Commit | Line | Data |
---|---|---|
25ab2d04 | 1 | <?xml version="1.0" encoding="UTF-8"?> |
99951f50 | 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/6.0/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="Accelatech RSSCrawler"> |
12 | <name>Accelatech</name> | |
13 | </spider> | |
14 | <spider ident="Accoona-AI-Agent"> | |
15 | <name>Accoona</name> | |
cdfa27f5 | 16 | <url>https://www.accoona.com/about/</url> |
25ab2d04 MW |
17 | </spider> |
18 | <spider ident="aconon Index"> | |
19 | <name>aconon Index (raubfische.de)</name> | |
20 | </spider> | |
21 | <spider ident="AcoonBot"> | |
22 | <name>Acoon</name> | |
23 | <url>http://www.acoon.de/robot.asp</url> | |
24 | </spider> | |
25 | <spider ident="Ahoy!"> | |
26 | <name>Ahoy!</name> | |
665cc30d | 27 | <url>http://www.robotstxt.org/db/ahoythehomepagefinder.html</url> |
25ab2d04 MW |
28 | </spider> |
29 | <spider ident="AhrefsBot"> | |
30 | <name>Ahrefs</name> | |
31 | <url>http://ahrefs.com/robot/</url> | |
32 | </spider> | |
33 | <spider ident="AlkalineBOT"> | |
34 | <name>Alkaline</name> | |
665cc30d | 35 | <url>http://www.robotstxt.org/db/Alkaline.html</url> |
25ab2d04 | 36 | </spider> |
3018aace I |
37 | <spider ident="Amazonbot"> |
38 | <name>Amazonbot</name> | |
39 | <url>https://developer.amazon.com/support/amazonbot</url> | |
40 | </spider> | |
f55aa1aa P |
41 | <spider ident="AlexaBOT"> |
42 | <name>Alexa</name> | |
43 | <url>http://www.alexa.com/help/webmasters</url> | |
44 | </spider> | |
25ab2d04 MW |
45 | <spider ident="http://www.almaden.ibm.com/cs/crawler"> |
46 | <name>Almaden Crawler</name> | |
47 | <url>http://www.almaden.ibm.com/cs/crawler/</url> | |
48 | </spider> | |
2af2b30d I |
49 | <spider ident="Barkrowler"> |
50 | <name>Barkrowler</name> | |
51 | <url>https://www.babbar.tech/crawler</url> | |
52 | </spider> | |
25ab2d04 MW |
53 | <spider ident="EMC Spider"> |
54 | <name>ananzi</name> | |
55 | </spider> | |
56 | <spider ident="Anthill"> | |
57 | <name>Anthill</name> | |
665cc30d | 58 | <url>http://www.robotstxt.org/db/anthill.html</url> |
25ab2d04 MW |
59 | </spider> |
60 | <spider ident="Aport"> | |
61 | <name>Aport</name> | |
62 | <url>http://www.aport.ru/</url> | |
63 | </spider> | |
64 | <spider ident="AppleSyndication"> | |
65 | <name>Apple</name> | |
66 | </spider> | |
6aa6c9ba | 67 | <spider ident="Applebot"> |
68 | <name>Applebot</name> | |
69 | <url>https://support.apple.com/en-gb/HT204683</url> | |
70 | </spider> | |
25ab2d04 MW |
71 | <spider ident="Arachnophilia"> |
72 | <name>Arachnophilia</name> | |
665cc30d | 73 | <url>http://www.robotstxt.org/db/arachnophilia.html</url> |
25ab2d04 MW |
74 | </spider> |
75 | <spider ident="Araneo"> | |
76 | <name>Araneo</name> | |
665cc30d | 77 | <url>http://www.robotstxt.org/db/araneo.html</url> |
25ab2d04 MW |
78 | </spider> |
79 | <spider ident="ArchitextSpider"> | |
80 | <name>ArchitextSpider</name> | |
665cc30d | 81 | <url>http://www.robotstxt.org/db/architext.html</url> |
25ab2d04 | 82 | </spider> |
89b52a1a | 83 | <spider ident="archive.org_bot"> |
25ab2d04 | 84 | <name>Archive.org</name> |
89b52a1a | 85 | <url>https://archive.org/details/archive.org_bot</url> |
25ab2d04 MW |
86 | </spider> |
87 | <spider ident="arks/1.0"> | |
88 | <name>arks</name> | |
665cc30d | 89 | <url>http://www.robotstxt.org/db/arks.html</url> |
25ab2d04 MW |
90 | </spider> |
91 | <spider ident="ASpider"> | |
92 | <name>ASpider</name> | |
665cc30d | 93 | <url>http://www.robotstxt.org/db/aspider.html</url> |
25ab2d04 MW |
94 | </spider> |
95 | <spider ident="ATN_Worldwide"> | |
96 | <name>ATN Worldwide</name> | |
665cc30d | 97 | <url>http://www.robotstxt.org/db/atn.html</url> |
25ab2d04 MW |
98 | </spider> |
99 | <spider ident="Atomz"> | |
100 | <name>Atomz.com</name> | |
665cc30d | 101 | <url>http://www.robotstxt.org/db/atomz.html</url> |
25ab2d04 MW |
102 | </spider> |
103 | <spider ident="AURESYS"> | |
104 | <name>AURESYS</name> | |
665cc30d | 105 | <url>http://www.robotstxt.org/db/auresys.html</url> |
25ab2d04 | 106 | </spider> |
94a6867f I |
107 | <spider ident="AwarioSmartBot"> |
108 | <name>AwarioSmartBot</name> | |
109 | <url>https://awario.com/bots.html</url> | |
110 | </spider> | |
111 | <spider ident="AwarioRssBot"> | |
112 | <name>AwarioRssBot</name> | |
113 | <url>https://awario.com/bots.html</url> | |
114 | </spider> | |
25ab2d04 MW |
115 | <spider ident="BackRub"> |
116 | <name>BackRub</name> | |
665cc30d | 117 | <url>http://www.robotstxt.org/db/backrub.html</url> |
25ab2d04 MW |
118 | </spider> |
119 | <spider ident="Baiduspider"> | |
120 | <name>Baiduspider</name> | |
121 | <url>http://www.baidu.com/search/spider.htm</url> | |
122 | </spider> | |
25ab2d04 MW |
123 | <spider ident="BecomeBot"> |
124 | <name>BecomeBot</name> | |
125 | <url>http://www.become.com/webmasters.html</url> | |
126 | </spider> | |
127 | <spider ident="Big Brother"> | |
128 | <name>Big Brother</name> | |
665cc30d | 129 | <url>http://www.robotstxt.org/db/bigbrother.html</url> |
25ab2d04 MW |
130 | </spider> |
131 | <spider ident="BigmirSpider"> | |
132 | <name>Bigmir</name> | |
133 | <url>http://www.bigmir.net/</url> | |
134 | </spider> | |
135 | <spider ident="bingbot"> | |
136 | <name>Bing</name> | |
137 | <url>http://www.bing.com/bingbot.htm</url> | |
138 | </spider> | |
139 | <spider ident="Bitacle bot"> | |
140 | <name>Bitacle</name> | |
141 | <url>http://bitacle.org/</url> | |
142 | </spider> | |
d73de6dc I |
143 | <spider ident="BitBot"> |
144 | <name>BitBot</name> | |
145 | <url>https://bitbot.dev</url> | |
146 | </spider> | |
25ab2d04 MW |
147 | <spider ident="Biz360 Spider"> |
148 | <name>Biz</name> | |
149 | <url>http://www.biz360.com</url> | |
150 | </spider> | |
151 | <spider ident="Bjaaland"> | |
152 | <name>Bjaaland</name> | |
665cc30d | 153 | <url>http://www.robotstxt.org/db/bjaaland.html</url> |
25ab2d04 MW |
154 | </spider> |
155 | <spider ident="BlackWidow"> | |
156 | <name>BlackWidow</name> | |
665cc30d | 157 | <url>http://www.robotstxt.org/db/blackwidow.html</url> |
25ab2d04 | 158 | </spider> |
b730b757 MW |
159 | <spider ident="BLEXBot"> |
160 | <name>BLEXBot</name> | |
f2a434c0 | 161 | <url>http://webmeup-crawler.com/</url> |
b730b757 | 162 | </spider> |
25ab2d04 MW |
163 | <spider ident="BlogCrawler by Xango"> |
164 | <name>BlogCrawler</name> | |
165 | </spider> | |
166 | <spider ident="blogdb"> | |
167 | <name>BlogDb</name> | |
168 | <url>http://blogdb.jp</url> | |
169 | </spider> | |
170 | <spider ident="blog search engine by BlogFan.ORG"> | |
171 | <name>BlogFan</name> | |
172 | <url>http://www.blogfan.org</url> | |
173 | </spider> | |
174 | <spider ident="Bloglines"> | |
175 | <name>Bloglies</name> | |
176 | <url>http://www.bloglines.com</url> | |
177 | </spider> | |
178 | <spider ident="BlogPulse (ISSpider-3.0)"> | |
179 | <name>BlogPulse</name> | |
180 | </spider> | |
181 | <spider ident="BlogSearch"> | |
182 | <name>BlogSearch</name> | |
183 | <url>http://www.icerocket.com</url> | |
184 | </spider> | |
185 | <spider ident="BlogsNowBot"> | |
186 | <name>BlogsNow</name> | |
187 | <url>http://www.blogsnow.com/</url> | |
188 | </spider> | |
189 | <spider ident="BlogStreetBot"> | |
190 | <name>BlogStreetBot</name> | |
191 | <url>http://www.blogstreet.com/</url> | |
192 | </spider> | |
193 | <spider ident="Bulkfeeds"> | |
194 | <name>BlogStreetBot</name> | |
195 | <url>http://bulkfeeds.net</url> | |
196 | </spider> | |
197 | <spider ident="BoardPulse"> | |
198 | <name>BoardPulse</name> | |
199 | <url>http://www.boardpulse.com/</url> | |
200 | </spider> | |
201 | <spider ident="BoardReader"> | |
202 | <name>BoardReader</name> | |
203 | <url>http://www.boardreader.com/aboutus.asp</url> | |
204 | </spider> | |
205 | <spider ident="BoardViewer"> | |
206 | <name>BoardViewer</name> | |
207 | <url>http://www.boardviewer.com/</url> | |
