Commit | Line | Data |
---|---|---|
25ab2d04 | 1 | <?xml version="1.0" encoding="UTF-8"?> |
3c9bb073 | 2 | <data xmlns="http://www.woltlab.com" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.woltlab.com http://www.woltlab.com/XSD/5.4/spiderList.xsd"> |
25ab2d04 MW |
3 | <spider ident="ABCdatos"> |
4 | <name>ABCdatos BotLink</name> | |
665cc30d | 5 | <url>http://www.robotstxt.org/db/abcdatos.html</url> |
25ab2d04 | 6 | </spider> |
9581146e PM |
7 | <spider ident="AbraveSpider"> |
8 | <name>Abrave</name> | |
9 | <url>http://robot.abrave.co.uk/</url> | |
10 | </spider> | |
25ab2d04 MW |
11 | <spider ident="abot/"> |
12 | <name>abot</name> | |
25ab2d04 MW |
13 | </spider> |
14 | <spider ident="Accelatech RSSCrawler"> | |
15 | <name>Accelatech</name> | |
16 | </spider> | |
17 | <spider ident="Accoona-AI-Agent"> | |
18 | <name>Accoona</name> | |
19 | <url>http://accoona.com/about/about_accoona.jsp</url> | |
20 | </spider> | |
21 | <spider ident="aconon Index"> | |
22 | <name>aconon Index (raubfische.de)</name> | |
23 | </spider> | |
24 | <spider ident="AcoonBot"> | |
25 | <name>Acoon</name> | |
26 | <url>http://www.acoon.de/robot.asp</url> | |
27 | </spider> | |
28 | <spider ident="Ahoy!"> | |
29 | <name>Ahoy!</name> | |
665cc30d | 30 | <url>http://www.robotstxt.org/db/ahoythehomepagefinder.html</url> |
25ab2d04 MW |
31 | </spider> |
32 | <spider ident="AhrefsBot"> | |
33 | <name>Ahrefs</name> | |
34 | <url>http://ahrefs.com/robot/</url> | |
35 | </spider> | |
36 | <spider ident="AlkalineBOT"> | |
37 | <name>Alkaline</name> | |
665cc30d | 38 | <url>http://www.robotstxt.org/db/Alkaline.html</url> |
25ab2d04 | 39 | </spider> |
f55aa1aa P |
40 | <spider ident="AlexaBOT"> |
41 | <name>Alexa</name> | |
42 | <url>http://www.alexa.com/help/webmasters</url> | |
43 | </spider> | |
25ab2d04 MW |
44 | <spider ident="http://www.almaden.ibm.com/cs/crawler"> |
45 | <name>Almaden Crawler</name> | |
46 | <url>http://www.almaden.ibm.com/cs/crawler/</url> | |
47 | </spider> | |
2af2b30d I |
48 | <spider ident="Barkrowler"> |
49 | <name>Barkrowler</name> | |
50 | <url>https://www.babbar.tech/crawler</url> | |
51 | </spider> | |
25ab2d04 MW |
52 | <spider ident="EMC Spider"> |
53 | <name>ananzi</name> | |
54 | </spider> | |
55 | <spider ident="Anthill"> | |
56 | <name>Anthill</name> | |
665cc30d | 57 | <url>http://www.robotstxt.org/db/anthill.html</url> |
25ab2d04 MW |
58 | </spider> |
59 | <spider ident="Aport"> | |
60 | <name>Aport</name> | |
61 | <url>http://www.aport.ru/</url> | |
62 | </spider> | |
63 | <spider ident="AppleSyndication"> | |
64 | <name>Apple</name> | |
65 | </spider> | |
6aa6c9ba | 66 | <spider ident="Applebot"> |
67 | <name>Applebot</name> | |
68 | <url>https://support.apple.com/en-gb/HT204683</url> | |
69 | </spider> | |
25ab2d04 MW |
70 | <spider ident="Arachnophilia"> |
71 | <name>Arachnophilia</name> | |
665cc30d | 72 | <url>http://www.robotstxt.org/db/arachnophilia.html</url> |
25ab2d04 MW |
73 | </spider> |
74 | <spider ident="Araneo"> | |
75 | <name>Araneo</name> | |
665cc30d | 76 | <url>http://www.robotstxt.org/db/araneo.html</url> |
25ab2d04 MW |
77 | </spider> |
78 | <spider ident="ArchitextSpider"> | |
79 | <name>ArchitextSpider</name> | |
665cc30d | 80 | <url>http://www.robotstxt.org/db/architext.html</url> |
25ab2d04 | 81 | </spider> |
89b52a1a | 82 | <spider ident="archive.org_bot"> |
25ab2d04 | 83 | <name>Archive.org</name> |
89b52a1a | 84 | <url>https://archive.org/details/archive.org_bot</url> |
25ab2d04 MW |
85 | </spider> |
86 | <spider ident="arks/1.0"> | |
87 | <name>arks</name> | |
665cc30d | 88 | <url>http://www.robotstxt.org/db/arks.html</url> |
25ab2d04 MW |
89 | </spider> |
90 | <spider ident="ASpider"> | |
91 | <name>ASpider</name> | |
665cc30d | 92 | <url>http://www.robotstxt.org/db/aspider.html</url> |
25ab2d04 MW |
93 | </spider> |
94 | <spider ident="ATN_Worldwide"> | |
95 | <name>ATN Worldwide</name> | |
665cc30d | 96 | <url>http://www.robotstxt.org/db/atn.html</url> |
25ab2d04 MW |
97 | </spider> |
98 | <spider ident="Atomz"> | |
99 | <name>Atomz.com</name> | |
665cc30d | 100 | <url>http://www.robotstxt.org/db/atomz.html</url> |
25ab2d04 MW |
101 | </spider> |
102 | <spider ident="AURESYS"> | |
103 | <name>AURESYS</name> | |
665cc30d | 104 | <url>http://www.robotstxt.org/db/auresys.html</url> |
25ab2d04 MW |
105 | </spider> |
106 | <spider ident="BackRub"> | |
107 | <name>BackRub</name> | |
665cc30d | 108 | <url>http://www.robotstxt.org/db/backrub.html</url> |
25ab2d04 MW |
109 | </spider> |
110 | <spider ident="Baiduspider"> | |
111 | <name>Baiduspider</name> | |
112 | <url>http://www.baidu.com/search/spider.htm</url> | |
113 | </spider> | |
25ab2d04 MW |
114 | <spider ident="BecomeBot"> |
115 | <name>BecomeBot</name> | |
116 | <url>http://www.become.com/webmasters.html</url> | |
117 | </spider> | |
118 | <spider ident="Big Brother"> | |
119 | <name>Big Brother</name> | |
665cc30d | 120 | <url>http://www.robotstxt.org/db/bigbrother.html</url> |
25ab2d04 MW |
121 | </spider> |
122 | <spider ident="BigmirSpider"> | |
123 | <name>Bigmir</name> | |
124 | <url>http://www.bigmir.net/</url> | |
125 | </spider> | |
126 | <spider ident="bingbot"> | |
127 | <name>Bing</name> | |
128 | <url>http://www.bing.com/bingbot.htm</url> | |
129 | </spider> | |
130 | <spider ident="Bitacle bot"> | |
131 | <name>Bitacle</name> | |
132 | <url>http://bitacle.org/</url> | |
133 | </spider> | |
134 | <spider ident="Biz360 Spider"> | |
135 | <name>Biz</name> | |
136 | <url>http://www.biz360.com</url> | |
137 | </spider> | |
138 | <spider ident="Bjaaland"> | |
139 | <name>Bjaaland</name> | |
665cc30d | 140 | <url>http://www.robotstxt.org/db/bjaaland.html</url> |
25ab2d04 MW |
141 | </spider> |
142 | <spider ident="BlackWidow"> | |
143 | <name>BlackWidow</name> | |
665cc30d | 144 | <url>http://www.robotstxt.org/db/blackwidow.html</url> |
25ab2d04 | 145 | </spider> |
b730b757 MW |
146 | <spider ident="BLEXBot"> |
147 | <name>BLEXBot</name> | |
148 | <url>http://webmeup.com/crawler.html</url> | |
149 | </spider> | |
25ab2d04 MW |
150 | <spider ident="BlogCrawler by Xango"> |
151 | <name>BlogCrawler</name> | |
152 | </spider> | |
153 | <spider ident="blogdb"> | |
154 | <name>BlogDb</name> | |
155 | <url>http://blogdb.jp</url> | |
156 | </spider> | |
157 | <spider ident="blog search engine by BlogFan.ORG"> | |
158 | <name>BlogFan</name> | |
159 | <url>http://www.blogfan.org</url> | |
160 | </spider> | |
161 | <spider ident="Bloglines"> | |
162 | <name>Bloglies</name> | |
163 | <url>http://www.bloglines.com</url> | |
164 | </spider> | |
165 | <spider ident="BlogPulse (ISSpider-3.0)"> | |
166 | <name>BlogPulse</name> | |
167 | </spider> | |
168 | <spider ident="BlogSearch"> | |
169 | <name>BlogSearch</name> | |
170 | <url>http://www.icerocket.com</url> | |
171 | </spider> | |
172 | <spider ident="BlogsNowBot"> | |
173 | <name>BlogsNow</name> | |
174 | <url>http://www.blogsnow.com/</url> | |
175 | </spider> | |
