php-embed · oscarotero · Oct 5, 2025 · Oct 4, 2025 · Oct 5, 2025 · Oct 5, 2025
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -23,15 +23,15 @@ jobs:
 
         steps:
             - name: Checkout
-              uses: actions/checkout@v2
+              uses: actions/checkout@v4
 
             - name: Install PHP
               uses: shivammathur/setup-php@v2
               with:
                   php-version: ${{ matrix.php }}
 
             - name: Cache PHP dependencies
-              uses: actions/cache@v2
+              uses: actions/cache@v4
               with:
                   path: vendor
                   key: ${{ runner.os }}-php-${{ matrix.php }}-composer-${{ hashFiles('**/composer.json') }}

diff --git a/src/Document.php b/src/Document.php
@@ -31,31 +31,56 @@ public function __construct(Extractor $extractor)
         preg_match('/charset=(?:"|\')?(.*?)(?=$|\s|;|"|\'|>)/i', $contentType, $match);
         if (!empty($match[1])) {
             $encoding = trim($match[1], ',');
-            try {
-                $ret = mb_encoding_aliases($encoding ?? '');
-                if ($ret === false) {
-                    $encoding = null;
-                }
-            } catch (\ValueError $exception) {
-                $encoding = null;
-            }
+            $encoding = $this->getValidEncoding($encoding);
         }
         if (is_null($encoding) && !empty($html)) {
             preg_match('/charset=(?:"|\')?(.*?)(?=$|\s|;|"|\'|>)/i', $html, $match);
             if (!empty($match[1])) {
                 $encoding = trim($match[1], ',');
+                $encoding = $this->getValidEncoding($encoding);
             }
+        }
+        $this->document = !empty($html) ? Parser::parse($html, $encoding) : new DOMDocument();
+        $this->initXPath();
+    }
+
+    /**
+     * Get valid encoding name if it exists, otherwise return null
+     *
+     * Uses mb_encoding_aliases() to verify the encoding is valid.
+     *
+     * TODO: When dropping PHP 7.4 support, remove the PHP_VERSION_ID < 80000 branch.
+     * PHP version differences:
+     * - PHP 7.4: mb_encoding_aliases() returns false for invalid encoding and throws Warning for empty string
+     * - PHP 8.0+: mb_encoding_aliases() throws ValueError for invalid/empty encoding
+     *
+     * @see https://www.php.net/manual/en/function.mb-encoding-aliases.php
+     */
+    private function getValidEncoding(?string $encoding): ?string
+    {
+        if (PHP_VERSION_ID < 80000) {
+            // PHP 7.4: Check return value (false = invalid encoding)
+            // Need to check empty() first to avoid Warning
+            // TODO: Remove this entire branch when PHP 7.4 support is dropped
+            if (empty($encoding)) {
+                return null;
+            }
+            $ret = mb_encoding_aliases($encoding);
+            if ($ret === false) {
+                return null;
+            } else {
+                return $encoding;
+            }
+        } else {
+            // PHP 8.0+: ValueError exception is thrown for invalid/empty encoding
             try {
-                $ret = mb_encoding_aliases($encoding ?? '');
-                if ($ret === false) {
-                    $encoding = null;
-                }
+                $aliases = mb_encoding_aliases($encoding ?? '');
+                // Check if aliases array is not empty (valid encoding should have at least one alias)
+                return !empty($aliases) ? $encoding : null;
             } catch (\ValueError $exception) {
-                $encoding = null;
+                return null;
             }
         }
-        $this->document = !empty($html) ? Parser::parse($html, $encoding) : new DOMDocument();
-        $this->initXPath();
     }
 
     private function initXPath()

diff --git a/tests/DocumentTest.php b/tests/DocumentTest.php
@@ -28,7 +28,7 @@ public function testSelectors()
         $extractor = self::getEmbed()->get('http://www.wired.com/?p=2064839');
         $document = $extractor->getDocument();
 
-        $expected = 23;
+        $expected = 3;
 
         $this->assertCount($expected, $document->select('.//p')->nodes());
         $this->assertCount($expected, $document->selectCss('p')->nodes());

