php for packaging any URL with embedded javascript and css?

Question

We need a cronjob that creates a static version of our anonymous pages.

Each URL should be saved as a single HTML document, with all external <script src=""> tags replaced with their javascript and all <link href=""> tags replaced with their CSS. (css doesn't need to be inlined as attributes).

Before I re-invent the wheel, are there any simple packaging scripts in PHP to do this?

Answer 1

my simply solution...

$ch = curl_init();
  curl_setopt($ch, CURLOPT_HEADER, false);
  curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
  curl_setopt($ch, CURLOPT_URL, $url);
  curl_setopt($ch, CURLOPT_REFERER, $url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
  //curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0);
  //curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
  curl_setopt($ch, CURLOPT_VERBOSE, 1);
  $html = curl_exec($ch);
  if($errno = curl_errno($ch)) {
      $error_message = curl_strerror($errno) . ' -- ' . $url;
      die ("cURL error ({$errno}):\n {$error_message}");
  }
  curl_close($ch);

  $doc = new DOMDocument();
  $doc->strictErrorChecking = false;
  $doc->recover = true;
  $internalErrors = libxml_use_internal_errors(true);
  $doc->loadHTML($html);
  libxml_use_internal_errors($internalErrors);

  foreach($doc->getElementsByTagName('script') as $script) {
      if($script->hasAttribute('src')) {
          $path = $script->getAttribute('src');
          if (strpos($path, 'http') !== 0) {
            if (strpos($path, '?') > -1)  $path = substr($path, 0, strpos($path, '?'));
            $path = ROOT_CD . $path;
          }
          $source = file_get_contents($path);

          $new = $doc->createElement('script');
          $new->setAttribute('type', 'text/javascript');
          $new->setAttribute('sourcePath', $script->getAttribute('src'));
          $new->setAttribute('language', 'javascript');
          $source = $doc->createTextNode($source);
          $new->appendChild($source);

          $script->parentNode->replaceChild($new, $script);
      }
  }

  foreach($doc->getElementsByTagName('link') as $script) {
      if($script->hasAttribute('href') && $script->hasAttribute('rel')) {
          $type = $script->getAttribute('rel');
          if ($type !== 'stylesheet') continue;

          $path = $script->getAttribute('href');
          if (strpos($path, 'http') !== 0) {
            if (strpos($path, '?') > -1)  $path = substr($path, 0, strpos($path, '?'));
            $path = ROOT_CD . $path;
          }
          $source = file_get_contents($path);

          $new = $doc->createElement('style');
          $new->setAttribute('type', 'text/css');
          $new->setAttribute('sourcePath', $script->getAttribute('src'));
          $source = $doc->createTextNode($source);
          $new->appendChild($source);

          $script->parentNode->replaceChild($new, $script);
      }
  }


  $html = $doc->saveHTML();
  require_once '../preprocessing/minifier.php';
  $html = compressHTML($html);
    file_put_contents("static-login-".$platform.".html", $html);
    echo $html;