3 "operator": "[Ai2](https://allenai.org/crawler)",
4 "respect": "Yes",
5 "function": "Content is used to train open language models.",
6 "frequency": "No information provided.",
7 "description": "Explores 'certain domains' to find web content.",
10 "description": "Explores 'certain domains' to find web content.",
11 "frequency": "No information provided.",
12 "function": "Content is used to train open language models.",
13 "operator": "[Ai2](https://allenai.org/crawler)",
14 "respect": "Yes",
17 "operator": "Amazon",
18 "respect": "Yes",
19 "function": "Service improvement and enabling answers for Alexa users.",
20 "frequency": "No information provided.",
21 "description":
25 "operator": "[Anthropic](https://www.anthropic.com)",
26 "respect": "Unclear at this time.",
27 "function": "Scrapes data to train Anthropic's AI products.",
28 "frequency": "No information provided.",
29 "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
32 "operator": "Unclear at this time.",
33 "respect": "Unclear at this time.",
34 "function": "AI Search Crawlers",
35 "frequency": "Unclear at this time.",
36 "description":
40 "operator": "[Apple](https://support.apple.com/en-us/119829#datausage)",
41 "respect": "Yes",
42 "function": "Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others.",
43 "frequency": "Unclear at this time.",
44 "description":
48 "operator": "ByteDance",
49 "respect": "No",
50 "function": "LLM training.",
51 "frequency": "Unclear at this time.",
52 "description": "Downloads data to train LLMS, including ChatGPT competitors.",
55 "operator": "[Common Crawl Foundation](https://commoncrawl.org)",
56 "respect": "[Yes](https://commoncrawl.org/ccbot)",
57 "function": "Provides open crawl dataset, used for many purposes, including Machine Learning/AI.",
58 "frequency": "Monthly at present.",
59 "description":
63 "operator": "[OpenAI](https://openai.com)",
64 "respect": "Yes",
65 "function": "Takes action based on user prompts.",
66 "frequency": "Only when prompted by a user.",
67 "description": "Used by plugins in ChatGPT to answer queries based on user input.",
70 "operator": "[Anthropic](https://www.anthropic.com)",
71 "respect": "Unclear at this time.",
72 "function": "Scrapes data to train Anthropic's AI products.",
73 "frequency": "No information provided.",
74 "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
78 "respect":
79 "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)",
80 "function": "Scrapes data to train Anthropic's AI products.",
81 "frequency": "No information provided.",
82 "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
85 "operator": "[Cohere](https://cohere.com)",
86 "respect": "Unclear at this time.",
87 "function": "Retrieves data to provide responses to user-initiated prompts.",
88 "frequency": "Takes action based on user prompts.",
89 "description": "Retrieves data based on user prompts.",
93 "Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products",
94 "respect": "Unclear at this time.",
95 "function": "AI Data Scrapers",
96 "frequency": "Unclear at this time.",
97 "description":
101 "operator": "[Crawlspace](https://crawlspace.dev)",
102 "respect": "[Yes](https://news.ycombinator.com/item?id=42756654)",
103 "function": "Scrapes data",
104 "frequency": "Unclear at this time.",
105 "description": "Provides crawling services for any purpose, probably including AI model training.",
108 "operator": "[Diffbot](https://www.diffbot.com/)",
109 "respect": "At the discretion of Diffbot users.",
110 "function": "Aggregates structured web data for monitoring and AI model training.",
111 "frequency": "Unclear at this time.",
112 "description":
116 "operator": "Unclear at this time.",
117 "respect": "Unclear at this time.",
118 "function": "AI Assistants",
119 "frequency": "Unclear at this time.",
120 "description":
124 "operator": "Meta/Facebook",
125 "respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)",
126 "function": "Training language models",
127 "frequency": "Up to 1 page per second",
128 "description":
132 "description": "Unclear who the operator is; but data is used for training/machine learning.",
133 "frequency": "Unclear at this time.",
134 "function": "We are using the data from the crawler to build datasets for machine learning experiments.",
135 "operator": "Unknown",
136 "respect": "[Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler)",
139 "operator": "Google",
140 "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
141 "function": "LLM training.",
142 "frequency": "No information.",
143 "description":
148 "\"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.\"",
149 "frequency": "No information.",
150 "function": "Scrapes data.",
151 "operator": "Google",
152 "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
156 "\"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.\"",
157 "frequency": "No information.",
158 "function": "Scrapes data.",
159 "operator": "Google",
160 "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
164 "\"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.\"",
165 "frequency": "No information.",
166 "function": "Scrapes data.",
167 "operator": "Google",
168 "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
171 "operator": "[OpenAI](https://openai.com)",
172 "respect": "Yes",
173 "function": "Scrapes data to train OpenAI's products.",
174 "frequency": "No information.",
175 "description":
