برای بهینه کردن سایت برای موتورهای جستجوگر نیازمند تابعی هستم که از طریق user agent بتونه موتورهای جستجو را تشخیص بده.
خیلی ممنون می شم.
Printable View
برای بهینه کردن سایت برای موتورهای جستجوگر نیازمند تابعی هستم که از طریق user agent بتونه موتورهای جستجو را تشخیص بده.
خیلی ممنون می شم.
بسم الله الرحمن الرحیم
سلام
خوب برای اینکه بتونید موتورهای جست و جو رو بشناسید باید ip وبخز های موتور های جست و جو رو هم بدست آورید / که این کار کمی مشکله
فکر می کنم یک کلاس آماده ای موجود باشه. البته از طریق متغیر http_user_agent می شه تشخیص داد!
به جواب رسیدم . من فقط اسسم موتورهای جستجو رو نیاز داشتم:
[PHP]
$bot_list = array("Teoma", "alexa","yahoo", "froogle", "Gigabot", "inktomi",
"looksmart", "URL_Spider_SQL", "Firefly", "NationalDirectory",
"Ask Jeeves", "TECNOSEEK", "InfoSeek", "WebFindBot", "girafabot",
"crawler", "www.galaxy.com", "Googlebot", "Scooter", "Slurp",
"msnbot", "appie", "FAST", "WebBug", "Spade", "ZyBorg", "rabaz",
"Baiduspider", "Feedfetcher-Google", "TechnoratiSnoop", "Rankivabot",
"Mediapartners-Google", "Sogou web spider", "WebAlta Crawler");
function detect_search_bot()
{
global $bot_list;
foreach($bot_list as $bot)
{
if(ereg($bot, $_SERVER['HTTP_USER_AGENT']))
{
$thebot = $bot;
}
}
if ($thebot)
{
return $thebot;
}
return NULL;
}
[/PHP]
یعنی ما اینهمه Agent داریم!!!
ولی فکر میکنم جای Yahoo خالیه. شاید Slurp ای که شما نوشتین باشه ولی فکر میکنم اسمش Yahoo! slurp ه یا !!
راست می گی یاهو یادم رفته. اصلاح شد!
ولی در مورد Yahoo! slurp نمی دونم!
نه یه گوگل زدم همونطور که فکر میکردم اسمش Yahoo! Slurp ه نه yahoo
راستی یه چیز یادم رفت بگم!
به این لینک سر بزنید لیست تمام user agent ها رو جمع آوری کرده یعنی میشه گفت یه رفرنس کامله
مثلآ واسه خود یاهو رو چند تا معرفی کرده یه نمونش روبوت ژاپنشه.
واسه Seo چیز خوبیه.
حتمآ ببینید
در ضمن به راهنماشون هم نگاه کنید که کدومش Spider،robot،crawler و کدومشون Spam / bad botکد:http://www.user-agents.org
این هم آرایه agent های کامل:
[PHP]
/**
* detect to search engine robots
* @return boolean
*/
function detect_search_engine_bot()
{
$bot_list = array(
"adsacomponent (postmaster@cnds.ucd.ie)",
"mozilla/2.0 (compatible; aol-iweng 3.0; win16)",
"aspseek/1.2.10",
"aspseek/1.2.11",
"aspseek/1.2.12",
"http://www.almaden.ibm.com/cs/crawler [c01]",
"http://www.almaden.ibm.com/cs/crawler [fc3]",
"http://www.almaden.ibm.com/cs/crawler [wf224]",
"http://www.almaden.ibm.com/cs/crawler [wf55]",
"amfibibot/0.06 (amfibi robot; http://www.amfibi.com; agent@amfibi.com)",
"mozilla/4.0 (search engine marketing tactics amsterdam 2002 information spider)",
"answerbus (http://www.answerbus.com/)",
"antibot-v1.1.11/i586-linux-2.2",
"antibot-v1.1.13/i586-linux-2.2",
"antibot-v1.2.0/redhat-linux-9",
"appie 1.1 (www.walhello.com)",
"argus/1.1 (nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)",
"art-online.com 0.9(beta)",
"mozilla/2.0 (compatible; ask jeeves)",
"mozilla/2.0 (compatible; ask jeeves/teoma)",
"mozilla/3.0 (compatible; avantgo 3.2)",
"bdfetch",
"bdncentral crawler v2.3 [en] (http://www.bdncentral.com/robot.html)",
"bdncentral crawler v2.3 [en] (http://www.bdncentral.com/robot.html) (x11; i; linux 2.0.44 i686)",
"baiduspider",
"baiduspider+(+http://www.baidu.com/search/spider.htm)",
"battlebot",
"big brother (http://pauillac.inria.fr/~fpottier/)",
"blogbot/1.2",
"boitho.com-dc/0.4 ( http://www.boitho.com/dcbot.html )",
"boitho.com-dc/0.5 ( http://www.boitho.com/dcbot.html )",
"boitho.com-dc/0.66 ( http://www.boitho.com/dcbot.html )",
"boitho.com-robot/1.0",
"boitho.com-robot/1.1",
"mozilla/4.0 (compatible; bordermanager 3.0)",
"braillebot 1.0",
"bruinbot (+http://webarchive.cs.ucla.edu/bruinbot.html)",