208 | </spider> | |
209 | <spider ident="boitho.com-robot"> | |
210 | <name>Boitho</name> | |
211 | <url>http://www.boitho.com/bot.html</url> | |
212 | </spider> | |
213 | <spider ident="borg-bot"> | |
214 | <name>Borg-Bot</name> | |
665cc30d | 215 | <url>http://www.robotstxt.org/db/borg-bot.html</url> |
25ab2d04 MW |
216 | </spider> |
217 | <spider ident="BSpider"> | |
218 | <name>BSpider</name> | |
665cc30d | 219 | <url>http://www.robotstxt.org/db/bspider.html</url> |
25ab2d04 | 220 | </spider> |
1ac02f65 I |
221 | <spider ident="BublupBot"> |
222 | <name>BublupBot</name> | |
223 | <url>https://www.bublup.com/bublup-bot.html</url> | |
224 | </spider> | |
1b4bb70a SM |
225 | <spider ident="Buck/2.2"> |
226 | <name>Buck</name> | |
227 | <url>https://app.hypefactors.com/media-monitoring/about.html</url> | |
228 | </spider> | |
36fb7271 I |
229 | <spider ident="Bytespider"> |
230 | <name>Bytespider</name> | |
231 | <url>https://www.bytedance.com/</url> | |
232 | </spider> | |
25ab2d04 MW |
233 | <spider ident="CACTVS Chemistry Spider"> |
234 | <name>CACTVS Chemistry</name> | |
235 | </spider> | |
236 | <spider ident="Calif"> | |
237 | <name>Calif</name> | |
238 | </spider> | |
239 | <spider ident="CaRP/3.6Evolution"> | |
240 | <name>CaRP</name> | |
241 | <url>http://www.biz360.com</url> | |
242 | </spider> | |
71bfd426 I |
243 | <spider ident="CensysInspect"> |
244 | <name>Censys</name> | |
245 | <url>https://about.censys.io/</url> | |
246 | </spider> | |
25ab2d04 MW |
247 | <spider ident="Checkbot"> |
248 | <name>Checkbot</name> | |
249 | </spider> | |
250 | <spider ident="ChristCrawler.com"> | |
251 | <name>ChristCrawler.com</name> | |
252 | </spider> | |
253 | <spider ident="www.cienciaficcion.net"> | |
254 | <name>cIeNcIaFiCcIoN.nEt</name> | |
255 | </spider> | |
fc42a807 I |
256 | <spider ident="Cincraw"> |
257 | <name>Cincraw</name> | |
258 | <url>http://cincrawdata.net/bot/</url> | |
259 | </spider> | |
25ab2d04 MW |
260 | <spider ident="CipinetBot"> |
261 | <name>Cipinet</name> | |
262 | <url>http://www.cipinet.com/bot.html</url> | |
263 | </spider> | |
264 | <spider ident="CJNetworkQuality"> | |
265 | <name>CJNetworkQuality</name> | |
266 | <url>http://www.cj.com/networkquality/</url> | |
267 | </spider> | |
268 | <spider ident="CMC/0.01"> | |
269 | <name>CMC/0.01</name> | |
270 | </spider> | |
271 | <spider ident="ColdFusion"> | |
272 | <name>ColdFusion</name> | |
273 | </spider> | |
274 | <spider ident="combine"> | |
275 | <name>Combine System</name> | |
276 | </spider> | |
277 | <spider ident="Crawler (cometsearch@cometsystems.com)"> | |
278 | <name>cometsystems.com</name> | |
279 | </spider> | |
280 | <spider ident="ComputingSite Robi/1.0"> | |
281 | <name>ComputingSite Robi/1.0</name> | |
282 | </spider> | |
283 | <spider ident="conceptbot"> | |
284 | <name>Conceptbot</name> | |
285 | </spider> | |
cbfe141b I |
286 | <spider ident="Cookiebot"> |
287 | <name>Cookiebot</name> | |
288 | <url>https://www.cookiebot.com/</url> | |
289 | </spider> | |
25ab2d04 MW |
290 | <spider ident="Cooby.de Crawler"> |
291 | <name>Cooby.de Crawler</name> | |
292 | </spider> | |
293 | <spider ident="CoolBot"> | |
294 | <name>CoolBot</name> | |
295 | </spider> | |
36fb7271 I |
296 | <spider ident="CriteoBot"> |
297 | <name>Criteo</name> | |
298 | <url>https://www.criteo.com/criteo-crawler/</url> | |
299 | </spider> | |
25ab2d04 MW |
300 | <spider ident="Cusco"> |
301 | <name>Cusco</name> | |
302 | </spider> | |
303 | <spider ident="CyberSpyder"> | |
304 | <name>CyberSpyder</name> | |
305 | </spider> | |
36fb7271 | 306 | <spider ident="DataForSeoBot"> |
eef85e19 | 307 | <name>DataForSEO</name> |
36fb7271 I |
308 | <url>https://dataforseo.com/dataforseo-bot</url> |
309 | </spider> | |
25ab2d04 MW |
310 | <spider ident="daypopbot"> |
311 | <name>daypop</name> | |
312 | </spider> | |
313 | <spider ident="DesertRealm.com"> | |
314 | <name>Desert Realm</name> | |
315 | </spider> | |
316 | <spider ident="Deweb"> | |
317 | <name>DeWeb(c)</name> | |
318 | </spider> | |
319 | <spider ident="Die Blinde Kuh"> | |
320 | <name>Die Blinde Kuh</name> | |
665cc30d | 321 | <url>http://www.robotstxt.org/db/blindekuh.html</url> |
25ab2d04 MW |
322 | </spider> |
323 | <spider ident="dienstspider"> | |
324 | <name>DienstSpider</name> | |
325 | </spider> | |
326 | <spider ident="Digger/1.0 JDK/1.3.0"> | |
327 | <name>Digger</name> | |
328 | </spider> | |
329 | <spider ident="Digimarc WebReader"> | |
330 | <name>Digimarc MarcSpider</name> | |
331 | </spider> | |
332 | <spider ident="Digimarc CGIReader"> | |
333 | <name>Digimarc Marcspider/CGI</name> | |
334 | </spider> | |
335 | <spider ident="DIIbot"> | |
336 | <name>Digital Integrity Robot</name> | |
337 | </spider> | |
338 | <spider ident="grabber"> | |
339 | <name>Direct Hit Grabber</name> | |
340 | </spider> | |
341 | <spider ident="discobot"> | |
342 | <name>Discovery</name> | |
343 | <url>http://discoveryengine.com/discobot.html</url> | |
344 | </spider> | |
a370eb7d | 345 | <spider ident="Discordbot"> |
346 | <name>Discord</name> | |
347 | <url>https://discordapp.com/</url> | |
348 | </spider> | |
25ab2d04 MW |
349 | <spider ident="DNAbot/1.0"> |
350 | <name>DNAbot</name> | |
351 | </spider> | |
40154603 I |
352 | <spider ident="Domains Project"> |
353 | <name>Domains Project</name> | |
354 | <url>https://domainsproject.org/</url> | |
355 | </spider> | |
f51b8b91 | 356 | <spider ident="DotBot"> |
fdaca223 C |
357 | <name>Moz DotBot</name> |
358 | <url>http://www.opensiteexplorer.org/dotbot</url> | |
359 | </spider> | |
25ab2d04 MW |
360 | <spider ident="DragonBot/1.0 libwww/5.0"> |
361 | <name>DragonBot</name> | |
362 | </spider> | |
b8e6d8fb I |
363 | <spider ident="dragonmetrics"> |
364 | <name>Dragon Metrics</name> | |
365 | <url>https://help.dragonmetrics.com/en/articles/213883-about-dragonbot</url> | |
366 | </spider> | |
3533d304 I |
367 | <spider ident="Dubbotbot"> |
368 | <name>DubBot</name> | |
369 | <url>https://help.dubbot.com/en/articles/2923576-dubbot-s-crawler-ip-address-and-user-agent</url> | |
370 | </spider> | |
a370eb7d | 371 | <spider ident="DuckDuckBot"> |
372 | <name>DuckDuckGo</name> | |
05e2373e | 373 | <url>https://help.duckduckgo.com/duckduckgo-help-pages/results/duckduckbot/</url> |
a370eb7d | 374 | </spider> |
25ab2d04 MW |
375 | <spider ident="DWCP/2.0"> |
376 | <name>DWCP (Dridus' Web Cataloging Project)</name> | |
377 | </spider> | |
378 | <spider ident="e-SocietyRobot"> | |
379 | <name>e-Society</name> | |
380 | <url>http://www.yama.info.waseda.ac.jp/~yamana/es/index_eng.htm</url> | |
381 | </spider> | |
382 | <spider ident="exactseek-pagereaper"> | |
383 | <name>eaxactseek-page</name> | |
384 | </spider> | |
385 | <spider ident="EbiNess/0.01a"> | |
386 | <name>EbiNess</name> | |
387 | </spider> | |
388 | <spider ident="edgeio-retriever"> | |
389 | <name>Edgeio</name> | |
390 | <url>http://www.edgeio.com</url> | |
391 | </spider> | |
392 | <spider ident="EIT-Link-Verifier-Robot/0.2"> | |
393 | <name>EIT Link Verifier Robot</name> | |
394 | </spider> | |
395 | <spider ident="elfinbot"> | |
396 | <name>ELFINBOT</name> | |
397 | </spider> | |
398 | <spider ident="Emacs-w3/v[0-9\.]+"> | |
399 | <name>Emacs-w3 Search Engine</name> | |
400 | </spider> | |
401 | <spider ident="esther"> | |
402 | <name>Esther</name> | |
403 | </spider> | |
404 | <spider ident="EuripBot/"> | |
405 | <name>EuripBot</name> | |
406 | </spider> | |
30de0ef8 I |
407 | <spider ident="ev-crawler"> |
408 | <name>Headline Web Crawler</name> | |
409 | <url>https://headline.com/legal/crawler</url> | |
410 | </spider> | |
25ab2d04 MW |
411 | <spider ident="Evliya Celebi"> |
412 | <name>Evliya Celebi</name> | |
413 | </spider> | |
414 | <spider ident="ExactSeek_Spider"> | |
415 | <name>ExactSeek_Spider</name> | |