176 | <spider ident="BlogStreetBot"> | |
177 | <name>BlogStreetBot</name> | |
178 | <url>http://www.blogstreet.com/</url> | |
179 | </spider> | |
180 | <spider ident="Bulkfeeds"> | |
181 | <name>BlogStreetBot</name> | |
182 | <url>http://bulkfeeds.net</url> | |
183 | </spider> | |
184 | <spider ident="BoardPulse"> | |
185 | <name>BoardPulse</name> | |
186 | <url>http://www.boardpulse.com/</url> | |
187 | </spider> | |
188 | <spider ident="BoardReader"> | |
189 | <name>BoardReader</name> | |
190 | <url>http://www.boardreader.com/aboutus.asp</url> | |
191 | </spider> | |
192 | <spider ident="BoardViewer"> | |
193 | <name>BoardViewer</name> | |
194 | <url>http://www.boardviewer.com/</url> | |
195 | </spider> | |
196 | <spider ident="boitho.com-robot"> | |
197 | <name>Boitho</name> | |
198 | <url>http://www.boitho.com/bot.html</url> | |
199 | </spider> | |
200 | <spider ident="borg-bot"> | |
201 | <name>Borg-Bot</name> | |
665cc30d | 202 | <url>http://www.robotstxt.org/db/borg-bot.html</url> |
25ab2d04 MW |
203 | </spider> |
204 | <spider ident="BSpider"> | |
205 | <name>BSpider</name> | |
665cc30d | 206 | <url>http://www.robotstxt.org/db/bspider.html</url> |
25ab2d04 | 207 | </spider> |
1b4bb70a SM |
208 | <spider ident="Buck/2.2"> |
209 | <name>Buck</name> | |
210 | <url>https://app.hypefactors.com/media-monitoring/about.html</url> | |
211 | </spider> | |
25ab2d04 MW |
212 | <spider ident="CACTVS Chemistry Spider"> |
213 | <name>CACTVS Chemistry</name> | |
214 | </spider> | |
215 | <spider ident="Calif"> | |
216 | <name>Calif</name> | |
217 | </spider> | |
218 | <spider ident="CaRP/3.6Evolution"> | |
219 | <name>CaRP</name> | |
220 | <url>http://www.biz360.com</url> | |
221 | </spider> | |
222 | <spider ident="Checkbot"> | |
223 | <name>Checkbot</name> | |
224 | </spider> | |
225 | <spider ident="ChristCrawler.com"> | |
226 | <name>ChristCrawler.com</name> | |
227 | </spider> | |
228 | <spider ident="www.cienciaficcion.net"> | |
229 | <name>cIeNcIaFiCcIoN.nEt</name> | |
230 | </spider> | |
231 | <spider ident="CipinetBot"> | |
232 | <name>Cipinet</name> | |
233 | <url>http://www.cipinet.com/bot.html</url> | |
234 | </spider> | |
235 | <spider ident="CJNetworkQuality"> | |
236 | <name>CJNetworkQuality</name> | |
237 | <url>http://www.cj.com/networkquality/</url> | |
238 | </spider> | |
239 | <spider ident="CMC/0.01"> | |
240 | <name>CMC/0.01</name> | |
241 | </spider> | |
242 | <spider ident="ColdFusion"> | |
243 | <name>ColdFusion</name> | |
244 | </spider> | |
245 | <spider ident="combine"> | |
246 | <name>Combine System</name> | |
247 | </spider> | |
248 | <spider ident="Crawler (cometsearch@cometsystems.com)"> | |
249 | <name>cometsystems.com</name> | |
250 | </spider> | |
251 | <spider ident="ComputingSite Robi/1.0"> | |
252 | <name>ComputingSite Robi/1.0</name> | |
253 | </spider> | |
254 | <spider ident="conceptbot"> | |
255 | <name>Conceptbot</name> | |
256 | </spider> | |
cbfe141b I |
257 | <spider ident="Cookiebot"> |
258 | <name>Cookiebot</name> | |
259 | <url>https://www.cookiebot.com/</url> | |
260 | </spider> | |
25ab2d04 MW |
261 | <spider ident="Cooby.de Crawler"> |
262 | <name>Cooby.de Crawler</name> | |
263 | </spider> | |
264 | <spider ident="CoolBot"> | |
265 | <name>CoolBot</name> | |
266 | </spider> | |
267 | <spider ident="Cusco"> | |
268 | <name>Cusco</name> | |
269 | </spider> | |
270 | <spider ident="CyberSpyder"> | |
271 | <name>CyberSpyder</name> | |
272 | </spider> | |
273 | <spider ident="daypopbot"> | |
274 | <name>daypop</name> | |
275 | </spider> | |
276 | <spider ident="DesertRealm.com"> | |
277 | <name>Desert Realm</name> | |
278 | </spider> | |
279 | <spider ident="Deweb"> | |
280 | <name>DeWeb(c)</name> | |
281 | </spider> | |
282 | <spider ident="Die Blinde Kuh"> | |
283 | <name>Die Blinde Kuh</name> | |
665cc30d | 284 | <url>http://www.robotstxt.org/db/blindekuh.html</url> |
25ab2d04 MW |
285 | </spider> |
286 | <spider ident="dienstspider"> | |
287 | <name>DienstSpider</name> | |
288 | </spider> | |
289 | <spider ident="Digger/1.0 JDK/1.3.0"> | |
290 | <name>Digger</name> | |
291 | </spider> | |
292 | <spider ident="Digimarc WebReader"> | |
293 | <name>Digimarc MarcSpider</name> | |
294 | </spider> | |
295 | <spider ident="Digimarc CGIReader"> | |
296 | <name>Digimarc Marcspider/CGI</name> | |
297 | </spider> | |
298 | <spider ident="DIIbot"> | |
299 | <name>Digital Integrity Robot</name> | |
300 | </spider> | |
301 | <spider ident="grabber"> | |
302 | <name>Direct Hit Grabber</name> | |
303 | </spider> | |
304 | <spider ident="discobot"> | |
305 | <name>Discovery</name> | |
306 | <url>http://discoveryengine.com/discobot.html</url> | |
307 | </spider> | |
a370eb7d | 308 | <spider ident="Discordbot"> |
309 | <name>Discord</name> | |
310 | <url>https://discordapp.com/</url> | |
311 | </spider> | |
25ab2d04 MW |
312 | <spider ident="DNAbot/1.0"> |
313 | <name>DNAbot</name> | |
314 | </spider> | |
f51b8b91 | 315 | <spider ident="DotBot"> |
fdaca223 C |
316 | <name>Moz DotBot</name> |
317 | <url>http://www.opensiteexplorer.org/dotbot</url> | |
318 | </spider> | |
25ab2d04 MW |
319 | <spider ident="DragonBot/1.0 libwww/5.0"> |
320 | <name>DragonBot</name> | |
321 | </spider> | |
a370eb7d | 322 | <spider ident="DuckDuckBot"> |
323 | <name>DuckDuckGo</name> | |
05e2373e | 324 | <url>https://help.duckduckgo.com/duckduckgo-help-pages/results/duckduckbot/</url> |
a370eb7d | 325 | </spider> |
25ab2d04 MW |
326 | <spider ident="DWCP/2.0"> |
327 | <name>DWCP (Dridus' Web Cataloging Project)</name> | |
328 | </spider> | |
329 | <spider ident="e-SocietyRobot"> | |
330 | <name>e-Society</name> | |
331 | <url>http://www.yama.info.waseda.ac.jp/~yamana/es/index_eng.htm</url> | |
332 | </spider> | |
333 | <spider ident="exactseek-pagereaper"> | |
334 | <name>eaxactseek-page</name> | |
335 | </spider> | |
336 | <spider ident="EbiNess/0.01a"> | |
337 | <name>EbiNess</name> | |
338 | </spider> | |
339 | <spider ident="edgeio-retriever"> | |
340 | <name>Edgeio</name> | |
341 | <url>http://www.edgeio.com</url> | |
342 | </spider> | |
343 | <spider ident="EIT-Link-Verifier-Robot/0.2"> | |
344 | <name>EIT Link Verifier Robot</name> | |
345 | </spider> | |
346 | <spider ident="elfinbot"> | |
347 | <name>ELFINBOT</name> | |
348 | </spider> | |
349 | <spider ident="Emacs-w3/v[0-9\.]+"> | |
350 | <name>Emacs-w3 Search Engine</name> | |
351 | </spider> | |
352 | <spider ident="esther"> | |
353 | <name>Esther</name> | |
354 | </spider> | |
355 | <spider ident="EuripBot/"> | |
356 | <name>EuripBot</name> | |
357 | </spider> | |
30de0ef8 I |
358 | <spider ident="ev-crawler"> |
359 | <name>Headline Web Crawler</name> | |
360 | <url>https://headline.com/legal/crawler</url> | |
361 | </spider> | |
25ab2d04 MW |
362 | <spider ident="Evliya Celebi"> |
363 | <name>Evliya Celebi</name> | |
364 | </spider> | |
365 | <spider ident="ExactSeek_Spider"> | |
366 | <name>ExactSeek_Spider</name> | |
367 | <url>http://www.askjeevs.com</url> | |