"bumblebee/1.0 (bumblebee@relevare.com; http://www.relevare.com/)",
"computer_and_automation_research_institute_crawle r (nospamspidernospam@spider.ilab.sztakinospam.hunos pam)",
"computer_and_automation_research_institute_crawle r (spider@spider.ilab.sztaki.hu)",
"cd34/0.1",
"mozilla/4.0 (compatible; cerberian drtrs version-3.0-build-41)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.0-build-43)",
"cerberiandrtrs/version-3.0-release-24",
"mozilla/4.0 (compatible; cerberian drtrs version-3.0-build-40)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.1-build-11)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.1-build-12)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.1-build-13)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.1-build-16)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.1-build-17)",
"mozilla/4.0 (compatible; cerberian drtrs version-3.2-build-0)",
"cipinetbot (http://www.cipinet.com/bot.html)",
"clushbot/2.1 (+http://www.clush.com/bot.html)",
"clushbot/3.21-binaryfury (+http://www.clush.com/bot.html)",
"clushbot/3.23-binaryfury (+http://www.clush.com/bot.html)",
"clushbot/3.24-binaryfury (+http://www.clush.com/bot.html)",
"clushbot/3.6-binaryfury (+http://www.clush.com/bot.html)",
"clushbot/3.9-binaryfury (+http://www.clush.com/bot.html)",
"commoonity lambdamoo/1.8.1",
"crawlconvera0.1 (crawlconvera@yahoo.com)",
"crawlconvera0.1 (www.authoritativeweb.com)",
"converacrawler/0.2",
"converacrawler/0.5 (+http://www",
"cosmos/0.9_(robot@xyleme.com)",
"cowbot-0.1 (nhn corp. / +82-2-3011-1954 / nhnbot@naver.com)",
"cowbot-0.1.1 (nhn corp. / +82-2-3011-1954 / nhnbot@naver.com)",
"crawl_application",
"croccrawler v3.3 [en] (http://www.croccrawler.com) (x11; i; linux 2.0.44 i686)",
"croccrawler v4.3 [en] (http://www.croccrawler.com) (x11; i; linux 2.0.44 i686)",
"custo 2.0 (www.netwu.com)",
"cydralspider/1.9 (cydral web image search; http://www.cydral.com)",
"demozulator 1.0 (macos, dmoz url check agent, trebor@animeigo.com)",
"deepindex (http://www.deepindex.com)",
"docomo/1.0/n504i/c10/tb",
"docomo/1.0/p504is/c10/tb",
"dual proxy",
"dumbot(version 0.1 beta - dumbfind.com)",
"dumbot(version 0.1 beta - http://www.dumbfind.com/dumbot.html)",
"dumbot(version 0.1 beta)",
"e-societyrobot(http://www.yama.info.waseda.ac.jp/~yamana/es/)",
"earthcom.info/1.2",
"emailsiphon",
"enterprise_search/1.00.136;mssql (http://www.innerprise.net/es-spider.asp)",
"exactseek-crawler-2.63 (crawler@exactseek.com)",
"exactseek-crawler-2.63 crawler@exactseek.com",
"exactseek-crawler-2.63-5 (crawler@exactseek.com)",
"exactseek-crawler-2.63-5 crawler@exactseek.com",
"explorer 6",
"fast enterprise crawler/6 (crawler@fast.no)",
"fast enterprise crawler/6 (www.fastsearch.com)",
"fast firstpage retriever (compatible; msie 5.5; mozilla/4.0)",
"fast-webcrawler/3.2 test",
"fast-webcrawler/3.4/partnersite (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
"fast-webcrawler/3.6 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.6/firstpage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.6/firstpage (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
"fast-webcrawler/3.7 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.7/firstpage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.8 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.8 (atw-crawler at fast dot no; http://www.alltheweb.com/help/webmaster/crawler)",
"fast-webcrawler/3.8 (crawler at trd dot overture dot com; http://www.alltheweb.com/help/webmaster/crawler)",
"fast-webcrawler/3.8/fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
"fast-webcrawler/3.x multimedia",
"fast-webcrawler/3.x multimedia (mm dash crawler at fast dot no)",