416 | <url>http://www.askjeevs.com</url> | |
417 | </spider> | |
418 | <spider ident="NG/2.0"> | |
419 | <name>ExaLead</name> | |
420 | <url>http://botspotter.net/bs-389.html</url> | |
421 | </spider> | |
422 | <spider ident="ExaBot"> | |
423 | <name>ExaLead Beta</name> | |
424 | <url>http://beta.exalead.com/search/C=0/2p=Help.7</url> | |
425 | </spider> | |
f55aa1aa P |
426 | <spider ident="ExaLead"> |
427 | <name>ExaLead</name> | |
428 | <url>http://www.exalead.com/search</url> | |
429 | </spider> | |
25ab2d04 MW |
430 | <spider ident="facebookexternalhit"> |
431 | <name>Facebook</name> | |
05e2373e | 432 | <url>https://developers.facebook.com/docs/sharing/webmasters/crawler/</url> |
25ab2d04 MW |
433 | </spider> |
434 | <spider ident="fast-webcrawler"> | |
435 | <name>FAST / AlltheWeb</name> | |
436 | <url>http://help.yahoo.com/help/us/ysearch/slurp/index.html</url> | |
437 | </spider> | |
438 | <spider ident="FastCrawler"> | |
439 | <name>FastCrawler</name> | |
440 | </spider> | |
441 | <spider ident="Feed24.com"> | |
442 | <name>Feed24</name> | |
443 | <url>http://www.feed24.com</url> | |
444 | </spider> | |
445 | <spider ident="FeedBlitz"> | |
446 | <name>FeedBlitz</name> | |
447 | <url>http://www.feedblitz.com</url> | |
448 | </spider> | |
449 | <spider ident="FeedBurner"> | |
450 | <name>FeedBurner</name> | |
451 | <url>http://www.FeedBurner.com</url> | |
452 | </spider> | |
7a944c3f MW |
453 | <spider ident="Feedly"> |
454 | <name>Feedly</name> | |
455 | <url>http://www.feedly.com/fetcher.html</url> | |
456 | </spider> | |
d84d7011 | 457 | <spider ident="FeedFetcher-Google"> |
25ab2d04 MW |
458 | <name>FeedFetcher-Google</name> |
459 | <url>http://www.google.com/feedfetcher.html</url> | |
460 | </spider> | |
d84d7011 SG |
461 | <spider ident="Google-Read-Aloud"> |
462 | <name>Google Read Aloud</name> | |
463 | <url>https://developers.google.com/search/docs/crawling-indexing/read-aloud-user-agent</url> | |
464 | </spider> | |
465 | <spider ident="Google-Site-Verification/1.0"> | |
466 | <name>Google Site Verifier</name> | |
467 | <url>https://support.google.com/webmasters/answer/9008080</url> | |
468 | </spider> | |
469 | <spider ident="Google-Extended"> | |
470 | <name>Google-Extended</name> | |
471 | </spider> | |
25ab2d04 MW |
472 | <spider ident="UniversalFeedParser"> |
473 | <name>FeedParser</name> | |
474 | <url>http://www.feedparser.org</url> | |
475 | </spider> | |
476 | <spider ident="Feedster Crawler"> | |
477 | <name>Feedster</name> | |
478 | <url>http://www.feedstermedia.com/</url> | |
479 | </spider> | |
480 | <spider ident="FEHLSTART Superspider"> | |
481 | <name>FEHLSTART</name> | |
482 | </spider> | |
483 | <spider ident="FelixIDE"> | |
484 | <name>Felix IDE</name> | |
485 | </spider> | |
486 | <spider ident="ESIRover"> | |
487 | <name>FetchRover</name> | |
488 | </spider> | |
489 | <spider ident="fido"> | |
490 | <name>fido</name> | |
491 | </spider> | |
492 | <spider ident="findlinks"> | |
493 | <name>FindLinks</name> | |
494 | <url>http://wortschatz.uni-leipzig.de/findlinks/</url> | |
495 | </spider> | |
496 | <spider ident="FindoryBot"> | |
497 | <name>Findroy</name> | |
498 | <url>http://www.findory.com</url> | |
499 | </spider> | |
500 | <spider ident="Fish-Search-Robot"> | |
501 | <name>Fish search</name> | |
502 | </spider> | |
503 | <spider ident="Mozilla/4.0 (compatible: FDSE robot)"> | |
504 | <name>Fluid Dynamics</name> | |
505 | </spider> | |
a153da52 I |
506 | <spider ident="my-tiny-bot"> |
507 | <name>My-Tiny-Bot</name> | |
508 | </spider> | |
25ab2d04 MW |
509 | <spider ident="fouineur.9bit.qc.ca"> |
510 | <name>Fouineur</name> | |
511 | </spider> | |
512 | <spider ident="Freecrawl"> | |
513 | <name>Freecrawl</name> | |
514 | </spider> | |
a62fd64b I |
515 | <spider ident="FreeWebMonitoring SiteChecker"> |
516 | <name>FreeWebMonitoring SiteChecker</name> | |
517 | <url>https://www.freewebmonitoring.com/bot.html</url> | |
518 | </spider> | |
2f86459f SM |
519 | <spider ident="FreshpingBot"> |
520 | <name>Freshping</name> | |
521 | <url>https://freshping.io/</url> | |
522 | </spider> | |
cd1dc17e I |
523 | <spider ident="FreshRSS"> |
524 | <name>FreshRSS</name> | |
525 | <url>https://freshrss.org</url> | |
526 | </spider> | |
25ab2d04 MW |
527 | <spider ident="FunnelWeb"> |
528 | <name>FunnelWeb</name> | |
529 | </spider> | |
530 | <spider ident="GaisBot"> | |
531 | <name>Gais</name> | |
532 | <url>http://gais.cs.ccu.edu.tw/robot.php</url> | |
533 | </spider> | |
534 | <spider ident="gamekitbot"> | |
535 | <name>GAMEKIT</name> | |
536 | <url>http://www.uchoose.de/crawler/gamekitbot/</url> | |
537 | </spider> | |
538 | <spider ident="gammaSpider"> | |
539 | <name>gammaSpider</name> | |
540 | </spider> | |
541 | <spider ident="gazz"> | |
542 | <name>gazz</name> | |
543 | </spider> | |
544 | <spider ident="gcreep"> | |
545 | <name>GCreep</name> | |
546 | </spider> | |
547 | <spider ident="genieBot"> | |
548 | <name>genieBot</name> | |
549 | <url>http://64.5.245.11/faq/faq.html</url> | |
550 | </spider> | |
551 | <spider ident="geourl"> | |
552 | <name>GeoURL</name> | |
553 | <url>http://geourl.org/bot.html</url> | |
554 | </spider> | |
555 | <spider ident="GetterroboPlus"> | |
556 | <name>GetterroboPlus Puu</name> | |
557 | </spider> | |
558 | <spider ident="GetURL.rexx"> | |
559 | <name>GetURL</name> | |
560 | </spider> | |
561 | <spider ident="Gigabot"> | |
562 | <name>Gigabot</name> | |
563 | <url>http://www.gigablast.com/spider.html</url> | |
564 | </spider> | |
565 | <spider ident="Girafabot"> | |
566 | <name>Girafabot</name> | |
567 | <url>http://www.girafa.com/</url> | |
568 | </spider> | |
569 | <spider ident="Goku"> | |
570 | <name>Goku</name> | |
571 | <url>http://goku.ru/bot.htm; bot@goku.ru</url> | |
572 | </spider> | |
573 | <spider ident="Golem"> | |
574 | <name>Golem</name> | |
575 | </spider> | |
576 | <spider ident="gonzo"> | |
577 | <name>Gonzo</name> | |
578 | </spider> | |
579 | <spider ident="Googlebot/"> | |
580 | <name>Google</name> | |
581 | <url>http://www.google.com/bot.html</url> | |
582 | </spider> | |
583 | <spider ident="Mediapartners-Google"> | |
584 | <name>Google AdSense</name> | |
585 | <url>https://www.google.com/adsense/faq</url> | |
586 | </spider> | |
587 | <spider ident="Googlebot-Image"> | |
588 | <name>Googlebot-Image</name> | |
589 | <url>http://www.googlebot.com/bot.html</url> | |
590 | </spider> | |
591 | <spider ident="Googlebot-Mobile"> | |
592 | <name>Googlebot-Mobile</name> | |
593 | <url>http://www.google.com/bot.html</url> | |
594 | </spider> | |
2f4ab6f1 | 595 | <spider ident="Googlebot-Video/1.0"> |
596 | <name>Googlebot-Video</name> | |
5ef610cb | 597 | <url>https://developers.google.com/search/docs/advanced/crawling/overview-google-crawlers</url> |
2f4ab6f1 | 598 | </spider> |
d84d7011 SG |
599 | <spider ident="APIs-Google"> |
600 | <name>APIs-Google</name> | |
601 | <url>https://developers.google.com/search/docs/crawling-indexing/apis-user-agent</url> | |
602 | </spider> | |
603 | <spider ident="Google Favicon"> | |
604 | <name>Google Favicon</name> | |
605 | <url>https://developers.google.com/search/docs/appearance/favicon-in-search</url> | |
606 | </spider> | |
607 | <spider ident="Storebot-Google/1.0"> | |
608 | <name>Google StoreBot</name> | |
609 | <url>https://support.google.com/merchants/answer/13294660</url> | |
610 | </spider> | |
611 | <spider ident="Google-InspectionTool/1.0"> | |
612 | <name>Google-InspectionTool</name> | |
613 | <url>https://support.google.com/webmasters/answer/9012289</url> | |
614 | </spider> | |
5c30f4c0 AE |
615 | <spider ident="GoogleStackdriverMonitoring-UptimeChecks"> |
616 | <name>Google Stackdriver Monitoring</name> | |
617 | <url>https://cloud.google.com/monitoring/alerts/uptime-checks</url> | |
