brittainmedia/phpcrawl

This package is abandoned and no longer maintained. No replacement package was suggested.

PHPCrawl is a webcrawler/webspider-library written in PHP. It supports filters, limiters, cookie-handling, robots.txt-handling, multiprocessing and much more.

0.10.1 2023-04-19 21:40 UTC

GPL-2.0

README

phpcrawl

composer require brittainmedia/phpcrawl

use PHPCrawl\Enums\PHPCrawlerAbortReasons;
use PHPCrawl\Enums\PHPCrawlerMultiProcessModes;
use PHPCrawl\Enums\PHPCrawlerUrlCacheTypes;
use PHPCrawl\PHPCrawler;
use PHPCrawl\PHPCrawlerDocumentInfo;

// New custom crawler
$crawler = new class() extends PHPCrawler {

    /**
     * @param $PageInfo
     * @return int
     */
    function handleDocumentInfo($PageInfo): int
    {
        // Print the URL of the document
        echo "URL: " . $PageInfo->url . PHP_EOL;

        // Print the http-status-code
        echo "HTTP-statuscode: " . $PageInfo->http_status_code . PHP_EOL;

        // Print the number of found links in this document
        echo "Links found: " . count($PageInfo->links_found_url_descriptors) . PHP_EOL;

        // ..

        // continue crawling
        return 1;
    }
};

$crawler->setURL($url = 'https://bbc.co.uk/news');

// Optional
//$crawler->setProxy($proxy_host, $proxy_port, $proxy_username, $proxy_password);

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

// Ignore links to ads...
$advertFilterRule = "/\bads\b|2o7|a1\.yimg|ad(brite|click|farm|revolver|server|tech|vert)|at(dmt|wola)|banner|bizrate|blogads|bluestreak|burstnet|casalemedia|coremetrics|(double|fast)click|falkag|(feedster|right)media|googlesyndication|hitbox|httpads|imiclk|intellitxt|js\.overture|kanoodle|kontera|mediaplex|nextag|pointroll|qksrv|speedera|statcounter|tribalfusion|webtrends/";
$crawler->addURLFilterRule($advertFilterRule);

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

// Limits set, successfully retrieved only
$crawler->setRequestLimit(1);

/**
 * 3 - The crawler only follows links to pages or files located in or under the same path like the one of the root-url.</b>
 * E.g. if the root-url is
 * "http://www.foo.com/bar/index.html",
 * the crawler will follow links to "http://www.foo.com/bar/page.html" and "http://www.foo.com/bar/path/index.html",
 * but not links to "http://www.foo.com/page.html".
 *
 */
$crawler->setFollowMode(3);

// Keep going until resolved
$crawler->setFollowRedirectsTillContent(TRUE);

// tmp directory
$crawler->setWorkingDirectory(sys_get_temp_dir() . DIRECTORY_SEPARATOR . 'phpcrawl' .DIRECTORY_SEPARATOR);

// Cache
$crawler->setUrlCacheType(PHPCrawlerUrlCacheTypes::URLCACHE_MEMORY);

// File crawling - Store to file or set limit for large files
#$crawler->addStreamToFileContentType('##');
#$crawler->setContentSizeLimit(500000); // Google only crawls pages 500kb and below?

//Decides whether the crawler should obey "nofollow"-tags, we will obey
$crawler->obeyNoFollowTags(true);

//Decides whether the crawler should obey robot.txt, we will not obey!
$crawler->obeyRobotsTxt(false);

// Delay to stop blocking
$crawler->setRequestDelay(0.5);

// fake browser or use fake robot one
$crawler->setUserAgentString('Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:70.0) Gecko/20100101 Firefox/70.0');

// Multiprocess (optional) - Forces PHPCrawlerUrlCacheTypes::URLCACHE_SQLITE use, must have link priorities!
$crawler->addLinkPriority("/news/", 10);
$crawler->addLinkPriority("/\.jpeg/", 5);
$crawler->goMultiProcessed(PHPCrawlerMultiProcessModes::MPMODE_CHILDS_EXECUTES_USERCODE);

// 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();

echo 'Finished crawling site: ' . $url . PHP_EOL;
echo 'Summary:' . PHP_EOL;
echo 'Links followed: ' . $report->links_followed . PHP_EOL;
echo 'Documents received: ' . $report->files_received . PHP_EOL;
echo 'Bytes received: ' . $report->bytes_received . ' bytes' . PHP_EOL;
echo 'Process runtime: ' . $report->process_runtime . ' sec' . PHP_EOL;
echo 'Process memory: ' . $report->memory_peak_usage . ' sec' . PHP_EOL;
echo 'Server connect time: ' . $report->avg_server_connect_time . ' sec' . PHP_EOL;
echo 'Server response time: ' . $report->avg_server_response_time . ' sec' . PHP_EOL;
echo 'Server transfer rate: ' . $report->avg_proc_data_transfer_rate . ' bytes' . PHP_EOL;

$abortReason = $report->abort_reason;
switch ($abortReason) {
    case PHPCrawlerAbortReasons::ABORTREASON_PASSEDTHROUGH:
        echo 'Crawling-process aborted because everything is done/passed through.' . PHP_EOL;
        break;
    case PHPCrawlerAbortReasons::ABORTREASON_TRAFFICLIMIT_REACHED:
        echo 'Crawling-process aborted because the traffic limit set by user was reached.' . PHP_EOL;
        break;
    case PHPCrawlerAbortReasons::ABORTREASON_FILELIMIT_REACHED:
        echo 'Crawling-process aborted because the file limit set by user was reached.' . PHP_EOL;
        break;
    case PHPCrawlerAbortReasons::ABORTREASON_USERABORT:
        echo 'Crawling-process aborted because the handleDocumentInfo-method returned a negative value.' . PHP_EOL;
        break;
    default:
        echo 'Unknown abort reason.' . PHP_EOL;
        break;

}

Initially just a copy of http://phpcrawl.cuab.de/ forked from mmerian for using with composer.

Due to the main project now seemingly being abandoned (having no updates for 4 years) I am going to proceed to make any changes/fixes in this repository.

Latest updates

• 0.9 compatible PHP 7 Only.
• 0.10 compatible PHP 8. (Submit issues)
• Introduced namespaces
• Lots of bug fixes
• Refactored various class sections

Now archived...