"mozilla/4.0 (compatible: fdse robot)",
"fastbug http://www.ay-up.com",
"favicon finder at http://iconsurf.com/",
"favicon monitor at http://iconsurf.com/",
"filangy/0.01-beta (filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)",
"filangy/1.01 (filangy; http://www.filangy.com/filangyinfo.jsp?inc=robots.jsp; filangy-agent@filangy.com)",
"filangy/1.01 (filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)",
"findlinks/0.71 (+http://wortschatz.uni-leipzig.de/findlinks/)",
"findlinks/0.82 (+http://wortschatz.uni-leipzig.de/findlinks/)",
"findlinks/0.87 (+http://wortschatz.uni-leipzig.de/findlinks/)",
"findlinks/0.89 (+http://wortschatz.uni-leipzig.de/findlinks/)",
"firefly/1.0 (compatible; mozilla 4.0; msie 5.5)",
"flickbot 1.1 rpt-httpclient/0.3-3",
"flickbot 2.0 rpt-httpclient/0.3-3",
"mozilla/3.0 (compatible; fluffy the spider; http://www.searchhippo.com/; info@searchhippo.com)",
"mozilla/4.0 (compatible; msie 5.0; www.galaxy.com; http://www.pgts.com.au/; +http://www.galaxy.com/info/crawler.html)",
"fyberspider (+http://www.fybersearch.com/fyberspider.php)",
"gais robot/1.1a2",
"gaisbot/3.0+(robot@gais.cs.ccu.edu.tw;+http://gais.cs.ccu.edu.tw/robot.php)",
"galaxybot/1.0 (http://www.galaxy.com/galaxybot.html)",
"gatherer/0.9",
"gazz/5.0 (gazz@nttr.co.jp)",
"generic",
"geonabot 1.0; http://www.geona.com/",
"geonabot/1.1; http://www.geona.com/",
"getright/4.5e",
"gigabot/1.0",
"mozilla/4.0 (compatible; msie 5.0; windows nt; girafabot; girafabot at girafa dot com; http://www.girafa.com)",
"goldfire server",
"googlebot/2.1 (+http://www.google.com/bot.html)",
"googlebot/2.1 (+http://www.googlebot.com/bot.html)",
"mozilla/5.0 (compatible; googlebot/2.1; +http://www.google.com/bot.html)",
"googlebot/test (+http://www.googlebot.com/bot.html)",
"googlebot-image/1.0",
"googlebot-image/1.0 (+http://www.googlebot.com/bot.html)",
"green research, inc.",
"gregbot (compatible; msie; windows; q312461)",
"mozilla/4.0 (compatible; grub-client-0.3.0; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.0.3; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.0.4; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.0.5; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.0.6; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.0.7; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.07; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.1.1; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.2.1; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.3.1; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.3.7; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.4.3; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-1.5.3; crawl your own stuff with http://grub.org)",
"mozilla/4.0 (compatible; grub-client-2.3)",
"grub-client",
"crawler [en] (compatible; crawler gulper web bot 0.2.4 www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/link/gulperbot)",
"mozilla/5.0 [en] (compatible; gulper web bot 0.2.4 www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/link/gulperbot)",
"httpconnect",
"mozilla/4.5 (compatible; httrack 3.0x; windows 98)",
"harvest-ng/1.0.2",
"hatena antenna/0.4 (http://a.hatena.ne.jp/help#robot)",
"hatena antenna/0.4 (http://a.hatena.ne.jp/help)",
"hget/0.3",
"hitwise spider v1.0 http://www.hitwise.com",
"htdig/3.1.5 (admin@ipc-opc.lan)",
"htdig/3.1.5 (unconfigured@htdig.searchengine.maintainer)",
"htdig/3.1.6 (http://computerorgs.com)",
"htdig",
"html link validator (www.lithopssoft.com)",
"httpcheck/1.0 (perl 5.006001)",
"httpget-5.2.2",
"mozilla/4.0 (compatible; ics 1.2.105)",
"ipiumbot laurion(dot)com",