618 | </spider> | |
fdaca223 C |
619 | <spider ident="Google-Ads-Creatives-Assistant"> |
620 | <name>Google-Ads-Creatives-Assistant</name> | |
621 | </spider> | |
622 | <spider ident="Google-AdWords-Express"> | |
623 | <name>Google-AdWords-Express</name> | |
624 | </spider> | |
625 | <spider ident="AdsBot-Google"> | |
626 | <name>Google Ads-Bot</name> | |
627 | <url>http://www.google.com/adsbot.html</url> | |
628 | </spider> | |
d84d7011 SG |
629 | <spider ident="AdsBot-Google-Mobile"> |
630 | <name>Google Ads-Bot Mobile</name> | |
631 | <url>http://www.google.com/adsbot.html</url> | |
632 | </spider> | |
25ab2d04 MW |
633 | <spider ident="Gpostbot"> |
634 | <name>Gpostbot</name> | |
635 | <url>http://www.gpost.info/help.php?c=bot</url> | |
636 | </spider> | |
637 | <spider ident="griffon"> | |
638 | <name>Griffon</name> | |
639 | </spider> | |
640 | <spider ident="Gromit"> | |
641 | <name>Gromit</name> | |
642 | </spider> | |
643 | <spider ident="http://grub.org"> | |
644 | <name>Grub Client</name> | |
645 | </spider> | |
646 | <spider ident="Gulper Web Bot"> | |
647 | <name>Gulper Bot</name> | |
648 | </spider> | |
649 | <spider ident="havIndex"> | |
650 | <name>havIndex</name> | |
651 | </spider> | |
652 | <spider ident="HeinrichderMiragoRobot"> | |
653 | <name>HeinrichderMiragoRobot</name> | |
654 | </spider> | |
655 | <spider ident="HenryTheMiragoRobot"> | |
656 | <name>HenryTheMiragoRobot</name> | |
657 | </spider> | |
658 | <spider ident="heritrix"> | |
659 | <name>Heritrix</name> | |
05e2373e | 660 | <url>https://github.com/internetarchive/heritrix3/wiki</url> |
25ab2d04 MW |
661 | </spider> |
662 | <spider ident="HKU WWW Robot"> | |
663 | <name>HKU WWW Octopus</name> | |
664 | </spider> | |
665 | <spider ident="HolyCowDude"> | |
666 | <name>HolyCowDude</name> | |
667 | <url>http://www.holycowdude.com/spider.htm</url> | |
668 | </spider> | |
9581146e PM |
669 | <spider ident="HomeTags"> |
670 | <name>HomeTags</name> | |
671 | <url>http://www.hometags.nl/bot</url> | |
672 | </spider> | |
25ab2d04 MW |
673 | <spider ident="Hometown"> |
674 | <name>Hometown</name> | |
675 | </spider> | |
676 | <spider ident="htdig"> | |
677 | <name>ht://Dig</name> | |
678 | </spider> | |
679 | <spider ident="AITCSRobot"> | |
680 | <name>HTML Index</name> | |
681 | </spider> | |
682 | <spider ident="HTMLgobble"> | |
683 | <name>HTMLgobble</name> | |
684 | </spider> | |
685 | <spider ident="I Robot"> | |
686 | <name>I, Robot</name> | |
687 | </spider> | |
688 | <spider ident="iajaBot"> | |
689 | <name>iajaBot</name> | |
690 | </spider> | |
691 | <spider ident="IBM_Planetwide"> | |
692 | <name>IBM_Planetwide</name> | |
693 | </spider> | |
694 | <spider ident="+http://www.icerocket.com/"> | |
695 | <name>IceRocket</name> | |
696 | <url>http://www.icerocket.com/</url> | |
697 | </spider> | |
698 | <spider ident="ichiro"> | |
699 | <name>ichiro</name> | |
700 | </spider> | |
701 | <spider ident="IlTrovatore-Setaccio"> | |
702 | <name>IlTrovatore-Setaccio</name> | |
703 | <url>http://www.iltrovatore.it/aiuto/faq.html</url> | |
704 | </spider> | |
705 | <spider ident="image.kapsi.net"> | |
706 | <name>image.kapsi.net</name> | |
707 | </spider> | |
708 | <spider ident="Mozilla 3.01 PBWF (Win95)"> | |
709 | <name>Imagelock</name> | |
710 | </spider> | |
711 | <spider ident="IncyWincy"> | |
712 | <name>IncyWincy</name> | |
713 | </spider> | |
d1430201 I |
714 | <spider ident="infoobot"> |
715 | <name>infoobot</name> | |
716 | <url>https://www.infoo.nl/bot.html</url> | |
717 | </spider> | |
25ab2d04 MW |
718 | <spider ident="Informant"> |
719 | <name>Informant</name> | |
720 | </spider> | |
721 | <spider ident="InfoSeek Robot"> | |
722 | <name>InfoSeek Robot 1.0</name> | |
723 | </spider> | |
724 | <spider ident="Infoseek Sidewinder"> | |
725 | <name>Infoseek Sidewinder</name> | |
726 | </spider> | |
727 | <spider ident="InfoSpiders"> | |
728 | <name>InfoSpiders</name> | |
729 | </spider> | |
730 | <spider ident="INGRID"> | |
731 | <name>Ingrid</name> | |
732 | </spider> | |
733 | <spider ident="slurp@inktomi"> | |
734 | <name>Inktomi</name> | |
735 | </spider> | |
736 | <spider ident="Insitor"> | |
737 | <name>Insitor</name> | |
738 | <url>http://www.insitor.de/</url> | |
739 | </spider> | |
740 | <spider ident="inspectorwww"> | |
741 | <name>Inspector Web</name> | |
742 | </spider> | |
743 | <spider ident="IAGENT"> | |
744 | <name>IntelliAgent</name> | |
745 | </spider> | |
746 | <spider ident="Intelliseek"> | |
747 | <name>Intelliseek</name> | |
748 | <url>http://www.intelliseek.com/</url> | |
749 | </spider> | |
750 | <spider ident="Internet Cruiser Robot"> | |
751 | <name>Internet Cruiser</name> | |
752 | </spider> | |
753 | <spider ident="internetseer"> | |
754 | <name>Internet Seer</name> | |
755 | </spider> | |
756 | <spider ident="sharp-info-agent"> | |
757 | <name>Internet Shinchakubin</name> | |
758 | </spider> | |
759 | <spider ident="InternetLinkAgent"> | |
760 | <name>InternetLinkAgent</name> | |
761 | </spider> | |
762 | <spider ident="IRLbot"> | |
763 | <name>IRL Crawler</name> | |
764 | <url>http://irl.cs.tamu.edu/crawler</url> | |
765 | </spider> | |
de9232b3 I |
766 | <spider ident="IonCrawl"> |
767 | <name>IonCrawl</name> | |
768 | <url>https://www.ionos.de/terms-gtc/faq-crawler-en</url> | |
769 | </spider> | |
25ab2d04 MW |
770 | <spider ident="Iron33"> |
771 | <name>Iron33</name> | |
772 | </spider> | |
773 | <spider ident="IsraeliSearch"> | |
774 | <name>Israeli-search</name> | |
775 | </spider> | |
776 | <spider ident="itchBot"> | |
777 | <name>itch</name> | |
25ab2d04 MW |
778 | </spider> |
779 | <spider ident="JavaBee"> | |
780 | <name>JavaBee</name> | |
781 | </spider> | |
782 | <spider ident="JBot"> | |
783 | <name>JBot</name> | |
784 | </spider> | |
785 | <spider ident="JCrawler"> | |
786 | <name>JCrawler</name> | |
787 | </spider> | |
788 | <spider ident="JetBot"> | |
789 | <name>JetEye</name> | |
790 | <url>http://www.jeteye.com/jetbot.html</url> | |
791 | </spider> | |
792 | <spider ident="JoBo"> | |
793 | <name>JoBo</name> | |
794 | </spider> | |
795 | <spider ident="Jobot"> | |
796 | <name>Jobot</name> | |
797 | </spider> | |
798 | <spider ident="jobs.de"> | |
799 | <name>Jobs.de</name> | |
800 | <url>http://www.jobs.de/</url> | |
801 | </spider> | |
802 | <spider ident="JoeBot"> | |
803 | <name>JoeBot</name> | |
804 | </spider> | |
805 | <spider ident="jumpstation"> | |
806 | <name>JumpStation</name> | |
807 | </spider> | |
808 | <spider ident="Katipo"> | |
809 | <name>Katipo</name> | |
810 | </spider> | |
811 | <spider ident="KDD-Explorer"> | |
812 | <name>KDD-Explorer</name> | |
813 | </spider> | |
814 | <spider ident="KIT-Fireball"> | |
815 | <name>KIT-Fireball</name> | |
816 | </spider> | |
817 | <spider ident="KO_Yappo_Robot"> | |
818 | <name>KO_Yappo_Robot</name> | |
819 | </spider> | |
820 | <spider ident="LabelGrab"> | |
821 | <name>LabelGrabber</name> | |
822 | </spider> | |
823 | <spider ident="larbin"> | |
824 | <name>larbin</name> | |
825 | </spider> | |
826 | <spider ident="legs"> | |
827 | <name>legs</name> | |
828 | </spider> | |
0cf0a5c1 C |
829 | <spider ident="linkdexbot"> |
830 | <name>Linkdex</name> | |
831 | <url>http://www.linkdex.com/bots/</url> | |
832 | </spider> | |
25ab2d04 MW |
833 | <spider ident="LinkScan Server"> |
834 | <name>LinkScan</name> | |
835 | </spider> | |
836 | <spider ident="LinkWalker"> | |
837 | <name>LinkWalker</name> | |
838 | </spider> | |
f55aa1aa P |
839 | <spider ident="Linguee Bot"> |
840 | <name>Linguee</name> | |
841 | <url>http://www.linguee.com/bot</url> | |
842 | </spider> | |
25ab2d04 MW |
843 | <spider ident="livedoorCheckers/"> |
844 | <name>livedoorCheckers</name> | |
845 | </spider> | |
846 | <spider ident="Lockon"> | |
847 | <name>Lockon</name> | |
848 | </spider> | |
