Facebook
From Corrupt Pelican, 5 Years ago, written in Plain Text.
Embed
Download Paste or View Raw
Hits: 369
  1.  
  2. RewriteCond %{HTTP_USER_AGENT} \
  3. 12soso|\
  4. 192\.comagent|\
  5. 1noonbot|\
  6. 1on1searchbot|\
  7. 3de\_search2|\
  8. 3d\_search|\
  9. 3g\ bot|\
  10. 3gse|\
  11. 50\.nu|\
  12. a1\ sitemap\ generator|\
  13. a1\ website\ download|\
  14. a6\-indexer|\
  15. aasp|\
  16. abachobot|\
  17. abonti|\
  18. abotemailsearch|\
  19. aboundex|\
  20. aboutusbot|\
  21. accmonitor\ compliance\ server|\
  22. accoon|\
  23. achulkov\.net\ page\ walker|\
  24. acme\.spider|\
  25. acoonbot|\
  26. acquia\-crawler|\
  27. activetouristbot|\
  28. ad\ muncher|\
  29. adamm\ bot|\
  30. adbeat\_bot|\
  31. adminshop\.com|\
  32. advanced\ email\ extractor|\
  33. aesop\_com\_spiderman|\
  34. aespider|\
  35. af\ knowledge\ now\ verity\ spider|\
  36. aggregator:vocus|\
  37. ah\-ha\.com\ crawler|\
  38. ahrefs|\
  39. aibot|\
  40. aidu|\
  41. aihitbot|\
  42. aipbot|\
  43. aisiid|\
  44. aitcsrobot/1\.1|\
  45. ajsitemap|\
  46. akamai\-sitesnapshot|\
  47. alexawebsearchplatform|\
  48. alexfdownload|\
  49. alexibot|\
  50. alkalinebot|\
  51. all\ acronyms\ bot|\
  52. alpha\ search\ agent|\
  53. amerla\ search\ bot|\
  54. amfibibot|\
  55. ampmppc\.com|\
  56. amznkassocbot|\
  57. anemone|\
  58. anonymous|\
  59. anotherbot|\
  60. answerbot|\
  61. answerbus|\
  62. answerchase\ prove|\
  63. antbot|\
  64. antibot|\
  65. antisantyworm|\
  66. antro\.net|\
  67. aonde\-spider|\
  68. aport|\
  69. appengine\-google|\
  70. appid\:\ s\~stremor\-crawler\-|\
  71. aqua\_products|\
  72. arabot|\
  73. arachmo|\
  74. arachnophilia|\
  75. archive\.org\_bot|\
  76. aria\ equalizer|\
  77. arianna\.libero\.it|\
  78. arikus\_spider|\
  79. art\-online\.com|\
  80. artavisbot|\
  81. artera|\
  82. asaha\ search\ engine\ turkey|\
  83. ask|\
  84. aspider|\
  85. aspseek|\
  86. asterias|\
  87. astrofind|\
  88. athenusbot|\
  89. atlocalbot|\
  90. atomic\_email\_hunter|\
  91. attach|\
  92. attrakt|\
  93. attributor|\
  94. augurfind|\
  95. auresys|\
  96. autobaron\ crawler|\
  97. autoemailspider|\
  98. autowebdir|\
  99. avsearch\-|\
  100. axfeedsbot|\
  101. axonize\-bot|\
  102. ayna|\
  103. b2w|\
  104. backdoorbot|\
  105. backrub|\
  106. backstreet\ browser|\
  107. backweb|\
  108. baidu|\
  109. bandit|\
  110. batchftp|\
  111. baypup|\
  112. bdfetch|\
  113. becomebot|\
  114. becomejpbot|\
  115. beetlebot|\
  116. bender|\
  117. besserscheitern\-crawl|\
  118. betabot|\
  119. big\ brother|\
  120. big\ data|\
  121. bigado\.com|\
  122. bigcliquebot|\
  123. bigfoot|\
  124. biglotron|\
  125. bilbo|\
  126. bilgibetabot|\
  127. bilgibot|\
  128. bintellibot|\
  129. bitlybot|\
  130. bitvouseragent|\
  131. bizbot003|\
  132. bizbot04|\
  133. bizworks\ retriever|\
  134. black\ hole|\
  135. black\.hole|\
  136. blackbird|\
  137. blackmask\.net\ search\ engine|\
  138. blackwidow|\
  139. bladder\ fusion|\
  140. blaiz\-bee|\
  141. blexbot|\
  142. blinkx|\
  143. blitzbot|\
  144. blog\ conversation\ project|\
  145. blogmyway|\
  146. blogpulselive|\
  147. blogrefsbot|\
  148. blogscope|\
  149. blogslive|\
  150. bloobybot|\
  151. blowfish|\
  152. blt|\
  153. bnf\.fr\_bot|\
  154. boaconstrictor|\
  155. boardreader|\
  156. boia\-scan\-agent|\
  157. boia\.org|\
  158. boitho|\
  159. boi\_crawl\_00|\
  160. bookmark\ buddy\ bookmark\ checker|\
  161. bookmark\ search\ tool|\
  162. bosug|\
  163. bot\ apoena|\
  164. botalot|\
  165. botrighthere|\
  166. botswana|\
  167. bottybot|\
  168. bpbot|\
  169. braintime\_search|\
  170. brokenlinkcheck\.com|\
  171. browseremulator|\
  172. browsermob|\
  173. bruinbot|\
  174. bsearchr&d|\
  175. bspider|\
  176. btbot|\
  177. btsearch|\
  178. bubing|\
  179. buddy|\
  180. buibui|\
  181. buildcms\ crawler|\
  182. builtbottough|\
  183. bullseye|\
  184. bumblebee|\
  185. bunnyslippers|\
  186. buscadorclarin|\
  187. buscaplus\ robi|\
  188. butterfly|\
  189. buyhawaiibot|\
  190. buzzbot|\
  191. byindia|\
  192. byspider|\
  193. byteserver|\
  194. bzbot|\
  195. c\ r\ a\ w\ l\ 3\ r|\
  196. cacheblaster|\
  197. caddbot|\
  198. cafi|\
  199. camcrawler|\
  200. camelstampede|\
  201. canon\-webrecord|\