"irlbot/1.0 (+http://irl.cs.tamu.edu/crawler)",
"ia_archiver",
"lcabotaccept: */*",
"ichiro/1.0 (ichiro@nttr.co.jp)",
"iconsurf/2.0 favicon monitor (see http://iconsurf.com/robot.html)",
"iltrovatore-setaccio/0.03-dev (indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio/1.2 (+http://www.iltrovatore.it/aiuto/faq.html)",
"iltrovatore-setaccio/1.2 (indexing; http://www.iltrovatore.it/bot.html; bot@iltrovatore.it)",
"iltrovatore-setaccio/1.2 (indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio/1.2 (it-bot; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio/1.2-dev (indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio (+http://www.iltrovatore.it)",
"iltrovatore-setaccio/0.3-dev (indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio/1.2 (it-bot; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
"iltrovatore-setaccio",
"imagefetch/0.1 libwww-perl/5.66",
"mozilla/3.0 (compatible; indy library)",
"inelabot/0.2 (+http://inelegant.org/bot)",
"infoseek sidewinder/1.0a",
"infoseek sidewinder/1.45 (compatible; msie 10.0; unix)",
"infoseek sidewinder/2.0b (linux 2.4 i686)",
"mozilla/3.0 (ingrid/3.0 mt; webcrawler@nospamexperimental.net; http://aanmelden.ilse.nl/?aanmeld_mode=webhints)",
"mozilla/3.0 (slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
"mozilla/5.0 (slurp/cat; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
"mozilla/5.0 (slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
"slurp/2.0 (slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
"slurp/si-emb (slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
"internetlinkagent/3.1",
"http://www.istarthere.com (spider@istarthere.com)",
"java1.4.0",
"jobo/1.3 (http://www.matuschek.net/jobo.html)",
"k2spider",
"kmcrawler",
"knowledge.com/0.2",
"knowledge.com/0.3",
"knowledge engine",
"kuloko-bot/0.2",
"lnspiderguy",
"larbin larbin2.6.2@unspecified.mail",
"larbin_2.6.2 (kalou@kalou.net)",
"larbin_2.6.2 (larbin2.6.2@unspecified.mail)",
"larbin_2.6.2 (larbin@correa.org)",
"larbin_2.6.2 (pimenas@softnet.tuc.gr)",
"larbin_2.6.2 (pimenas@systems.tuc.gr)",
"larbin_2.6.2 (sumeet_sobti@yahoo.com)",
"larbin_2.6.2 (vitalbox1@hotmail.com)",
"larbin_2.6.2 (vshelk@yahoo.com)",
"larbin_2.6.2 larbin2.6.2@unspecified.mail",
"larbin_2.6.2 larbin@correa.org",
"larbin_2.6.2 pimenas@systems.tuc.gr",
"larbin_2.6.2 sumeet_sobti@yahoo.com",
"larbin_2.6.2 vitalbox1@hotmail.com",
"larbin_2.6.3 (andreas.beder@chello.at)",
"larbin_2.6.3 (larbin-crawler@un.bewaff.net)",
"larbin_2.6.3 (larbin2.6.3@unspecified.mail)",
"larbin_2.6.3 (pimenas@softnet.tuc.gr)",
"larbin_2.6.3 larbin2.6.3@unspecified.mail",
"larbin_2.6.3_for_(http://cosco.hiit.fi/search/) (tomi.silander@hiit.fi)",
"larbin_2.6.3_for_(http://cosco.hiit.fi/search/) (tsilande@hiit.fi)",
"larbin_2.6.3_for_(http://cosco.hiit.fi/search/) tomi.silander@hiit.fi",
"larbin_2.6.3_for_(http://cosco.hiit.fi/search/) tsilande@hiit.fi",
"eseek-crawler-larbin-2.63 (crawler@exactseek.com)",
"eseek-crawler-larbin-2.63 crawler@exactseek.com",
"larbin-experimental (efp@gmx.net)",
"larbin-experimental efp@gmx.net",
"larbin (larbin2.6.2@unspecified.mail)",
"msie-5.13 (larbin@unspecified.mail)",
"msie-5.13 larbin@unspecified.mail",
"mozilla (la2@unspecified.mail)",
"mozilla la2@unspecified.mail",
"mozilla/4.0 (efp@gmx.net)",
"mozilla/4.0 efp@gmx.net",
"searchguild_dmoz_experiment (chris@searchguild.com)",
"searchguild_dmoz_experiment chris@searchguild.com",
"winampmpeg/2.00 (larbin@unspecified.mail)",
"winampmpeg/2.00 larbin@unspecified.mail",
"larbin (samualt9@bigfoot.com)",
"larbin samualt9@bigfoot.com",
"larbin_extended (larbin@oktie.com)",