849 | <spider ident="logo.gif crawler"> | |
850 | <name>logo.gif</name> | |
851 | </spider> | |
852 | <spider ident="Lycos"> | |
853 | <name>Lycos</name> | |
854 | </spider> | |
855 | <spider ident="Magpie"> | |
856 | <name>Magpie</name> | |
857 | </spider> | |
858 | <spider ident="MJ12bot"> | |
859 | <name>Majestics MJ12bot</name> | |
449482a3 | 860 | <url>https://mj12bot.com/</url> |
25ab2d04 MW |
861 | </spider> |
862 | <spider ident="Mammoth"> | |
863 | <name>Mammoth</name> | |
864 | <url>http://www.sli-systems.com</url> | |
865 | </spider> | |
866 | <spider ident="Marvin"> | |
867 | <name>Marvin</name> | |
868 | </spider> | |
869 | <spider ident="marvin/infoseek"> | |
870 | <name>marvin/infoseek</name> | |
871 | </spider> | |
872 | <spider ident="M/3.8"> | |
873 | <name>Mattie</name> | |
874 | </spider> | |
875 | <spider ident="MediaFox"> | |
876 | <name>MediaFox</name> | |
877 | </spider> | |
d9cc31f0 SG |
878 | <spider ident="memorybot"> |
879 | <name>Memorybot</name> | |
880 | <url>http://archivethe.net/en/index.php/about/internet_memory1</url> | |
881 | </spider> | |
25ab2d04 MW |
882 | <spider ident="mercator"> |
883 | <name>Mercator</name> | |
884 | <url>http://research.compaq.com/SRC/mercator/</url> | |
885 | </spider> | |
886 | <spider ident="MerzScope"> | |
887 | <name>MerzScope</name> | |
888 | </spider> | |
889 | <spider ident="METASpider"> | |
890 | <name>META</name> | |
891 | <url>http://www.meta.com.ua/</url> | |
892 | </spider> | |
893 | <spider ident="MetaGer-LinkChecker"> | |
894 | <name>MetaGer</name> | |
895 | </spider> | |
896 | <spider ident="MindCrawler"> | |
897 | <name>MindCrawler</name> | |
898 | </spider> | |
899 | <spider ident="Miva"> | |
900 | <name>Miva</name> | |
901 | </spider> | |
902 | <spider ident="UdmSearch"> | |
903 | <name>mnoGoSearch</name> | |
904 | </spider> | |
905 | <spider ident="moget"> | |
906 | <name>moget</name> | |
907 | </spider> | |
36fb7271 I |
908 | <spider ident="MojeekBot"> |
909 | <name>Mojeek</name> | |
910 | <url>https://www.mojeek.com/bot.html</url> | |
911 | </spider> | |
25ab2d04 MW |
912 | <spider ident="MOMspider"> |
913 | <name>MOMspider</name> | |
914 | </spider> | |
915 | <spider ident="Monster"> | |
916 | <name>Monster</name> | |
917 | </spider> | |
918 | <spider ident="Moreoverbot"> | |
919 | <name>Moreover</name> | |
920 | <url>http://www.moreover.com</url> | |
921 | </spider> | |
922 | <spider ident="msnbot"> | |
923 | <name>MSNBot</name> | |
924 | <url>http://search.msn.com/msnbot.htm</url> | |
925 | </spider> | |
926 | <spider ident="MSRBOT"> | |
927 | <name>MSRBOT</name> | |
928 | <url>http://research.microsoft.com/research/sv/msrbot/</url> | |
929 | </spider> | |
930 | <spider ident="MuscatFerret"> | |
931 | <name>Muscat Ferret</name> | |
932 | </spider> | |
933 | <spider ident="MwdSearch"> | |
934 | <name>Mwd.Search</name> | |
935 | </spider> | |
936 | <spider ident="NPBot"> | |
937 | <name>NameProtect</name> | |
938 | </spider> | |
939 | <spider ident="NaverBot"> | |
940 | <name>NaverBot</name> | |
941 | <url>http://www.spidermatic.com/en/robot-spider/20</url> | |
52bb0ca4 | 942 | </spider> |
6a3fbb36 | 943 | <spider ident="NDSpider"> |
52bb0ca4 | 944 | <name>NDSpider</name> |
25ab2d04 MW |
945 | </spider> |
946 | <spider ident="NEC-MeshExplorer"> | |
947 | <name>NEC-MeshExplorer</name> | |
948 | </spider> | |
949 | <spider ident="Nederland.zoek"> | |
950 | <name>Nederland.zoek</name> | |
951 | </spider> | |
c1398cdd I |
952 | <spider ident="Neevabot"> |
953 | <name>Neeva</name> | |
954 | <url>https://neeva.com/neevabot</url> | |
955 | </spider> | |
89b52a1a MW |
956 | <spider ident="NerdyBot"> |
957 | <name>NerdyBot</name> | |
958 | <url>http://nerdybot.com/</url> | |
959 | </spider> | |
25ab2d04 MW |
960 | <spider ident="NetCarta CyberPilot Pro"> |
961 | <name>NetCarta WebMap</name> | |
962 | </spider> | |
963 | <spider ident="Netcraft"> | |
964 | <name>Netcraft Web Server Survey</name> | |
965 | <url>http://news.netcraft.com/</url> | |
966 | </spider> | |
9f4d894d I |
967 | <spider ident="Neticle Crawler"> |
968 | <name>Neticle Crawler</name> | |
969 | <url>https://neticle.com/bot/en/</url> | |
970 | </spider> | |
25ab2d04 MW |
971 | <spider ident="NetMechanic"> |
972 | <name>NetMechanic</name> | |
973 | </spider> | |
974 | <spider ident="NetScoop"> | |
975 | <name>NetScoop</name> | |
976 | </spider> | |
977 | <spider ident="newscan-online"> | |
978 | <name>newscan-online</name> | |
979 | </spider> | |
980 | <spider ident="NextGenSearchBot 1"> | |
981 | <name>NextGenSearchBot</name> | |
982 | <url>http://www.zoominfo.com/NextGenSearchBot</url> | |
983 | </spider> | |
984 | <spider ident="NHSEWalker"> | |
985 | <name>NHSE Web Forager</name> | |
986 | </spider> | |
987 | <spider ident="NIF"> | |
988 | <name>NIF</name> | |
d04e330e | 989 | <url>http://www.newsisfree.com/robot.php</url> |
25ab2d04 MW |
990 | </spider> |
991 | <spider ident="NimbleCrawler"> | |
992 | <name>NimbleCrawler</name> | |
993 | <url>http://www.healthline.com/aboutus.jsp</url> | |
994 | </spider> | |
995 | <spider ident="Nomad"> | |
996 | <name>Nomad</name> | |
997 | </spider> | |
998 | <spider ident="Norbert the Spider"> | |
999 | <name>Norbert</name> | |
1000 | <url>http://www.Burf.com</url> | |
1001 | </spider> | |
1002 | <spider ident="Gulliver"> | |
1003 | <name>Northern Light</name> | |
1004 | </spider> | |
1005 | <spider ident="explorersearch"> | |
1006 | <name>nzexplorer</name> | |
1007 | </spider> | |
1008 | <spider ident="Occam"> | |
1009 | <name>Occam</name> | |
1010 | </spider> | |
1011 | <spider ident="Ocelli"> | |
1012 | <name>Ocelli</name> | |
1013 | <url>http://www.globalspec.com/Ocelli</url> | |
1014 | </spider> | |
1015 | <spider ident="Online24-Bot"> | |
1016 | <name>Online24-Bot</name> | |
1017 | </spider> | |
1018 | <spider ident="Openbot"> | |
1019 | <name>Openbot</name> | |
1020 | <url>http://www.openfind.com.tw/robot.html</url> | |
1021 | </spider> | |
1022 | <spider ident="Openfind"> | |
1023 | <name>Openfind data gatherer</name> | |
1024 | </spider> | |
1025 | <spider ident="Orbsearch"> | |
1026 | <name>Orb Search</name> | |
1027 | </spider> | |
1028 | <spider ident="PackRat"> | |
1029 | <name>Pack Rat</name> | |
1030 | </spider> | |
1031 | <spider ident="PageBoy"> | |
1032 | <name>PageBoy</name> | |
1033 | </spider> | |
a7331d8e I |
1034 | <spider ident="PagePeeker"> |
1035 | <name>PagePeeker</name> | |
1036 | <url>https://pagepeeker.com/robots/</url> | |
1037 | </spider> | |
5657c6b8 N |
1038 | <spider ident="Pandalytics"> |
1039 | <name>Pandalytics</name> | |
1040 | <url>https://domainsbot.com/pandalytics/</url> | |
1041 | </spider> | |
25ab2d04 MW |
1042 | <spider ident="ParaSite"> |
1043 | <name>ParaSite</name> | |
1044 | </spider> | |
1045 | <spider ident="Patric"> | |
1046 | <name>Patric</name> | |
1047 | </spider> | |
1048 | <spider ident="PEGASUS"> | |
1049 | <name>pegasus</name> | |
1050 | </spider> | |
1051 | <spider ident="PerlCrawler/1.0 Xavatoria/2.0"> | |
1052 | <name>PerlCrawler 1.0</name> | |
1053 | </spider> | |
6ca2411e | 1054 | <spider ident="PetalBot"> |
1055 | <name>PetalBot</name> | |
1056 | <url>https://aspiegel.com/petalbot</url> | |
1057 | </spider> | |
25ab2d04 MW |
1058 | <spider ident="PGP-KA"> |
1059 | <name>PGP Key Agent</name> | |
1060 | </spider> | |
1061 | <spider ident="Duppies"> | |
1062 | <name>Phantom</name> | |
1063 | </spider> | |
1064 | <spider ident="phpdig"> | |
1065 | <name>PhpDig</name> | |
1066 | </spider> | |
1067 | <spider ident="PiltdownMan"> | |
1068 | <name>PiltdownMan</name> | |
1069 | </spider> | |
1070 | <spider ident="Pimptrain's robot"> | |
1071 | <name>Pimptrain.com's</name> | |
1072 | </spider> | |
1073 | <spider ident="pingalink"> | |
1074 | <name>PingALink</name> | |
1075 | </spider> | |
1076 | <spider ident="Pioneer"> | |
