krlaboratories

use robots.txt for block bad bots and crawlers

Oct 30th, 2021 (edited)
600
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
PHP 5.25 KB | None | 0 0
  1. # Block Bad Bots Crawling your Website Blocked by Robots.txt
  2. User-agent: asterias
  3. Disallow:/
  4. User-agent: BackDoorBot/1.0
  5. Disallow:/
  6. User-agent: Black Hole
  7. Disallow:/
  8. User-agent: BlowFish/1.0
  9. Disallow:/
  10. User-agent: BotALot
  11. Disallow:/
  12. User-agent: BuiltBotTough
  13. Disallow:/
  14. User-agent: Bullseye/1.0
  15. Disallow:/
  16. User-agent: BunnySlippers
  17. Disallow:/
  18. User-agent: Cegbfeieh
  19. Disallow:/
  20. User-agent: CheeseBot
  21. Disallow:/
  22. User-agent: CherryPicker
  23. Disallow:/
  24. User-agent: CherryPickerElite/1.0
  25. Disallow:/
  26. User-agent: CherryPickerSE/1.0
  27. Disallow:/
  28. User-agent: CopyRightCheck
  29. Disallow:/
  30. User-agent: cosmos
  31. Disallow:/
  32. User-agent: Crescent
  33. Disallow:/
  34. User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0
  35. Disallow:/
  36. User-agent: DittoSpyder
  37. Disallow:/
  38. User-agent: EmailCollector
  39. Disallow:/
  40. User-agent: EmailSiphon
  41. Disallow:/
  42. User-agent: EmailWolf
  43. Disallow:/
  44. User-agent: EroCrawler
  45. Disallow:/
  46. User-agent: ExtractorPro
  47. Disallow:/
  48. User-agent: Foobot
  49. Disallow:/
  50. User-agent: Harvest/1.5
  51. Disallow:/
  52. User-agent: hloader
  53. Disallow:/
  54. User-agent: httplib
  55. Disallow:/
  56. User-agent: humanlinks
  57. Disallow:/
  58. User-agent: InfoNaviRobot
  59. Disallow:/
  60. User-agent: JennyBot
  61. Disallow:/
  62. User-agent: Kenjin Spider
  63. Disallow:/
  64. User-agent: Keyword Density/0.9
  65. Disallow:/
  66. User-agent: LexiBot
  67. Disallow:/
  68. User-agent: libWeb/clsHTTP
  69. Disallow:/
  70. User-agent: LinkextractorPro
  71. Disallow:/
  72. User-agent: LinkScan/8.1a Unix
  73. Disallow:/
  74. User-agent: LinkWalker
  75. Disallow:/
  76. User-agent: LNSpiderguy
  77. Disallow:/
  78. User-agent: lwp-trivial
  79. Disallow:/
  80. User-agent: lwp-trivial/1.34
  81. Disallow:/
  82. User-agent: Mata Hari
  83. Disallow:/
  84. User-agent: Microsoft URL Control - 5.01.4511
  85. Disallow:/
  86. User-agent: Microsoft URL Control - 6.00.8169
  87. Disallow:/
  88. User-agent: MIIxpc
  89. Disallow:/
  90. User-agent: MIIxpc/4.2
  91. Disallow:/
  92. User-agent: Mister PiX
  93. Disallow:/
  94. User-agent: moget
  95. Disallow:/
  96. User-agent: moget/2.1
  97. Disallow:/
  98. User-agent: mozilla/4
  99. Disallow:/
  100. User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95)
  101. Disallow:/
  102. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 95)
  103. Disallow:/
  104. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 98)
  105. Disallow:/
  106. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows NT)
  107. Disallow:/
  108. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows XP)
  109. Disallow:/
  110. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 2000)
  111. Disallow:/
  112. User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows ME)
  113. Disallow:/
  114. User-agent: mozilla/5
  115. Disallow:/
  116. User-agent: NetAnts
  117. Disallow:/
  118. User-agent: NICErsPRO
  119. Disallow:/
  120. User-agent: Offline Explorer
  121. Disallow:/
  122. User-agent: Openfind
  123. Disallow:/
  124. User-agent: Openfind data gathere
  125. Disallow:/
  126. User-agent: ProPowerBot/2.14