"larbin_test (nobody@airmail.etn)",
"libwww-mget/1.0 libwww/5.2.8",
"/ libwww/5.3.2",
"/ libwww/5.4.0",
"libwww-perl/5.48",
"libwww-perl/5.50",
"libwww-perl/5.51",
"libwww-perl/5.52 fp/4.0",
"libwww-perl/5.53",
"libwww-perl/5.63",
"libwww-perl/5.64",
"myapp/0.1 libwww-perl/5.65",
"libwww-perl/5.65",
"rawiswar/0.1 libwww-perl/5.66",
"libwww-perl/5.68",
"vanillazilla/0.1 libwww-perl/5.69",
"libwww-perl/5.69",
"libwww-perl/5.74",
"libwww-perl/5.75",
"libwww-perl/5.76",
"libwww-perl/5.800",
"libwww-perl/5.801",
"libwww-perl/5.802",
"libwww-perl/5.803",
"perl-win32::internet/0.082",
"limebot/1.0 (+www.cruiselime.com/limebot.php)",
"linklint-checkonly/2.3.5",
"linkbot 3.0",
"linknzbot 2004/(+http://www.linknz.co.nz/robot.php)",
"linknzbot/ (+http://www.linknz.co.nz/robot.php)",
"links sql (http://gossamer-threads.com/scripts/links-sql/)",
"lite bot 0616b",
"look.com",
"lwp-trivial/1.29",
"lwp-trivial/1.35",
"lwp-trivial/1.36",
"lwp-request/2.01",
"lwp::simple/5.48",
"lwp::simple/5.65",
"lycos_spider_(modspider)",
"microsoft data access internet publishing provider cache manager",
"microsoft data access internet publishing provider dav",
"microsoft data access internet publishing provider dav 1.1",
"microsoft data access internet publishing provider protocol discovery",
"msfrontpage/4.0",
"mozilla/2.0 (compatible; ms frontpage 4.0)",
"msfrontpage/5.0",
"mozilla/2.0 (compatible; ms frontpage 5.0)",
"mozilla/4.0 (compatible; msie 5.01; windows nt 5.0; msiecrawler)",
"mozilla/4.0 (compatible; msie 5.5; windows 98; win 9x 4.90; q312461; btopenworld; msiecrawler)",
"mozilla/4.0 (compatible; msie 5.5; windows nt 4.0; msiecrawler)",
"mozilla/4.0 (compatible; msie 5.5; windows nt 5.0; msiecrawler)",
"mozilla/4.0 (compatible; msie 6.0; windows nt 5.0; q312461; msiecrawler)",
"mozilla/4.0 (compatible; msie 6.0; windows nt 5.0; matlas-2.0.2501; msiecrawler)",
"mozilla/4.0 (compatible; msie 6.0; windows nt 5.1; msiecrawler)",
"msproxy/2.0",
"msrbot/0.1 (http://research.microsoft.com/research/sv/msrbot/)",
"mediapartners-google/2.1",
"mediapartners-google/2.1 (+http://www.googlebot.com/bot.html)",
"mercator-2.0",
"metager-linkchecker",
"metacarta (crawler@metacarta.com)",
"metacarta crawler@metacarta.com",
"microsoft url control - 5.00.3609",
"microsoft url control - 5.01.4319",
"microsoft url control - 6.00.8169",
"microsoft url control - 6.00.8862",
"microsoft-atl-native/7.00",
"microsoftprototypecrawler (how's my crawling? mailto:newbiecrawler@hotmail.com)",
"moget/1.0 (moget@goo.ne.jp)",
"moget/2.1 (moget@goo.ne.jp)",
"mozdex/0.04-dev (mozdex; http://www.mozdex.com/bot.html; spider@mozdex.com)",
"mozdex/0.05-dev (mozdex; http://www.mozdex.com/bot.html; spider@mozdex.com)",
"mozilla/4.0 (compatible; netcraft web server survey)",
"msnbot/0.1 (http://search.msn.com/msnbot.htm)",
"msnbot/0.11 (+http://search.msn.com/msnbot.htm)",
"msnbot/0.3 (+http://search.msn.com/msnbot.htm)",
"msnbot/1.0 (+http://search.msn.com/msnbot.htm)",
"mozilla/3.01 (compatible;)",
"ng/1.0",
"npbot",
"npbot (http://www.nameprotect.com/botinfo.html)",
"npbot-1/2.0",
"npbot-1/2.0 (http://www.nameprotect.com/botinfo.html)",
"naverbot-1.0 (nhn corp. / +82-2-3011-1954 / nhnbot@naver.com)",
"naverbot_dloader/1.5",
"dloader(naverrobot)/1.0",
"dloader(naverrobot)/1.5",
"netants/1.25",
"netnosecrawler/v1.0",
"mozilla/4.0 (compatible; msie 5.0; netnose-crawler 2.0; a new search experience: http://www.netnose.com)",
"netresearchserver/2.4(loopimprovements.com/robot.html)",
"netresearchserver/2.5(loopimprovements.com/robot.html)",
"netresearchserver/2.7(loopimprovements.com/robot.html)",
"netresearchserver/2.8(loopimprovements.com/robot.html)",