  202. careerbot|\
  203. cataguru|\
  204. catchbot|\
  205. cazoodle|\
  206. ccbot|\
  207. ccgcrawl|\
  208. ccubee|\
  209. cd\-preload|\
  210. ce\-preload|\
  211. cegbfeieh|\
  212. cerberian\ drtrs|\
  213. cert\ figleafbot|\
  214. cfetch|\
  215. cfnetwork|\
  216. chameleon|\
  217. charlotte|\
  218. check&get|\
  219. checkbot|\
  220. checklinks|\
  221. cheesebot|\
  222. chemiede\-nodebot|\
  223. cherrypicker|\
  224. chilkat|\
  225. chinaclaw|\
  226. cipinetbot|\
  227. cis455crawler|\
  228. citeseerxbot|\
  229. cizilla|\
  230. clariabot|\
  231. climate\ ark|\
  232. climateark\ spider|\
  233. clshttp|\
  234. clushbot|\
  235. coast\ scan\ engine|\
  236. coast\ webmaster\ pro|\
  237. coccoc|\
  238. collapsarweb|\
  239. collector|\
  240. colocrossing|\
  241. combine|\
  242. connectsearch|\
  243. conpilot|\
  244. contentsmartz|\
  245. contextad\ bot|\
  246. contype|\
  247. cookienet|\
  248. coolbot|\
  249. coolcheck|\
  250. copernic|\
  251. copier|\
  252. copyrightcheck|\
  253. core\-project|\
  254. cosmos|\
  255. covario\-ids|\
  256. cowbot\-|\
  257. cowdog\ bot|\
  258. crabbybot|\
  259. craftbot\@yahoo\.com|\
  260. crawler\.kpricorn\.org|\
  261. crawler43\.ejupiter\.com|\
  262. crawler4j|\
  263. crawler@|\
  264. crawler\_for\_infomine|\
  265. crawly|\
  266. crawl\_application|\
  267. creativecommons|\
  268. crescent|\
  269. cs\-crawler|\
  270. cse\ html\ validator|\
  271. cshttpclient|\
  272. cuasarbot|\
  273. culsearch|\
  274. curl|\
  275. custo|\
  276. cvaulev|\
  277. cyberdog|\
  278. cybernavi\_webget|\
  279. cyberpatrol\ sitecat\ webbot|\
  280. cyberspyder|\
  281. cydralspider|\
  282. d1garabicengine|\
  283. datacha0s|\
  284. datafountains|\
  285. dataparksearch|\
  286. dataprovider\.com|\
  287. datascape\ robot|\
  288. dataspearspiderbot|\
  289. dataspider|\
  290. dattatec\.com|\
  291. daumoa|\
  292. dblbot|\
  293. dcpbot|\
  294. declumbot|\
  295. deepindex|\
  296. deepnet\ crawler|\
  297. deeptrawl|\
  298. dejan|\
  299. del\.icio\.us\-thumbnails|\
  300. deltascan|\
  301. delvubot|\
  302. der\ gro§e\ bildersauger|\
  303. der\ große\ bildersauger|\
  304. deusu|\
  305. dfs\-fetch|\
  306. diagem|\
  307. diamond|\
  308. dibot|\
  309. didaxusbot|\
  310. digext|\
  311. digger|\
  312. digi\-rssbot|\
  313. digitalarchivesbot|\
  314. digout4u|\
  315. diibot|\
  316. dillo|\
  317. dir\_snatch\.exe|\
  318. disco|\
  319. distilled\-reputation\-monitor|\
  320. djangotraineebot|\
  321. dkimrepbot|\
  322. dmoz\ downloader|\
  323. docomo|\
  324. dof\-verify|\
  325. domaincrawler|\
  326. domainscan|\
  327. domainwatcher\ bot|\
  328. dotbot|\
  329. dotspotsbot|\
  330. dow\ jones\ searchbot|\
  331. download|\
  332. doy|\
  333. dragonfly|\
  334. drip|\
  335. drone|\
  336. dtaagent|\
  337. dtsearchspider|\
  338. dumbot|\
  339. dwaar|\
  340. dxseeker|\
  341. e\-societyrobot|\
  342. eah|\
  343. earth\ platform\ indexer|\
  344. earth\ science\ educator\ \ robot|\
  345. easydl|\
  346. ebingbong|\
  347. ec2linkfinder|\
  348. ecairn\-grabber|\
  349. ecatch|\
  350. echoosebot|\
  351. edisterbot|\
  352. edugovsearch|\
  353. egothor|\
  354. eidetica\.com|\
  355. eirgrabber|\
  356. elblindo\ the\ blind\ bot|\
  357. elisabot|\
  358. ellerdalebot|\
  359. email\ exractor|\
  360. emailcollector|\
  361. emailleach|\
  362. emailsiphon|\
  363. emailwolf|\
  364. emeraldshield|\
  365. empas\_robot|\
  366. enabot|\
  367. endeca|\
  368. enigmabot|\
  369. enswer\ neuro\ bot|\
  370. enter\ user\-agent|\
  371. entitycubebot|\
  372. erocrawler|\
  373. estylesearch|\
  374. esyndicat\ bot|\
  375. eurosoft\-bot|\
  376. evaal|\
  377. eventware|\
  378. everest\-vulcan\ inc\.|\
  379. exabot|\
  380. exactsearch|\
  381. exactseek|\
  382. exooba|\
  383. exploder|\
  384. express\ webpictures|\
  385. extractor|\
  386. eyenetie|\
  387. ez\-robot|\
  388. ezooms|\
  389. f\-bot\ test\ pilot|\
  390. factbot|\
  391. fairad\ client|\
  392. falcon|\
  393. fast\ data\ search\ document\ retriever|\
  394. fast\ esp|\
  395. fast\-search\-engine|\
  396. fastbot\ crawler|\
  397. fastbot\.de\ crawler|\
  398. fatbot|\
  399. favcollector|\
  400. faviconizer|\
  401. favorites\ sweeper|\
  402. fdm|\
  403. fdse\ robot|\
