django-bots 1.2.2__tar.gz → 1.2.4__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (41) hide show
  1. {django_bots-1.2.2/src/django_bots.egg-info → django_bots-1.2.4}/PKG-INFO +1 -1
  2. {django_bots-1.2.2 → django_bots-1.2.4}/pyproject.toml +1 -1
  3. django_bots-1.2.4/src/django_bots/data/VERSIONS.json +3 -0
  4. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/data/ai_robots.json +202 -6
  5. {django_bots-1.2.2 → django_bots-1.2.4/src/django_bots.egg-info}/PKG-INFO +1 -1
  6. django_bots-1.2.2/src/django_bots/data/VERSIONS.json +0 -3
  7. {django_bots-1.2.2 → django_bots-1.2.4}/LICENSE +0 -0
  8. {django_bots-1.2.2 → django_bots-1.2.4}/README.md +0 -0
  9. {django_bots-1.2.2 → django_bots-1.2.4}/setup.cfg +0 -0
  10. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/__init__.py +0 -0
  11. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/ai.py +0 -0
  12. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/apps.py +0 -0
  13. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/checks.py +0 -0
  14. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/conf.py +0 -0
  15. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/crawlers.py +0 -0
  16. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/data/LICENSE-ai-robots-txt +0 -0
  17. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/data/ai_categories.json +0 -0
  18. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/middleware.py +0 -0
  19. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/py.typed +0 -0
  20. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/templates/django_bots/robots.txt +0 -0
  21. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/templatetags/__init__.py +0 -0
  22. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/templatetags/bots.py +0 -0
  23. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/templatetags/user_agents.py +0 -0
  24. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/useragent.py +0 -0
  25. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/utils.py +0 -0
  26. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots/views.py +0 -0
  27. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots.egg-info/SOURCES.txt +0 -0
  28. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots.egg-info/dependency_links.txt +0 -0
  29. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots.egg-info/requires.txt +0 -0
  30. {django_bots-1.2.2 → django_bots-1.2.4}/src/django_bots.egg-info/top_level.txt +0 -0
  31. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_ai.py +0 -0
  32. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_checks.py +0 -0
  33. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_conf.py +0 -0
  34. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_crawlers.py +0 -0
  35. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_middleware.py +0 -0
  36. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_scripts.py +0 -0
  37. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_templatetags.py +0 -0
  38. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_useragent.py +0 -0
  39. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_useragent_compat.py +0 -0
  40. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_utils.py +0 -0
  41. {django_bots-1.2.2 → django_bots-1.2.4}/tests/test_views.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: django-bots
3
- Version: 1.2.2
3
+ Version: 1.2.4
4
4
  Summary: User-agent parsing, crawler detection and AI bot blocking for Django.
5
5
  Author-email: M4p4 <homejr@protonmail.com>
6
6
  License-Expression: MIT
@@ -4,7 +4,7 @@ requires = [ "setuptools>=77" ]
4
4
 
5
5
  [project]
6
6
  name = "django-bots"
7
- version = "1.2.2"
7
+ version = "1.2.4"
8
8
  description = "User-agent parsing, crawler detection and AI bot blocking for Django."
9
9
  readme = "README.md"
10
10
  keywords = [ "ai", "bots", "crawlers", "django", "robots.txt", "user-agents" ]
@@ -0,0 +1,3 @@
1
+ {
2
+ "ai_robots_txt": "v2.2"
3
+ }
@@ -1,4 +1,11 @@
1
1
  {
2
+ "__usage_ai-training": {
3
+ "operator": "Not applicable.",
4
+ "respect": "Yes ([Anthropic](https://mailarchive.ietf.org/arch/msg/ai-control/mddjatOxSR0h6GmLRBWlc839c7w/), [OpenAI](https://openai.com/index/helping-websites-express-ai-training-preferences/), [Google](https://developers.google.com/search/blog/2026/10/ai-training-control), [Microsoft Bing](https://blogs.bing.com/search/2026/10/your-content-your-choice-clearer-preferences-for-training-and-grounding/))",
5
+ "function": "AI Data Scrapers",
6
+ "frequency": "Not applicable.",
7
+ "description": "`__usage_ai-training` is a policy token defined in an [Internet Draft](https://datatracker.ietf.org/doc/draft-kelley-aipref-training-preference-signal/) that Anthropic's Kevin Kelley submitted to the AI Preferences working group at the IETF to show a preference against crawling data for AI training."