"netresearchserver/2.9(loopimprovements.com/robot.html)",
"netresearchserver/3.4(loopimprovements.com/robot.html)",
"netresearchserver(http://www.look.com)",
"nextgensearchbot 1 (for information visit http://www.eliyon.com/nextgensearchbot)",
"none",
"nusearch spider www.nusearch.com",
"nutchcvs/0.05 (nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)",
"nutchcvs/0.05-dev (nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)",
"creativecommons/0.06-dev (nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)",
"robot: nutchcrawler, owner: wdavies@acm.org",
"nutchorg/0.03-dev (nutch; http://www.nutch.org/docs/bot.html; nutch-agent@lists.sourceforge.net)",
"owr_crawler 0.1",
"mozilla/4.0 (compatible; msie 5.5; windows nt 4.0; obot)",
"obot",
"ocelli/1.3 (http://www.globalspec.com/ocelli)",
"omniexplorer_bot/1.07 (+http://www.omni-explorer.com) internet categorizer",
"omniexplorer_bot/1.07 (+http://www.omni-explorer.com) job crawler",
"openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)",
"openbot/3.0+(robot@monkia.com.tw;+http://gais.cs.ccu.edu.tw/robot.php)",
"openfind data gatherer, openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)",
"orangebot",
"mozilla/4.0 (compatible; advanced email extractor v2.24)",
"overture-webcrawler/3.8/fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
"peerbot www.peerbot.com",
"pws.kiosk - content filtering",
"parabot (paracite@ecs.soton.ac.uk)",
"patwebbot (http://www.herz-power.de/technik.html)",
"pavuk/0.9pl28 i586-pc-cygwin",
"pavuk/0.9pl29b i686-pc-linux-gnu",
"pipeliner/0.3a (pipeline spider; http://www.pipeline-search.com/webmaster.html; webmaster@pipeline-search.com)",
"http://www.planethosting.com",
"polybot 1.0 (http://cis.poly.edu/polybot/)",
"pompos/1.1 http://pompos.iliad.fr",
"pompos/1.2 http://pompos.iliad.fr",
"pompos/1.3 http://dir.com/pompos.html",
"portal manager 0.7",
"potbot 1.0",
"prowebguide link checker (http://www.prowebguide.com)",
"program shareware 1.0.3",
"psbot/0.1 (+http://www.picsearch.com/bot.html)",
"pverify/1.2",
"qpcreep test rig ( we are not indexing, just testing )",
"quepasacreep v0.9.14",
"quepasacreep ( crawler@quepasacorp.com )",
"quepasacreep v0.9.13",
"rpt-httpclient/0.3-3",
"reifier.org (admin@reifier.org)",
"reifier.org admin@reifier.org",
"rico/0.1",
"rixbot (http://www.oops-as.no/rix/)",
"robopal (http://www.findpal.com/)",
"robotmidareru/0.7libwww-perl/5.65",
"search engine world robots.txt validator at http://www.searchengineworld.com/cgi-bin/robotcheck.cgi",
"robozilla/1.0",
"mozilla/5.0 (compatible; syclikcontrol/linkchecker;)",
"safaribookmarkchecker/1.25 (+http://www.coriolis.ch/)",
"safaribookmarkchecker/1.26 (+http://www.coriolis.ch/)",
"scooter/1.0",
"scooter-ars-1.1",
"scooter-3.0.fs - altavista.com",
"scooter-3.2",
"scooter-3.2.bt",
"scooter-3.2.ex",
"scooter-3.2.fnr",
"scooter-3.2.pdf",
"scooter-3.2.sf0",
"scooter-3.2.tx.fnr",
"scooter-3.2.xx0",
"scooter/3.2",
"scooter/3.2.sf0",
"scooter_x0-3.2.ex",
"scooter/3.3",
"scooter/3.3.qa",
"scooter/3.3.qa.pczukor",
"scooter/3.3.vscooter",
"scooter/3.3_sf",
"scrubby/2.1 (http://www.scrubtheweb.com/abs/meta-check.html)",
"scrubby/2.2 (http://www.scrubtheweb.com/)",
"search agent 1.0",
"searchspider.com/1.1",
"seekbot/1.0 (http://www.seekbot.net/bot.html) httpfetcher/0.3",
"seekbot/1.0 (http://www.seekbot.net/bot.html) robotstxtfetcher/1.0 (xdf)",
"semanticdiscovery/0.1",
"sensis.com.au web crawler (search_comments\at\sensis\dot\com\dot\au)",
"sherlock/1.3 httpget/1.3",
"sherlock_spider (jimfan@163.com)",
"sitexpert",
"internetseer.com",
"sitecheck.internetseer.com (for more info see: http://sitecheck.internetseer.com)",