368 | </spider> | |
369 | <spider ident="NG/2.0"> | |
370 | <name>ExaLead</name> | |
371 | <url>http://botspotter.net/bs-389.html</url> | |
372 | </spider> | |
373 | <spider ident="ExaBot"> | |
374 | <name>ExaLead Beta</name> | |
375 | <url>http://beta.exalead.com/search/C=0/2p=Help.7</url> | |
376 | </spider> | |
f55aa1aa P |
377 | <spider ident="ExaLead"> |
378 | <name>ExaLead</name> | |
379 | <url>http://www.exalead.com/search</url> | |
380 | </spider> | |
25ab2d04 MW |
381 | <spider ident="facebookexternalhit"> |
382 | <name>Facebook</name> | |
05e2373e | 383 | <url>https://developers.facebook.com/docs/sharing/webmasters/crawler/</url> |
25ab2d04 MW |
384 | </spider> |
385 | <spider ident="fast-webcrawler"> | |
386 | <name>FAST / AlltheWeb</name> | |
387 | <url>http://help.yahoo.com/help/us/ysearch/slurp/index.html</url> | |
388 | </spider> | |
389 | <spider ident="FastCrawler"> | |
390 | <name>FastCrawler</name> | |
391 | </spider> | |
392 | <spider ident="Feed24.com"> | |
393 | <name>Feed24</name> | |
394 | <url>http://www.feed24.com</url> | |
395 | </spider> | |
396 | <spider ident="FeedBlitz"> | |
397 | <name>FeedBlitz</name> | |
398 | <url>http://www.feedblitz.com</url> | |
399 | </spider> | |
400 | <spider ident="FeedBurner"> | |
401 | <name>FeedBurner</name> | |
402 | <url>http://www.FeedBurner.com</url> | |
403 | </spider> | |
7a944c3f MW |
404 | <spider ident="Feedly"> |
405 | <name>Feedly</name> | |
406 | <url>http://www.feedly.com/fetcher.html</url> | |
407 | </spider> | |
25ab2d04 MW |
408 | <spider ident="Feedfetcher-Google"> |
409 | <name>FeedFetcher-Google</name> | |
410 | <url>http://www.google.com/feedfetcher.html</url> | |
411 | </spider> | |
412 | <spider ident="UniversalFeedParser"> | |
413 | <name>FeedParser</name> | |
414 | <url>http://www.feedparser.org</url> | |
415 | </spider> | |
416 | <spider ident="Feedster Crawler"> | |
417 | <name>Feedster</name> | |
418 | <url>http://www.feedstermedia.com/</url> | |
419 | </spider> | |
420 | <spider ident="FEHLSTART Superspider"> | |
421 | <name>FEHLSTART</name> | |
422 | </spider> | |
423 | <spider ident="FelixIDE"> | |
424 | <name>Felix IDE</name> | |
425 | </spider> | |
426 | <spider ident="ESIRover"> | |
427 | <name>FetchRover</name> | |
428 | </spider> | |
429 | <spider ident="fido"> | |
430 | <name>fido</name> | |
431 | </spider> | |
432 | <spider ident="findlinks"> | |
433 | <name>FindLinks</name> | |
434 | <url>http://wortschatz.uni-leipzig.de/findlinks/</url> | |
435 | </spider> | |
436 | <spider ident="FindoryBot"> | |
437 | <name>Findroy</name> | |
438 | <url>http://www.findory.com</url> | |
439 | </spider> | |
440 | <spider ident="Fish-Search-Robot"> | |
441 | <name>Fish search</name> | |
442 | </spider> | |
443 | <spider ident="Mozilla/4.0 (compatible: FDSE robot)"> | |
444 | <name>Fluid Dynamics</name> | |
445 | </spider> | |
446 | <spider ident="fouineur.9bit.qc.ca"> | |
447 | <name>Fouineur</name> | |
448 | </spider> | |
449 | <spider ident="Freecrawl"> | |
450 | <name>Freecrawl</name> | |
451 | </spider> | |
2f86459f SM |
452 | <spider ident="FreshpingBot"> |
453 | <name>Freshping</name> | |
454 | <url>https://freshping.io/</url> | |
455 | </spider> | |
25ab2d04 MW |
456 | <spider ident="FunnelWeb"> |
457 | <name>FunnelWeb</name> | |
458 | </spider> | |
459 | <spider ident="GaisBot"> | |
460 | <name>Gais</name> | |
461 | <url>http://gais.cs.ccu.edu.tw/robot.php</url> | |
462 | </spider> | |
463 | <spider ident="gamekitbot"> | |
464 | <name>GAMEKIT</name> | |
465 | <url>http://www.uchoose.de/crawler/gamekitbot/</url> | |
466 | </spider> | |
467 | <spider ident="gammaSpider"> | |
468 | <name>gammaSpider</name> | |
469 | </spider> | |
470 | <spider ident="gazz"> | |
471 | <name>gazz</name> | |
472 | </spider> | |
473 | <spider ident="gcreep"> | |
474 | <name>GCreep</name> | |
475 | </spider> | |
476 | <spider ident="genieBot"> | |
477 | <name>genieBot</name> | |
478 | <url>http://64.5.245.11/faq/faq.html</url> | |
479 | </spider> | |
480 | <spider ident="geourl"> | |
481 | <name>GeoURL</name> | |
482 | <url>http://geourl.org/bot.html</url> | |
483 | </spider> | |
484 | <spider ident="GetterroboPlus"> | |
485 | <name>GetterroboPlus Puu</name> | |
486 | </spider> | |
487 | <spider ident="GetURL.rexx"> | |
488 | <name>GetURL</name> | |
489 | </spider> | |
490 | <spider ident="Gigabot"> | |
491 | <name>Gigabot</name> | |
492 | <url>http://www.gigablast.com/spider.html</url> | |
493 | </spider> | |
494 | <spider ident="Girafabot"> | |
495 | <name>Girafabot</name> | |
496 | <url>http://www.girafa.com/</url> | |
497 | </spider> | |
498 | <spider ident="Goku"> | |
499 | <name>Goku</name> | |
500 | <url>http://goku.ru/bot.htm; bot@goku.ru</url> | |
501 | </spider> | |
502 | <spider ident="Golem"> | |
503 | <name>Golem</name> | |
504 | </spider> | |
505 | <spider ident="gonzo"> | |
506 | <name>Gonzo</name> | |
507 | </spider> | |
508 | <spider ident="Googlebot/"> | |
509 | <name>Google</name> | |
510 | <url>http://www.google.com/bot.html</url> | |
511 | </spider> | |
512 | <spider ident="Mediapartners-Google"> | |
513 | <name>Google AdSense</name> | |
514 | <url>https://www.google.com/adsense/faq</url> | |
515 | </spider> | |
516 | <spider ident="Googlebot-Image"> | |
517 | <name>Googlebot-Image</name> | |
518 | <url>http://www.googlebot.com/bot.html</url> | |
519 | </spider> | |
520 | <spider ident="Googlebot-Mobile"> | |
521 | <name>Googlebot-Mobile</name> | |
522 | <url>http://www.google.com/bot.html</url> | |
523 | </spider> | |
2f4ab6f1 | 524 | <spider ident="Googlebot-Video/1.0"> |
525 | <name>Googlebot-Video</name> | |
5ef610cb | 526 | <url>https://developers.google.com/search/docs/advanced/crawling/overview-google-crawlers</url> |
2f4ab6f1 | 527 | </spider> |
5c30f4c0 AE |
528 | <spider ident="GoogleStackdriverMonitoring-UptimeChecks"> |
529 | <name>Google Stackdriver Monitoring</name> | |
530 | <url>https://cloud.google.com/monitoring/alerts/uptime-checks</url> | |
531 | </spider> | |
fdaca223 C |
532 | <spider ident="Google-Ads-Creatives-Assistant"> |
533 | <name>Google-Ads-Creatives-Assistant</name> | |
534 | </spider> | |
535 | <spider ident="Google-AdWords-Express"> | |
536 | <name>Google-AdWords-Express</name> | |
537 | </spider> | |
538 | <spider ident="AdsBot-Google"> | |
539 | <name>Google Ads-Bot</name> | |
540 | <url>http://www.google.com/adsbot.html</url> | |
541 | </spider> | |
25ab2d04 MW |
542 | <spider ident="Gpostbot"> |
543 | <name>Gpostbot</name> | |
544 | <url>http://www.gpost.info/help.php?c=bot</url> | |
545 | </spider> | |
546 | <spider ident="griffon"> | |
547 | <name>Griffon</name> | |
548 | </spider> | |
549 | <spider ident="Gromit"> | |
550 | <name>Gromit</name> | |
551 | </spider> | |
552 | <spider ident="http://grub.org"> | |
553 | <name>Grub Client</name> | |
554 | </spider> | |
555 | <spider ident="Gulper Web Bot"> | |
556 | <name>Gulper Bot</name> | |
557 | </spider> | |