  404. fedcontractorbot|\
  405. fembot|\
  406. fetch\ api\ request|\
  407. fetch\_ici|\
  408. fgcrawler|\
  409. filangy|\
  410. filehound|\
  411. findanisp\.com\_isp\_finder|\
  412. findlinks|\
  413. findweb|\
  414. firebat|\
  415. firstgov\.gov\ search|\
  416. flaming\ attackbot|\
  417. flamingo\_searchengine|\
  418. flashcapture|\
  419. flashget|\
  420. flickysearchbot|\
  421. fluffy\ the\ spider|\
  422. flunky|\
  423. focused\_crawler|\
  424. followsite|\
  425. foobot|\
  426. fooooo\_web\_video\_crawl|\
  427. fopper|\
  428. formulafinderbot|\
  429. forschungsportal|\
  430. francis|\
  431. freewebmonitoring\ sitechecker|\
  432. freshcrawler|\
  433. freshdownload|\
  434. freshlinks\.exe|\
  435. friendfeedbot|\
  436. frodo\.at|\
  437. froggle|\
  438. frontpage|\
  439. froola\ bot|\
  440. fr\_crawler|\
  441. fu\-nbi|\
  442. full\_breadth\_crawler|\
  443. funnelback|\
  444. furlbot|\
  445. g10\-bot|\
  446. gaisbot|\
  447. galaxybot|\
  448. gazz|\
  449. gbplugin|\
  450. generate\_infomine\_category\_classifiers|\
  451. genevabot|\
  452. geniebot|\
  453. genieo|\
  454. geomaxenginebot|\
  455. geometabot|\
  456. geonabot|\
  457. geovisu|\
  458. germcrawler\ |\
  459. gethtmlcontents|\
  460. getleft|\
  461. getright|\
  462. getsmart|\
  463. geturl\.rexx|\
  464. getweb!|\
  465. giant|\
  466. gigablastopensource|\
  467. gigabot|\
  468. girafabot|\
  469. gleamebot|\
  470. gnome\-vfs|\
  471. go!zilla|\
  472. go\-ahead\-got\-it|\
  473. go\-http\-client|\
  474. goforit\.com|\
  475. goforitbot|\
  476. gold\ crawler|\
  477. goldfire\ server|\
  478. golem|\
  479. goodjelly|\
  480. gordon\-college\-google\-mini|\
  481. goroam|\
  482. goseebot|\
  483. gotit|\
  484. govbot|\
  485. gpu\ p2p\ crawler|\
  486. grabber|\
  487. grabnet|\
  488. grafula|\
  489. grapefx|\
  490. grapeshot|\
  491. grbot|\
  492. greenyogi|\
  493. gromit|\
  494. grub|\
  495. gsa|\
  496. gslfbot|\
  497. gulliver|\
  498. gulperbot|\
  499. gurujibot|\
  500. gvc\ business\ crawler|\
  501. gvc\ crawler|\
  502. gvc\ search\ bot|\
  503. gvc\ web\ crawler|\
  504. gvc\ weblink\ crawler|\
  505. gvc\ world\ links|\
  506. gvcbot\.com|\
  507. happyfunbot|\
  508. harvest|\
  509. hatena\ antenna|\
  510. hawler|\
  511. hcat|\
  512. hclsreport\-crawler|\
  513. hd\ nutch\ agent|\
  514. header\_test\_client|\
  515. healia\
  516.  [NC,OR]
  517. #500 new rule
  518. RewriteCond %{HTTP_USER_AGENT} \
  519. helix|\
  520. here\ will\ be\ link\ to\ crawler\ site|\
  521. heritrix|\
  522. hiscan|\
  523. hisoftware\ accmonitor\ server|\
  524. hisoftware\ accverify|\
  525. hitcrawler|\
  526. hivabot|\
  527. hloader|\
  528. hmsebot|\
  529. hmview|\
  530. hoge|\
  531. holmes|\
  532. homepagesearch|\
  533. hooblybot\-image|\
  534. hoowwwer|\
  535. hostcrawler|\
  536. hsft\ \\-\ link\ scanner|\
  537. hsft\ \\-\ lvu\ scanner|\
  538. hslide|\
  539. ht://check|\
  540. htdig|\
  541. html\ link\ validator|\
  542. htmlparser|\
  543. httplib|\
  544. httrack|\
  545. huaweisymantecspider|\
  546. hul\-wax|\
  547. humanlinks|\
  548. hyperestraier|\
  549. hyperix|\
  550. iaarchiver\-|\
  551. ia\_archiver|\
  552. ibuena|\
  553. icab|\
  554. icds\-ingestion|\
  555. ichiro|\
  556. icopyright\ conductor|\
  557. ieautodiscovery|\
  558. iecheck|\
  559. ihwebchecker|\
  560. iiitbot|\
  561. iim\_405|\
  562. ilsebot|\
  563. iltrovatore|\
  564. image\ stripper|\
  565. image\ sucker|\
  566. image\-fetcher|\
  567. imagebot|\
  568. imagefortress|\
  569. imageshereimagesthereimageseverywhere|\
  570. imagevisu|\
  571. imds\_monitor|\
  572. imo\-google\-robot\-intelink|\
  573. inagist\.com\ url\ crawler|\
  574. indexer|\
  575. industry\ cortex\ webcrawler|\
  576. indy\ library|\
  577. indylabs\_marius|\
  578. inelabot|\
  579. inet32\ ctrl|\
  580. inetbot|\
  581. info\ seeker|\
  582. infolink|\
  583. infomine|\
  584. infonavirobot|\
  585. informant|\
  586. infoseek\ sidewinder|\
  587. infotekies|\
  588. infousabot|\
  589. ingrid|\
  590. inktomi|\
  591. insightscollector|\
  592. insightsworksbot|\
  593. inspirebot|\
  594. insumascout|\
  595. intelix|\
  596. intelliseek|\
  597. interget|\
  598. internet\ ninja|\
  599. internet\ radio\ crawler|\
