/**
* Return the job id of the slurp
*/
public static function slurp($url)
{
$url_format = '/^(https?):\\/\\/' . '(([a-z0-9$_\\.\\+!\\*\'\\(\\),;\\?&=-]|%[0-9a-f]{2})+' . '(:([a-z0-9$_\\.\\+!\\*\'\\(\\),;\\?&=-]|%[0-9a-f]{2})+)?' . '@)?(?#' . ')((([a-z0-9][a-z0-9-]*[a-z0-9]\\.)*' . '[a-z][a-z0-9-]*[a-z0-9]' . '|((\\d|[1-9]\\d|1\\d{2}|2[0-4][0-9]|25[0-5])\\.){3}' . '(\\d|[1-9]\\d|1\\d{2}|2[0-4][0-9]|25[0-5])' . ')(:\\d+)?' . ')(((\\/+([a-z0-9$_\\.\\+!\\*\'\\(\\),;:@&=-]|%[0-9a-f]{2})*)*' . '(\\?([a-z0-9$_\\.\\+!\\*\'\\(\\),;:@&=-]|%[0-9a-f]{2})*)' . '?)?)?' . '(#([a-z0-9$_\\.\\+!\\*\'\\(\\),;:@&=-]|%[0-9a-f]{2})*)?' . '$/i';
if (!preg_match($url_format, $url)) {
throw new Mijireh_NotFound('Unable to slurp invalid URL: $url');
}
try {
$rest = new Mijireh_Rest($url);
$html = $rest->get('');
$data = array('url' => $url, 'html' => $html);
$rest = new Mijireh_RestJSON(self::$url);
$rest->setupAuth(self::$access_key, '');
$result = $rest->post('slurps', $data);
return $result['job_id'];
} catch (Mijireh_Rest_Unauthorized $e) {
throw new Mijireh_Unauthorized("Unauthorized. Please check your api access key");
} catch (Mijireh_Rest_NotFound $e) {
throw new Mijireh_NotFound("Mijireh resource not found: " . $rest->last_request['url']);
} catch (Mijireh_Rest_ClientError $e) {
throw new Mijireh_ClientError($e->getMessage());
} catch (Mijireh_Rest_ServerError $e) {
throw new Mijireh_ServerError($e->getMessage());
} catch (Mijireh_Rest_UnknownResponse $e) {
throw new Mijireh_Exception('Unable to slurp the URL: $url');
}
}
protected function prepRequest($opts, $url)
{
$opts[CURLOPT_HTTPHEADER][] = 'Accept: application/json';
$opts[CURLOPT_HTTPHEADER][] = 'Content-Type: application/json';
return parent::prepRequest($opts, $url);
}