558 | <spider ident="havIndex"> | |
559 | <name>havIndex</name> | |
560 | </spider> | |
561 | <spider ident="HeinrichderMiragoRobot"> | |
562 | <name>HeinrichderMiragoRobot</name> | |
563 | </spider> | |
564 | <spider ident="HenryTheMiragoRobot"> | |
565 | <name>HenryTheMiragoRobot</name> | |
566 | </spider> | |
567 | <spider ident="heritrix"> | |
568 | <name>Heritrix</name> | |
05e2373e | 569 | <url>https://github.com/internetarchive/heritrix3/wiki</url> |
25ab2d04 MW |
570 | </spider> |
571 | <spider ident="HKU WWW Robot"> | |
572 | <name>HKU WWW Octopus</name> | |
573 | </spider> | |
574 | <spider ident="HolyCowDude"> | |
575 | <name>HolyCowDude</name> | |
576 | <url>http://www.holycowdude.com/spider.htm</url> | |
577 | </spider> | |
9581146e PM |
578 | <spider ident="HomeTags"> |
579 | <name>HomeTags</name> | |
580 | <url>http://www.hometags.nl/bot</url> | |
581 | </spider> | |
25ab2d04 MW |
582 | <spider ident="Hometown"> |
583 | <name>Hometown</name> | |
584 | </spider> | |
585 | <spider ident="htdig"> | |
586 | <name>ht://Dig</name> | |
587 | </spider> | |
588 | <spider ident="AITCSRobot"> | |
589 | <name>HTML Index</name> | |
590 | </spider> | |
591 | <spider ident="HTMLgobble"> | |
592 | <name>HTMLgobble</name> | |
593 | </spider> | |
594 | <spider ident="I Robot"> | |
595 | <name>I, Robot</name> | |
596 | </spider> | |
597 | <spider ident="iajaBot"> | |
598 | <name>iajaBot</name> | |
599 | </spider> | |
600 | <spider ident="IBM_Planetwide"> | |
601 | <name>IBM_Planetwide</name> | |
602 | </spider> | |
603 | <spider ident="+http://www.icerocket.com/"> | |
604 | <name>IceRocket</name> | |
605 | <url>http://www.icerocket.com/</url> | |
606 | </spider> | |
607 | <spider ident="ichiro"> | |
608 | <name>ichiro</name> | |
609 | </spider> | |
610 | <spider ident="IlTrovatore-Setaccio"> | |
611 | <name>IlTrovatore-Setaccio</name> | |
612 | <url>http://www.iltrovatore.it/aiuto/faq.html</url> | |
613 | </spider> | |
614 | <spider ident="image.kapsi.net"> | |
615 | <name>image.kapsi.net</name> | |
616 | </spider> | |
617 | <spider ident="Mozilla 3.01 PBWF (Win95)"> | |
618 | <name>Imagelock</name> | |
619 | </spider> | |
620 | <spider ident="IncyWincy"> | |
621 | <name>IncyWincy</name> | |
622 | </spider> | |
623 | <spider ident="Informant"> | |
624 | <name>Informant</name> | |
625 | </spider> | |
626 | <spider ident="InfoSeek Robot"> | |
627 | <name>InfoSeek Robot 1.0</name> | |
628 | </spider> | |
629 | <spider ident="Infoseek Sidewinder"> | |
630 | <name>Infoseek Sidewinder</name> | |
631 | </spider> | |
632 | <spider ident="InfoSpiders"> | |
633 | <name>InfoSpiders</name> | |
634 | </spider> | |
635 | <spider ident="INGRID"> | |
636 | <name>Ingrid</name> | |
637 | </spider> | |
638 | <spider ident="slurp@inktomi"> | |
639 | <name>Inktomi</name> | |
640 | </spider> | |
641 | <spider ident="Insitor"> | |
642 | <name>Insitor</name> | |
643 | <url>http://www.insitor.de/</url> | |
644 | </spider> | |
645 | <spider ident="inspectorwww"> | |
646 | <name>Inspector Web</name> | |
647 | </spider> | |
648 | <spider ident="IAGENT"> | |
649 | <name>IntelliAgent</name> | |
650 | </spider> | |
651 | <spider ident="Intelliseek"> | |
652 | <name>Intelliseek</name> | |
653 | <url>http://www.intelliseek.com/</url> | |
654 | </spider> | |
655 | <spider ident="Internet Cruiser Robot"> | |
656 | <name>Internet Cruiser</name> | |
657 | </spider> | |
658 | <spider ident="internetseer"> | |
659 | <name>Internet Seer</name> | |
660 | </spider> | |
661 | <spider ident="sharp-info-agent"> | |
662 | <name>Internet Shinchakubin</name> | |
663 | </spider> | |
664 | <spider ident="InternetLinkAgent"> | |
665 | <name>InternetLinkAgent</name> | |
666 | </spider> | |
667 | <spider ident="IRLbot"> | |
668 | <name>IRL Crawler</name> | |
669 | <url>http://irl.cs.tamu.edu/crawler</url> | |
670 | </spider> | |
671 | <spider ident="Iron33"> | |
672 | <name>Iron33</name> | |
673 | </spider> | |
674 | <spider ident="IsraeliSearch"> | |
675 | <name>Israeli-search</name> | |
676 | </spider> | |
677 | <spider ident="itchBot"> | |
678 | <name>itch</name> | |
25ab2d04 MW |
679 | </spider> |
680 | <spider ident="JavaBee"> | |
681 | <name>JavaBee</name> | |
682 | </spider> | |
683 | <spider ident="JBot"> | |
684 | <name>JBot</name> | |
685 | </spider> | |
686 | <spider ident="JCrawler"> | |
687 | <name>JCrawler</name> | |
688 | </spider> | |
689 | <spider ident="JetBot"> | |
690 | <name>JetEye</name> | |
691 | <url>http://www.jeteye.com/jetbot.html</url> | |
692 | </spider> | |
693 | <spider ident="JoBo"> | |
694 | <name>JoBo</name> | |
695 | </spider> | |
696 | <spider ident="Jobot"> | |
697 | <name>Jobot</name> | |
698 | </spider> | |
699 | <spider ident="jobs.de"> | |
700 | <name>Jobs.de</name> | |
701 | <url>http://www.jobs.de/</url> | |
702 | </spider> | |
703 | <spider ident="JoeBot"> | |
704 | <name>JoeBot</name> | |
705 | </spider> | |
706 | <spider ident="jumpstation"> | |
707 | <name>JumpStation</name> | |
708 | </spider> | |
709 | <spider ident="Katipo"> | |
710 | <name>Katipo</name> | |
711 | </spider> | |
712 | <spider ident="KDD-Explorer"> | |
713 | <name>KDD-Explorer</name> | |
714 | </spider> | |
715 | <spider ident="KIT-Fireball"> | |
716 | <name>KIT-Fireball</name> | |
717 | </spider> | |
718 | <spider ident="KO_Yappo_Robot"> | |
719 | <name>KO_Yappo_Robot</name> | |
720 | </spider> | |
721 | <spider ident="LabelGrab"> | |
722 | <name>LabelGrabber</name> | |
723 | </spider> | |
724 | <spider ident="larbin"> | |
725 | <name>larbin</name> | |
726 | </spider> | |
727 | <spider ident="legs"> | |
728 | <name>legs</name> | |
729 | </spider> | |
0cf0a5c1 C |
730 | <spider ident="linkdexbot"> |
731 | <name>Linkdex</name> | |
732 | <url>http://www.linkdex.com/bots/</url> | |
733 | </spider> | |
25ab2d04 MW |
734 | <spider ident="LinkScan Server"> |
735 | <name>LinkScan</name> | |
736 | </spider> | |
737 | <spider ident="LinkWalker"> | |
738 | <name>LinkWalker</name> | |
739 | </spider> | |
f55aa1aa P |
740 | <spider ident="Linguee Bot"> |
741 | <name>Linguee</name> | |
742 | <url>http://www.linguee.com/bot</url> | |
743 | </spider> | |
25ab2d04 MW |
744 | <spider ident="livedoorCheckers/"> |
745 | <name>livedoorCheckers</name> | |
746 | </spider> | |
747 | <spider ident="Lockon"> | |
748 | <name>Lockon</name> | |
749 | </spider> | |
750 | <spider ident="logo.gif crawler"> | |
751 | <name>logo.gif</name> | |
752 | </spider> | |
753 | <spider ident="Lycos"> | |
754 | <name>Lycos</name> | |
755 | </spider> | |
756 | <spider ident="Magpie"> | |
757 | <name>Magpie</name> | |
758 | </spider> | |
759 | <spider ident="MJ12bot"> | |
760 | <name>Majestics MJ12bot</name> | |
761 | </spider> | |
762 | <spider ident="Mammoth"> | |
763 | <name>Mammoth</name> | |
764 | <url>http://www.sli-systems.com</url> | |
765 | </spider> | |
766 | <spider ident="Marvin"> | |
767 | <name>Marvin</name> | |
768 | </spider> | |
769 | <spider ident="marvin/infoseek"> | |
770 | <name>marvin/infoseek</name> | |