1077 | <name>Pioneer</name> | |
1078 | </spider> | |
1079 | <spider ident="PluckFeedCrawler"> | |
1080 | <name>Pluck</name> | |
1081 | <url>http://www.pluck.com</url> | |
1082 | </spider> | |
1083 | <spider ident="PlumtreeWebAccessor"> | |
1084 | <name>PlumtreeWebAccessor</name> | |
1085 | </spider> | |
1086 | <spider ident="PodNova"> | |
1087 | <name>PodNova</name> | |
1088 | <url>http://www.podnova.com</url> | |
1089 | </spider> | |
1090 | <spider ident="Pompos"> | |
1091 | <name>Pompos</name> | |
1092 | <url>http://dir.com/pompos.html</url> | |
1093 | </spider> | |
1094 | <spider ident="Poppi"> | |
1095 | <name>Poppi</name> | |
1096 | </spider> | |
0cf0a5c1 C |
1097 | <spider ident="publiclibraryarchive.org"> |
1098 | <name>publiclibraryarchive.org</name> | |
1099 | </spider> | |
25ab2d04 MW |
1100 | <spider ident="gestaltIconoclast"> |
1101 | <name>Popular Iconoclast</name> | |
1102 | </spider> | |
1103 | <spider ident="PortalJuice.com"> | |
1104 | <name>Portal Juice</name> | |
1105 | </spider> | |
1106 | <spider ident="PortalBSpider"> | |
1107 | <name>PortalB Spider</name> | |
1108 | </spider> | |
f55aa1aa P |
1109 | <spider ident="Qualidator"> |
1110 | <name>Qualidator</name> | |
1111 | <url>www.qualidator.com/Web/de/Support/FAQ_OnlineTestStatistiken.htm</url> | |
1112 | </spider> | |
25ab2d04 MW |
1113 | <spider ident="www.kolinka.com"> |
1114 | <name>Project Kolinka Forum Search</name> | |
1115 | <url>http://www.kolinka.com/</url> | |
1116 | </spider> | |
1117 | <spider ident="psbot"> | |
1118 | <name>psbot</name> | |
1119 | </spider> | |
1120 | <spider ident="Qango.com Web Directory"> | |
1121 | <name>Qango</name> | |
1122 | <url>http://www.qango.com</url> | |
1123 | </spider> | |
71a53c20 SM |
1124 | <spider ident="Qwant"> |
1125 | <name>Qwant</name> | |
1126 | <url>https://help.qwant.com/bot/</url> | |
1127 | </spider> | |
f55aa1aa P |
1128 | <spider ident="SBSearch"> |
1129 | <name>SecretSearchEngineLabs.com</name> | |
1130 | <url>http://www.secretsearchenginelabs.com/secret-web-crawler.php</url> | |
1131 | </spider> | |
307ef0a2 | 1132 | <spider ident="SemrushBot"> |
1133 | <name>SemrushBot</name> | |
1134 | <url>http://semrush.com/bot/</url> | |
1135 | </spider> | |
25ab2d04 MW |
1136 | <spider ident="StackRambler"> |
1137 | <name>Rambler</name> | |
1138 | <url>http://www.rambler.ru/</url> | |
1139 | </spider> | |
1140 | <spider ident="Raven"> | |
1141 | <name>Raven Search</name> | |
1142 | </spider> | |
1143 | <spider ident="Resume Robot"> | |
1144 | <name>Resume Robot</name> | |
1145 | </spider> | |
1146 | <spider ident="Road Runner: ImageScape Robot"> | |
1147 | <name>Road Runner: The ImageScape Robot</name> | |
1148 | </spider> | |
1149 | <spider ident="RHCS"> | |
1150 | <name>RoadHouse Crawling System</name> | |
1151 | </spider> | |
1152 | <spider ident="Robbie"> | |
1153 | <name>Robbie the Robot</name> | |
1154 | </spider> | |
1155 | <spider ident="RoboCrawl"> | |
1156 | <name>RoboCrawl</name> | |
1157 | </spider> | |
1158 | <spider ident="Robofox"> | |
1159 | <name>RoboFox</name> | |
1160 | </spider> | |
1161 | <spider ident="Robot du CRIM 1.0a"> | |
1162 | <name>Robot Francoroute</name> | |
1163 | </spider> | |
1164 | <spider ident="Robozilla"> | |
1165 | <name>Robozilla</name> | |
1166 | </spider> | |
1167 | <spider ident="Roverbot"> | |
1168 | <name>Roverbot</name> | |
1169 | </spider> | |
1170 | <spider ident="RSS-SPIDER"> | |
1171 | <name>RSS Feed Seeker</name> | |
1172 | <url>http://www.rss-spider.com/fsb.php</url> | |
1173 | </spider> | |
1174 | <spider ident="RuLeS"> | |
1175 | <name>RuLeS</name> | |
1176 | </spider> | |
9581146e PM |
1177 | <spider ident="RyzeCrawler"> |
1178 | <name>RyzeCrawler</name> | |
1179 | <url>http://www.domain2day.nl/crawler/</url> | |
1180 | </spider> | |
25ab2d04 MW |
1181 | <spider ident="SafetyNet Robot"> |
1182 | <name>SafetyNet</name> | |
1183 | </spider> | |
1184 | <spider ident="SBIder"> | |
1185 | <name>SBIder.</name> | |
1186 | <url>http://www.sitesell.com/sbider.html</url> | |
1187 | </spider> | |
1188 | <spider ident="Scharia"> | |
1189 | <name>Scharia</name> | |
1190 | </spider> | |
1191 | <spider ident="Science-Index"> | |
1192 | <name>Science-Index</name> | |
1193 | </spider> | |
1194 | <spider ident="Scooter"> | |
1195 | <name>Scooter</name> | |
1196 | </spider> | |
e034e5a9 I |
1197 | <spider ident="SearchAtlas"> |
1198 | <name>SearchAtlas</name> | |
1199 | <url>https://searchatlas.com/</url> | |
1200 | </spider> | |
25ab2d04 MW |
1201 | <spider ident="SearchNZ"> |
1202 | <name>SearchNZ</name> | |
1203 | <url>http://www.searchnz.co.nz/</url> | |
1204 | </spider> | |
1205 | <spider ident="searchprocess"> | |
1206 | <name>SearchProcess</name> | |
1207 | </spider> | |
1208 | <spider ident="SearchmetricsBot"> | |
1209 | <name>SearchmetricsBot</name> | |
1210 | <url>http://www.searchmetrics.com/en/searchmetrics-bot/</url> | |
1211 | </spider> | |
1212 | <spider ident="Seekbot"> | |
1213 | <name>Seekbot</name> | |
1214 | <url>http://www.seekbot.net/bot.html</url> | |
1215 | </spider> | |
4cba12bf I |
1216 | <spider ident="SeekportBot"> |
1217 | <name>Seekport Bot</name> | |
1218 | <url>https://bot.seekport.com</url> | |
1219 | </spider> | |
25ab2d04 MW |
1220 | <spider ident="Senrigan"> |
1221 | <name>Senrigan</name> | |
1222 | </spider> | |
1223 | <spider ident="Sensis Web Crawler"> | |
1224 | <name>Sensis Web Crawler</name> | |
1225 | <url>http://www.sensis.com.au/help.do</url> | |
1226 | </spider> | |
16240335 | 1227 | <spider ident="SentiBot"> |
4c8c4953 | 1228 | <name>SentiBot</name> |
16240335 C |
1229 | <url>http://www.sentibot.eu</url> |
1230 | </spider> | |
548371c0 I |
1231 | <spider ident="SEO Scanner"> |
1232 | <name>SEO Scanner</name> | |
1233 | </spider> | |
8cbe75a7 I |
1234 | <spider ident="SeobilityBot"> |
1235 | <name>SeobilityBot</name> | |
1236 | <url>https://www.seobility.net/sites/bot.html</url> | |
1237 | </spider> | |
abafa2ec SM |
1238 | <spider ident="SEOkicks"> |
1239 | <name>SEOkicks</name> | |
1240 | <url>https://www.seokicks.de/robot.html</url> | |
1241 | </spider> | |
f9dfae3d I |
1242 | <spider ident="seostar.co"> |
1243 | <name>Seostar</name> | |
1244 | <url>https://seostar.co/robot/</url> | |
1245 | </spider> | |
2f45b485 I |
1246 | <spider ident="SerendeputyBot"> |
1247 | <name>SerendeputyBot</name> | |
1248 | <url>http://serendeputy.com/about/serendeputy-bot</url> | |
1249 | </spider> | |
08bf1baa SM |
1250 | <spider ident="serpstatbot"> |
1251 | <name>serpstatbot</name> | |
1252 | <url>http://serpstatbot.com/</url> | |
1253 | </spider> | |
a2b39a59 C |
1254 | <spider ident="SeznamBot/3.2"> |
1255 | <name>Seznam Bot</name> | |
1256 | <url>http://napoveda.seznam.cz/en/seznambot-intro/</url> | |
1257 | </spider> | |
25ab2d04 MW |
1258 | <spider ident="SG-Scout"> |
1259 | <name>SG-Scout</name> | |
1260 | </spider> | |
1261 | <spider ident="Shagseeker"> | |
1262 | <name>ShagSeeker</name> | |
1263 | </spider> | |
1264 | <spider ident="Shai'Hulud"> | |
1265 | <name>Shai'Hulud</name> | |
1266 | </spider> | |
1267 | <spider ident="SimBot/1.0"> | |
1268 | <name>Simmany Robot Ver1.0</name> | |
1269 | </spider> | |
34ae61a1 I |
1270 | <spider ident="SimplePie"> |
1271 | <name>SimplePie</name> | |
1272 | <url>https://simplepie.org</url> | |
1273 | </spider> | |
a370eb7d | 1274 | <spider ident="SkypeUriPreview"> |
1275 | <name>Skype Preview</name> | |
1276 | <url>https://www.skype.com/</url> | |
1277 | </spider> | |
25ab2d04 MW |
1278 | <spider ident="ssearcher100"> |
1279 | <name>Site Searcher</name> | |
1280 | </spider> | |
1281 | <spider ident="Site Valet"> | |
1282 | <name>Site Valet</name> | |
1283 | </spider> | |
1284 | <spider ident="http://www.site-list.net"> | |
1285 | <name>Site-List</name> | |
1286 | <url>http://www.site-list.net</url> | |