diff --git a/tests/cache/www.wired.com..1202600986b37d2c6a30336f82c671f8.php b/tests/cache/www.wired.com..1202600986b37d2c6a30336f82c671f8.php
diff --git a/...res/4pda.to.2022-12-04-406834-sostoyalsya_reliz_clown_of_duty_parodii_na_call_of_duty.php b/...res/4pda.to.2022-12-04-406834-sostoyalsya_reliz_clown_of_duty_parodii_na_call_of_duty.php
@@ -11,7 +11,9 @@
     'feeds' => [],
     'icon' => 'https://4pda.to/s/as6ywymaTWM6wnea1mxojxCz0Yet7IeumfOBnaxb.png',
     'image' => 'https://i.4pda.ws/s/as6yueQrUwnKt0LgJ5m26uBjbZsccTet21FqwJkADfGw.jpg?v=1669981373',
-    'keywords' => ['состоялся релиз clown of duty — пародии на call of duty'],
+    'keywords' => [
+        'состоялся релиз clown of duty — пародии на call of duty'
+    ],
     'language' => 'ru-RU',
     'languages' => [],
     'license' => null,
@@ -23,5 +25,5 @@
     'url' => 'https://4pda.to/2022/12/04/406834/sostoyalsya_reliz_clown_of_duty_parodii_na_call_of_duty/',
     'linkedData' => [],
     'oEmbed' => [],
-    'allLinkedData' => [],
+    'allLinkedData' => []
 ];
diff --git a/tests/fixtures/animoto.com.play-gjsj1gu0wdrfr4pgw12xzq.php b/tests/fixtures/animoto.com.play-gjsj1gu0wdrfr4pgw12xzq.php
@@ -2,50 +2,55 @@
 declare(strict_types = 1);
 
