function philosophize($next_page, $rand)
{
// create URL by concatenating the part of the address common to all articles
// with the particular article title
$url = "http://en.wikipedia.org/wiki/" . $next_page;
// load html into a string
$aContext = array('http' => array('proxy' => 'tcp://10.2.20.18:9090', 'request_fulluri' => true));
$cxContext = stream_context_create($aContext);
$source = file_get_contents($url, False, $cxContext);
if (strcasecmp(substr($source, 0, 15), "<!DOCTYPE html>") != 0) {
$source = gzdecoder($source);
}
if ($source === false) {
return false;
}
$title = gettitle($source);
unset($next_page);
// Magic!
$next = scrape($source, 0);
if ($next === false) {
return false;
}
return ["next" => $next, "title" => $title, "rand" => $rand == true ? str_replace(' ', '_', $title) : null];
}
function sd_finallink($curl_content)
{
$regex = '/"sd_src_no_ratelimit":"([^"]+)"/';
if (preg_match($regex, $curl_content, $match1)) {
$str = preg_replace_callback('/\\\\u([0-9a-f]{4})/i', 'replace_unicode_escape_sequence', $match1[1]);
$decodedStr = str_replace('\\/', '/', $str);
return $decodedStr;
} else {
return;
}
}
function gettitle($curl_content)
{
$regex = "/title id=\"pageTitle\">(.+?)<\\/title>/";
if (preg_match($regex, $curl_content, $title_match)) {
$title_match = explode("|", $title_match[1]);
return $title_match[0];
} else {
return;
}
}
$hdlink = hd_finallink($data);
$sdlink = sd_finallink($data);
$title = gettitle($data);
$message = array();
if ($sdlink != "") {
$message = array('type' => 'success', 'title' => $title, 'hd_download_url' => $hdlink, 'sd_download_url' => $sdlink);
} else {
$message = array('type' => 'failure', 'message' => 'Error retrieving the download link for the url. Please try again later');
}
echo json_encode($message);
}
if ($end == '.jp2' || $end == '.tif') {
// get basename
$base = basename($dfil, $end);
$seqdir = getseqdir($base);
$dirname = getdirname($base);
print "Now working with {$dirname}...\n";
// find seq
$s = explode('/', $seqdir);
$seq = $s[1];
$newdir = './' . $seqdir;
$new = './' . $seqdir . "/" . 'OBJ' . $end;
// what is xbase xml of this image
$thisxml = getdirname($base) . ".xml";
// get booktitle specific to this image
$booktitle = gettitle($thisxml, $meta);
// encode entities
$booktitle = htmlentities($booktitle, ENT_QUOTES, 'UTF-8');
// make mods.xml
$pagexml = <<<EOL
<?xml version="1.0" encoding="UTF-8"?>
<mods:mods xmlns:mods="http://www.loc.gov/mods/v3" xmlns="http://www.loc.gov/mods/v3">
<mods:titleInfo>
<mods:title>{$booktitle} : page {$seq}</mods:title>
</mods:titleInfo>
</mods:mods>
EOL;
// switch contexts to fix syntax highlighting
$mfile = $seqdir . "/" . "MODS.xml";
print "Writing MODS.xml\n";
file_put_contents($mfile, $pagexml);