  600. internetlinkagent|\
  601. interseek|\
  602. ioi|\
  603. ip\-web\-crawler\.com|\
  604. ipadd\ bot|\
  605. ipselonbot|\
  606. ips\-agent|\
  607. iria|\
  608. irlbot|\
  609. iron33|\
  610. isara|\
  611. isearch|\
  612. isilox|\
  613. istellabot|\
  614. its\-learning\ crawler|\
  615. iu\_csci\_b659\_class\_crawler|\
  616. ivia|\
  617. jadynave|\
  618. java|\
  619. jbot|\
  620. jemmathetourist|\
  621. jennybot|\
  622. jetbot|\
  623. jetbrains\ omea\ pro|\
  624. jetcar|\
  625. jim|\
  626. jobo|\
  627. jobspider\_ba|\
  628. joc|\
  629. joedog|\
  630. joyscapebot|\
  631. jspyda|\
  632. junut\ bot|\
  633. justview|\
  634. jyxobot|\
  635. k\.s\.bot|\
  636. kakclebot|\
  637. kalooga|\
  638. katatudo\-spider|\
  639. kbeta1|\
  640. keepni\ web\ site\ monitor|\
  641. kenjin\.spider|\
  642. keybot\ translation\-search\-machine|\
  643. keywenbot|\
  644. keyword\ density|\
  645. keyword\.density|\
  646. kinjabot|\
  647. kitenga\-crawler\-bot|\
  648. kiwistatus|\
  649. kmbot\-|\
  650. kmccrew\ bot\ search|\
  651. knight|\
  652. knowitall|\
  653. knowledge\ engine|\
  654. knowledge\.com|\
  655. koepabot|\
  656. koninklijke|\
  657. korniki|\
  658. krowler|\
  659. ksbot|\
  660. kuloko\-bot|\
  661. kulturarw3|\
  662. kummhttp|\
  663. kurzor|\
  664. kyluka\ crawl|\
  665. l\.webis|\
  666. labhoo|\
  667. labourunions411|\
  668. lachesis|\
  669. lament|\
  670. lamerexterminator|\
  671. lapozzbot|\
  672. larbin|\
  673. lbot|\
  674. leaptag|\
  675. leechftp|\
  676. leechget|\
  677. letscrawl\.com|\
  678. lexibot|\
  679. lexxebot|\
  680. lftp|\
  681. libcrawl|\
  682. libiviacore|\
  683. libw|\
  684. likse|\
  685. linguee\ bot|\
  686. link\ checker|\
  687. link\ validator|\
  688. linkalarm|\
  689. linkbot|\
  690. linkcheck\ by\ siteimprove\.com|\
  691. linkcheck\ scanner|\
  692. linkchecker|\
  693. linkdex\.com|\
  694. linkextractorpro|\
  695. linklint|\
  696. linklooker|\
  697. linkman|\
  698. links\ sql|\
  699. linkscan|\
  700. linksmanager\.com\_bot|\
  701. linksweeper|\
  702. linkwalker|\
  703. link\_checker|\
  704. litefinder|\
  705. litlrbot|\
  706. little\ grabber\ at\ skanktale\.com|\
  707. livelapbot|\
  708. lm\ harvester|\
  709. lmqueuebot|\
  710. lnspiderguy|\
  711. loadtimebot|\
  712. localcombot|\
  713. locust|\
  714. lolongbot|\
  715. lookbot|\
  716. lsearch|\
  717. lssbot|\
  718. lt\ scotland\ checklink|\
  719. ltx71.com|\
  720. lwp|\
  721. lycos\_spider|\
  722. lydia\ entity\ spider|\
  723. lynnbot|\
  724. lytranslate|\
  725. mag\-net|\
  726. magnet|\
  727. magpie\-crawler|\
  728. magus\ bot|\
  729. mail\.ru|\
  730. mainseek\_bot|\
  731. mammoth|\
  732. map\ robot|\
  733. markwatch|\
  734. masagool|\
  735. masidani\_bot\_|\
  736. mass\ downloader|\
  737. mata\ hari|\
  738. mata\.hari|\
  739. matentzn\ at\ cs\ dot\ man\ dot\ ac\ dot\ uk|\
  740. maxamine\.com\-\-robot|\
  741. maxamine\.com\-robot|\
  742. maxomobot|\
  743. mcbot|\
  744. medrabbit|\
  745. megite|\
  746. memacbot|\
  747. memo|\
  748. mendeleybot|\
  749. mercator\-|\
  750. mercuryboard\_user\_agent\_sql\_injection\.nasl|\
  751. metacarta|\
  752. metaeuro\ web\ search|\
  753. metager2|\
  754. metagloss|\
  755. metal\ crawler|\
  756. metaquerier|\
  757. metaspider|\
  758. metaspinner|\
  759. metauri|\
  760. mfcrawler|\
  761. mfhttpscan|\
  762. midown\ tool|\
  763. miixpc|\
  764. mini\-robot|\
  765. minibot|\
  766. minirank|\
  767. mirror|\
  768. missigua\ locator|\
  769. mister\ pix|\
  770. mister\.pix|\
  771. miva|\
  772. mj12bot|\
  773. mnogosearch|\
  774. moduna\.com|\
  775. mod\_accessibility|\
  776. moget|\
  777. mojeekbot|\
  778. monkeycrawl|\
  779. moses|\
  780. mowserbot|\
  781. mqbot|\
  782. mse360|\
  783. msindianwebcrawl|\
  784. msmobot|\
  785. msnptc|\
  786. msrbot|\
  787. mt\-soft|\
  788. multitext|\
  789. my\-heritrix\-crawler|\
  790. myapp|\
  791. mycompanybot|\
  792. mycrawler|\
  793. myengines\-us\-bot|\
  794. myfamilybot|\
  795. myra|\
  796. my\_little\_searchengine\_project|\
  797. nabot|\
  798. najdi\.si|\
  799. nambu|\
  800. nameprotect|\
  801. nasa\ search|\
  802. natchcvs|\
  803. natweb\-bad\-link\-mailer|\
  804. naver|\
  805. navroad|\
  806. nearsite|\
