diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/Readability.php | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/src/Readability.php b/src/Readability.php index 93fc810..053d37f 100644 --- a/src/Readability.php +++ b/src/Readability.php @@ -997,7 +997,9 @@ class Readability $MINIMUM_TOPCANDIDATES = 3; if (count($alternativeCandidateAncestors) >= $MINIMUM_TOPCANDIDATES) { $parentOfTopCandidate = $topCandidate->parentNode; - while ($parentOfTopCandidate->nodeName !== 'body') { + + // Check if we are actually dealing with a DOMNode and not a DOMDocument node or higher + while ($parentOfTopCandidate->nodeName !== 'body' && $parentOfTopCandidate->nodeType === XML_ELEMENT_NODE) { $listsContainingThisAncestor = 0; for ($ancestorIndex = 0; $ancestorIndex < count($alternativeCandidateAncestors) && $listsContainingThisAncestor < $MINIMUM_TOPCANDIDATES; $ancestorIndex++) { $listsContainingThisAncestor += (int)in_array($parentOfTopCandidate, $alternativeCandidateAncestors[$ancestorIndex]); @@ -1027,8 +1029,7 @@ class Readability $scoreThreshold = $lastScore / 3; /* @var DOMElement $parentOfTopCandidate */ - // Check if we are actually dealing with a DOMNode and not a DOMDocument node or higher - while ($parentOfTopCandidate->nodeName !== 'body' && $parentOfTopCandidate->nodeType === XML_ELEMENT_NODE) { + while ($parentOfTopCandidate->nodeName !== 'body') { $parentScore = $parentOfTopCandidate->contentScore; if ($parentScore < $scoreThreshold) { break; @@ -1175,6 +1176,7 @@ class Readability $this->_clean($article, 'h1'); $this->_clean($article, 'footer'); $this->_clean($article, 'link'); + $this->_clean($article, 'aside'); // Clean out elements have "share" in their id/class combinations from final top candidates, // which means we don't remove the top candidates even they have "share". |