771 | </spider> | |
772 | <spider ident="M/3.8"> | |
773 | <name>Mattie</name> | |
774 | </spider> | |
775 | <spider ident="MediaFox"> | |
776 | <name>MediaFox</name> | |
777 | </spider> | |
d9cc31f0 SG |
778 | <spider ident="memorybot"> |
779 | <name>Memorybot</name> | |
780 | <url>http://archivethe.net/en/index.php/about/internet_memory1</url> | |
781 | </spider> | |
25ab2d04 MW |
782 | <spider ident="mercator"> |
783 | <name>Mercator</name> | |
784 | <url>http://research.compaq.com/SRC/mercator/</url> | |
785 | </spider> | |
786 | <spider ident="MerzScope"> | |
787 | <name>MerzScope</name> | |
788 | </spider> | |
789 | <spider ident="METASpider"> | |
790 | <name>META</name> | |
791 | <url>http://www.meta.com.ua/</url> | |
792 | </spider> | |
793 | <spider ident="MetaGer-LinkChecker"> | |
794 | <name>MetaGer</name> | |
795 | </spider> | |
796 | <spider ident="MindCrawler"> | |
797 | <name>MindCrawler</name> | |
798 | </spider> | |
799 | <spider ident="Miva"> | |
800 | <name>Miva</name> | |
801 | </spider> | |
802 | <spider ident="UdmSearch"> | |
803 | <name>mnoGoSearch</name> | |
804 | </spider> | |
805 | <spider ident="moget"> | |
806 | <name>moget</name> | |
807 | </spider> | |
808 | <spider ident="MOMspider"> | |
809 | <name>MOMspider</name> | |
810 | </spider> | |
811 | <spider ident="Monster"> | |
812 | <name>Monster</name> | |
813 | </spider> | |
814 | <spider ident="Moreoverbot"> | |
815 | <name>Moreover</name> | |
816 | <url>http://www.moreover.com</url> | |
817 | </spider> | |
818 | <spider ident="msnbot"> | |
819 | <name>MSNBot</name> | |
820 | <url>http://search.msn.com/msnbot.htm</url> | |
821 | </spider> | |
822 | <spider ident="MSRBOT"> | |
823 | <name>MSRBOT</name> | |
824 | <url>http://research.microsoft.com/research/sv/msrbot/</url> | |
825 | </spider> | |
826 | <spider ident="MuscatFerret"> | |
827 | <name>Muscat Ferret</name> | |
828 | </spider> | |
829 | <spider ident="MwdSearch"> | |
830 | <name>Mwd.Search</name> | |
831 | </spider> | |
832 | <spider ident="NPBot"> | |
833 | <name>NameProtect</name> | |
834 | </spider> | |
835 | <spider ident="NaverBot"> | |
836 | <name>NaverBot</name> | |
837 | <url>http://www.spidermatic.com/en/robot-spider/20</url> | |
52bb0ca4 | 838 | </spider> |
6a3fbb36 | 839 | <spider ident="NDSpider"> |
52bb0ca4 | 840 | <name>NDSpider</name> |
25ab2d04 MW |
841 | </spider> |
842 | <spider ident="NEC-MeshExplorer"> | |
843 | <name>NEC-MeshExplorer</name> | |
844 | </spider> | |
845 | <spider ident="Nederland.zoek"> | |
846 | <name>Nederland.zoek</name> | |
847 | </spider> | |
89b52a1a MW |
848 | <spider ident="NerdyBot"> |
849 | <name>NerdyBot</name> | |
850 | <url>http://nerdybot.com/</url> | |
851 | </spider> | |
25ab2d04 MW |
852 | <spider ident="NetCarta CyberPilot Pro"> |
853 | <name>NetCarta WebMap</name> | |
854 | </spider> | |
855 | <spider ident="Netcraft"> | |
856 | <name>Netcraft Web Server Survey</name> | |
857 | <url>http://news.netcraft.com/</url> | |
858 | </spider> | |
859 | <spider ident="NetMechanic"> | |
860 | <name>NetMechanic</name> | |
861 | </spider> | |
862 | <spider ident="NetScoop"> | |
863 | <name>NetScoop</name> | |
864 | </spider> | |
865 | <spider ident="newscan-online"> | |
866 | <name>newscan-online</name> | |
867 | </spider> | |
868 | <spider ident="NextGenSearchBot 1"> | |
869 | <name>NextGenSearchBot</name> | |
870 | <url>http://www.zoominfo.com/NextGenSearchBot</url> | |
871 | </spider> | |
872 | <spider ident="NHSEWalker"> | |
873 | <name>NHSE Web Forager</name> | |
874 | </spider> | |
875 | <spider ident="NIF"> | |
876 | <name>NIF</name> | |
d04e330e | 877 | <url>http://www.newsisfree.com/robot.php</url> |
25ab2d04 MW |
878 | </spider> |
879 | <spider ident="NimbleCrawler"> | |
880 | <name>NimbleCrawler</name> | |
881 | <url>http://www.healthline.com/aboutus.jsp</url> | |
882 | </spider> | |
883 | <spider ident="Nomad"> | |
884 | <name>Nomad</name> | |
885 | </spider> | |
886 | <spider ident="Norbert the Spider"> | |
887 | <name>Norbert</name> | |
888 | <url>http://www.Burf.com</url> | |
889 | </spider> | |
890 | <spider ident="Gulliver"> | |
891 | <name>Northern Light</name> | |
892 | </spider> | |
893 | <spider ident="explorersearch"> | |
894 | <name>nzexplorer</name> | |
895 | </spider> | |
896 | <spider ident="Occam"> | |
897 | <name>Occam</name> | |
898 | </spider> | |
899 | <spider ident="Ocelli"> | |
900 | <name>Ocelli</name> | |
901 | <url>http://www.globalspec.com/Ocelli</url> | |
902 | </spider> | |
903 | <spider ident="Online24-Bot"> | |
904 | <name>Online24-Bot</name> | |
905 | </spider> | |
906 | <spider ident="Openbot"> | |
907 | <name>Openbot</name> | |
908 | <url>http://www.openfind.com.tw/robot.html</url> | |
909 | </spider> | |
910 | <spider ident="Openfind"> | |
911 | <name>Openfind data gatherer</name> | |
912 | </spider> | |
913 | <spider ident="Orbsearch"> | |
914 | <name>Orb Search</name> | |
915 | </spider> | |
916 | <spider ident="PackRat"> | |
917 | <name>Pack Rat</name> | |
918 | </spider> | |
919 | <spider ident="PageBoy"> | |
920 | <name>PageBoy</name> | |
921 | </spider> | |
5657c6b8 N |
922 | <spider ident="Pandalytics"> |
923 | <name>Pandalytics</name> | |
924 | <url>https://domainsbot.com/pandalytics/</url> | |
925 | </spider> | |
25ab2d04 MW |
926 | <spider ident="ParaSite"> |
927 | <name>ParaSite</name> | |
928 | </spider> | |
929 | <spider ident="Patric"> | |
930 | <name>Patric</name> | |
931 | </spider> | |
932 | <spider ident="PEGASUS"> | |
933 | <name>pegasus</name> | |
934 | </spider> | |
935 | <spider ident="PerlCrawler/1.0 Xavatoria/2.0"> | |
936 | <name>PerlCrawler 1.0</name> | |
937 | </spider> | |
6ca2411e | 938 | <spider ident="PetalBot"> |
939 | <name>PetalBot</name> | |
940 | <url>https://aspiegel.com/petalbot</url> | |
941 | </spider> | |
25ab2d04 MW |
942 | <spider ident="PGP-KA"> |
943 | <name>PGP Key Agent</name> | |
944 | </spider> | |
945 | <spider ident="Duppies"> | |
946 | <name>Phantom</name> | |
947 | </spider> | |
948 | <spider ident="phpdig"> | |
949 | <name>PhpDig</name> | |
950 | </spider> | |
951 | <spider ident="PiltdownMan"> | |
952 | <name>PiltdownMan</name> | |
953 | </spider> | |
954 | <spider ident="Pimptrain's robot"> | |
955 | <name>Pimptrain.com's</name> | |
956 | </spider> | |
957 | <spider ident="pingalink"> | |
958 | <name>PingALink</name> | |
959 | </spider> | |
960 | <spider ident="Pioneer"> | |
961 | <name>Pioneer</name> | |
962 | </spider> | |
963 | <spider ident="PluckFeedCrawler"> | |
964 | <name>Pluck</name> | |
965 | <url>http://www.pluck.com</url> | |
966 | </spider> | |
967 | <spider ident="PlumtreeWebAccessor"> | |
968 | <name>PlumtreeWebAccessor</name> | |
969 | </spider> | |
970 | <spider ident="PodNova"> | |
971 | <name>PodNova</name> | |
972 | <url>http://www.podnova.com</url> | |
973 | </spider> | |
974 | <spider ident="Pompos"> | |
975 | <name>Pompos</name> | |
976 | <url>http://dir.com/pompos.html</url> | |
977 | </spider> | |
