-
Notifications
You must be signed in to change notification settings - Fork 36
/
robots.json
289 lines (289 loc) · 15.7 KB
/
robots.json
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
{
"AI2Bot": {
"operator": "[Ai2](https://allenai.org/crawler)",
"respect": "Yes",
"function": "Content is used to train open language models.",
"frequency": "No information provided.",
"description": "Explores 'certain domains' to find web content."
},
"Ai2Bot-Dolma": {
"description": "Explores 'certain domains' to find web content.",
"frequency": "No information provided.",
"function": "Content is used to train open language models.",
"operator": "[Ai2](https://allenai.org/crawler)",
"respect": "Yes"
},
"Amazonbot": {
"operator": "Amazon",
"respect": "Yes",
"function": "Service improvement and enabling answers for Alexa users.",
"frequency": "No information provided.",
"description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses."
},
"anthropic-ai": {
"operator": "[Anthropic](https://www.anthropic.com)",
"respect": "Unclear at this time.",
"function": "Scrapes data to train Anthropic's AI products.",
"frequency": "No information provided.",
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
},
"Applebot": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Search Crawlers",
"frequency": "Unclear at this time.",
"description": "Applebot is a web crawler used by Apple to index search results that allow the Siri AI Assistant to answer user questions. Siri's answers normally contain references to the website. More info can be found at https://darkvisitors.com/agents/agents/applebot"
},
"Applebot-Extended": {
"operator": "[Apple](https://support.apple.com/en-us/119829#datausage)",
"respect": "Yes",
"function": "Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others.",
"frequency": "Unclear at this time.",
"description": "Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools."
},
"Bytespider": {
"operator": "ByteDance",
"respect": "No",
"function": "LLM training.",
"frequency": "Unclear at this time.",
"description": "Downloads data to train LLMS, including ChatGPT competitors."
},
"CCBot": {
"operator": "[Common Crawl Foundation](https://commoncrawl.org)",
"respect": "[Yes](https://commoncrawl.org/ccbot)",
"function": "Provides open crawl dataset, used for many purposes, including Machine Learning/AI.",
"frequency": "Monthly at present.",
"description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)."
},
"ChatGPT-User": {
"operator": "[OpenAI](https://openai.com)",
"respect": "Yes",
"function": "Takes action based on user prompts.",
"frequency": "Only when prompted by a user.",
"description": "Used by plugins in ChatGPT to answer queries based on user input."
},
"Claude-Web": {
"operator": "[Anthropic](https://www.anthropic.com)",
"respect": "Unclear at this time.",
"function": "Scrapes data to train Anthropic's AI products.",
"frequency": "No information provided.",
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
},
"ClaudeBot": {
"operator": "[Anthropic](https://www.anthropic.com)",
"respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)",
"function": "Scrapes data to train Anthropic's AI products.",
"frequency": "No information provided.",
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
},
"cohere-ai": {
"operator": "[Cohere](https://cohere.com)",
"respect": "Unclear at this time.",
"function": "Retrieves data to provide responses to user-initiated prompts.",
"frequency": "Takes action based on user prompts.",
"description": "Retrieves data based on user prompts."
},
"Diffbot": {
"operator": "[Diffbot](https://www.diffbot.com/)",
"respect": "At the discretion of Diffbot users.",
"function": "Aggregates structured web data for monitoring and AI model training.",
"frequency": "Unclear at this time.",
"description": "Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training."
},
"DuckAssistBot": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Assistants",
"frequency": "Unclear at this time.",
"description": "DuckAssistBot is used by DuckDuckGo's DuckAssist feature to fetch content and generate realtime AI answers to user searches. More info can be found at https://darkvisitors.com/agents/agents/duckassistbot"
},
"FacebookBot": {
"operator": "Meta/Facebook",
"respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)",
"function": "Training language models",
"frequency": "Up to 1 page per second",
"description": "Officially used for training Meta \"speech recognition technology,\" unknown if used to train Meta AI specifically."
},
"facebookexternalhit": {
"description": "Unclear at this time.",
"frequency": "Unclear at this time.",
"function": "No information.",
"operator": "Meta/Facebook",
"respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)"
},
"FriendlyCrawler": {
"description": "Unclear who the operator is; but data is used for training/machine learning.",
"frequency": "Unclear at this time.",
"function": "We are using the data from the crawler to build datasets for machine learning experiments.",
"operator": "Unknown",
"respect": "[Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler)"
},
"Google-Extended": {
"operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
"function": "LLM training.",
"frequency": "No information.",
"description": "Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search."
},
"GoogleOther": {
"description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"",
"frequency": "No information.",
"function": "Scrapes data.",
"operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
},
"GoogleOther-Image": {
"description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"",
"frequency": "No information.",
"function": "Scrapes data.",
"operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
},
"GoogleOther-Video": {
"description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"",
"frequency": "No information.",
"function": "Scrapes data.",
"operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
},
"GPTBot": {
"operator": "[OpenAI](https://openai.com)",
"respect": "Yes",
"function": "Scrapes data to train OpenAI's products.",
"frequency": "No information.",
"description": "Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies."