1287 | </spider> | |
1288 | <spider ident="SiteTech-Rover"> | |
1289 | <name>SiteTech-Rover</name> | |
1290 | </spider> | |
1291 | <spider ident="+SitiDi.net/SitiDiBot/"> | |
1292 | <name>SitiDi.net/SitiDiBot</name> | |
1293 | </spider> | |
1294 | <spider ident="aWapClient"> | |
1295 | <name>Skymob.com</name> | |
1296 | </spider> | |
677899c2 AE |
1297 | <spider ident="Slack"> |
1298 | <name>Slackbot</name> | |
1299 | <url>https://api.slack.com/robots</url> | |
1300 | </spider> | |
25ab2d04 MW |
1301 | <spider ident="SLCrawler"> |
1302 | <name>SLCrawler</name> | |
1303 | </spider> | |
1304 | <spider ident="Sleek Spider"> | |
1305 | <name>Sleek</name> | |
1306 | </spider> | |
1307 | <spider ident="ESISmartSpider"> | |
1308 | <name>Smart Spider</name> | |
1309 | </spider> | |
1310 | <spider ident="Snapbot"> | |
1311 | <name>Snapbot</name> | |
1312 | <url>http://www.snap.com/</url> | |
1313 | </spider> | |
1314 | <spider ident="Snooper"> | |
1315 | <name>Snooper</name> | |
1316 | </spider> | |
1317 | <spider ident="sohu-search"> | |
1318 | <name>sohu-search</name> | |
1319 | </spider> | |
1320 | <spider ident="Solbot"> | |
1321 | <name>Solbot</name> | |
1322 | </spider> | |
1323 | <spider ident="Speedy Spider"> | |
1324 | <name>Speedy Spider</name> | |
1325 | <url>http://www.entireweb.com/about/search_tech/speedyspider/</url> | |
1326 | </spider> | |
1327 | <spider ident="Sphere Scout"> | |
1328 | <name>Sphere</name> | |
1329 | </spider> | |
1330 | <spider ident="Sphider2"> | |
1331 | <name>Sphider</name> | |
1332 | </spider> | |
1333 | <spider ident="SpiderBot"> | |
1334 | <name>SpiderBot</name> | |
1335 | </spider> | |
1336 | <spider ident="spiderline"> | |
1337 | <name>Spiderline Crawler</name> | |
1338 | </spider> | |
1339 | <spider ident="SpiderMan"> | |
1340 | <name>SpiderMan</name> | |
1341 | </spider> | |
1342 | <spider ident="SpiderView"> | |
1343 | <name>SpiderView(tm)</name> | |
1344 | </spider> | |
1345 | <spider ident="mouse.house"> | |
1346 | <name>spider_monkey</name> | |
1347 | </spider> | |
1348 | <spider ident="suke"> | |
1349 | <name>Suke</name> | |
1350 | </spider> | |
1351 | <spider ident="suntek"> | |
1352 | <name>suntek search engine</name> | |
1353 | </spider> | |
ea6ec8d3 I |
1354 | <spider ident="Superfeedr"> |
1355 | <name>Superfeedr</name> | |
1356 | <url>http://superfeedr.com</url> | |
1357 | </spider> | |
59192e17 I |
1358 | <spider ident="SurdotlyBot"> |
1359 | <name>SurdotlyBot</name> | |
1360 | <url>http://sur.ly/bot.html</url> | |
1361 | </spider> | |
25ab2d04 MW |
1362 | <spider ident="Szukacz"> |
1363 | <name>Szukacz</name> | |
1364 | <url>http://www.szukacz.pl/html/RobotEnglishVersion.html</url> | |
1365 | </spider> | |
1366 | <spider ident="T-H-U-N-D-E-R-S-T-O-N-E"> | |
1367 | <name>T-H-U-N-D-E-R-S-T-O-N-E</name> | |
1368 | </spider> | |
f55aa1aa P |
1369 | <spider ident="TinEye Crawler"> |
1370 | <name>TinEye</name> | |
1371 | <url>http://tineye.com/crawler.html</url> | |
1372 | </spider> | |
25ab2d04 MW |
1373 | <spider ident="Black Widow"> |
1374 | <name>TACH Black Widow</name> | |
1375 | </spider> | |
e7d8bd51 | 1376 | <spider ident="Tapatalk CloudSearch"> |
0cf0a5c1 C |
1377 | <name>Tapatalk CloudSearch</name> |
1378 | </spider> | |
25ab2d04 MW |
1379 | <spider ident="Tarantula"> |
1380 | <name>Tarantula</name> | |
1381 | </spider> | |
1382 | <spider ident="tarspider"> | |
1383 | <name>tarspider</name> | |
1384 | </spider> | |
1385 | <spider ident="dlw3robot"> | |
1386 | <name>Tcl W3 Robot</name> | |
1387 | </spider> | |
1388 | <spider ident="TechBOT"> | |
1389 | <name>TechBOT</name> | |
1390 | </spider> | |
1391 | <spider ident="Technoratibot"> | |
1392 | <name>Technorati</name> | |
1393 | <url>http://technorati.com/about/</url> | |
1394 | </spider> | |
1395 | <spider ident="Templeton"> | |
1396 | <name>Templeton</name> | |
1397 | </spider> | |
1398 | <spider ident="teoma"> | |
1399 | <name>Teoma/Ask Jeeves</name> | |
1400 | <url>http://sp.teoma.com/docs/teoma/about/</url> | |
1401 | </spider> | |
340a1799 I |
1402 | <spider ident="trovitBot"> |
1403 | <name>trovitBot</name> | |
1404 | <url>http://www.trovit.com/bot.html</url> | |
1405 | </spider> | |
25ab2d04 MW |
1406 | <spider ident="JubiiRobot"> |
1407 | <name>The Jubii</name> | |
1408 | </spider> | |
1409 | <spider ident="NorthStar"> | |
1410 | <name>The NorthStar Robot</name> | |
1411 | </spider> | |
1412 | <spider ident="w3index"> | |
1413 | <name>The NWI Robot</name> | |
1414 | </spider> | |
1415 | <spider ident="Peregrinator-Mathematics"> | |
1416 | <name>The Peregrinator</name> | |
1417 | </spider> | |
0cf0a5c1 C |
1418 | <spider ident="Pixray-Seeker"> |
1419 | <name>Pixray</name> | |
1420 | <url>http://www.pixray.com/pixraybot/</url> | |
1421 | </spider> | |
a370eb7d | 1422 | <spider ident="TelegramBot (like TwitterBot)"> |
1423 | <name>TelegramBot (like TwitterBot)</name> | |
1424 | <url>https://telegram.org/</url> | |
1425 | </spider> | |
84b3ca1c I |
1426 | <spider ident="Testomatobot"> |
1427 | <name>TestomatoBot</name> | |
1428 | <url>https://www.testomato.com/bot</url> | |
1429 | </spider> | |
25ab2d04 MW |
1430 | <spider ident="thumbshots-de-Bot"> |
1431 | <name>thumbshots-de-Bot</name> | |
1432 | </spider> | |
1433 | <spider ident="TITAN"> | |
1434 | <name>TITAN</name> | |
1435 | </spider> | |
1436 | <spider ident="TitIn"> | |
1437 | <name>TitIn</name> | |
1438 | </spider> | |
1439 | <spider ident="TLSpider"> | |
1440 | <name>TLSpider</name> | |
1441 | </spider> | |
1442 | <spider ident="TMCrawler"> | |
1443 | <name>TMCrawler</name> | |
1444 | </spider> | |
1445 | <spider ident="trendictionbot"> | |
1446 | <name>Trendiction-Bot</name> | |
1447 | <url>http://www.trendiction.com/bot</url> | |
1448 | </spider> | |
1449 | <spider ident="slysearch"> | |
1450 | <name>Turnitin.com</name> | |
1451 | <url>http://www.turnitin.com/static/products_services/search_engines.html</url> | |
1452 | </spider> | |
d2c93ade | 1453 | <spider ident="TurnitinBot"> |
25ab2d04 | 1454 | <name>TurnitinBot</name> |
d2c93ade | 1455 | <url>http://www.turnitin.com/robot/crawlerinfo.html</url> |
25ab2d04 MW |
1456 | </spider> |
1457 | <spider ident="TurtleScanner"> | |
1458 | <name>Turtle</name> | |
1459 | <url>http://www.turtle.ru/</url> | |
1460 | </spider> | |
9581146e PM |
1461 | <spider ident="TwengaBot"> |
1462 | <name>Twenga</name> | |
1463 | <url>http://www.twenga.com/bot.html</url> | |
1464 | </spider> | |
25ab2d04 MW |
1465 | <spider ident="Twiceler"> |
1466 | <name>Twiceler</name> | |
1467 | <url>http://www.cuill.com/twiceler/robot.html</url> | |
1468 | </spider> | |
a370eb7d | 1469 | <spider ident="Twitterbot"> |
1470 | <name>Twitterbot</name> | |
1471 | <url>https://twitter.com/</url> | |
1472 | </spider> | |
25ab2d04 MW |
1473 | <spider ident="UCSD-Crawler"> |
1474 | <name>UCSD Crawl</name> | |
1475 | </spider> | |
1476 | <spider ident="UMBC-memeta-Bot"> | |
1477 | <name>UMBC</name> | |
1478 | </spider> | |
1479 | <spider ident="unisterbot"> | |
1480 | <name>Unister</name> | |
1481 | </spider> | |
1482 | <spider ident="Unpartisan"> | |
1483 | <name>Unpartisan</name> | |
1484 | <url>http://www.unpartisan.com</url> | |
1485 | </spider> | |
4465d786 I |
1486 | <spider ident="Uptime-Kuma"> |
1487 | <name>Uptime-Kuma</name> | |
1488 | <url>https://uptime.kuma.pet/</url> | |
1489 | </spider> | |
a602e267 SK |
1490 | <spider ident="UptimeRobot/2.0"> |
1491 | <name>Uptime Robot</name> | |
1492 | <url>http://uptimerobot.com/</url> | |
1493 | </spider> | |
25ab2d04 MW |
1494 | <spider ident="urlck"> |
1495 | <name>URL Check</name> | |
1496 | </spider> | |
1497 | <spider ident="URL Spider Pro"> | |
1498 | <name>URL Spider Pro</name> | |
1499 | </spider> | |
1500 | <spider ident="Valkyrie"> | |
1501 | <name>Valkyrie</name> | |
1502 | </spider> | |