 return [
-    'authorName' => null,
-    'authorUrl' => null,
+    'authorName' => '@animoto',
+    'authorUrl' => 'https://twitter.com/animoto',
     'cms' => null,
-    'code' => [
-        'html' => '<iframe id="vp1GjsJ1" title="Video Player" width="640" height="360" frameborder="0" src="https://s3.amazonaws.com/embed.animoto.com/play.html?w=swf/production/vp1&e=1617549702&f=GjsJ1gu0WDRfr4pGw12xZQ&d=0&m=p&r=360p&i=m&asset_domain=s3-p.animoto.com&animoto_domain=animoto.com&options=start_hq" allowfullscreen></iframe>',
-        'width' => 640,
-        'height' => 360,
-        'ratio' => 56.25
+    'code' => null,
+    'description' => 'Create, edit, and share videos with our free video maker. Combine your photos, video clips, and music to make quality videos in minutes. Get started free!',
+    'favicon' => 'https://animoto.com/favicon-32x32.png?v=f7bad0df2a4af8688773dca5ee0b1ed6',
+    'feeds' => [
+        'https://animoto.com/rss.xml'
     ],
-    'description' => 'Animoto makes video creation easy! Animoto\'s video maker turns your photos and video clips into professional videos in minutes. Fast and shockingly simple!',
-    'favicon' => 'https://d14pr3cu5atb0x.cloudfront.net/images/icons/favicon-fbb19e53d0.ico',
-    'feeds' => [],
-    'icon' => 'https://d14pr3cu5atb0x.cloudfront.net/images/icons/touchicon-144-4a42d97241.png',
-    'image' => 'https://d2m23yiuv18ohn.cloudfront.net/Video/GjsJ1gu0WDRfr4pGw12xZQ/cover_648x360.jpg',
+    'icon' => 'https://animoto.com/icons/icon-48x48.png?v=f7bad0df2a4af8688773dca5ee0b1ed6',
+    'image' => null,
     'keywords' => [],
     'language' => null,
     'languages' => [],
     'license' => null,
     'providerName' => 'Animoto',
-    'providerUrl' => 'https://animoto.com/',
+    'providerUrl' => 'https://animoto.com',
     'publishedTime' => null,
     'redirect' => null,
-    'title' => 'taco bell',
+    'title' => 'Free Video Maker | Create & Edit Your Videos Easily',
     'url' => 'https://animoto.com/play/GjsJ1gu0WDRfr4pGw12xZQ',
-    'linkedData' => [],
+    'linkedData' => [
+        '@context' => 'http://schema.org',
+        '@type' => 'WebSite',
+        'url' => 'https://animoto.com',
+        'name' => 'Animoto video maker - Stand out on social media. Easily.',
+        'alternateName' => ''
+    ],
     'oEmbed' => [
-        'version' => 1.0,
-        'provider_name' => 'Animoto',
-        'provider_url' => 'https://animoto.com/',
-        'type' => 'video',
-        'author_name' => null,
-        'title' => 'taco bell',
-        'description' => '',
-        'thumbnail_url' => 'https://d2m23yiuv18ohn.cloudfront.net/Video/GjsJ1gu0WDRfr4pGw12xZQ/cover_648x360.jpg',
-        'thumbnail_height' => 360,
-        'thumbnail_width' => 648,
-        'icon_url' => 'https://d2m23yiuv18ohn.cloudfront.net/Video/GjsJ1gu0WDRfr4pGw12xZQ/cover_224x126.jpg',
-        'icon_height' => 54,
-        'icon_width' => 54,
-        'width' => 640,
-        'height' => 360,
-        'cache_age' => 604800,
-        'video_url' => 'https://d150hyw1dtprld.cloudfront.net/swf/w.swf?w=swf/production/vp1&e=1617549702&f=GjsJ1gu0WDRfr4pGw12xZQ&d=0&m=p&r=360p&i=m&asset_domain=s3-p.animoto.com&animoto_domain=animoto.com&options=start_hq',
-        'html' => '<iframe id="vp1GjsJ1" title="Video Player" width="640" height="360" frameborder="0" src="https://s3.amazonaws.com/embed.animoto.com/play.html?w=swf/production/vp1&e=1617549702&f=GjsJ1gu0WDRfr4pGw12xZQ&d=0&m=p&r=360p&i=m&asset_domain=s3-p.animoto.com&animoto_domain=animoto.com&options=start_hq" allowfullscreen></iframe>'
+        'error' => 'URL not supported or not found',
+        'url' => 'https://animoto.com/play/GjsJ1gu0WDRfr4pGw12xZQ'
     ],
-    'allLinkedData' => []
+    'allLinkedData' => [
+        [
+            '@context' => 'http://schema.org',
+            '@type' => 'WebSite',
+            'url' => 'https://animoto.com',
+            'name' => 'Animoto video maker - Stand out on social media. Easily.',
+            'alternateName' => ''
+        ],
+        [
+            '@context' => 'http://schema.org',
+            '@type' => 'VideoObject',
+            'name' => 'Animoto: Free Online Video Maker',
+            'contentUrl' => 'https://d2of6bhnpl91ni.cloudfront.net/cms/animoto-free-online-video-maker-e8d6870030.mp4',
+            'description' => 'With Animoto, you\'ll have everything you need to create your own professional videos in minutes. No experience required. All it takes is an idea. ',
+            'thumbnailUrl' => '//images.ctfassets.net/00i767ygo3tc/010bacg5wwIhMMx6xYS3qj/18e39c5d16f5614a3b477a284faea1a2/free-online-video-maker.webp',
+            'transcript' => 'We all have a story to tell, and video is the best way to make yours stand out. With Animoto, you\'ll have everything you need to create your own professional videos in minutes. No experience required. All it takes is an idea. We\'ve made it easy to get started with customizable templates for everything from saying Happy Birthday to selling your product. From there, it\'s as simple as dragging and dropping your photos and video clips, choosing from our millions of Getty stock images or recording with our built-in screen and webcam recorder. Customize your videos with transitions, music, voiceovers, and more. Then bring your videos on brand with a single click. Make sure your story is heard with Animoto. Everything you need to create your own videos is right at your fingertips. Start creating for free.',
+            'uploadDate' => '2020-09-15T21:58:55.636Z'
+        ]
+    ]
 ];
diff --git a/tests/fixtures/archive.org.details-dn2015-0220_vid.php b/tests/fixtures/archive.org.details-dn2015-0220_vid.php
@@ -43,8 +43,8 @@
     ],
     'oEmbed' => [],
     'api' => [
-        'server' => 'ia802600.us.archive.org',
-        'dir' => '/20/items/dn2015-0220_vid',
+        'server' => 'ia801600.us.archive.org',
+        'dir' => '/34/items/dn2015-0220_vid',
         'metadata' => [
             'identifier' => [
                 'dn2015-0220_vid'
@@ -786,11 +786,12 @@
             '/dn2015-0220_vid_files.xml' => [
                 'source' => 'original',
                 'format' => 'Metadata',
-                'md5' => '745ea2f6dde93e4b70b1c0b238d4c0e2'
+                'md5' => 'c8085d21bd5d528af0697f7d1cfff599',
+                'summation' => 'md5'
             ],
             '/dn2015-0220_vid_meta.xml' => [
                 'source' => 'original',
-                'mtime' => '1542757137',
+                'mtime' => '1675274129',
                 'size' => '1973',
                 'format' => 'Metadata',
                 'md5' => '6a144c80a58ab5f08c0ecffdb580954a',
@@ -799,12 +800,12 @@
             ]
         ],
         'misc' => [
-            'image' => 'https://ia802600.us.archive.org/20/items/dn2015-0220_vid/dn2015-0220.gif',
+            'image' => 'https://ia801600.us.archive.org/34/items/dn2015-0220_vid/dn2015-0220.gif',
             'collection-title' => 'Democracy Now!'
         ],
         'item' => [
-            'downloads' => 132,
-            'month' => 2,
+            'downloads' => 156,
+            'month' => 0,
             'item_size' => 3667677269,
             'files_count' => 68,
             'item_count' => null,

diff --git a/tests/fixtures/codepen.io.zhouzi-pen-jorazp.php b/tests/fixtures/codepen.io.zhouzi-pen-jorazp.php
@@ -3,10 +3,10 @@
 
