Merge branch 'feature/ignore-more-elements' into 'master'HEADmaster

Add config support for ignoring additional elements.

See merge request main/libraries/readability-php!1

3 files changed, 30 insertions, 4 deletions

diff --git a/README.md b/README.md
index c910714..547178c 100644
--- a/README.md
+++ b/README.md
@@ -117,6 +117,7 @@ Then you pass this Configuration object to Readability. The following options ar
 - **KeepClasses**: default value `false`, which removes all `class="..."` attribute values from HTML elements.
 - **Parser**: default value `html5`, which uses HTML5-PHP for parsing. Set to `libxml` to use that instead (not recommended for modern HTML documents).
 - **SummonCthulhu**: default value `false`, remove all `<script>` nodes via regex. This is not ideal as it might break things, but if you've set the parser to libxml (see above), it might be the only solution to [libxml problems with unescaped javascript](https://github.com/fivefilters/readability.php#known-libxml-parsing-issues).
+- **ExtraIgnoredElements**: default value `[]`, additional DOM elements that should be ignored.  `noscript` and `script` are always ignored.
 
 ### Debug log
 
diff --git a/src/Configuration.php b/src/Configuration.php
index 6d1f03f..0659a82 100644
--- a/src/Configuration.php
+++ b/src/Configuration.php
@@ -84,6 +84,11 @@ class Configuration
     protected $disableJSONLD = false;
 
     /**
+     * @var array<string>
+     */
+    protected $extraIgnoredElements = [];
+
+    /**
      * Configuration constructor.
      *
      * @param array $params
@@ -420,4 +425,24 @@ class Configuration
 
         return $this;
     }
+
+    /**
+     * @return array<string>
+     */
+    public function getExtraIgnoredElements()
+    {
+        return $this->extraIgnoredElements;
+    }
+
+    /**
+     * @param array<string>
+     *
+     * @return $this
+     */
+    public function setExtraIgnoredElements($extraIgnoredElements)
+    {
+        $this->extraIgnoredElements = $extraIgnoredElements;
+
+        return $this;
+    }
 }
diff --git a/src/Readability.php b/src/Readability.php
index 6407a92..c5318a4 100644
--- a/src/Readability.php
+++ b/src/Readability.php
@@ -342,7 +342,7 @@ class Readability
         // Extract JSON-LD metadata before removing scripts
         $this->jsonld = $this->configuration->getDisableJSONLD() ? [] : $this->getJSONLD($dom);
 
-        $this->removeScripts($dom);
+        $this->removeIgnoredElements($dom);
 
         $this->prepDocument($dom);
 
@@ -1188,13 +1188,13 @@ class Readability
     }
 
     /**
-     * Removes all the scripts of the html.
+     * Removes elements that should be ignored.
      *
      * @param DOMDocument $dom
      */
-    private function removeScripts(DOMDocument $dom)
+    private function removeIgnoredElements(DOMDocument $dom)
     {
-        foreach (['script', 'noscript'] as $tag) {
+        foreach (['noscript', 'script', ...$this->configuration->getExtraIgnoredElements()] as $tag) {
             $nodes = $dom->getElementsByTagName($tag);
             foreach (iterator_to_array($nodes) as $node) {
                 NodeUtility::removeNode($node);