},
"iaskspider/2.0": {
"description": "Used to provide answers to user queries.",
"frequency": "Unclear at this time.",
"function": "Crawls sites to provide answers to user queries.",
"operator": "iAsk",
"respect": "No"
},
"ICC-Crawler": {
"description": "Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business.",
"frequency": "No information.",
"function": "Scrapes data to train and support AI technologies.",
"operator": "[NICT](https://nict.go.jp)",
"respect": "Yes"
},
"ImagesiftBot": {
"description": "Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Our web intelligence products use this index to enable search and retrieval of similar images.",
"frequency": "No information.",
"function": "ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products",
"operator": "[ImageSift](https://imagesift.com)",
"respect": "[Yes](https://imagesift.com/about)"
},
"img2dataset": {
"description": "Downloads large sets of images into datasets for LLM training or other purposes.",
"frequency": "At the discretion of img2dataset users.",
"function": "Scrapes images for use in LLMs.",
"operator": "[img2dataset](https://github.com/rom1504/img2dataset)",
"respect": "Unclear at this time."
},
"ISSCyberRiskCrawler": {
"description": "Used to train machine learning based models to quantify cyber risk.",
"frequency": "No information.",
"function": "Scrapes data to train machine learning models.",
"operator": "[ISS-Corporate](https://iss-cyber.com)",
"respect": "No"
},
"Kangaroo Bot": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot"
},
"Meta-ExternalAgent": {
"operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)",
"respect": "Yes.",
"function": "Used to train models and improve products.",
"frequency": "No information.",
"description": "\"The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly.\""
},
"Meta-ExternalFetcher": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Assistants",
"frequency": "Unclear at this time.",
"description": "Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher"
},
"OAI-SearchBot": {
"operator": "[OpenAI](https://openai.com)",
"respect": "[Yes](https://platform.openai.com/docs/bots)",
"function": "Search result generation.",
"frequency": "No information.",
"description": "Crawls sites to surface as results in SearchGPT."
},
"omgili": {
"operator": "[Webz.io](https://webz.io/)",
"respect": "[Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/)",
"function": "Data is sold.",
"frequency": "No information.",
"description": "Crawls sites for APIs used by Hootsuite, Sprinklr, NetBase, and other companies. Data also sold for research purposes or LLM training."
},
"omgilibot": {
"description": "Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io.",
"frequency": "No information.",
"function": "Data is sold.",
"operator": "[Webz.io](https://webz.io/)",
"respect": "[Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html)"
},
"PerplexityBot": {
"operator": "[Perplexity](https://www.perplexity.ai/)",
"respect": "[No](https://www.macstories.net/stories/wired-confirms-perplexity-is-bypassing-efforts-by-websites-to-block-its-web-crawler/)",
"function": "Used to answer queries at the request of users.",
"frequency": "Takes action based on user prompts.",
"description": "Operated by Perplexity to obtain results in response to user queries."
},
"PetalBot": {
"description": "Operated by Huawei to provide search and AI assistant services.",
"frequency": "No explicit frequency provided.",
"function": "Used to provide recommendations in Hauwei assistant and AI search services.",
"operator": "[Huawei](https://huawei.com/)",
"respect": "Yes"
},
"Scrapy": {
"description": "\"AI and machine learning applications often need large amounts of quality data, and web data extraction is a fast, efficient way to build structured data sets.\"",
"frequency": "No information.",
"function": "Scrapes data for a variety of uses including training AI.",
"operator": "[Zyte](https://www.zyte.com)",
"respect": "Unclear at this time."
},
"Sidetrade indexer bot": {
"description": "AI product training.",
"frequency": "No information.",
"function": "Extracts data for a variety of uses including training AI.",
"operator": "[Sidetrade](https://www.sidetrade.com)",
"respect": "Unclear at this time."
},
"Timpibot": {
"operator": "[Timpi](https://timpi.io)",
"respect": "Unclear at this time.",
"function": "Scrapes data for use in training LLMs.",
"frequency": "No information.",
"description": "Makes data available for training AI models."
},
"VelenPublicWebCrawler": {
"description": "\"Our goal with this crawler is to build business datasets and machine learning models to better understand the web.\"",
"frequency": "No information.",
"function": "Scrapes data for business data sets and machine learning models.",
"operator": "[Velen Crawler](https://velen.io)",
"respect": "[Yes](https://velen.io)"
},
"Webzio-Extended": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended"
},
"YouBot": {
"operator": "[You](https://about.you.com/youchat/)",
"respect": "[Yes](https://about.you.com/youbot/)",
"function": "Scrapes data for search engine and LLMs.",
"frequency": "No information.",
"description": "Retrieves data used for You.com web search engine and LLMs."
}
}