Parse the OU Drupal supported modules Wiki page, and extract project names and hopefully Git tags

oudrupal.php

<?php
/**
 * Parse the OU Drupal supported modules Wiki page, and extract project names and hopefully Git tags.
 *
 * $ git tag -l "6.x-2.*"
 *
 * N.D.Freear, 2012-05-10.
 */

$url = 'http://www.open.ac.uk/wikis/drupal/Drupal_supported_modules_(6.21)';
$url_raw = 'http://www.open.ac.uk/wikis/drupal/index.php?title=Drupal_supported_modules_(6.21)&action=raw';


$res = _http_request_curl($url_raw);

$ouput = $human = '';
$describe = array();

if (preg_match('#Alphabetical.+?Version.+?\|-(.+)#ms', $res->data, $matches_outer)) {
	#var_dump($matches_outer);
	$data = $matches_outer[1];
	if (preg_match_all('#\|([\w ]+?)\s\|(http:.+?)\s\|(6.\w-[\w-.]+)#ms', $data, $matches, PREG_SET_ORDER)) {
		#var_dump(count($matches), $matches);
		foreach ($matches as $record) {
			$label = trim($record[1]);
			$url = $record[2];
			$tag = $record[3];
			$version = preg_replace('/.*-([\d\.x]{3,5}).*/', "$1", $tag);
			$project = NULL; #$label;
			if (preg_match('#.org\/project\/(.+)#', $url, $matches_url)) {
				$project = $matches_url[1];
			}
			if ($project) {
				$ouput .= "$project,$tag".PHP_EOL;
				$human .= "$label\t$project\t$tag\t$url".PHP_EOL;
				$describe[] = (object) array(
					'project' => $project,
					'tag' => $tag,
					'version' => $version,
				);
			}
		}
	}
}

var_dump($describe);


  /** Perform the HTTP request using cURL.
  */
  function _http_request_curl($url, $spoof=false, $options=array()) {
    if (!function_exists('curl_init'))  die('Error, cURL is required.');

$result = (object)array();

    $h_curl = curl_init($url);
    #curl_setopt($h_curl, CURLOPT_USERAGENT, $options['ua']);
    if (!$spoof) {
      #curl_setopt($h_curl, CURLOPT_REFERER, base_url());
    }

    if (isset($options['cookie'])) {
        curl_setopt($h_curl, CURLOPT_COOKIE, $options['cookie']);
        header('X-Proxy-Cookie: '.$options['cookie']);
    }

    curl_setopt($h_curl, CURLOPT_AUTOREFERER, TRUE);
    #curl_setopt($h_curl, CURLOPT_MAXREDIRS, $options['max_redirects']);
    curl_setopt($h_curl, CURLOPT_FOLLOWLOCATION, TRUE);
    #curl_setopt($h_curl, CURLOPT_TIMEOUT, $options['timeout']);

        

    $http_proxy = 'wwwcache.open.ac.uk:80'; #$this->CI->config->item('http_proxy');
    if ($http_proxy) {
          curl_setopt($h_curl, CURLOPT_PROXY, $http_proxy);
    }
    curl_setopt($h_curl, CURLOPT_RETURNTRANSFER, TRUE);
    $result->data = curl_exec($h_curl);
    if ($errno = curl_errno($h_curl)) {
      //Error. Quietly log?
      $this->CI->_log('error', "cURL $errno, ".curl_error($h_curl)." GET $url");
      #$this->CI->firephp->fb("cURL $errno", "cURL error", "ERROR");
    }
    $result->info = curl_getinfo($h_curl);
    $result->success = ($result->info['http_code'] < 300);
    return (object) $result;
  }