<?php

// It may take a whils to crawl a site ...
set_time_limit(10000);

// Inculde the phpcrawl-mainclass
include("PHPCrawl/libs/PHPCrawler.class.php");

// Extend the class and override the handleDocumentInfo()-method
class MyCrawler extends PHPCrawler
{
  function handleDocumentInfo($DocInfo)
  {
    // Just detect linebreak for output ("\n" in CLI-mode, otherwise "<br>").
    if (PHP_SAPI == "cli") $lb = "\n";
    else $lb = "<br />";

    // Print the URL and the HTTP-status-Code
    echo "Page requested: ".$DocInfo->url." (".$DocInfo->http_status_code.")".$lb;
    if($DocInfo->http_status_code==505) {
        echo "Error_code: ".$DocInfo->error_code.$lb."Occured: ".$DocInfo->error_occured.$lb."String: ".$DocInfo->error_string.$lb;
        echo $DocInfo->header_send.$lb;
    }
    echo "File: ".$DocInfo->file.$lb;
    echo "C: ".$DocInfo->content_type." (size: ".strlen($DocInfo->content).").".$lb;

    // Print if the content of the document was be recieved or not

    // Now you should do something with the content of the actual
    // received page or file ($DocInfo->source), we skip it in this example

    echo $lb;

    flush();
  }
}

// Now, create a instance of your class, define the behaviour
// of the crawler (see class-reference for more options and details)
// and start the crawling-process.

$crawler = new MyCrawler();

// URL to crawl
$crawler->setURL("http://www.lidingo.se/toppmeny/stadpolitik/handlingarochprotokoll/sammantraden.html");

// Only receive content of files with content-type "text/html"
$crawler->addContentTypeReceiveRule("#text/html#");
$crawler->addContentTypeReceiveRule("#application/pdf#");

$crawler->addURLFollowRule("#handlingarochprotokoll|lexportlet#");

// Ignore links to pictures, dont even request pictures
$crawler->addURLFilterRule("#\.(jpg|jpeg|gif|png)$|print# i");

// Store and send cookie-data like a browser does
$crawler->enableCookieHandling(true);

$crawler->setPageLimit(400);


// Set the traffic-limit to 1 MB (in bytes,
// for testing we dont want to "suck" the whole site)
//$crawler->setTrafficLimit(1000 * 1024);

// Thats enough, now here we go
$crawler->go();

// At the end, after the process is finished, we print a short
// report (see method getProcessReport() for more information)
$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".$lb;
echo "Process runtime: ".$report->process_runtime." sec".$lb;
?>