/**
* Save the plain data into a file and hash the resulting filename.
*
* Note: Overwrites old files and uses existing subdirectories.
*
* @param Result $result
*
* @return Result
*/
public function execute(Result $result)
{
$subDir = $this->dir . DIRECTORY_SEPARATOR . substr($result->getHash(), 0, 1);
$saveTo = $subDir . DIRECTORY_SEPARATOR . $result->getHash();
$fs = new Filesystem();
$fs->dumpFile($saveTo, $result->getData());
return $result;
}
/**
* Return text that matches a XPath expression.
*
* @param Result $result
*
* @return Result
*/
public function execute(Result $result)
{
$domCrawler = new DOMCrawler();
$domCrawler->addContent($result->getData());
$domCrawler->filterXPath($this->xpath)->each(function (DOMCrawler $node) {
$text = trim($node->text());
if (!empty($text)) {
echo $text . PHP_EOL;
}
});
return $result;
}
/**
* Save the plain data into a file and hash the resulting filename.
*
* Note: Overwrites old files and uses existing subdirectories.
*
* @param Result $result
*
* @return Result
*/
public function execute(Result $result)
{
// strip protocol and www.
$url = preg_replace('/^((https?):\\/\\/)?(www\\d{0,3}\\.)?/', '', $result->getLink());
// URLs like blog.com/posts and blog.com/posts/a would conflict, because
// the first URL would be created as a file and the same name cannot be used for
// a directory with the same name. Workaround is to simply attach an underscore
// to the *index* file.
if ($this->isPrettyUrl($url)) {
$url = $url . '_';
}
$saveTo = $this->dir . DIRECTORY_SEPARATOR . $url;
$fs = new Filesystem();
$fs->dumpFile($saveTo, $result->getData());
return $result;
}
/**
* Minify HTML.
*
* @param Result $result
*
* @return Result
*/
public function execute(Result $result)
{
$result->setData(HTMLMinify::minify($result->getData(), array('optimizationLevel' => HTMLMinify::OPTIMIZATION_ADVANCED)));
return $result;
}