"sitescooper/3.1.2 (http://sitescooper.org) libwww-perl/5.51",
"slysearch/1.3 (http://www.slysearch.com)",
"slysearch/1.3 http://www.slysearch.com",
"sohu-search",
"speedy spider (http://www.entireweb.com)",
"mozilla/4.0 (compatible; speedyspider; www.entireweb.com)",
"speedy_spider_(http://www.entireweb.com)",
"spiderku/0.9",
"spidermonkey/7.04 (spidermonkey.ca info at http://spidermonkey.ca/sm.shtml)",
"spider_monkey/7.06 (spidermonkey.ca info at http://spidermonkey.ca /sm.shtml)",
"spider_monkey/7.06 (spidermonkey.ca info at http://www.spidermonkey.ca/sm.shtml)",
"mozilla/5.0 (compatible; spurlbot/0.2)",
"sqworm/2.9.85-beta (beta_release; 20011115-775; i686-pc-linux-gnu)",
"star downloader",
"steeler/1.3 (http://www.tkl.iis.u-tokyo.ac.jp/~crawler/)",
"mozilla/4.0 (compatible; supercleaner 2.56; windows nt 5.1)",
"szukacz/1.5",
"szukacz/1.5 (robot; www.szukacz.pl/jakdzialarobot.html; info@szukacz.pl)",
"tarantula experimental crawler",
"tcl http client package 1.0",
"tcl http client package 2.3",
"(teradex mapper; mapper@teradex.com; http://www.teradex.com)",
"teradex_crawler (crawler@teradex.com; http://crawler.teradex.com)",
"thesubot/0.1 (www.thesubot.de)",
"thesubot-beta-www.thesubot.de",
"thumbshots-de-bot (version: 1.02, powered by www.thumbshots.de)",
"timbobot/0.9 http://www.breakingblogs.com/timbo_bot.html",
"tkensaku/0.9 (http://www.tkensaku.com/q.html)",
"transgenikbot (http://www.tsgk.net)",
"transgenikbot http://www.tsgk.net",
"tulipchain/5.7 (http://ostermiller.org/tulipchain/) java/1.4.0_02 (http://java.sun.com/) windows_me/4.90",
"tulipchain/5.94 (http://ostermiller.org/tulipchain/) java/1.4.1_01 (http://apple.com/) mac_os_x/10.2.8",
"tulipchain/6.01 (http://ostermiller.org/tulipchain/) java/1.4.2_03 (http://java.sun.com/) windows_xp/5.1 rpt-httpclient/0.3-3",
"tulipchain/6.02 (http://ostermiller.org/tulipchain/) java/1.4.2_03 (http://apple.com/) mac_os_x/10.3.3 rpt-httpclient/0.3-3",
"tulipchain/6.03 (http://ostermiller.org/tulipchain/) java/1.4.2_05 (http://java.sun.com/) windows_xp/5.1 rpt-httpclient/0.3-3",
"turnitinbot/1.4 (http://www.turnitin.com/robot/crawlerinfo.html)",
"turnitinbot/1.4 http://www.turnitin.com/robot/crawlerinfo.html",
"turnitinbot/1.5 (http://www.turnitin.com/robot/crawlerinfo.html)",
"turnitinbot/1.5 http://www.turnitin.com/robot/crawlerinfo.html",
"turnitinbot/2.0 (http://www.turnitin.com/robot/crawlerinfo.html)",
"turnitinbot/2.0 http://www.turnitin.com/robot/crawlerinfo.html",
"tutorgigbot/1.5 ( +http://www.tutorgig.info )",
"tutorial crawler 1.4 (http://www.tutorgig.com/crawler)",
"uiowacrawler/1.0",
"uiowacrawler/2.0",
"usyd-nlp-spider (http://www.it.usyd.edu.au/~vinci/bot.html)",
"udmsearch/3.1.20",
"unchaos_crawler_2.0.2 (search.engine@unchaos.com)",
"updated/0.1beta (updated.com; http://www.updated.com; crawler@updated.om)",
"vse/1.0 (vsecrawler@hotmail.com)",
"vagabondo/2.0 mt (webagent at wise-guys dot nl)",
"vagabondo/2.0 mt (webagent@nospamwise-guys.nl)",
"mozilla/5.0 (compatible; vagabondo/2.1; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)",
"vivante link checker (http://www.vivante.com)",
"void-bot/0.1 (bot@void.be; http://www.void.be/)",
"mozilla/4.0 (compatible; msie 5.0; windows 95) voilabot; 1.6",
"mozilla/4.0_(compatible;_msie_5.0;_windows_95)_voilabot/1.6 libwww/5.3.2",
"vspider",
"w3c-checklink/2.90 libwww-perl/5.64",
"w3c-checklink/3.6.2.3 libwww-perl/5.64",
"w3c-checklink/3.9.2 [3.17] libwww-perl/5.79",
"w3c-checklink/4.0 [4.4] libwww-perl/5.800",
"w3c-checklink/4.1 [4.14] libwww-perl/5.800",
"w3c_validator/1.183 libwww-perl/5.64",
"w3c_validator/1.305.2.109 libwww-perl/5.79",
