* @version 0.1 - Aug 25 2006
*/
//error_reporting(E_ALL);
require_once('../../../../wp-config.php');
require_once('clsParseXML.php');
array('•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•', '•');
array('A', 'A', 'A', 'A', 'A', 'A', 'AE', 'C', 'E', 'E', 'E', 'E', 'I', 'I', 'I', 'I', 'ETH', 'N', 'O', 'O', 'O', 'O', 'O', 'O', 'U', 'U', 'U', 'U', 'Y', 'ss', 'a', 'a', 'a', 'a', 'a', 'a', 'ae', 'e', 'e', 'e', 'e', 'e', 'i', 'i', 'i', 'i', 'eth', 'n', 'o', 'o', 'o', 'o', 'o', 'o', 'u', 'u', 'u', 'u', 'y', 'y');
class Scrib_importer{
private function prep_xml($xmlsrc, $is_string = NULL) {
if ($is_string) {
$xmlraw = $xmlsrc;
} else {
$xmlraw = utf8_encode(file_get_contents($xmlsrc));
}
// This is where we compensate for stoned XML
$xmlraw = preg_replace('%>[#&\x80-\xFF](.*?)<\/%s', '>GarbageDataget_var("SELECT post_id FROM $btaggy->meta_table WHERE tag_type = 'sourceid' AND tag_small = '$sourceid'");
}
public function insertharvest($bibr) {
global $wpdb, $scrib;
$wpdb->get_results("REPLACE INTO $scrib->harvest_table
(source_id, harvest_date, imported, content)
VALUES ('". $wpdb->escape($bibr['the_sourceid']) ."', NOW(), 0, '". $wpdb->escape(serialize($bibr)) ."')");
echo "harvested source_id {$bibr['the_sourceid']}
";
return;
}
public function insertpost($bibr){
global $bsuite, $btaggy, $wpdb;
if($this->post_exists($bibr['the_sourceid']))
$postdata['ID'] = self::post_exists($bibr['the_sourceid']);
$postdata['post_title'] = $wpdb->escape(str_replace('\"', '"', $bibr['the_title']));
$postdata['post_date'] = $bibr['the_pubdate'];
$postdata['post_date_gmt'] = $bibr['the_acqdate'];
$postdata['comment_status'] = get_option('default_comment_status');
$postdata['ping_status'] = get_option('default_pingback_flag');
$postdata['post_status'] = 'publish';
$postdata['post_type'] = 'scrib';
$postdata['post_content'] = $wpdb->escape(str_replace('\"', '"', $bibr['the_content']));
$postdata['post_excerpt'] = $wpdb->escape(str_replace('\"', '"', $bibr['the_excerpt']));
$postdata['post_author'] = 0;
$post_id = wp_insert_post($postdata);
$btaggy->taggy_update($post_id, $bibr['the_content']);
$bsuite->searchsmart_upindex($post_id, $wpdb->escape($bibr['the_content']));
if($postdata['ID']){
echo "Updated post_id $post_id / source_id {$bibr['the_sourceid']} · ";
}else{
echo "Inserted post_id $post_id / source_id {$bibr['the_sourceid']} · ";
}
/*
if(SCRIB_DEBUG){
echo '
';
print_r($bibr);
echo '
';
}
*/
return($post_id);
}
public function get_altisbn($isbn) {
$result = array();
// OCLC's xISBN
// http://www.oclc.org/research/projects/xisbn/
$xmlopacurl = 'http://labs.oclc.org/xisbn/' . $isbn;
$xml = self::prep_xml($xmlopacurl);
foreach ($xml->xpath('/idlist/isbn') as $temp) {
$result[] = (string) $temp;
}
// the first element of the array is always the same as the query ISBN, delete it
array_shift($result);
/*
// LibraryThing's thingISBN
// http://www.librarything.com/thingology/2006/06/introducing-thingisbn_14.php
$xmlopacurl = 'http://www.librarything.com/api/thingISBN/' . $isbn;
$xml = self::prep_xml($xmlopacurl);
foreach ($xml->xpath('/idlist/isbn') as $temp) {
$result[] = (string) $temp;
}
*/
return($result);
}
public function enrich($isbn_list){
foreach($isbn_list as $isbn){
//echo $isbn . "
\n";
// there's an ugly hack/work around below. For some reason the API server is returning crunk at the head of the serialized result. I'm removing it with substring, but i should fix it at the source.
$record = unserialize(substr(file_get_contents('http://api.scriblio.net/v01a/enrich/?isbn='. $isbn),3));
if($record['status']){
return($record);
}
}
}
}
?>