179 "description": "Used to provide answers to user queries.",
180 "frequency": "Unclear at this time.",
181 "function": "Crawls sites to provide answers to user queries.",
182 "operator": "iAsk",
183 "respect": "No",
187 "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.",
188 "frequency": "No information.",
189 "function": "Scrapes data to train and support AI technologies.",
190 "operator": "[NICT](https://nict.go.jp)",
191 "respect": "Yes",
195 "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.",
196 "frequency": "No information.",
197 "function":
198 "ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products",
199 "operator": "[ImageSift](https://imagesift.com)",
203 "description": "Downloads large sets of images into datasets for LLM training or other purposes.",
204 "frequency": "At the discretion of img2dataset users.",
205 "function": "Scrapes images for use in LLMs.",
206 "operator": "[img2dataset](https://github.com/rom1504/img2dataset)",
207 "respect": "Unclear at this time.",
210 "description": "Used to train machine learning based models to quantify cyber risk.",
211 "frequency": "No information.",
212 "function": "Scrapes data to train machine learning models.",
213 "operator": "[ISS-Corporate](https://iss-cyber.com)",
214 "respect": "No",
217 "operator": "Unclear at this time.",
218 "respect": "Unclear at this time.",
219 "function": "AI Data Scrapers",
220 "frequency": "Unclear at this time.",
221 "description":
225 "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)",
226 "respect": "Yes.",
227 "function": "Used to train models and improve products.",
228 "frequency": "No information.",
229 "description":
233 "operator": "Unclear at this time.",
234 "respect": "Unclear at this time.",
235 "function": "AI Assistants",
236 "frequency": "Unclear at this time.",
237 "description":
241 "operator": "[OpenAI](https://openai.com)",
242 "respect": "[Yes](https://platform.openai.com/docs/bots)",
243 "function": "Search result generation.",
244 "frequency": "No information.",
245 "description": "Crawls sites to surface as results in SearchGPT.",
248 "operator": "[Webz.io](https://webz.io/)",
249 "respect": "[Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/)",
250 "function": "Data is sold.",
251 "frequency": "No information.",
252 "description":
257 "Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io.",
258 "frequency": "No information.",
259 "function": "Data is sold.",
260 "operator": "[Webz.io](https://webz.io/)",
261 "respect": "[Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html)",
264 "operator": "the Chinese company Huawei",
265 "respect": "Unclear at this time.",
266 "function": "AI Data Scrapers",
267 "frequency": "Unclear at this time.",
268 "description":
273 "respect":
274 "[No](https://www.macstories.net/stories/wired-confirms-perplexity-is-bypassing-efforts-by-websites-to-block-its-web-crawler/)",
275 "function": "Used to answer queries at the request of users.",
276 "frequency": "Takes action based on user prompts.",
277 "description": "Operated by Perplexity to obtain results in response to user queries.",
280 "description": "Operated by Huawei to provide search and AI assistant services.",
281 "frequency": "No explicit frequency provided.",
282 "function": "Used to provide recommendations in Hauwei assistant and AI search services.",
283 "operator": "[Huawei](https://huawei.com/)",
284 "respect": "Yes",
288 "\"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.\"",
289 "frequency": "No information.",
290 "function": "Scrapes data for a variety of uses including training AI.",
291 "operator": "[Zyte](https://www.zyte.com)",
292 "respect": "Unclear at this time.",
295 "operator": "[Semrush](https://www.semrush.com/)",
296 "respect": "[Yes](https://www.semrush.com/bot/)",
297 "function": "Scrapes data for use in LLM article-writing tool.",
298 "frequency": "Roughly once every 10 seconds.",
299 "description":
300 "SemrushBot is a bot which, among other functions, scrapes data for use in ContentShake AI tool reports.",
301 },
302 "Sidetrade indexer bot": {
303 "description": "AI product training.",
304 "frequency": "No information.",
305 "function": "Extracts data for a variety of uses including training AI.",
306 "operator": "[Sidetrade](https://www.sidetrade.com)",
307 "respect": "Unclear at this time.",
310 "operator": "[Timpi](https://timpi.io)",
311 "respect": "Unclear at this time.",
312 "function": "Scrapes data for use in training LLMs.",
313 "frequency": "No information.",
314 "description": "Makes data available for training AI models.",
318 "\"Our goal with this crawler is to build business datasets and machine learning models to better understand the web.\"",
319 "frequency": "No information.",
320 "function": "Scrapes data for business data sets and machine learning models.",
321 "operator": "[Velen Crawler](https://velen.io)",
322 "respect": "[Yes](https://velen.io)",
325 "operator": "Unclear at this time.",
326 "respect": "Unclear at this time.",
327 "function": "AI Data Scrapers",
328 "frequency": "Unclear at this time.",
329 "description":
333 "operator": "[You](https://about.you.com/youchat/)",
334 "respect": "[Yes](https://about.you.com/youbot/)",
335 "function": "Scrapes data for search engine and LLMs.",
336 "frequency": "No information.",
337 "description": "Retrieves data used for You.com web search engine and LLMs.",