8
+ },
2
9
  "AddSearchBot": {
3
10
  "operator": "Unclear at this time.",
4
11
  "respect": "Unclear at this time.",
@@ -20,6 +27,13 @@
20
27
  "frequency": "Requests RSS feed every 5-6 minutes.",
21
28
  "description": "Scrapes data for AI news aggregation and republishing."
22
29
  },
30
+ "AGI Agent": {
31
+ "operator": "AGI, Inc",
32
+ "respect": "Unclear at this time.",
33
+ "function": "AI Agents",
34
+ "frequency": "Unclear at this time.",
35
+ "description": "AGI Agent is an AI assistant operated by AGI, Inc. that navigates websites to complete user-directed tasks, including online purchases and other actions. More info can be found at https://knownagents.com/agents/agi-agent"
36
+ },
23
37
  "AI2Bot": {
24
38
  "operator": "[Ai2](https://allenai.org/crawler)",
25
39
  "respect": "Yes",
@@ -32,7 +46,7 @@
32
46
  "respect": "Unclear at this time.",
33
47
  "function": "AI Assistants",
34
48
  "frequency": "Unclear at this time.",
35
- "description": "Ai2Bot-DeepResearchEval is operated by Ai2, a non-profit AI research institute. It's used to collect and scan resources used in deep research queries performed by Ai2's o… More info can be found at https://knownagents.com/agents/ai2bot-deepresearcheval"
49
+ "description": "AI2Bot-DeepResearchEval retrieves resources used to evaluate deep-research queries performed by Ai2's open-source models. More info can be found at https://knownagents.com/agents/ai2bot-deepresearcheval"
36
50
  },
37
51
  "Ai2Bot-Dolma": {
38
52
  "operator": "[Ai2](https://allenai.org/crawler)",
@@ -230,6 +244,13 @@
230
244
  "frequency": "Unclear at this time.",
231
245
  "description": "Downloads data to train LLMS, including ChatGPT competitors."
232
246
  },
247
+ "CartAI Agentic Commerce": {
248
+ "operator": "CartAI that accesses online stores to support user-directed shopping and checkout workflows",
249
+ "respect": "Unclear at this time.",
250
+ "function": "AI Agents",
251
+ "frequency": "Unclear at this time.",
252
+ "description": "CartAI Agentic Commerce is a signed browser agent operated by CartAI that accesses online stores to support user-directed shopping and checkout workflows. More info can be found at https://knownagents.com/agents/cartai-agentic-commerce"
253
+ },
233
254
  "CCBot": {
234
255
  "operator": "[Common Crawl Foundation](https://commoncrawl.org)",
235
256
  "respect": "[Yes](https://commoncrawl.org/ccbot)",
@@ -265,6 +286,13 @@
265
286
  "frequency": "Only when prompted by a user.",
266
287
  "description": "ChatGPT-User is OpenAI's web crawler that visits websites when ChatGPT users request information. This enables ChatGPT to include links in its responses. More info can be found at https://knownagents.com/agents/chatgpt-user"
267
288
  },
289
+ "Claude-Agent": {
290
+ "operator": "Unclear at this time.",
291
+ "respect": "Unclear at this time.",
292
+ "function": "AI Agents",
293
+ "frequency": "Unclear at this time.",
294
+ "description": "Claude-Agent is Anthropic's cloud browser agent for Claude Duet. It navigates websites and completes multi-step tasks on behalf of users. More info can be found at https://knownagents.com/agents/claude-agent"
295
+ },
268
296
  "Claude-Code": {
269
297
  "operator": "Unclear at this time.",
270
298
  "respect": "Unclear at this time.",
@@ -300,6 +328,13 @@
300
328
  "frequency": "No information provided.",
301
329
  "description": "Scrapes data to train LLMs and AI products offered by Anthropic."
