prova con questo scrippettino:
Codice PHP:
pagina 1:
<?php
/* ------------------------------------------------------------ */
/* Spider-Sense */
/* Detects bot activity and alerts you to their presence */
/* By Shawn Raloff */
/* [url]http://www.side2.com[/url] */
/* ------------------------------------------------------------ */
/* ---------- You must set these variables ---------- */
$domain = "www.tuosito.it";
$email = "info@tuosito.it";
/* ---------- No need to edit beyond this point ---------- */
$bot = $_SERVER['HTTP_USER_AGENT'];
$page = $_SERVER['PHP_SELF'];
/* ---------- Look for bots ---------- */
ini_set("sendmail_from",'info@tuosito.it');
//mail("$email", "aaaa", "aaa");
$myFile = fopen("spider-sense.dat","r");
while(!feof($myFile))
{
$myLine = chop(fgets($myFile, 255));
list($agent,$url) = split("[|]", $myLine);
if( eregi($agent,$bot) )
{
mail("$email", "$agent detected on $domain", "$agent has crawled $page on $domain");
}
}
fclose($myFile);
//echo "[url='http://www.side2.com']Powered By Side2.com[/url]";
?>
spider-sense.dat:
Codice PHP:
AbachoBOT|[url]www.abacho.com[/url]
abcdatos_botlink|[url]www.abcdatos.com[/url]
AESOP_com_SpiderMan|[url]www.aesop.com[/url]
ah-ha.com crawler|[url]www.ah-ha.com[/url]
ia_archiver|[url]www.alexa.com[/url]
Scooter|[url]www.altavista.com[/url]
AltaVista-Intranet|[url]www.altavista.co.uk[/url]
FAST-WebCrawler|[url]www.alltheweb.com[/url]
Acoon Robot|[url]www.acoon.de[/url]
antibot|[url]www.antisearch.net[/url]
Atomz|[url]www.atomz.com[/url]
Buscaplus Robi|[url]www.buscaplus.com[/url]
CanSeek|[url]www.canseek.ca[/url]
ChristCRAWLER|[url]www.christcrawler.com[/url]
Crawler|[url]www.crawler.de[/url]
DaAdLe.com ROBOT|[url]www.daadle.com[/url]
RaBot|[url]www.daum.net[/url]
DeepIndex|[url]www.en.deepindex.com[/url]
DittoSpyder|[url]www.ditto.com[/url]
Jack|domanova.co.uk
Speedy Spider|[url]www.entireweb.com[/url]
ArchitextSpider|[url]www.excite.com[/url]
Arachnoidea|[url]www.euroseek.net[/url]
EZResult|[url]www.ezresults.com[/url]
Fast PartnerSite Crawler|[url]www.fastsearch.net[/url]
KIT-Fireball|[url]www.fireball.de[/url]
FyberSearch|[url]www.fybersearch.com[/url]
GalaxyBot|[url]www.galaxy.com[/url]
geckobot|[url]www.geckobot.com[/url]
GenCrawler|[url]www.gendoor.com[/url]
GeonaBot|[url]www.geona.com[/url]
Googlebot|[url]www.google.com[/url]
Aranha|[url]www.girafa.com[/url]
Slurp|[url]www.inktomisearch.com[/url]
Toutatis|hoppa.com
Hubater|[url]www.hubat.com[/url]
IlTrovatore-Setaccio|[url]www.iltrovatore.it[/url]
IncyWincy|[url]www.incywincy.com[/url]
UltraSeek|[url]www.infoseek.com[/url]
Mole2|[url]www.intags.de[/url]
MP3Bot|mp3bot.de
C-PBWF-ip3000.com-crawler|[url]www.ip3000.com[/url]
kuloko-bot|[url]www.kuloko.com[/url]
LNSpiderguy|[url]www.lexis-nexis.com[/url]
NetResearchServer|[url]www.look.com[/url]
MantraAgent|[url]www.looksmart.com[/url]
NetResearchServer|[url]www.loopimprovements.com[/url]
Lycos_Spider|[url]www.lycos.com[/url]
JoocerBot|[url]www.joocer.com[/url]
HenryTheMiragoRobot|[url]www.mirago.co.uk[/url]
mozDex|[url]www.mozdex.com[/url]
MSNBOT|search.msn.com
Gulliver|[url]www.northernlight.com[/url]
ObjectsSearch|[url]www.objectssearch.com[/url]
PicoSearch|[url]www.picosearch.com[/url]
PJspider|[url]www.portaljuice.com[/url]
DIIbot|[url]www.powerinter.net[/url]
nttdirectory_robot|navi.ocn.ne.jp
NationalDirectory-SuperSpider|[url]www.nationaldirectory.com[/url]
Openfind piranha,Shark|[url]www.openfind.com[/url]
psbot|[url]www.picsearch.org[/url]
CrawlerBoy Pinpoint.com|[url]www.pinpoint.com[/url]
AlkalineBOT|[url]www.vestris.com[/url]
Fluffy the spider|[url]www.searchhippo.com[/url]
Scrubby|[url]www.scrubtheweb.com[/url]
asterias|[url]www.singingfish.com[/url]
Kototoi|[url]www.s.u-tokyo.ac.jp[/url]
Searchspider|[url]www.searchspider.com[/url]
SightQuestBot|[url]www.sightquest.com[/url]
Spider_Monkey|[url]www.spidermonkey.ca[/url]
Surfnomore Spider|[url]www.surfnomore.com[/url]
[email]Robot@SuperSnooper.Com[/email]|[url]www.supersnooper.com[/url]
teoma|[url]www.teoma.com[/url]
Teradex_Mapper|mapper.teradex.com
ESISmartSpider|[url]www.travel-finder.com[/url]
Spider TraficDublu|[url]www.traficdublu.ro[/url]
Tutorial Crawler|[url]www.tutorgig.com[/url]
UK Searcher Spider|[url]www.uksearcher.co.uk[/url]
Vivante Link Checker|[url]www.vivante.com[/url]
appie|[url]www.walhello.com[/url]
Nazilla|[url]www.websmostlinked.com[/url]
[url]www.WebWombat.com.au[/url]|[url]www.webwombat.com.au[/url]
marvininfoseek|[url]www.webseek.de[/url]
MuscatFerret|[url]www.webtop.com[/url]
WhizBang! Lab|[url]www.whizbanglabs.com[/url]
ZyBorg|[url]www.wisenut.com[/url]
WIRE WebRefiner|[url]www.wire.co.uk[/url]
WSCbot|[url]www.worldsearchcenter.com[/url]
Yandex|[url]www.yandex.com[/url]
Yellopet-Spider|[url]www.yellowpet.com[/url]