$filename = 'afd.ris';
$filename = '296e26ee-ce62-4efa-8f80-a7a037570a45.ris';
//$filename = '757e3d6a-bbcc-4573-8de3-210c611dc93d.ris';
$filename = '8f5f6ff0-6dcc-49f6-bb7c-60a8325ee210.ris';
$filename = '03811041-933f-4bd1-9b52-44a09d5fcf2e.ris';
$filename = 'c202c04e-3c81-4a8e-a648-1ea83db1cd21.ris';
$filename = 'b72ae515-9c9e-49df-b3f1-936c7c2e3833.ris';
$filename = '21bc7535-4317-4ce0-a287-e13e47efabbe.ris';
$filename = 'b8d89012-9059-4af0-a0a1-093cb69103e8.ris';
$filename = 'c7ae0257-fb30-4e4d-adfd-e68724df0b69.ris';
$filename = 'bd6ed9f5-0edd-4be8-8e39-a8754d8a1985.ris';
$filename = 'db86c064-6846-42c9-81a9-e7d9a1d3fbd0.ris';
$filename = '8da39a69-b913-40ce-a32b-c0bda72cabfc.ris';
// Geo
$filename = '7eb47f5d-f491-45b8-84ef-00a1f7cbf3c8.ris';
$filename = 'e08b6613-7add-4f2e-b934-9869b1d68884.ris';
$filename = 'bc2438b9-9840-45fb-a549-27a934cf1462.ris';
$filename = 'd47ad5f4-08d8-4893-96b0-a4c492077dbe.ris';
$filename = 'c696c01d-88d3-449c-b392-ea592474bec7.ris';
$filename = 'b23c9277-e4d9-48ef-84d1-a124812d7dcb.ris';
$filename = '2fb8db9d-e944-4a5d-8938-3c8e98008d20.ris';
// addme-2010-12-06
$filename = 'addme-2010-12-06.ris';
// 2011-01-10 (first result from checkparse)
$filename = '2011-01-10.ris';
// Import a RIS file and add to CouchDB database
$file = @fopen($filename, "r") or die("couldn't open {$filename}");
$ris = @fread($file, filesize($filename));
fclose($file);
import_ris($ris, 'couchdb_import');
$html[$reference->year] .= '<div>';
$html[$reference->year] .= '<a href="' . $reference->url . '" target="_new"><img src="http://biostor.org/bhl_image.php?PageID=' . $PageID . '&thumbnail" /></a><br/>';
$html[$reference->year] .= '<a href="http://www.biodiversitylibrary.org/page/' . $PageID . '" target="_new">' . $PageID . '</a><br/>';
$html[$reference->year] .= $reference->title . '<br/>';
$html[$reference->year] .= '</div>';
}
} else {
$year_roman[$reference->year]++;
}
}
$filename = 'all.ris';
//$filename = 'test.ris';
$file = @fopen($filename, "r") or die("couldn't open {$filename}");
$ris = @fread($file, filesize($filename));
fclose($file);
import_ris($ris, 'import');
/*
echo "Articles in each year\n";
print_r($year_actual);
echo "Articles in each year found in BioStor\n";
print_r($year_found);
echo "Articles in each year with roman numbers\n";
print_r($year_roman);
*/
foreach ($html as $year => $h) {
$h .= '</body></html>';
$filename = $year . '.html';
$file = @fopen($filename, "w") or die("couldn't open {$filename}");
fwrite($file, $h);
fclose($file);
}
// Clean
$html = preg_replace('/<font size=-2 class="w"><b>\\[PDF\\]<\\/b><\\/font> <span class=a>►<\\/span>/', '', $html);
$html = preg_replace('/<span class=a>►<\\/span>/', '', $html);
$html = str_replace("\n", " ", $html);
//echo $html;
//exit();
$title_url = '';
// get URLs
if (preg_match('/<h3 class="r"><a href="(?<url>([^"]|(?R))*)/', $html, $matches)) {
$title_url = $matches['url'];
}
// get RIS
if (preg_match('/<a href="\\/scholar.ris\\?(?<q>.*)">Import into RefMan<\\/a>/Uu', $html, $matches)) {
//print_r($matches);
$url = 'http://scholar.google.com/scholar.ris?' . str_replace('&', '&', $matches['q']);
//echo $url;
curl_setopt($ch, CURLOPT_URL, $url);
$ris = curl_exec($ch);
if (curl_errno($ch) != 0) {
}
$ris = str_replace("\r\nER", "\r\nUR - {$title_url}\r\nER", $ris);
$ris = utf8_encode($ris);
header("Content-type: text/plain; charset=utf-8\n\n");
echo $ris;
if (preg_match('/TY \\- JOUR/', $ris)) {
if ($store) {
import_ris($ris);
echo "\r\nStored\r\n";
}
}
}