  807. nec\-meshexplorer|\
  808. neosciocrawler|\
  809. nerdbynature\.bot|\
  810. nerdybot|\
  811. nerima\-crawl-|\
  812. nessus|\
  813. nestreader|\
  814. net\ vampire|\
  815. net::trackback|\
  816. netants|\
  817. netcarta\ cyberpilot\ pro|\
  818. netcraft|\
  819. netexperts|\
  820. netid\.com\ bot|\
  821. netmechanic|\
  822. netprospector|\
  823. netresearchserver|\
  824. netseer|\
  825. netshift=|\
  826. netsongbot|\
  827. netsparker|\
  828. netspider|\
  829. netsrcherp|\
  830. netzip|\
  831. newmedhunt|\
  832. news\ bot|\
  833. newsgatherer|\
  834. newsgroupreporter|\
  835. newstrovebot|\
  836. news\_search\_app|\
  837. nextgensearchbot|\
  838. nextthing\.org|\
  839. nicebot|\
  840. nicerspro|\
  841. niki\-bot|\
  842. nimblecrawler|\
  843. nimbus\-1|\
  844. ninetowns|\
  845. ninja|\
  846. njuicebot|\
  847. nlese|\
  848. nogate|\
  849. norbert\ the\ spider|\
  850. noteworthybot|\
  851. npbot|\
  852. nrcan\ intranet\ crawler|\
  853. nsdl\_search\_bot|\
  854. nuggetize\.com\ bot|\
  855. nusearch\ spider|\
  856. nutch|\
  857. nu\_tch|\
  858. nwspider|\
  859. nymesis|\
  860. nys\-crawler|\
  861. objectssearch|\
  862. obot|\
  863. obvius\ external\ linkcheck|\
  864. ocelli|\
  865. octopus|\
  866. odp\ entries\ t\_st|\
  867. oegp|\
  868. offline\ navigator|\
  869. offline\.explorer|\
  870. ogspider|\
  871. omiexplorer\_bot|\
  872. omniexplorer|\
  873. omnifind|\
  874. omniweb|\
  875. onetszukaj|\
  876. online\ link\ validator|\
  877. oozbot|\
  878. openbot|\
  879. openfind|\
  880. openintelligencedata|\
  881. openisearch|\
  882. openlink\ virtuoso\ rdf\ crawler|\
  883. opensearchserver\_bot|\
  884. opidig|\
  885. optidiscover|\
  886. oracle\ secure\ enterprise\ search|\
  887. oracle\ ultra\ search|\
  888. orangebot|\
  889. orisbot|\
  890. ornl\_crawler|\
  891. ornl\_mercury|\
  892. osis\-project\.jp|\
  893. oso|\
  894. outfoxbot|\
  895. outfoxmelonbot|\
  896. owler\-bot|\
  897. owsbot|\
  898. ozelot|\
  899. p3p\ client|\
  900. pagebiteshyperbot|\
  901. pagebull|\
  902. pagedown|\
  903. pagefetcher|\
  904. pagegrabber|\
  905. pagepeeker|\
  906. pagerank\ monitor|\
  907. page\_verifier|\
  908. pamsnbot\.htm|\
  909. panopy\ bot|\
  910. panscient\.com|\
  911. pansophica|\
  912. papa\ foto|\
  913. paperlibot|\
  914. parasite|\
  915. parsijoo|\
  916. pathtraq|\
  917. pattern|\
  918. patwebbot|\
  919. pavuk|\
  920. paxleframework|\
  921. pbbot|\
  922. pcbrowser|\
  923. pcore\-http|\
  924. pd\-crawler|\
  925. penthesila|\
  926. perform\_crawl|\
  927. perman|\
  928. personal\ ultimate\ crawler|\
  929. php\ version\ tracker|\
  930. phpcrawl|\
  931. phpdig|\
  932. picosearch|\
  933. pieno\ robot|\
  934. pipbot|\
  935. pipeliner|\
  936. pita|\
  937. pixfinder|\
  938. piyushbot|\
  939. planetwork\ bot\ search|\
  940. plucker|\
  941. plukkie|\
  942. plumtree|\
  943. pockey|\
  944. pocohttp|\
  945. pogodak\.ba|\
  946. pogodak\.co\.yu|\
  947. poirot|\
  948. polybot|\
  949. pompos|\
  950. poodle\ predictor|\
  951. popscreenbot|\
  952. postpost|\
  953. privacyfinder|\
  954. projectwf\-java\-test\-crawler|\
  955. propowerbot|\
  956. prowebwalker|\
  957. proxem\ websearch|\
  958. proximic|\
  959. proxy\ crawler|\
  960. psbot|\
  961. pss\-bot|\
  962. psycheclone|\
  963. pub\-crawler|\
  964. pucl|\
  965. pulsebot|\
  966. pump|\
  967. pwebot|\
  968. python|\
  969. qeavis\ agent|\
  970. qfkbot|\
  971. qualidade|\
  972. qualidator\.com\ bot|\
  973. quepasacreep|\
  974. queryn\ metasearch|\
  975. queryn\.metasearch|\
  976. quest\.durato|\
  977. quintura\-crw|\
  978. qunarbot|\
  979. qwantify|\
  980. qweerybot|\
  981. qweery\_robot\.txt\_checkbot|\
  982. r2ibot|\
  983. r6\_commentreader|\
  984. r6\_feedfetcher|\
  985. r6\_votereader|\
  986. rabot|\
  987. radian6|\
  988. radiation\ retriever|\
  989. rampybot|\
  990. rankivabot|\
  991. rankur|\
  992. rational\ sitecheck|\
  993. rcstartbot|\
  994. realdownload|\
  995. reaper|\
  996. rebi\-shoveler|\
  997. recorder|\
  998. redbot|\
  999. redcarpet|\
  1000. reget|\
  1001. repomonkey|\
  1002. research\ robot|\
  1003. riddler|\
  1004. riight|\
  1005. risenetbot|\
  1006. riverglassscanner\
  1007.  [NC,OR]
  1008.  
