dema501

Hertry:
Вот нашел на одном форуме такую тему, скажите, это то?

RewriteEngine On
RewriteCond %{HTTP_USER_AGENT} ^Web.Downloader.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^FAST.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^HTTPClient.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^DISCo\Pump.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Drip.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^EirGrabber.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^FlashGet.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^GetRight.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Gets.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Grafula.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^IBrowse.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^InterGET.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Internet\Ninja.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^JetCar.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^JustView.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^MIDown\tool.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Mister\PiX.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^NearSite.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^NetSpider.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Offline\Explorer.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^PageGrabber.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Papa\Foto.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Pockey.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^ReGet.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Slurp.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^SpaceBison.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^SuperHTTP.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Teleport.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebAuto.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebCopier.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebFetch.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebReaper.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebSauger.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebStripper.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebWhacker.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^WebZIP.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Web\Image\Collector.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Web\Sucker.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Webster.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^Wget.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^eCatch.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^ia_archiver.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^lftp.* [OR]
RewriteCond %{HTTP_USER_AGENT} ^tAkeOut.*
RewriteRule \.(gif|jpg|php|htm|html|shtm|shtml)$ /error.ico.[L]

dzutaro:
Долго искал такой скрипт, но нашел только плагин для WordPress,
похожей направленности, но для других нужд.

Переделал под свои :)

function get_domain_name_from_uri($uri)

{

	preg_match("/^(http:\/\/)?([^\/]+)/i", $uri, $matches);

	$host = $matches[2];

	preg_match("/[^\.\/]+\.[^\.\/]+$/", $host, $matches);

	return $matches[0];

}



function is_external_link($link, $HOST)

{

	return (get_domain_name_from_uri($link) != get_domain_name_from_uri($HOST));

}



function get_external_links_cnt($uri)

{

	$ExternalLinksCnt = 0;

	$Pattern          = '/<a (.*?)href="(.*?)\/\/(.*?)"(.*?)>(.*?)<\/a>/i';

	$Matches          = array();



	if (FALSE === $Content = file_get_contents($uri))

	{

		return FALSE;

	}



	preg_match_all($Pattern, $Content, $Matches);



	foreach($Matches[3] as $Link)

	{

		if (is_external_link($Link, $uri))

		{

			++$ExternalLinksCnt;

		}

	}



	unset($Content);

	unset($Matches);



	return $ExternalLinksCnt;

}



$url = 'http://history.ru/';

echo get_external_links_cnt($url);