$crawler = new MyCrawler();
$crawler->setURL("www.php.net");
$crawler->addContentTypeReceiveRule("#text/html#");
$crawler->addURLFilterRule("#\\.(jpg|jpeg|gif|png)\$# i");
$crawler->setPageLimit(50);
// Set the page-limit to 50 for testing
// Important for resumable scripts/processes!
$crawler->enableResumption();
// At the firts start of the script retreive the crawler-ID and store it
// (in a temporary file in this example)
if (!file_exists("/tmp/mycrawlerid_for_php.net.tmp")) {
$crawler_ID = $crawler->getCrawlerId();
file_put_contents("/tmp/mycrawlerid_for_php.net.tmp", $crawler_ID);
} else {
$crawler_ID = file_get_contents("/tmp/mycrawlerid_for_php.net.tmp");
$crawler->resume($crawler_ID);
}
// Start crawling
$crawler->goMultiProcessed(5);
// Delete the stored crawler-ID after the process is finished completely and successfully.
unlink("/tmp/mycrawlerid_for_php.net.tmp");
$report = $crawler->getProcessReport();
if (PHP_SAPI == "cli") {
$lb = "\n";
} else {
$lb = "<br />";
}
echo "Summary:" . $lb;
echo "Links followed: " . $report->links_followed . $lb;
echo "Documents received: " . $report->files_received . $lb;
echo "Bytes received: " . $report->bytes_received . " bytes" . $lb;
