Website scraper for datavisualization

scraper.php

<?php

$urls = [];


foreach ($urls as $url) {

  $data = file_get_contents($url);

  $date_regex = '|<a href="\/party\/day\/(\d*)\/(\d*)\/(\d*)">|';
  $title_regex = '|<meta property="og:title" content="(.*)" \/><meta property="og:type" content="partyflock:event" \/>|';
  $lineup_regex = '|<div id="lineup">(.*)<div class="l box-column" style="width:50%">|';

  preg_match($date_regex, $data, $date);
  preg_match($title_regex, $data, $title);
  preg_match($lineup_regex, $data, $lineup);

  $title = preg_replace('|festival|', '', $title[1]);

  $year = $date[1];

  $dat = preg_replace('|</div>|', '&break', $lineup[1]);
  $dat = preg_replace("|<span(.*?)</span>|", "", $dat);
  $dat = preg_replace("|<th(.*?)</th>|", "", $dat);
  $dat = strip_tags($dat, '<*><a>');
  $dat = preg_replace('|&break|', "\r\n", $dat);
  $dat = preg_replace('|&nbsp;|', '', $dat);
  $dat = preg_replace('|live:|', '', $dat);
  $dat = preg_replace('|00:00,-,00:00:|', '00:00 - 00:00:', $dat);

  $dat_arr = array_filter(explode(PHP_EOL, $dat));
  $artist_regex = '|<a itemprop="performer" href="\/artist\/(.*)">(.*)<\/a>|';

  mkdir("./{$title}");
  $file = fopen("./{$title}/{$year}.txt", "a");

  foreach ($dat_arr as $artist) {
      preg_match($artist_regex, $artist, $artist_result);
      if (isset($artist_result[1], $artist_result[2])) {
          $artist_data = file_get_contents("http://partyflock.nl/artist/" . $artist_result[1]);
          $nat_regex = '|<a\b[^>]* href="/country/(.*?)">(.*?)</a>|';
          preg_match($nat_regex, $artist_data, $nat_result);
          if(isset($nat_result[2])) {
              $result = "{$artist_result[2]},{$nat_result[2]}\r\n";
              fwrite($file, $result);
          } else {
              $result = "{$artist_result[2]}\r\n";
              fwrite($file, $result);
          }
      }
  }

  fclose($file);

}

?>