/**
* @brief Populate record for one name with details from ION web site using screen scraping
*
* @param item ION record
*
*/
function ion_process(&$item)
{
$debug = true;
$url = $item->link;
//echo $url . "\n";
$html = get($url);
//echo $html;
$author = '';
// extract
$matches = array();
if (preg_match('/<\\/h1><p>(.*)<\\/p><div class="documentContent">/', $html, $matches)) {
//print_r($matches);
$author = html_entity_decode($matches[1]);
if (preg_match('/(.*)<\\/li>/', $author)) {
$pos = strpos($author, "<");
if ($pos != false) {
$author = substr($author, 0, $pos);
}
}
$item->taxonAuthor = $author;
//echo "author=$author\n";
}
// if (preg_match('/<h4>Original Description Reference<\/h4><ul><li>(.*)\s*\[Zoological/', $html, $matches))
if (preg_match('/<h3>Original Description Reference<\\/h3><ul><li>([^<]+|(?R))*<\\/li>/', $html, $matches)) {
//print_r($matches);
$description = html_entity_decode($matches[1]);
$item->full_publication = $description;
if (preg_match('/(.*)\\[Zoological Record/', $description)) {
$pos = strpos($description, "[Zoological Record");
if ($pos != false) {
$description = substr($description, 0, $pos);
}
}
// Remove article title
$description = trim(str_replace($item->publicationTitle, '', $description));
//echo "description=$description\n";
$item->full_publication = $description;
//Natuurwetenschappelijke Studiekring voor Suriname en de Nederlandse Antillen, No. 112 1984: 1-167.
// Extract bibliographic details
if (parse_ion_ref($description, $matches)) {
//print_r($matches);
$item->publication->journal = $matches['journal'];
$item->publication->volume = $matches['volume'];
$item->publication->issue = $matches['issue'];
$item->publication->year = $matches['year'];
$item->publication->spage = $matches['spage'];
$item->publication->epage = $matches['epage'];
$item->publication->date = $matches['date'];
$item->publication->actualyear = $matches['actualyear'];
if (isset($item->publication->date)) {
$d = format_date($item->publication->date);
if ($d != '') {
$item->publication->yyyy_mm_dd = $d;
}
}
}
}
// Do stuff for this record... (such as get DOI if it exists)
if (isset($item->publication->journal) && isset($item->publication->volume) && isset($item->publication->spage)) {
$url = 'http://bioguid.info/openurl?genre=article' . '&title=' . urlencode($item->publication->journal) . '&volume=' . $item->publication->volume . '&spage=' . $item->publication->spage . '&display=json';
$j = json_decode(get($url));
if ($debug) {
print_r($j);
}
if ($j->status == 'ok') {
if (isset($j->doi)) {
$item->publication->doi = $j->doi;
}
if (isset($j->pmid)) {
$item->publication->pmid = $j->pmid;
}
if (isset($j->hdl)) {
$item->publication->hdl = $j->hdl;
}
if (isset($j->url)) {
$item->publication->url = $j->url;
}
}
}
// Store
store_item($item);
}
$item->doi = $j->doi;
}
if (isset($j->pmid)) {
$item->pmid = $j->pmid;
}
if (isset($j->hdl)) {
$item->hdl = $j->hdl;
}
if (isset($j->url)) {
$item->url = $j->url;
}
}
}
}
print_r($item);
$item_id = store_item($item);
// if ($item->pmid != '') exit();
//-----------------------------------------------------------------------------------------------
// Handle names
// keywords are taxon names uBio has extracted from articles/abstracts
foreach ($item->keywords as $k) {
echo $k, "\n";
}
// Do our thang
$annotations = extract_new_names(strip_tags($item->title), $item->keywords);
echo "Names--------------------\n";
print_r($annotations);
// store names
foreach ($annotations as $k => $v) {
// lookup name
$namebankID = 0;