  1009. #1000 new rule
  1010. RewriteCond %{HTTP_USER_AGENT} \
  1011. robopal|\
  1012. robosourcer|\
  1013. robotek|\
  1014. robozilla|\
  1015. roger|\
  1016. rome\ client|\
  1017. rondello|\
  1018. rotondo|\
  1019. roverbot|\
  1020. rpt\-httpclient|\
  1021. rtgibot|\
  1022. rufusbot|\
  1023. runnk\ online\ rss\ reader|\
  1024. runnk\ rss\ aggregator|\
  1025. s2bot|\
  1026. safaribookmarkchecker|\
  1027. safednsbot|\
  1028. safetynet\ robot|\
  1029. saladspoon|\
  1030. sapienti|\
  1031. sapphireweb|\
  1032. sbider|\
  1033. sbl\-bot|\
  1034. scfcrawler|\
  1035. scich|\
  1036. scientificcommons\.org|\
  1037. scollspider|\
  1038. scooperbot|\
  1039. scooter|\
  1040. scoutjet|\
  1041. scrapebox|\
  1042. scrapy|\
  1043. scrawltest|\
  1044. screaming\ frog|\
  1045. scrubby|\
  1046. scspider|\
  1047. scumbot|\
  1048. search\ publisher|\
  1049. search\ x\-bot|\
  1050. search\-channel|\
  1051. search\-engine\-studio|\
  1052. search\.kumkie\.com|\
  1053. search\.updated\.com|\
  1054. search\.usgs\.gov|\
  1055. searcharoo\.net|\
  1056. searchblox|\
  1057. searchbot|\
  1058. searchengine|\
  1059. searchhippo\.com|\
  1060. searchit\-bot|\
  1061. searchmarking|\
  1062. searchmarks|\
  1063. searchmee!|\
  1064. searchmee\_v|\
  1065. searchmining|\
  1066. searchnowbot|\
  1067. searchpreview|\
  1068. searchspider\.com|\
  1069. searqubot|\
  1070. seb\ spider|\
  1071. seekbot|\
  1072. seeker\.lookseek\.com|\
  1073. seeqbot|\
  1074. seeqpod\-vertical\-crawler|\
  1075. selflinkchecker|\
  1076. semager|\
  1077. semanticdiscovery|\
  1078. semantifire|\
  1079. semisearch|\
  1080. semrushbot|\
  1081. seoengworldbot|\
  1082. seokicks|\
  1083. seznambot|\
  1084. shablastbot|\
  1085. shadowwebanalyzer|\
  1086. shareaza|\
  1087. shelob|\
  1088. sherlock|\
  1089. shim\-crawler|\
  1090. shopsalad|\
  1091. shopwiki|\
  1092. showlinks|\
  1093. showyoubot|\
  1094. siclab|\
  1095. silk|\
  1096. simplepie|\
  1097. siphon|\
  1098. sitebot|\
  1099. sitecheck|\
  1100. sitefinder|\
  1101. siteguardbot|\
  1102. siteorbiter|\
  1103. sitesnagger|\
  1104. sitesucker|\
  1105. sitesweeper|\
  1106. sitexpert|\
  1107. skimbot|\
  1108. skimwordsbot|\
  1109. skreemrbot|\
  1110. skywalker|\
  1111. sleipnir|\
  1112. slow\-crawler|\
  1113. slysearch|\
  1114. smart\-crawler|\
  1115. smartdownload|\
  1116. smarte\ bot|\
  1117. smartwit\.com|\
  1118. snake|\
  1119. snap\.com\ beta\ crawler|\
  1120. snapbot|\
  1121. snappreviewbot|\
  1122. snappy|\
  1123. snookit|\
  1124. snooper|\
  1125. snoopy|\
  1126. societyrobot|\
  1127. socscibot|\
  1128. soft411\ directory|\
  1129. sogou|\
  1130. sohu\ agent|\
  1131. sohu\-search|\
  1132. sokitomi\ crawl|\
  1133. solbot|\
  1134. sondeur|\
  1135. sootle|\
  1136. sosospider|\
  1137. space\ bison|\
  1138. space\ fung|\
  1139. spacebison|\
  1140. spankbot|\
  1141. spanner|\
  1142. spatineo\ monitor\ controller|\
  1143. spatineo\ serval\ controller|\
  1144. spatineo\ serval\ getmapbot|\
  1145. special\_archiver|\
  1146. speedy|\
  1147. sphere\ scout|\
  1148. sphider|\
  1149. spider\.terranautic\.net|\
  1150. spiderengine|\
  1151. spiderku|\
  1152. spiderman|\
  1153. spinn3r|\
  1154. spinne|\
  1155. sportcrew\-bot|\
  1156. sproose|\
  1157. spyder3\.microsys\.com|\
  1158. sq\ webscanner|\
  1159. sqlmap|\
  1160. squid\-prefetch|\
  1161. squidclamav\_redirector|\
  1162. sqworm|\
  1163. srevbot|\
  1164. sslbot|\
  1165. ssm\ agent|\
  1166. stackrambler|\
  1167. stardownloader|\
  1168. statbot|\
  1169. statcrawler|\
  1170. statedept\-crawler|\
  1171. steeler|\