978 | <spider ident="Poppi"> | |
979 | <name>Poppi</name> | |
980 | </spider> | |
0cf0a5c1 C |
981 | <spider ident="publiclibraryarchive.org"> |
982 | <name>publiclibraryarchive.org</name> | |
983 | </spider> | |
25ab2d04 MW |
984 | <spider ident="gestaltIconoclast"> |
985 | <name>Popular Iconoclast</name> | |
986 | </spider> | |
987 | <spider ident="PortalJuice.com"> | |
988 | <name>Portal Juice</name> | |
989 | </spider> | |
990 | <spider ident="PortalBSpider"> | |
991 | <name>PortalB Spider</name> | |
992 | </spider> | |
f55aa1aa P |
993 | <spider ident="Qualidator"> |
994 | <name>Qualidator</name> | |
995 | <url>www.qualidator.com/Web/de/Support/FAQ_OnlineTestStatistiken.htm</url> | |
996 | </spider> | |
25ab2d04 MW |
997 | <spider ident="www.kolinka.com"> |
998 | <name>Project Kolinka Forum Search</name> | |
999 | <url>http://www.kolinka.com/</url> | |
1000 | </spider> | |
1001 | <spider ident="psbot"> | |
1002 | <name>psbot</name> | |
1003 | </spider> | |
1004 | <spider ident="Qango.com Web Directory"> | |
1005 | <name>Qango</name> | |
1006 | <url>http://www.qango.com</url> | |
1007 | </spider> | |
71a53c20 SM |
1008 | <spider ident="Qwant"> |
1009 | <name>Qwant</name> | |
1010 | <url>https://help.qwant.com/bot/</url> | |
1011 | </spider> | |
f55aa1aa P |
1012 | <spider ident="SBSearch"> |
1013 | <name>SecretSearchEngineLabs.com</name> | |
1014 | <url>http://www.secretsearchenginelabs.com/secret-web-crawler.php</url> | |
1015 | </spider> | |
307ef0a2 | 1016 | <spider ident="SemrushBot"> |
1017 | <name>SemrushBot</name> | |
1018 | <url>http://semrush.com/bot/</url> | |
1019 | </spider> | |
25ab2d04 MW |
1020 | <spider ident="StackRambler"> |
1021 | <name>Rambler</name> | |
1022 | <url>http://www.rambler.ru/</url> | |
1023 | </spider> | |
1024 | <spider ident="Raven"> | |
1025 | <name>Raven Search</name> | |
1026 | </spider> | |
1027 | <spider ident="Resume Robot"> | |
1028 | <name>Resume Robot</name> | |
1029 | </spider> | |
1030 | <spider ident="Road Runner: ImageScape Robot"> | |
1031 | <name>Road Runner: The ImageScape Robot</name> | |
1032 | </spider> | |
1033 | <spider ident="RHCS"> | |
1034 | <name>RoadHouse Crawling System</name> | |
1035 | </spider> | |
1036 | <spider ident="Robbie"> | |
1037 | <name>Robbie the Robot</name> | |
1038 | </spider> | |
1039 | <spider ident="RoboCrawl"> | |
1040 | <name>RoboCrawl</name> | |
1041 | </spider> | |
1042 | <spider ident="Robofox"> | |
1043 | <name>RoboFox</name> | |
1044 | </spider> | |
1045 | <spider ident="Robot du CRIM 1.0a"> | |
1046 | <name>Robot Francoroute</name> | |
1047 | </spider> | |
1048 | <spider ident="Robozilla"> | |
1049 | <name>Robozilla</name> | |
1050 | </spider> | |
1051 | <spider ident="Roverbot"> | |
1052 | <name>Roverbot</name> | |
1053 | </spider> | |
1054 | <spider ident="RSS-SPIDER"> | |
1055 | <name>RSS Feed Seeker</name> | |
1056 | <url>http://www.rss-spider.com/fsb.php</url> | |
1057 | </spider> | |
1058 | <spider ident="RuLeS"> | |
1059 | <name>RuLeS</name> | |
1060 | </spider> | |
9581146e PM |
1061 | <spider ident="RyzeCrawler"> |
1062 | <name>RyzeCrawler</name> | |
1063 | <url>http://www.domain2day.nl/crawler/</url> | |
1064 | </spider> | |
25ab2d04 MW |
1065 | <spider ident="SafetyNet Robot"> |
1066 | <name>SafetyNet</name> | |
1067 | </spider> | |
1068 | <spider ident="SBIder"> | |
1069 | <name>SBIder.</name> | |
1070 | <url>http://www.sitesell.com/sbider.html</url> | |
1071 | </spider> | |
1072 | <spider ident="Scharia"> | |
1073 | <name>Scharia</name> | |
1074 | </spider> | |
1075 | <spider ident="Science-Index"> | |
1076 | <name>Science-Index</name> | |
1077 | </spider> | |
1078 | <spider ident="Scooter"> | |
1079 | <name>Scooter</name> | |
1080 | </spider> | |
1081 | <spider ident="SearchNZ"> | |
1082 | <name>SearchNZ</name> | |
1083 | <url>http://www.searchnz.co.nz/</url> | |
1084 | </spider> | |
1085 | <spider ident="searchprocess"> | |
1086 | <name>SearchProcess</name> | |
1087 | </spider> | |
1088 | <spider ident="SearchmetricsBot"> | |
1089 | <name>SearchmetricsBot</name> | |
1090 | <url>http://www.searchmetrics.com/en/searchmetrics-bot/</url> | |
1091 | </spider> | |
1092 | <spider ident="Seekbot"> | |
1093 | <name>Seekbot</name> | |
1094 | <url>http://www.seekbot.net/bot.html</url> | |
1095 | </spider> | |
4cba12bf I |
1096 | <spider ident="SeekportBot"> |
1097 | <name>Seekport Bot</name> | |
1098 | <url>https://bot.seekport.com</url> | |
1099 | </spider> | |
25ab2d04 MW |
1100 | <spider ident="Senrigan"> |
1101 | <name>Senrigan</name> | |
1102 | </spider> | |
1103 | <spider ident="Sensis Web Crawler"> | |
1104 | <name>Sensis Web Crawler</name> | |
1105 | <url>http://www.sensis.com.au/help.do</url> | |
1106 | </spider> | |
16240335 | 1107 | <spider ident="SentiBot"> |
4c8c4953 | 1108 | <name>SentiBot</name> |
16240335 C |
1109 | <url>http://www.sentibot.eu</url> |
1110 | </spider> | |
548371c0 I |
1111 | <spider ident="SEO Scanner"> |
1112 | <name>SEO Scanner</name> | |
1113 | </spider> | |
abafa2ec SM |
1114 | <spider ident="SEOkicks"> |
1115 | <name>SEOkicks</name> | |
1116 | <url>https://www.seokicks.de/robot.html</url> | |
1117 | </spider> | |
08bf1baa SM |
1118 | <spider ident="serpstatbot"> |
1119 | <name>serpstatbot</name> | |
1120 | <url>http://serpstatbot.com/</url> | |
1121 | </spider> | |
a2b39a59 C |
1122 | <spider ident="SeznamBot/3.2"> |
1123 | <name>Seznam Bot</name> | |
1124 | <url>http://napoveda.seznam.cz/en/seznambot-intro/</url> | |
1125 | </spider> | |
25ab2d04 MW |
1126 | <spider ident="SG-Scout"> |
1127 | <name>SG-Scout</name> | |
1128 | </spider> | |
1129 | <spider ident="Shagseeker"> | |
1130 | <name>ShagSeeker</name> | |
1131 | </spider> | |
1132 | <spider ident="Shai'Hulud"> | |
1133 | <name>Shai'Hulud</name> | |
1134 | </spider> | |
1135 | <spider ident="SimBot/1.0"> | |
1136 | <name>Simmany Robot Ver1.0</name> | |
1137 | </spider> | |
a370eb7d | 1138 | <spider ident="SkypeUriPreview"> |
1139 | <name>Skype Preview</name> | |
1140 | <url>https://www.skype.com/</url> | |
1141 | </spider> | |
25ab2d04 MW |
1142 | <spider ident="ssearcher100"> |
1143 | <name>Site Searcher</name> | |
1144 | </spider> | |
1145 | <spider ident="Site Valet"> | |
1146 | <name>Site Valet</name> | |
1147 | </spider> | |
1148 | <spider ident="http://www.site-list.net"> | |
1149 | <name>Site-List</name> | |
1150 | <url>http://www.site-list.net</url> | |
1151 | </spider> | |
1152 | <spider ident="SiteTech-Rover"> | |
1153 | <name>SiteTech-Rover</name> | |
1154 | </spider> | |
1155 | <spider ident="+SitiDi.net/SitiDiBot/"> | |
1156 | <name>SitiDi.net/SitiDiBot</name> | |
1157 | </spider> | |
1158 | <spider ident="aWapClient"> | |
1159 | <name>Skymob.com</name> | |
1160 | </spider> | |
677899c2 AE |
1161 | <spider ident="Slack"> |
1162 | <name>Slackbot</name> | |
1163 | <url>https://api.slack.com/robots</url> | |
1164 | </spider> | |
25ab2d04 MW |
1165 | <spider ident="SLCrawler"> |
1166 | <name>SLCrawler</name> | |
