/**
* Checks the density of links within a node, is there not much text and most of it contains linky shit?
* if so it's no good
*
* @param Element $node
* @param double $limit
*
* @return bool
*/
private function isHighLinkDensity(Element $node, $limit = 1.0)
{
$links = $node->find('a, [onclick]');
if ($links->count() == 0) {
return false;
}
$words = preg_split('@[\\s]+@iu', $node->text(), -1, PREG_SPLIT_NO_EMPTY);
if (count($words) == 0) {
return false;
}
$sb = [];
foreach ($links as $link) {
$sb[] = Helper::textNormalise($link->text());
}
$linkText = implode('', $sb);
$linkWords = explode(' ', $linkText);
$numberOfLinkWords = count($linkWords);
$numberOfLinks = $links->count();
$linkDivisor = $numberOfLinkWords / count($words);
$score = $linkDivisor * $numberOfLinks;
if ($score >= $limit) {
return true;
}
return false;
}
/**
* @param Element $node
*
* @return LocallyStoredImage[]
*/
private function getImageCandidates(Element $node)
{
$images = $node->find('img');
$filteredImages = $this->filterBadNames($images);
$goodImages = $this->findImagesThatPassByteSizeTest($filteredImages);
return $goodImages;
}
/**
* we could have long articles that have tons of paragraphs so if we tried to calculate the base score against
* the total text score of those paragraphs it would be unfair. So we need to normalize the score based on the average scoring
* of the paragraphs within the top node. For example if our total score of 10 paragraphs was 1000 but each had an average value of
* 100 then 100 should be our base.
*
* @param Element $topNode
*
* @return int
*/
private function getBaselineScoreForSiblings(Element $topNode)
{
$base = 100000;
$numberOfParagraphs = 0;
$scoreOfParagraphs = 0;
$nodesToCheck = $topNode->find('p, strong');
foreach ($nodesToCheck as $node) {
$nodeText = $node->text();
$wordStats = $this->config()->getStopWords()->getStopwordCount($nodeText);
$highLinkDensity = $this->isHighLinkDensity($node);
if ($wordStats->getStopWordCount() > 2 && !$highLinkDensity) {
$numberOfParagraphs += 1;
$scoreOfParagraphs += $wordStats->getStopWordCount();
}
}
if ($numberOfParagraphs > 0) {
$base = $scoreOfParagraphs / $numberOfParagraphs;
}
return $base;
}