  1172. stegmann\-bot|\
  1173. stero|\
  1174. stripper|\
  1175. stumbler|\
  1176. suchclip|\
  1177. sucker|\
  1178. sumeetbot|\
  1179. sumitbot|\
  1180. summizebot|\
  1181. summizefeedreader|\
  1182. sunrise\ xp|\
  1183. superbot|\
  1184. superhttp|\
  1185. superlumin\ downloader|\
  1186. superpagesbot|\
  1187. supremesearch\.net|\
  1188. supybot|\
  1189. surdotlybot|\
  1190. surf|\
  1191. surveybot|\
  1192. suzuran|\
  1193. swebot|\
  1194. swish\-e|\
  1195. sygolbot|\
  1196. synapticwalker|\
  1197. syntryx\ ant\ scout\ chassis\ pheromone|\
  1198. systemsearch\-robot|\
  1199. szukacz|\
  1200. s\~stremor\-crawler|\
  1201. t\-h\-u\-n\-d\-e\-r\-s\-t\-o\-n\-e|\
  1202. tailrank|\
  1203. takeout|\
  1204. talkro\ web\-shot|\
  1205. tamu\_crawler|\
  1206. tapuzbot|\
  1207. tarantula|\
  1208. targetblaster\.com|\
  1209. targetyournews\.com\ bot|\
  1210. tausdatabot|\
  1211. taxinomiabot|\
  1212. teamsoft\ wininet\ component|\
  1213. tecomi\ bot|\
  1214. teezirbot|\
  1215. teleport|\
  1216. telesoft|\
  1217. teradex\ mapper|\
  1218. teragram\_crawler|\
  1219. terrawizbot|\
  1220. testbot|\
  1221. testing\ of\ bot|\
  1222. textbot|\
  1223. thatrobotsite\.com|\
  1224. the\ dyslexalizer|\
  1225. the\ intraformant|\
  1226. the\.intraformant|\
  1227. thenomad|\
  1228. theophrastus|\
  1229. theusefulbot|\
  1230. thumbbot|\
  1231. thumbnail\.cz\ robot|\
  1232. thumbshots\-de\-bot|\
  1233. tigerbot|\
  1234. tighttwatbot|\
  1235. tineye|\
  1236. titan|\
  1237. to\-dress\_ru\_bot\_|\
  1238. to\-night\-bot|\
  1239. tocrawl|\
  1240. topicalizer|\
  1241. topicblogs|\
  1242. toplistbot|\
  1243. topserver\ php|\
  1244. topyx\-crawler|\
  1245. touche|\
  1246. tourlentascanner|\
  1247. tpsystem|\
  1248. traazi|\
  1249. transgenikbot|\
  1250. travel\-search|\
  1251. travelbot|\
  1252. travellazerbot|\
  1253. treezy|\
  1254. trendiction|\
  1255. trex|\
  1256. tridentspider|\
  1257. trovator|\
  1258. true\_robot|\
  1259. tscholarsbot|\
  1260. tsm\ translation\-search\-machine|\
  1261. tswebbot|\
  1262. tulipchain|\
  1263. turingos|\
  1264. turnitinbot|\
  1265. tutorgigbot|\
  1266. tweetedtimes\ bot|\
  1267. tweetmemebot|\
  1268. twengabot|\
  1269. twice|\
  1270. twikle|\
  1271. twinuffbot|\
  1272. twisted\ pagegetter|\
  1273. twitturls|\
  1274. twitturly|\
  1275. tygobot|\
  1276. tygoprowler|\
  1277. typhoeus|\
  1278. u\.s\.\ government\ printing\ office|\
  1279. uberbot|\
  1280. ucb\-nutch|\
  1281. udmsearch|\
  1282. ufam\-crawler\-|\
  1283. ultraseek|\
  1284. unchaos|\
  1285. unisterbot|\
  1286. unidentified|\
  1287. unitek\ uniengine|\
  1288. universalsearch|\
  1289. unwindfetchor|\
  1290. uoftdb\_experiment|\
  1291. updated|\
  1292. url\ control|\
  1293. url\-checker|\
  1294. urlappendbot|\
  1295. urlblaze|\
  1296. urlchecker|\
  1297. urlck|\
  1298. urldispatcher|\
  1299. urlspiderpro|\
  1300. urly\ warning|\
  1301. urly\.warning|\
  1302. url\_gather|\
  1303. usaf\ afkn\ k2spider|\
  1304. usasearch|\
  1305. uss\-cosmix|\
  1306. usyd\-nlp\-spider|\
  1307. vacobot|\
  1308. vacuum|\
  1309. vadixbot|\
  1310. vagabondo|\
  1311. validator|\
  1312. valkyrie|\
  1313. vbseo|\
  1314. vci\ webviewer\ vci\ webviewer\ win32|\
  1315. verbstarbot|\
  1316. vericitecrawler|\
  1317. verifactrola|\
  1318. verity\-url\-gateway|\
  1319. vermut|\
  1320. versus\ crawler|\
  1321. versus\.integis\.ch|\
  1322. viasarchivinginformation\.html|\
  1323. vipr|\
  1324. virus\-detector|\
  1325. virus\_detector|\
  1326. visbot|\
  1327. vishal\ for\ clia|\
  1328. visweb|\
  1329. vital\ search'n\ urchin|\
  1330. vlad|\