 return [
     'authorName' => 'Gabin Aureche',
-    'authorUrl' => 'https://codepen.io/Zhouzi/',
+    'authorUrl' => 'https://codepen.io/Zhouzi',
     'cms' => null,
     'code' => [
-        'html' => '<iframe id="cp_embed_JoRazP" src="https://codepen.io/Zhouzi/embed/preview/JoRazP?height=300&amp;slug-hash=JoRazP&amp;default-tabs=js,result&amp;host=https://codepen.io" title="TheaterJS" scrolling="no" frameborder="0" height="300" allowtransparency="true" class="cp_embed_iframe" style="width: 100%; overflow: hidden;"></iframe>',
+        'html' => '<iframe id="cp_embed_JoRazP" src="https://codepen.io/Zhouzi/embed/preview/JoRazP?default-tabs=js%2Cresult&amp;height=300&amp;host=https%3A%2F%2Fcodepen.io&amp;slug-hash=JoRazP" title="TheaterJS" scrolling="no" frameborder="0" height="300" allowtransparency="true" class="cp_embed_iframe" style="width: 100%; overflow: hidden;"></iframe>',
         'width' => 800,
         'height' => 300,
         'ratio' => 37.5
@@ -15,7 +15,7 @@
     'favicon' => 'https://codepen.io/favicon.ico',
     'feeds' => [],
     'icon' => null,
-    'image' => 'https://assets.codepen.io/99102/internal/screenshots/pens/JoRazP.default.png?fit=cover&format=auto&ha=true&height=360&quality=75&v=2&version=1467971314&width=640',
+    'image' => 'https://shots.codepen.io/username/pen/JoRazP-512.jpg?version=1467971314',
     'keywords' => [],
     'language' => 'en-US',
     'languages' => [],
@@ -35,13 +35,13 @@
         'provider_url' => 'https://codepen.io',
         'title' => 'TheaterJS',
         'author_name' => 'Gabin Aureche',
-        'author_url' => 'https://codepen.io/Zhouzi/',
+        'author_url' => 'https://codepen.io/Zhouzi',
         'height' => '300',
         'width' => '800',
         'thumbnail_width' => '384',
         'thumbnail_height' => '225',
-        'thumbnail_url' => 'https://assets.codepen.io/99102/internal/screenshots/pens/JoRazP.default.png?fit=cover&amp;format=auto&amp;ha=true&amp;height=360&amp;quality=75&amp;v=2&amp;version=1467971314&amp;width=640',
-        'html' => '<iframe id="cp_embed_JoRazP" src="https://codepen.io/Zhouzi/embed/preview/JoRazP?height=300&amp;slug-hash=JoRazP&amp;default-tabs=js,result&amp;host=https://codepen.io" title="TheaterJS" scrolling="no" frameborder="0" height="300" allowtransparency="true" class="cp_embed_iframe" style="width: 100%; overflow: hidden;"></iframe>'
+        'thumbnail_url' => 'https://shots.codepen.io/username/pen/JoRazP-512.jpg?version=1467971314',
+        'html' => '<iframe id="cp_embed_JoRazP" src="https://codepen.io/Zhouzi/embed/preview/JoRazP?default-tabs=js%2Cresult&amp;height=300&amp;host=https%3A%2F%2Fcodepen.io&amp;slug-hash=JoRazP" title="TheaterJS" scrolling="no" frameborder="0" height="300" allowtransparency="true" class="cp_embed_iframe" style="width: 100%; overflow: hidden;"></iframe>'
     ],
     'allLinkedData' => []
 ];
diff --git a/tests/fixtures/drive.google.com.file-d-0b2rwn8wabvswbmfjdudnv2vsttg-view.php b/tests/fixtures/drive.google.com.file-d-0b2rwn8wabvswbmfjdudnv2vsttg-view.php
@@ -7,19 +7,19 @@
     'cms' => null,
     'code' => null,
     'description' => null,
-    'favicon' => 'https://ssl.gstatic.com/images/branding/product/1x/drive_2020q4_32dp.png',
+    'favicon' => 'https://drive.google.com/favicon.ico',
     'feeds' => [],
     'icon' => null,
     'image' => null,
     'keywords' => [],
     'language' => null,
     'languages' => [],
     'license' => null,
-    'providerName' => 'Google Docs',
+    'providerName' => 'Google',
     'providerUrl' => 'https://drive.google.com',
     'publishedTime' => null,
     'redirect' => null,
-    'title' => 'Entrevista_Rianxo_RadioFusion_150724.mp3',
+    'title' => null,
     'url' => 'https://drive.google.com/file/d/0B2rwN8wAbVSWbmFJdUdnV2VSTTg/view',
     'linkedData' => [],
     'oEmbed' => [],