function parse_html($url)
{
echo "Scraping {$url}\n";
//create an array of items to be parsed from HTML
$fields = array();
$html = file_get_contents($url);
$dom = new DOMDocument();
@$dom->loadHTML($html);
$xpath = new DOMXpath($dom);
//find the reference numbers
$refNode = $xpath->query("//p[@class='ttag'][contains(text(), 'Alternative')]/following-sibling::p[1]");
if ($refNode->length > 0) {
//parse as text and clean to generate an array of reference numbers
$refText = $dom->saveHTML($refNode->item(0));
$refText = str_replace('<p class="vtag">', '', str_replace('</p>', '', $refText));
$refs = explode('<br>', trim($refText));
foreach ($refs as $ref) {
$ref = trim($ref);
if (strpos($ref, 'RRC') !== FALSE || strpos($ref, 'Crawford') !== FALSE) {
echo "Parsing {$ref}\n";
$fields['reference'] = $ref;
$pieces = explode(' ', $ref);
$num = str_replace('/', '.', $pieces[1]);
$uri = "http://numismatics.org/crro/id/rrc-{$num}";
$typeValid = check_uri($uri);
if ($typeValid == true) {
$fields['coinType'] = $uri;
}
} else {
if (strpos($ref, 'price') !== FALSE) {
echo "Parsing {$ref}\n";
$fields['reference'] = $ref;
$pieces = explode(' ', $ref);
$num = $pieces[1];
$uri = "http://numismatics.org/pella/id/price.{$num}";
$typeValid = check_uri($uri);
if ($typeValid == true) {
$fields['coinType'] = $uri;
}
}
}
}
} else {
echo "No references.\n";
}
//parse measurements
$measurementsNode = $xpath->query("//p[@class='ttag'][contains(text(), 'Dimension')]/following-sibling::p[1]");
if ($measurementsNode->length > 0) {
$text = $dom->saveHTML($measurementsNode->item(0));
$text = str_replace('<p class="vtag">', '', str_replace('</p>', '', $text));
$measurements = explode('<br>', trim($text));
foreach ($measurements as $measurement) {
if (strpos($measurement, 'weight') !== FALSE) {
preg_match('/(\\d+\\.\\d+)/', $measurement, $matches);
if (is_numeric($matches[1])) {
$fields['weight'] = (double) $matches[1];
}
} elseif (strpos($measurement, 'axis') !== FALSE) {
preg_match('/(d+)/', $measurement, $matches);
$axis360 = $matches[1];
//round the 360 degree axis to the nearest clock integer
$axis = round($axis360 / 360 * 12);
//if axis is between 0 and 12, reset 0 to 12 and return the value
if ($axis <= 12 && $axis >= 0) {
if ($axis == 0) {
$axis = 12;
}
$fields['axis'] = $axis;
}
}
}
//var_dump($measurements);
}
return $fields;
}
if (is_numeric($row['Diameter'])) {
$record['diameter'] = $row['Diameter'];
}
if (is_numeric($row['Weight'])) {
$record['weight'] = $row['Weight'];
}
if (strlen($row['Hoard URI']) > 0) {
$record['hoard'] = $row['Hoard URI'];
}
//images
$id = str_replace('HCR', '', $row['Accession number']);
$record['obv_image'] = "http://hcr.ashmus.ox.ac.uk/images/coin/{$id}of.jpg";
$record['rev_image'] = "http://hcr.ashmus.ox.ac.uk/images/coin/{$id}rf.jpg";
//validate Price number
$uri = "http://numismatics.org/pella/id/price.{$row['Price number']}";
$typeValid = check_uri($uri);
if ($typeValid == true) {
$record['cointype'] = $uri;
}
$records[] = $record;
$count++;
}
//after the CSV has been parsed, then process the resulting records array into Nomisma-conformant RDF
generate_csv($records, $project);
generate_rdf($records, $project);
function check_uri($uri)
{
global $coinTypes;
//if the URI is in the array
if (array_key_exists($uri, $coinTypes)) {
if ($coinTypes[$uri] == true) {
} else {
$active = 'no';
}
$new_user->setActive($active);
$new_user->setData($_POST['userdata']);
if (!$new_user->save()) {
$msg = 'error_user_not_created';
} else {
SimpleSAML_Utilities::redirect(SimpleSAML_Utilities::selfURLNoQuery(), array('selectedtab' => $selectedtab));
}
}
}
}
if (isset($_POST['submit'])) {
if (!empty($_POST['entityid'])) {
if (check_uri($_POST['entityid'])) {
if (!isset($_POST['entityid']) || empty($_POST['entitytype'])) {
$msg = 'error_no_type';
$old_entityid = $_POST['entityid'];
$old_entitytype = $_POST['entitytype'];
} else {
$msg = $mcontrol->createNewEntity($_POST['entityid'], $_POST['entitytype']);
if (is_int($msg)) {
$entity = new sspmod_janus_Entity($janus_config);
$pm->subscribe($user->getUid(), 'ENTITYUPDATE-' . $msg);
$directlink = SimpleSAML_Module::getModuleURL('janus/editentity.php', array('eid' => $msg));
