/**
* Extract the content of the page if it exists
*
* @param \DOMDocument $document
* @return string|false
*/
protected function parseBody(\DOMDocument $document)
{
// Replace images with their sources
/** @var \DOMElement[] $images */
$images = $document->getElementsByTagName('img');
foreach ($images as $image) {
$src = 'img' . implode('', parent::extract($image->getAttribute('src')));
$image->parentNode->replaceChild($document->createElement('span', $src), $image);
}
// Extract raw text
/** @var \DOMElement $node */
$node = $document->getElementsByTagName('body')->item(0);
if (!$node) {
throw new \RuntimeException();
}
return $node->nodeValue;
}
public function testExtract()
{
$extractor = new SimpleTextExtractor();
static::assertEquals(['mary', 'is', 'very', 'tall', 'she', 'was', 'in', 'the', '9th', 'grade'], $extractor->extract('Mary is very tall. She was in the 9th grade.'));
}