37b2fc3c I |
1503 | <spider ident="VelenPublicWebCrawler"> |
1504 | <name>Velen Crawler</name> | |
1505 | <url>https://velen.io</url> | |
1506 | </spider> | |
25ab2d04 MW |
1507 | <spider ident="Verticrawl"> |
1508 | <name>Verticrawl</name> | |
1509 | </spider> | |
1510 | <spider ident="Victoria"> | |
1511 | <name>Victoria</name> | |
1512 | </spider> | |
1513 | <spider ident="vision-search"> | |
1514 | <name>vision-search</name> | |
1515 | </spider> | |
1516 | <spider ident="VoilaBot"> | |
1517 | <name>VoilaBot</name> | |
1518 | <url>http://www.voila.com/</url> | |
1519 | </spider> | |
9581146e PM |
1520 | <spider ident="VisBot"> |
1521 | <name>VisBot</name> | |
1522 | <url>http://www.visvo.com/webmasters.html</url> | |
1523 | </spider> | |
25ab2d04 MW |
1524 | <spider ident="Voyager"> |
1525 | <name>Voyager</name> | |
1526 | </spider> | |
1527 | <spider ident="VWbot_K"> | |
1528 | <name>VWbot</name> | |
1529 | </spider> | |
1530 | <spider ident="W3M2"> | |
1531 | <name>W3M2</name> | |
1532 | </spider> | |
1533 | <spider ident="w3mir"> | |
1534 | <name>w3mir</name> | |
1535 | </spider> | |
1536 | <spider ident="w@pSpider"> | |
1537 | <name>w@pSpider</name> | |
1538 | </spider> | |
1539 | <spider ident="appie"> | |
1540 | <name>Walhello appie</name> | |
665cc30d | 1541 | <url>http://www.robotstxt.org/db/appie.html</url> |
25ab2d04 MW |
1542 | </spider> |
1543 | <spider ident="CrawlPaper"> | |
1544 | <name>WallPaper</name> | |
1545 | </spider> | |
1546 | <spider ident="root"> | |
1547 | <name>Web Core / Roots</name> | |
1548 | </spider> | |
f55aa1aa P |
1549 | <spider ident="WBSearchBot"> |
1550 | <name>Ware Bay</name> | |
1551 | <url>http://www.warebay.com/bot.html</url> | |
1552 | </spider> | |
25ab2d04 MW |
1553 | <spider ident="WebMoose"> |
1554 | <name>Web Moose</name> | |
1555 | </spider> | |
1556 | <spider ident="WebBandit"> | |
1557 | <name>WebBandit</name> | |
1558 | </spider> | |
1559 | <spider ident="WebCatcher"> | |
1560 | <name>WebCatcher</name> | |
1561 | </spider> | |
1562 | <spider ident="Webclipping"> | |
1563 | <name>Webclipping</name> | |
1564 | </spider> | |
1565 | <spider ident="WebCopy"> | |
1566 | <name>WebCopy</name> | |
1567 | </spider> | |
1568 | <spider ident="WebFetcher"> | |
1569 | <name>webfetcher</name> | |
1570 | </spider> | |
1571 | <spider ident="weblayers"> | |
1572 | <name>weblayers</name> | |
1573 | </spider> | |
1574 | <spider ident="WebLinker"> | |
1575 | <name>WebLinker</name> | |
1576 | </spider> | |
1577 | <spider ident="wlm"> | |
1578 | <name>Weblog Monitor</name> | |
1579 | </spider> | |
1580 | <spider ident="WebQuest"> | |
1581 | <name>WebQuest</name> | |
1582 | </spider> | |
1583 | <spider ident="WebReaper"> | |
1584 | <name>WebReaper</name> | |
1585 | </spider> | |
1586 | <spider ident="webs@recruit.co.jp"> | |
1587 | <name>webs</name> | |
1588 | </spider> | |
1589 | <spider ident="websearchbench"> | |
1590 | <name>WebSearchBench</name> | |
1591 | <url>http://websearchbench.cs.uni-dortmund.de/</url> | |
1592 | </spider> | |
1593 | <spider ident="WOLP"> | |
1594 | <name>WebStolperer</name> | |
1595 | </spider> | |
1596 | <spider ident="webvac"> | |
1597 | <name>WebVac</name> | |
1598 | </spider> | |
1599 | <spider ident="webwalk"> | |
1600 | <name>webwalk</name> | |
1601 | </spider> | |
1602 | <spider ident="WebWalker"> | |
1603 | <name>WebWalker</name> | |
1604 | </spider> | |
1605 | <spider ident="WebWatch"> | |
1606 | <name>WebWatch</name> | |
52bb0ca4 | 1607 | </spider> |
6a3fbb36 | 1608 | <spider ident="WebZinger"> |
52bb0ca4 | 1609 | <name>WebZinger</name> |
25ab2d04 MW |
1610 | </spider> |
1611 | <spider ident="whatUseek_winona"> | |
1612 | <name>whatUseek Winona</name> | |
52bb0ca4 | 1613 | </spider> |
6a3fbb36 | 1614 | <spider ident="WhoWhere Robot"> |
52bb0ca4 P |
1615 | <name>WebWatch</name> |
1616 | <url>http://www.whowhere.com</url> | |
25ab2d04 MW |
1617 | </spider> |
1618 | <spider ident="SurveyBot"> | |
1619 | <name>Whois Source</name> | |
1620 | <url>http://www.whois.sc/info/webmasters/surveybot.html</url> | |
1621 | </spider> | |
1622 | <spider ident="Hazel's Ferret Web hopper"> | |
1623 | <name>Wild Ferret Web Hopper</name> | |
1624 | </spider> | |
0cf0a5c1 C |
1625 | <spider ident="HRCrawler"> |
1626 | <name>HRCrawler</name> | |
1627 | </spider> | |
25ab2d04 MW |
1628 | <spider ident="WinHTTP"> |
1629 | <name>WinHTTP</name> | |
1630 | </spider> | |
1631 | <spider ident="wired-digital-newsbot"> | |
1632 | <name>Wired Digital</name> | |
1633 | </spider> | |
1634 | <spider ident="zyborg"> | |
1635 | <name>WiseNut</name> | |
1636 | </spider> | |
c3fe17fb | 1637 | <spider ident="WoltLabSuite"> |
1638 | <name>WoltLab Suite</name> | |
1639 | </spider> | |
25ab2d04 MW |
1640 | <spider ident="OmniExplorer_Bot"> |
1641 | <name>WorldIndexer</name> | |
1642 | <url>http://www.omni-explorer.com</url> | |
1643 | </spider> | |
1644 | <spider ident="WWWC"> | |
1645 | <name>WWWC</name> | |
1646 | </spider> | |
1647 | <spider ident="WWWeasel Robot"> | |
1648 | <name>WWWeasel Robot</name> | |
1649 | </spider> | |
1650 | <spider ident="wwwster"> | |
1651 | <name>wwwster</name> | |
1652 | </spider> | |
1653 | <spider ident="WWWWanderer"> | |
1654 | <name>WWWWanderer</name> | |
1655 | </spider> | |
1656 | <spider ident="TECOMAC-Crawler"> | |
1657 | <name>X-Crawler</name> | |
1658 | </spider> | |
1659 | <spider ident="XGET"> | |
1660 | <name>XGET</name> | |
1661 | </spider> | |
1662 | <spider ident="cosmos"> | |
1663 | <name>XYLEME Robot</name> | |
1664 | </spider> | |
1665 | <spider ident="yacybot"> | |
1666 | <name>YaCy-Bot</name> | |
f0cbc030 | 1667 | <url>https://yacy.net/bot.html</url> |
25ab2d04 MW |
1668 | </spider> |
1669 | <spider ident="YahooYSMcm"> | |
1670 | <name>Yahoo Publisher Network</name> | |
1671 | <url>http://publisher.yahoo.com/</url> | |
1672 | </spider> | |
1673 | <spider ident="Yahoo-Blogs"> | |
1674 | <name>Yahoo-Blogs</name> | |
1675 | <url>http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html</url> | |
1676 | </spider> | |
1677 | <spider ident="Yahoo Pipes"> | |
1678 | <name>Yahoo Pipes</name> | |
1679 | </spider> | |
1680 | <spider ident="Yahoo! Slurp"> | |
1681 | <name>Yahoo! Slurp</name> | |
1682 | <url>http://help.yahoo.com/help/us/ysearch/slurp</url> | |
1683 | </spider> | |
1684 | <spider ident="Yahoo-VerticalCrawler"> | |
1685 | <name>Yahoo-VerticalCrawler</name> | |
1686 | </spider> | |
1687 | <spider ident="YahooFeedSeeker"> | |
1688 | <name>YahooFeedSeeker</name> | |
1689 | <url>http://my.yahoo.com/s/publishers.html</url> | |
1690 | </spider> | |
1691 | <spider ident="Yandex"> | |
1692 | <name>Yandex</name> | |
b16b1f57 | 1693 | <url>https://yandex.com/bots</url> |
25ab2d04 MW |
1694 | </spider> |
1695 | <spider ident="zeus"> | |
1696 | <name>Zeus Internet Marketing</name> | |
1697 | <url>http://www.cyber-robotics.com/</url> | |
1698 | </spider> | |
1699 | <spider ident="http://www.zorkk.com"> | |
1700 | <name>Zork</name> | |
1701 | <url>http://www.zorkk.com</url> | |
1702 | </spider> | |
f55aa1aa P |
1703 | <spider ident="Zookabot"> |
1704 | <name>Zookabotk</name> | |
1705 | <url>http://zookabot.com/</url> | |
1706 | </spider> | |
faf45819 SM |
1707 | <spider ident="ZoominfoBot"> |
1708 | <name>ZoominfoBot</name> | |
1709 | <url>https://www.zoominfo.com/about-zoominfo/zoominfobot</url> | |
1710 | </spider> | |
0cf0a5c1 C |
1711 | <spider ident="360Spider"> |
1712 | <name>360Spider</name> | |
1713 | </spider> | |
186a373f SG |
1714 | <spider ident="GPTBot/"> |
1715 | <name>GPTBot</name> | |
1716 | <url>https://openai.com/gptbot</url> | |
1717 | </spider> | |
f1945886 SG |
1718 | <spider ident="PerplexityBot/"> |
1719 | <name>PerplexityBot</name> | |
1720 | <url>https://perplexity.ai/perplexitybot</url> | |
1721 | </spider> | |
52bb0ca4 | 1722 | </data> |