PHP scraperWiki::get_var方法代码示例

        }
    }
}
function getData($query)
{
    if (!count(scraperwiki::table_info("swdata"))) {
        return false;
    }
    return scraperWiki::select($query);
}
if (!count(scraperwiki::table_info("swvariables"))) {
    // if no stored variables are available, start from beginning
    $start = '';
} else {
    // else, load last disease from database
    $start = scraperWiki::get_var('disease', '');
}
$html = scraperWiki::scrape("http://www.who.int/csr/don/archive/disease/en/index.html");
$dom = new simple_html_dom();
$dom->load($html);
$handleNextEntry = false;
// no previous entries -> start from beginning
if ($start == '') {
    $handleNextEntry = true;
} else {
    print "starting after: {$start}\n\n";
}
foreach ($dom->find("ul[@class='a_z'] li a") as $data) {
    $disease = trim($data->plaintext);
    print "fetching data for disease: {$disease}";
    if ($handleNextEntry) {

$synthList3 = file_get_contents("https://api.scraperwiki.com/api/1.0/datastore/sqlite?format=jsondict&name=current_synths&query=select%20DISTINCT%20manufacturer%2C%20url%2C%20name%20from%20%60swdata%60");
if (!empty($synthList3)) {
    $synthList3 = json_decode($synthList3);
}
$synths = array();
$synths = traverseList($synthList1);
$synths = array_merge(traverseList($synthList2), $synths);
$synths = array_merge(traverseList($synthList3), $synths);
$synths = array_map('unserialize', array_unique(array_map('serialize', $synths)));
echo "Total synths: " . count($synths) . "\n";
//var_dump($synths);
if (!empty($synths)) {
    //$dbName = "vintagesynth-scrape-".$today = date("m-d-Y");
    $saveMessage = scraperWiki::save_sqlite(array('manufacturer', 'name', 'url'), $synths);
    //print strval($saveMessage);
    scraperwiki::save_var('total_results', count($synths));
    print scraperWiki::get_var('total_results');
}
function traverseList($list)
{
    $dataList = array();
    foreach ($list as $item) {
        //Clean up the data
        foreach ($item as $key => $value) {
            $item->{$key} = preg_replace("/<*.>/", "", $value);
            //echo $item->$key."\n";
        }
        $dataList[] = $item;
    }
    return $dataList;
}

        scraperwiki::save(array('EMISNumber'), $tosave);
    } catch (Exception $e) {
        print 'Caught exception (' . $data->value . '): ' . $e->getMessage() . "\n";
    }
    //break; //uncomment to just process one school
}
scraperWiki::save_var('place', 'none');
$html = scraperWiki::scrape("http://wcedemis.pgwc.gov.za/wced/findschoolO.shtml?2");
require 'scraperwiki/simple_html_dom.php';
$dom = new simple_html_dom();
$dom->load($html);
//scraperwiki::sqliteexecute("CREATE TABLE `swdata` (`EMISNumber` text)");
//scraperWiki::save_var('place','none');
//scraperWiki::save_var('place','0130333352');
//exit();
$place = scraperWiki::get_var('place', 'none');
$resume = true;
if ($place == 'none') {
    $resume = false;
}
foreach ($dom->find("select[name='EMIS_NO'] option") as $data) {
    //loop through the list of ordinary schools
    $d = http_build_query(array('EMIS_NO' => $data->value));
    $dlength = strlen($d);
    if ($resume) {
        //we need to resume, so find the correct place
        if ($place == $data->value) {
            $resume = false;
        } else {
            continue;
        }