$pm->post('New entity created', 'Permalink: <a href="' . $directlink . '">' . $directlink . '</a><br /><br />A new entity has been created.<br />Entityid: ' . $_POST['entityid'] . '<br />Entity type: ' . $_POST['entitytype'], 'ENTITYCREATE', $user->getUid());
SimpleSAML_Utilities::redirect(SimpleSAML_Module::getModuleURL('janus/editentity.php'), array('eid' => $msg));
}
}
} else {
redirectTrustedUrl(SimpleSAML_Utilities::selfURLNoQuery(), array(), IS_AJAX);
}
}
}
}
/* END TAB ADMIN POST HANDLER *****************************************************************************************/
/* START ENTITIES POST HANDLER ****************************************************************************************/
if (isset($_POST['submit'])) {
if (!isset($_POST['csrf_token']) || !$csrf_provider->isCsrfTokenValid('entity_create', $_POST['csrf_token'])) {
SimpleSAML_Logger::warning('Janus: [SECURITY] CSRF token not found or invalid');
throw new SimpleSAML_Error_BadRequest('Missing valid csrf token!');
}
$selectedtab = SELECTED_TAB_ENTITIES;
if (!empty($_POST['entityid'])) {
$validateEntityId = $janus_config->getValue('entity.validateEntityId', true);
if (!$validateEntityId || $validateEntityId && check_uri($_POST['entityid'])) {
if (!isset($_POST['entityid']) || empty($_POST['entitytype'])) {
$msg = 'error_no_type';
$old_entityid = $_POST['entityid'];
$old_entitytype = $_POST['entitytype'];
} else {
$msg = $userController->createNewEntity($_POST['entityid'], $_POST['entitytype']);
if (is_int($msg)) {
$entity = new sspmod_janus_Entity($janus_config);
$pm->subscribe($user->getUid(), 'ENTITYUPDATE-' . $msg);
$directlink = SimpleSAML_Module::getModuleURL('janus/editentity.php', array('eid' => $msg));
$pm->post('New entity created', 'Permalink: ' . '<a href="' . htmlspecialchars($directlink) . '">' . htmlspecialchars($directlink) . '</a>' . '<br /><br />A new entity has been created.<br />' . 'Entityid: ' . htmlspecialchars($_POST['entityid']) . '<br />' . 'Entity type: ' . htmlspecialchars($_POST['entitytype']), 'ENTITYCREATE', $user->getUid());
redirectTrustedUrl(SimpleSAML_Module::getModuleURL('janus/editentity.php'), array('eid' => $msg), IS_AJAX);
}
}
} else {
} else {
$response_http = response_http(403);
}
} else {
$response_http = response_http(403);
}
break;
////////////////////////////////////////////////////////////////////////////////
// DELETE
////////////////////////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////
// DELETE
////////////////////////////////////////////////////////////////////////////////
case 'DELETE':
//check if the uri is valid
if (check_uri($uri, $valid_uri['DELETE'])) {
// generate query
switch (sizeof($loc)) {
case 2:
$query = sprintf("DELETE FROM %s WHERE id=%s", $loc[0], $loc[1]);
break;
case 3:
$query = sprintf("DELETE FROM %s WHERE %s='%s'", $loc[0], $loc[1], $loc[2]);
break;
case 5:
$query = sprintf("DELETE FROM %s WHERE %s='%s' AND %s='%s'", $loc[0], $loc[1], $loc[2], $loc[3], $loc[4]);
break;
}
$stmt = $db->prepare($query);
$stmt->execute();
$response_http = response_http(201);
// Check if user is allowed to se entity
$guard = new sspmod_janus_UIguard($janus_config->getArray('access', array()));
$allowedUsers = $mcontroller->getUsers();
if (!(array_key_exists($userid, $allowedUsers) || $guard->hasPermission('allentities', null, $user->getType(), TRUE))) {
SimpleSAML_Utilities::redirect(SimpleSAML_Module::getModuleURL('janus/index.php'));
}
$et = new SimpleSAML_XHTML_Template($config, 'janus:editentity.php', 'janus:editentity');
$language = $et->getLanguage();
$update = FALSE;
$note = '';
if (!empty($_POST)) {
// Array for collecting addresses to notify
$addresses = array();
// Change entityID
if (isset($_POST['entityid']) && $guard->hasPermission('changeentityid', $entity->getWorkflow(), $user->getType())) {
if (check_uri($_POST['entityid']) || true) {
# HACK: For SURFnetGuests : https://espee-test.surfnet.nl/federate/metadata/saml20/SURFnetGuests
$entityIdNeedsUpdating = $_POST['entityid'] != $entity->getEntityid();
if ($entityIdNeedsUpdating) {
$userController = new sspmod_janus_UserController($janus_config);
if ($userController->isEntityIdInUse($_POST['entityid'], $errorMessage)) {
$msg = $errorMessage;
} else {
if ($entity->setEntityid($_POST['entityid'])) {
$update = TRUE;
$note .= 'Changed entityID: ' . $_POST['entityid'] . '<br />';
$addresses[] = 'ENTITYUPDATE-' . $eid . '-CHANGEENTITYID';
}
}
}
} else {
