Web scraping using transients

Question

I'm using xPath to scrape tour dates from another website (with permission of course). Since it updates on every page load, I thought about using transients to store the data.

Unfortunately I have no experience using transients and don't get it to work. This is my code:

<?php
  $html = file_get_contents('http://www.example.com');       
  $doc = new DOMDocument();

  libxml_use_internal_errors(TRUE); // disable libxml errors

  if(!empty($html)) {

    $doc->loadHTML($html);
    libxml_clear_errors();

    $xpath = new DOMXPath($doc);

    // Get only the content needed
    $termine = $xpath->query('//ul[@class="artistEvents"]/li');            

    if ($termine->length > 0) {
      foreach ($termine as $termin) { 

        $date = $xpath->query("div[@class='left']/strong", $termin);
        $location = $xpath->query("div[contains(@class,'right')]", $termin);

        echo '<tr>';

        // Date     
        if ($date->length > 0) {
          $date = substr($date->item(0)->nodeValue, 3, 10);
          $date = strftime("%d.%m.%Y", strtotime($date));
          echo '<td class="live-date">' . $date . '</td>';
        }

        // Location
        if ($location->length > 0) {
          $location = substr($location->item(0)->nodeValue, 14);
          $location = utf8_decode($location);
          echo '<td class="live-location">' . $location . '</td>';
        }

        echo '</tr>';
      }
    }

    else {
      echo '<p>No dates available.</p>';
    }

  }
?>

Any help with how to use transients to store this query is greatly appreciated! Also, I've never used xPath before, so if my code needs any improvement (although it works) I'll be happy to know about it.

Thanks so much!

Answer 1

Try something like this, which would save in transient for 12 hours. Let me know if anything does not make sense.

<?php
$value = get_transient( 'value' );
if ( false === $value ) {
  $output = "";
  $html = file_get_contents('http://www.example.com');       
  $doc = new DOMDocument();

  libxml_use_internal_errors(TRUE); // disable libxml errors

  if(!empty($html)) {

    $doc->loadHTML($html);
    libxml_clear_errors();

    $xpath = new DOMXPath($doc);

    // Get only the content needed
    $termine = $xpath->query('//ul[@class="artistEvents"]/li');            

    if ($termine->length > 0) {
      foreach ($termine as $termin) { 

        $date = $xpath->query("div[@class='left']/strong", $termin);
        $location = $xpath->query("div[contains(@class,'right')]", $termin);

        $output .= '<tr>';

        // Date     
        if ($date->length > 0) {
          $date = substr($date->item(0)->nodeValue, 3, 10);
          $date = strftime("%d.%m.%Y", strtotime($date));
          $output .= '<td class="live-date">' . $date . '</td>';
        }

        // Location
        if ($location->length > 0) {
          $location = substr($location->item(0)->nodeValue, 14);
          $location = utf8_decode($location);
          $output .= '<td class="live-location">' . $location . '</td>';
        }

        $output .= '</tr>';
      }
    }
    else {
      $output .= '<p>No dates available.</p>';
    }
  }
  $value = $output;
  set_transient( 'value', $value, 12 * HOUR_IN_SECONDS );

}
echo $value;
?>