"w3c_validator/1.305.2.12 libwww-perl/5.64",
"w3c_validator/1.305.2.137 libwww-perl/5.79",
"w3c_validator/1.305.2.148 libwww-perl/5.800",
"w3c_validator/1.305.2.148 libwww-perl/5.803",
"wwweasel robot v1.00 (http://wwweasel.de)",
"webfilter robot 1.0",
"webrace/1.1 (university of cyprus, distributed crawler)",
"websauger 1.20b",
"websearch/2.0.1 (dez@blanchfield.com.au, http://www.websearch.com.au/)",
"websearch.com.au/3.0.1 (the australian search engine; http://websearch.com.au; search@websearch.com.au)",
"http://www.websearch.com.au/ - australian search engine/3.1.3 (sites@websearch.com.au)",
"http://www.websearch.com.au/ - australian search engine/3.1.6 (sites@websearch.com.au)",
"http://www.websearch.com.au/ (larbin2.6.2@unspecified.mail)",
"http://www.websearch.com.au/ larbin2.6.2@unspecified.mail",
"http://www.websearch.com.au (larbin2.6.2@unspecified.mail)",
"http://www.websearch.com.au larbin2.6.2@unspecified.mail",
"www.websearch.com.au (search@websearch.com.au)",
"www.websearch.com.au search@websearch.com.au",
"webbot",
"webclipping.com",
"webcollage/1.102",
"webcollage/1.104",
"webcollage/1.87",
"webcollage/1.93",
"webcollage/1.94",
"fri nov 15 04:51:18 est 2002webcraftboot java/1.4.1_01",
"sun apr 20 22:00:01 edt 2003webcraftboot java/1.4.2-beta",
"tue apr 15 22:00:03 edt 2003webcraftboot java/1.4.2-beta",
"thu mar 27 18:20:34 cet 2003webcraftboot",
"mozilla/3.0 (compatible; webinator-indexer.cyberalert.com/2.56)",
"www.webwombat.com.au",
"webyield robot (http://www.webyield.net/search/search.pl)",
"wget/1.5.2",
"wget/1.5.3",
"wget/1.5.3.1",
"wget/1.6",
"wget/1.7",
"wget/1.8",
"wget/1.8.1",
"wget/1.8.1+cvs",
"wget/1.8.2",
"wget/1.9",
"wget/1.9-beta",
"wget/1.9.1",
"willow internet crawler by twotrees v2.1",
"wotbox/alpha0.5.1 (bot@wotbox.com; http://www.wotbox.com) java/1.4.1_02",
"http://www.ciml.co.uk",
"xenu's link sleuth 1.1a",
"xenu link sleuth 1.2b",
"xenu link sleuth 1.2d",
"xenu link sleuth 1.2e",
"xenu link sleuth 1.2f",
"mozilla/5.0 (compatible; yahoo! slurp; http://help.yahoo.com/help/us/ysearch/slurp)",
"yahoo-mmcrawler/3.x (mms dash mmcrawler dash support at yahoo dash inc dot com)",
"yottacars_bot/4.12 (+http://www.yottacars.com) car search engine",
"zao/0.1 (http://www.kototoi.org/zao/)",
"zao/0.2 (http://www.kototoi.org/zao/)",
"zao-crawler",
"zeus 3140 webster pro v2.9 win32",
"zeus 57657 webster pro v2.9 win32",
"zipppbot/0.11 (zipppbot; http://www.zippp.net; webmaster@zippp.net)",
"zoomspider - wrensoft.com",
"mozilla/4.0 compatible zyborg/1.0 (zyborg@wisenutbot.com; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 (wn-1.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 (wn-12.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 (wn-2.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 dlc (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 daily refresh beta-d03 (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 daily refresh beta-d05 (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 dead link checker (wn.dlc@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 dead link checker (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"mozilla/4.0 compatible zyborg/1.0 dead link checker beta-d01 (wn.zyborg@looksmart.net; http://www.wisenutbot.com)",
"ansearchbot",
"anybrowser.com search engine",
"leechget 2002 (www.leechget.de)",
"leechget 2004 (www.leechget.net)",
"nationaldirectory-webspider/1.3",
"arianna.libero.it linux/2.4.9-34smp (linux)"
);
if(in_array(strtolower($_SERVER['HTTP_USER_AGENT']),$bot_list)){
return true;
}
else{
return false;
}
}
[/PHP]
(تکمیل شد)
اگر نقصی داشت بگو!