  127. Disallow:/
  128. User-agent: ProWebWalker
  129. Disallow:/
  130. User-agent: QueryN Metasearch
  131. Disallow:/
  132. User-agent: RepoMonkey
  133. Disallow:/
  134. User-agent: RepoMonkey Bait & Tackle/v1.01
  135. Disallow:/
  136. User-agent: RMA
  137. Disallow:/
  138. User-agent: SiteSnagger
  139. Disallow:/
  140. User-agent: SpankBot
  141. Disallow:/
  142. User-agent: spanner
  143. Disallow:/
  144. User-agent: suzuran
  145. Disallow:/
  146. User-agent: Szukacz/1.4
  147. Disallow:/
  148. User-agent: Teleport
  149. Disallow:/
  150. User-agent: TeleportPro
  151. Disallow:/
  152. User-agent: Telesoft
  153. Disallow:/
  154. User-agent: The Intraformant
  155. Disallow:/
  156. User-agent: TheNomad
  157. Disallow:/
  158. User-agent: TightTwatBot
  159. Disallow:/
  160. User-agent: Titan
  161. Disallow:/
  162. User-agent: toCrawl/UrlDispatcher
  163. Disallow:/
  164. User-agent: True_Robot
  165. Disallow:/
  166. User-agent: True_Robot/1.0
  167. Disallow:/
  168. User-agent: turingos
  169. Disallow:/
  170. User-agent: URLy Warning
  171. Disallow:/
  172. User-agent: VCI
  173. Disallow:/
  174. User-agent: VCI WebViewer VCI WebViewer Win32
  175. Disallow:/
  176. User-agent: Web Image Collector
  177. Disallow:/
  178. User-agent: WebAuto
  179. Disallow:/
  180. User-agent: WebBandit
  181. Disallow:/
  182. User-agent: WebBandit/3.50
  183. Disallow:/
  184. User-agent: WebCopier
  185. Disallow:/
  186. User-agent: WebEnhancer
  187. Disallow:/
  188. User-agent: WebmasterWorldForumBot
  189. Disallow:/
  190. User-agent: WebSauger
  191. Disallow:/
  192. User-agent: Website Quester
  193. Disallow:/
  194. User-agent: Webster Pro
  195. Disallow:/
  196. User-agent: WebStripper
  197. Disallow:/
  198. User-agent: WebZip
  199. Disallow:/
  200. User-agent: WebZip/4.0
  201. Disallow:/
  202. User-agent: Wget
  203. Disallow:/
  204. User-agent: Wget/1.5.3
  205. Disallow:/
  206. User-agent: Wget/1.6
  207. Disallow:/
  208. User-agent: WWW-Collector-E
  209. Disallow:/
  210. User-agent: Xenu's
  211. Disallow:/
  212. User-agent: Xenu's Link Sleuth 1.1c
  213. Disallow:/
  214. User-agent: Zeus
  215. Disallow:/
  216. User-agent: Zeus 32297 Webster Pro V2.9 Win32
  217. Disallow:/
  218. Crawl-delay: 20
  219.  
  220. #delay heavy handed bots:
  221.  
  222. User-agent: Googlebot
  223. Crawl-Delay:10
  224. User-agent: Googlebot-Image
  225. Crawl-Delay:10
  226. User-agent: Googlebot-Mobile
  227. Crawl-Delay:10
  228. User-Agent: AhrefsBot
  229. Crawl-Delay: 10
  230. User-Agent: MJ12bot
  231. Crawl-Delay: 10
  232. User-Agent: YandexBot
  233. Crawl-Delay: 10
  234. User-Agent: DotBot
  235. Crawl-Delay: 10
  236. User-Agent: spbot
  237. Crawl-Delay: 10
  238. User-Agent: SeznamBot
  239. Crawl-Delay: 10
  240. User-Agent: YandexImages
  241. Crawl-Delay: 10
  242. User-Agent: msnbot-media
  243. Crawl-Delay: 10
  244. User-Agent: AddThis
  245. Crawl-Delay: 10
  246. User-Agent: BOT
  247. Crawl-Delay: 10
  248. User-Agent: memoryBot
  249. Crawl-Delay: 10
  250. User-Agent: linkdexbot
  251. Crawl-Delay: 10
  252. User-Agent: Konqueror
  253. Crawl-Delay: 10
  254. User-Agent: Exabot
  255. Crawl-Delay: 10
  256. User-Agent: VoilaBot
  257. Crawl-Delay: 10
  258. User-Agent: facebookexternalhit
  259. Crawl-Delay: 10
  260. User-Agent: TurnitinBot
  261. Crawl-Delay: 10
  262. User-Agent: Baiduspider
  263. Crawl-Delay: 10
  264. User-Agent: bingbot
  265. Crawl-Delay: 10
Add Comment
Please, Sign In to add comment