Goose\Modules\Formatters\OutputFormatter::postExtractionCleanup PHP Method

postExtractionCleanup() private method

Remove any divs that looks like non-content, clusters of links, or paras with no gusto
private postExtractionCleanup ( )
    private function postExtractionCleanup()
    {
        $this->addSiblings($this->article()->getTopNode());
        foreach ($this->article()->getTopNode()->contents() as $node) {
            if ($node->is(self::$CLEANUP_IGNORE_SELECTOR)) {
                if ($this->isHighLinkDensity($node) || $this->isTableTagAndNoParagraphsExist($node) || !$this->isNodeScoreThreshholdMet($this->article()->getTopNode(), $node)) {
                    $node->remove();
                }
            }
        }
    }