1167 | </spider> | |
1168 | <spider ident="Sleek Spider"> | |
1169 | <name>Sleek</name> | |
1170 | </spider> | |
1171 | <spider ident="ESISmartSpider"> | |
1172 | <name>Smart Spider</name> | |
1173 | </spider> | |
1174 | <spider ident="Snapbot"> | |
1175 | <name>Snapbot</name> | |
1176 | <url>http://www.snap.com/</url> | |
1177 | </spider> | |
1178 | <spider ident="Snooper"> | |
1179 | <name>Snooper</name> | |
1180 | </spider> | |
1181 | <spider ident="sohu-search"> | |
1182 | <name>sohu-search</name> | |
1183 | </spider> | |
1184 | <spider ident="Solbot"> | |
1185 | <name>Solbot</name> | |
1186 | </spider> | |
1187 | <spider ident="Speedy Spider"> | |
1188 | <name>Speedy Spider</name> | |
1189 | <url>http://www.entireweb.com/about/search_tech/speedyspider/</url> | |
1190 | </spider> | |
1191 | <spider ident="Sphere Scout"> | |
1192 | <name>Sphere</name> | |
1193 | </spider> | |
1194 | <spider ident="Sphider2"> | |
1195 | <name>Sphider</name> | |
1196 | </spider> | |
1197 | <spider ident="SpiderBot"> | |
1198 | <name>SpiderBot</name> | |
1199 | </spider> | |
1200 | <spider ident="spiderline"> | |
1201 | <name>Spiderline Crawler</name> | |
1202 | </spider> | |
1203 | <spider ident="SpiderMan"> | |
1204 | <name>SpiderMan</name> | |
1205 | </spider> | |
1206 | <spider ident="SpiderView"> | |
1207 | <name>SpiderView(tm)</name> | |
1208 | </spider> | |
1209 | <spider ident="mouse.house"> | |
1210 | <name>spider_monkey</name> | |
1211 | </spider> | |
1212 | <spider ident="suke"> | |
1213 | <name>Suke</name> | |
1214 | </spider> | |
1215 | <spider ident="suntek"> | |
1216 | <name>suntek search engine</name> | |
1217 | </spider> | |
1218 | <spider ident="Szukacz"> | |
1219 | <name>Szukacz</name> | |
1220 | <url>http://www.szukacz.pl/html/RobotEnglishVersion.html</url> | |
1221 | </spider> | |
1222 | <spider ident="T-H-U-N-D-E-R-S-T-O-N-E"> | |
1223 | <name>T-H-U-N-D-E-R-S-T-O-N-E</name> | |
1224 | </spider> | |
f55aa1aa P |
1225 | <spider ident="TinEye Crawler"> |
1226 | <name>TinEye</name> | |
1227 | <url>http://tineye.com/crawler.html</url> | |
1228 | </spider> | |
25ab2d04 MW |
1229 | <spider ident="Black Widow"> |
1230 | <name>TACH Black Widow</name> | |
1231 | </spider> | |
e7d8bd51 | 1232 | <spider ident="Tapatalk CloudSearch"> |
0cf0a5c1 C |
1233 | <name>Tapatalk CloudSearch</name> |
1234 | </spider> | |
25ab2d04 MW |
1235 | <spider ident="Tarantula"> |
1236 | <name>Tarantula</name> | |
1237 | </spider> | |
1238 | <spider ident="tarspider"> | |
1239 | <name>tarspider</name> | |
1240 | </spider> | |
1241 | <spider ident="dlw3robot"> | |
1242 | <name>Tcl W3 Robot</name> | |
1243 | </spider> | |
1244 | <spider ident="TechBOT"> | |
1245 | <name>TechBOT</name> | |
1246 | </spider> | |
1247 | <spider ident="Technoratibot"> | |
1248 | <name>Technorati</name> | |
1249 | <url>http://technorati.com/about/</url> | |
1250 | </spider> | |
1251 | <spider ident="Templeton"> | |
1252 | <name>Templeton</name> | |
1253 | </spider> | |
1254 | <spider ident="teoma"> | |
1255 | <name>Teoma/Ask Jeeves</name> | |
1256 | <url>http://sp.teoma.com/docs/teoma/about/</url> | |
1257 | </spider> | |
1258 | <spider ident="JubiiRobot"> | |
1259 | <name>The Jubii</name> | |
1260 | </spider> | |
1261 | <spider ident="NorthStar"> | |
1262 | <name>The NorthStar Robot</name> | |
1263 | </spider> | |
1264 | <spider ident="w3index"> | |
1265 | <name>The NWI Robot</name> | |
1266 | </spider> | |
1267 | <spider ident="Peregrinator-Mathematics"> | |
1268 | <name>The Peregrinator</name> | |
1269 | </spider> | |
0cf0a5c1 C |
1270 | <spider ident="Pixray-Seeker"> |
1271 | <name>Pixray</name> | |
1272 | <url>http://www.pixray.com/pixraybot/</url> | |
1273 | </spider> | |
a370eb7d | 1274 | <spider ident="TelegramBot (like TwitterBot)"> |
1275 | <name>TelegramBot (like TwitterBot)</name> | |
1276 | <url>https://telegram.org/</url> | |
1277 | </spider> | |
25ab2d04 MW |
1278 | <spider ident="thumbshots-de-Bot"> |
1279 | <name>thumbshots-de-Bot</name> | |
1280 | </spider> | |
1281 | <spider ident="TITAN"> | |
1282 | <name>TITAN</name> | |
1283 | </spider> | |
1284 | <spider ident="TitIn"> | |
1285 | <name>TitIn</name> | |
1286 | </spider> | |
1287 | <spider ident="TLSpider"> | |
1288 | <name>TLSpider</name> | |
1289 | </spider> | |
1290 | <spider ident="TMCrawler"> | |
1291 | <name>TMCrawler</name> | |
1292 | </spider> | |
1293 | <spider ident="trendictionbot"> | |
1294 | <name>Trendiction-Bot</name> | |
1295 | <url>http://www.trendiction.com/bot</url> | |
1296 | </spider> | |
1297 | <spider ident="slysearch"> | |
1298 | <name>Turnitin.com</name> | |
1299 | <url>http://www.turnitin.com/static/products_services/search_engines.html</url> | |
1300 | </spider> | |
1301 | <spider ident="TurnitinBot/"> | |
1302 | <name>TurnitinBot</name> | |
1303 | </spider> | |
1304 | <spider ident="TurtleScanner"> | |
1305 | <name>Turtle</name> | |
1306 | <url>http://www.turtle.ru/</url> | |
1307 | </spider> | |
9581146e PM |
1308 | <spider ident="TwengaBot"> |
1309 | <name>Twenga</name> | |
1310 | <url>http://www.twenga.com/bot.html</url> | |
1311 | </spider> | |
25ab2d04 MW |
1312 | <spider ident="Twiceler"> |
1313 | <name>Twiceler</name> | |
1314 | <url>http://www.cuill.com/twiceler/robot.html</url> | |
1315 | </spider> | |
a370eb7d | 1316 | <spider ident="Twitterbot"> |
1317 | <name>Twitterbot</name> | |
1318 | <url>https://twitter.com/</url> | |
1319 | </spider> | |
25ab2d04 MW |
1320 | <spider ident="UCSD-Crawler"> |
1321 | <name>UCSD Crawl</name> | |
1322 | </spider> | |
1323 | <spider ident="UMBC-memeta-Bot"> | |
1324 | <name>UMBC</name> | |
1325 | </spider> | |
1326 | <spider ident="unisterbot"> | |
1327 | <name>Unister</name> | |
1328 | </spider> | |
1329 | <spider ident="Unpartisan"> | |
1330 | <name>Unpartisan</name> | |
1331 | <url>http://www.unpartisan.com</url> | |
1332 | </spider> | |
4465d786 I |
1333 | <spider ident="Uptime-Kuma"> |
1334 | <name>Uptime-Kuma</name> | |
1335 | <url>https://uptime.kuma.pet/</url> | |
1336 | </spider> | |
a602e267 SK |
1337 | <spider ident="UptimeRobot/2.0"> |
1338 | <name>Uptime Robot</name> | |
1339 | <url>http://uptimerobot.com/</url> | |
1340 | </spider> | |
25ab2d04 MW |
1341 | <spider ident="urlck"> |
1342 | <name>URL Check</name> | |
1343 | </spider> | |
1344 | <spider ident="URL Spider Pro"> | |
1345 | <name>URL Spider Pro</name> | |
1346 | </spider> | |
1347 | <spider ident="Valkyrie"> | |
1348 | <name>Valkyrie</name> | |
1349 | </spider> | |
37b2fc3c I |
1350 | <spider ident="VelenPublicWebCrawler"> |
1351 | <name>Velen Crawler</name> | |
1352 | <url>https://velen.io</url> | |
1353 | </spider> | |
25ab2d04 MW |
1354 | <spider ident="Verticrawl"> |
1355 | <name>Verticrawl</name> | |
1356 | </spider> | |
1357 | <spider ident="Victoria"> | |
1358 | <name>Victoria</name> | |
1359 | </spider> | |
1360 | <spider ident="vision-search"> | |
1361 | <name>vision-search</name> | |
1362 | </spider> | |
1363 | <spider ident="VoilaBot"> | |