  1331. vlsearch|\
  1332. voilabot|\
  1333. vmbot|\
  1334. vocusbot|\
  1335. voideye|\
  1336. voil|\
  1337. vortex|\
  1338. voyager|\
  1339. vspider|\
  1340. w3c\-webcon|\
  1341. w3c\_unicorn|\
  1342. w3search|\
  1343. wacbot|\
  1344. wanadoo|\
  1345. wastrix|\
  1346. water\ conserve\ portal|\
  1347. water\ conserve\ spider|\
  1348. watzbot|\
  1349. wauuu|\
  1350. wavefire|\
  1351. waypath|\
  1352. wazzup|\
  1353. wbdbot|\
  1354. web\ ceo\ online\ robot|\
  1355. web\ crawler|\
  1356. web\ downloader|\
  1357. web\ image\ collector|\
  1358. web\ link\ validator|\
  1359. web\ magnet|\
  1360. web\ site\ downloader|\
  1361. web\ sucker|\
  1362. web\-agent|\
  1363. web\-sniffer|\
  1364. web\.image\.collector|\
  1365. webaltbot|\
  1366. webauto|\
  1367. webbot|\
  1368. webbul\-bot|\
  1369. webcapture|\
  1370. webcheck|\
  1371. webclipping\.com|\
  1372. webcollage|\
  1373. webcopier|\
  1374. webcopy|\
  1375. webcorp|\
  1376. webcrawl\.net|\
  1377. webcrawler|\
  1378. webdatacentrebot|\
  1379. webdownloader\ for\ x|\
  1380. webdup|\
  1381. webemailextrac|\
  1382. webenhancer|\
  1383. webfetch|\
  1384. webgather|\
  1385. webgo\ is|\
  1386. webgobbler|\
  1387. webimages|\
  1388. webinator\-search2|\
  1389. webinator\-wbi|\
  1390. webindex|\
  1391. weblayers|\
  1392. webleacher|\
  1393. weblexbot|\
  1394. weblinker|\
  1395. weblyzard|\
  1396. webmastercoffee|\
  1397. webmasterworld\ extractor|\
  1398. webmasterworldforumbot|\
  1399. webminer|\
  1400. webmoose|\
  1401. webot|\
  1402. webpix|\
  1403. webreaper|\
  1404. webripper|\
  1405. websauger|\
  1406. webscan|\
  1407. websearchbench|\
  1408. website|\
  1409. webspear|\
  1410. websphinx|\
  1411. webspider|\
  1412. webster|\
  1413. webstripper|\
  1414. webtrafficexpress|\
  1415. webtrends\ link\ analyzer|\
  1416. webvac|\
  1417. webwalk|\
  1418. webwasher|\
  1419. webwatch|\
  1420. webwhacker|\
  1421. webxm|\
  1422. webzip|\
  1423. weddings\.info|\
  1424. wenbin|\
  1425. wep\ search|\
  1426. wepa|\
  1427. werelatebot|\
  1428. wget|\
  1429. whacker|\
  1430. whirlpool\ web\ engine|\
  1431. whowhere\ robot|\
  1432. widow|\
  1433. wikiabot|\
  1434. wikio|\
  1435. wikiwix\-bot\-|\
  1436. winhttp|\
  1437. wire|\
  1438. wisebot|\
  1439. wisenutbot|\
  1440. wish\-la|\
  1441. wish\-project|\
  1442. wisponbot|\
  1443. wmcai\-robot|\
  1444. wminer|\
  1445. wmsbot|\
  1446. woriobot|\
  1447. worldshop|\
  1448. worqmada|\
  1449. wotbox|\
  1450. wume\_crawler|\
  1451. www\ collector|\
  1452. www\-collector\-e|\
  1453. www\-mechanize|\
  1454. wwwoffle|\
  1455. wwwrobot|\
  1456. wwwster|\
  1457. wwwwanderer|\
  1458. wwwxref|\
  1459. wysigot|\
  1460. x\-clawler|\
  1461. x\-crawler|\
  1462. xaldon|\
  1463. xenu|\
  1464. xerka\ metabot|\
  1465. xerka\ webbot|\
  1466. xget|\
  1467. xirq|\
  1468. xmarksfetch|\
  1469. xqrobot|\
  1470. y!j|\
  1471. yacy\.net|\
  1472. yacybot|\
  1473. yanga\ worldsearch\ bot|\
  1474. yarienavoir\.net|\
  1475. yasaklibot|\
  1476. yats\ crawler|\
  1477. ybot|\
  1478. yebolbot|\
  1479. yellowjacket|\
  1480. yeti|\
  1481. yolinkbot|\
  1482. yooglifetchagent|\
  1483. yoono|\
  1484. yottacars\_bot|\
  1485. yourls|\
  1486. z\-add\ link\ checker|\
  1487. zagrebin|\
  1488. zao|\
  1489. zedzo\.validate|\
  1490. zermelo|\
  1491. zeus|\
  1492. zibber\-v|\
  1493. zimeno|\
  1494. zing-bottabot|\
  1495. zipppbot|\
  1496. zongbot|\
  1497. zoomspider|\
  1498. zotag\ search|\
  1499. zsebot|\
  1500. zuibot|\
  1501. zyborg|\
  1502. zyte\
  1503.  [NC]
  1504. RewriteRule .* - [F]
  1505. #bad bots end