 680w, http://0.0.0.0/srcset2 1536w"/></div>',
+                '<img src="http://0.0.0.0/src.jpg" srcset="http://0.0.0.0/srcset1 680w, http://0.0.0.0/srcset2 1536w"/>',
+            ],
         ];
     }