1364 | <name>VoilaBot</name> | |
1365 | <url>http://www.voila.com/</url> | |
1366 | </spider> | |
9581146e PM |
1367 | <spider ident="VisBot"> |
1368 | <name>VisBot</name> | |
1369 | <url>http://www.visvo.com/webmasters.html</url> | |
1370 | </spider> | |
25ab2d04 MW |
1371 | <spider ident="Voyager"> |
1372 | <name>Voyager</name> | |
1373 | </spider> | |
1374 | <spider ident="VWbot_K"> | |
1375 | <name>VWbot</name> | |
1376 | </spider> | |
1377 | <spider ident="W3M2"> | |
1378 | <name>W3M2</name> | |
1379 | </spider> | |
1380 | <spider ident="w3mir"> | |
1381 | <name>w3mir</name> | |
1382 | </spider> | |
1383 | <spider ident="w@pSpider"> | |
1384 | <name>w@pSpider</name> | |
1385 | </spider> | |
1386 | <spider ident="appie"> | |
1387 | <name>Walhello appie</name> | |
665cc30d | 1388 | <url>http://www.robotstxt.org/db/appie.html</url> |
25ab2d04 MW |
1389 | </spider> |
1390 | <spider ident="CrawlPaper"> | |
1391 | <name>WallPaper</name> | |
1392 | </spider> | |
1393 | <spider ident="root"> | |
1394 | <name>Web Core / Roots</name> | |
1395 | </spider> | |
f55aa1aa P |
1396 | <spider ident="WBSearchBot"> |
1397 | <name>Ware Bay</name> | |
1398 | <url>http://www.warebay.com/bot.html</url> | |
1399 | </spider> | |
25ab2d04 MW |
1400 | <spider ident="WebMoose"> |
1401 | <name>Web Moose</name> | |
1402 | </spider> | |
1403 | <spider ident="WebBandit"> | |
1404 | <name>WebBandit</name> | |
1405 | </spider> | |
1406 | <spider ident="WebCatcher"> | |
1407 | <name>WebCatcher</name> | |
1408 | </spider> | |
1409 | <spider ident="Webclipping"> | |
1410 | <name>Webclipping</name> | |
1411 | </spider> | |
1412 | <spider ident="WebCopy"> | |
1413 | <name>WebCopy</name> | |
1414 | </spider> | |
1415 | <spider ident="WebFetcher"> | |
1416 | <name>webfetcher</name> | |
1417 | </spider> | |
1418 | <spider ident="weblayers"> | |
1419 | <name>weblayers</name> | |
1420 | </spider> | |
1421 | <spider ident="WebLinker"> | |
1422 | <name>WebLinker</name> | |
1423 | </spider> | |
1424 | <spider ident="wlm"> | |
1425 | <name>Weblog Monitor</name> | |
1426 | </spider> | |
1427 | <spider ident="WebQuest"> | |
1428 | <name>WebQuest</name> | |
1429 | </spider> | |
1430 | <spider ident="WebReaper"> | |
1431 | <name>WebReaper</name> | |
1432 | </spider> | |
1433 | <spider ident="webs@recruit.co.jp"> | |
1434 | <name>webs</name> | |
1435 | </spider> | |
1436 | <spider ident="websearchbench"> | |
1437 | <name>WebSearchBench</name> | |
1438 | <url>http://websearchbench.cs.uni-dortmund.de/</url> | |
1439 | </spider> | |
1440 | <spider ident="WOLP"> | |
1441 | <name>WebStolperer</name> | |
1442 | </spider> | |
1443 | <spider ident="webvac"> | |
1444 | <name>WebVac</name> | |
1445 | </spider> | |
1446 | <spider ident="webwalk"> | |
1447 | <name>webwalk</name> | |
1448 | </spider> | |
1449 | <spider ident="WebWalker"> | |
1450 | <name>WebWalker</name> | |
1451 | </spider> | |
1452 | <spider ident="WebWatch"> | |
1453 | <name>WebWatch</name> | |
52bb0ca4 | 1454 | </spider> |
6a3fbb36 | 1455 | <spider ident="WebZinger"> |
52bb0ca4 | 1456 | <name>WebZinger</name> |
25ab2d04 MW |
1457 | </spider> |
1458 | <spider ident="whatUseek_winona"> | |
1459 | <name>whatUseek Winona</name> | |
52bb0ca4 | 1460 | </spider> |
6a3fbb36 | 1461 | <spider ident="WhoWhere Robot"> |
52bb0ca4 P |
1462 | <name>WebWatch</name> |
1463 | <url>http://www.whowhere.com</url> | |
25ab2d04 MW |
1464 | </spider> |
1465 | <spider ident="SurveyBot"> | |
1466 | <name>Whois Source</name> | |
1467 | <url>http://www.whois.sc/info/webmasters/surveybot.html</url> | |
1468 | </spider> | |
1469 | <spider ident="Hazel's Ferret Web hopper"> | |
1470 | <name>Wild Ferret Web Hopper</name> | |
1471 | </spider> | |
0cf0a5c1 C |
1472 | <spider ident="HRCrawler"> |
1473 | <name>HRCrawler</name> | |
1474 | </spider> | |
25ab2d04 MW |
1475 | <spider ident="WinHTTP"> |
1476 | <name>WinHTTP</name> | |
1477 | </spider> | |
1478 | <spider ident="wired-digital-newsbot"> | |
1479 | <name>Wired Digital</name> | |
1480 | </spider> | |
1481 | <spider ident="zyborg"> | |
1482 | <name>WiseNut</name> | |
1483 | </spider> | |
c3fe17fb | 1484 | <spider ident="WoltLabSuite"> |
1485 | <name>WoltLab Suite</name> | |
1486 | </spider> | |
25ab2d04 MW |
1487 | <spider ident="OmniExplorer_Bot"> |
1488 | <name>WorldIndexer</name> | |
1489 | <url>http://www.omni-explorer.com</url> | |
1490 | </spider> | |
1491 | <spider ident="WWWC"> | |
1492 | <name>WWWC</name> | |
1493 | </spider> | |
1494 | <spider ident="WWWeasel Robot"> | |
1495 | <name>WWWeasel Robot</name> | |
1496 | </spider> | |
1497 | <spider ident="wwwster"> | |
1498 | <name>wwwster</name> | |
1499 | </spider> | |
1500 | <spider ident="WWWWanderer"> | |
1501 | <name>WWWWanderer</name> | |
1502 | </spider> | |
1503 | <spider ident="TECOMAC-Crawler"> | |
1504 | <name>X-Crawler</name> | |
1505 | </spider> | |
1506 | <spider ident="XGET"> | |
1507 | <name>XGET</name> | |
1508 | </spider> | |
1509 | <spider ident="cosmos"> | |
1510 | <name>XYLEME Robot</name> | |
1511 | </spider> | |
1512 | <spider ident="yacybot"> | |
1513 | <name>YaCy-Bot</name> | |
f0cbc030 | 1514 | <url>https://yacy.net/bot.html</url> |
25ab2d04 MW |
1515 | </spider> |
1516 | <spider ident="YahooYSMcm"> | |
1517 | <name>Yahoo Publisher Network</name> | |
1518 | <url>http://publisher.yahoo.com/</url> | |
1519 | </spider> | |
1520 | <spider ident="Yahoo-Blogs"> | |
1521 | <name>Yahoo-Blogs</name> | |
1522 | <url>http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html</url> | |
1523 | </spider> | |
1524 | <spider ident="Yahoo Pipes"> | |
1525 | <name>Yahoo Pipes</name> | |
1526 | </spider> | |
1527 | <spider ident="Yahoo! Slurp"> | |
1528 | <name>Yahoo! Slurp</name> | |
1529 | <url>http://help.yahoo.com/help/us/ysearch/slurp</url> | |
1530 | </spider> | |
1531 | <spider ident="Yahoo-VerticalCrawler"> | |
1532 | <name>Yahoo-VerticalCrawler</name> | |
1533 | </spider> | |
1534 | <spider ident="YahooFeedSeeker"> | |
1535 | <name>YahooFeedSeeker</name> | |
1536 | <url>http://my.yahoo.com/s/publishers.html</url> | |
1537 | </spider> | |
1538 | <spider ident="Yandex"> | |
1539 | <name>Yandex</name> | |
1540 | <url>http://www.yandex.ru/</url> | |
1541 | </spider> | |
1542 | <spider ident="zeus"> | |
1543 | <name>Zeus Internet Marketing</name> | |
1544 | <url>http://www.cyber-robotics.com/</url> | |
1545 | </spider> | |
1546 | <spider ident="http://www.zorkk.com"> | |
1547 | <name>Zork</name> | |
1548 | <url>http://www.zorkk.com</url> | |
1549 | </spider> | |
f55aa1aa P |
1550 | <spider ident="Zookabot"> |
1551 | <name>Zookabotk</name> | |
1552 | <url>http://zookabot.com/</url> | |
1553 | </spider> | |
faf45819 SM |
1554 | <spider ident="ZoominfoBot"> |
1555 | <name>ZoominfoBot</name> | |
1556 | <url>https://www.zoominfo.com/about-zoominfo/zoominfobot</url> | |
1557 | </spider> | |
0cf0a5c1 C |
1558 | <spider ident="360Spider"> |
1559 | <name>360Spider</name> | |
1560 | </spider> | |
52bb0ca4 | 1561 | </data> |