302
330
  },
331
+ "CledaraBot": {
332
+ "operator": "Cledara that visits SaaS providers to complete customer-approved administrative tasks, including invoice collection and user managem…",
333
+ "respect": "Unclear at this time.",
334
+ "function": "AI Agents",
335
+ "frequency": "Unclear at this time.",
336
+ "description": "CledaraBot is an AI agent operated by Cledara that visits SaaS providers to complete customer-approved administrative tasks, including invoice collection and user managem… More info can be found at https://knownagents.com/agents/cledarabot"
337
+ },
303
338
  "Cloudflare-AutoRAG": {
304
339
  "operator": "[Cloudflare](https://developers.cloudflare.com/autorag)",
305
340
  "respect": "Yes",
@@ -329,6 +364,13 @@
329
364
  "description": "Code (GitHub Copilot) is an AI coding agent that can autonomously plan, build, and execute development tasks, functioning as a collaborative AI pair programmer. More info can be found at https://knownagents.com/agents/code",
330
365
  "has_name_and_version": true
331
366
  },
367
+ "Codex": {
368
+ "operator": "Unclear at this time.",
369
+ "respect": "Unclear at this time.",
370
+ "function": "AI Coding Agents",
371
+ "frequency": "Unclear at this time.",
372
+ "description": "Codex is an AI coding agent by OpenAI that helps developers write, review, debug, and ship code. More info can be found at https://knownagents.com/agents/codex"
373
+ },
332
374
  "cohere-ai": {
333
375
  "operator": "[Cohere](https://cohere.com)",
334
376
  "respect": "Unclear at this time.",
@@ -411,7 +453,14 @@
411
453
  "respect": "Yes",
412
454
  "function": "AI Assistants",
413
455
  "frequency": "Only when prompted by a user.",
414
- "description": "Diffbot-User is used by requests originating on behalf of a human user browsing a URL using Diffbot software, in response to their input. Documented by Diffbot at https://docs.diffbot.com/docs/does-crawl-respect-robotstxt"
456
+ "description": "Diffbot-User fetches URLs on behalf of human users interacting with Diffbot software. More info can be found at https://knownagents.com/agents/diffbot-user"
457
+ },
458
+ "Dot": {
459
+ "operator": "Unclear at this time.",
460
+ "respect": "Unclear at this time.",
461
+ "function": "AI Agents",
462
+ "frequency": "Unclear at this time.",
463
+ "description": "Dot is an OpenAI AI agent that uses a cloud browser to research websites and carry out ongoing tasks for users. More info can be found at https://knownagents.com/agents/dot"
415
464
  },
416
465
  "DoubaoBot": {
417
466
  "operator": "ByteDance",
@@ -441,6 +490,20 @@
441
490
  "frequency": "Unclear at this time.",
442
491
  "description": "Supports company's AI-powered social and email management products."
443
492
  },
493
+ "ElevenlabsBot": {
494
+ "operator": "[ElevenLabs](https://elevenlabs.io)",
495
+ "respect": "Yes",
496
+ "function": "AI Assistants",
497
+ "frequency": "Unclear at this time.",
498
+ "description": "ElevenlabsBot fetches pages that customers add to or refresh in ElevenLabs agents' knowledge bases, making that content available in conversations. More info can be found at https://knownagents.com/agents/elevenlabsbot"
499
+ },
500
+ "ElevenlabsCrawler": {
501
+ "operator": "[ElevenLabs](https://elevenlabs.io)",
502
+ "respect": "Yes",
503
+ "function": "AI Data Scraper",
504
+ "frequency": "Unclear at this time.",
505
+ "description": "ElevenlabsCrawler is ElevenLabs' web crawler that collects public content that may be used to train its generative AI models. More info can be found at https://knownagents.com/agents/elevenlabscrawler"
506
+ },
444
507
  "ERNIEBot": {
445
508
  "operator": "Baidu",
446
509
  "respect": "Unclear at this time.",
@@ -462,6 +525,13 @@
462
525
  "frequency": "Unclear at this time.",
463
526
  "description": "ExaSearchBot is a web crawler operated by Exa that discovers and indexes public web pages so their content can be found, retrieved, and cited through Exa. More info can be found at https://knownagents.com/agents/exasearchbot"
464
527
  },
528
+ "ExaUser": {
529
+ "operator": "Unclear at this time.",
530
+ "respect": "Unclear at this time.",
531
+ "function": "AI Assistants",
532
+ "frequency": "Unclear at this time.",
533
+ "description": "ExaUser is Exa's on-demand fetcher that retrieves live website content when a user or an application built on the Exa API requests it. More info can be found at https://knownagents.com/agents/exauser"
534
+ },
465
535
  "FacebookBot": {
466
536
  "operator": "Meta/Facebook",
467
537
  "respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)",
@@ -546,12 +616,19 @@
546
616
  "frequency": "Unclear at this time.",
547
617
  "description": "Gemini CLI is an AI coding agent by Google that can query and edit large codebases, generate apps from images or PDFs, and automate complex workflows directly from the te… More info can be found at https://knownagents.com/agents/google-gemini-cli"
548
618
  },
619
+ "Google-GeminiNotebook": {
620
+ "operator": "Unclear at this time.",
621
+ "respect": "Unclear at this time.",
622
+ "function": "AI Assistants",
623
+ "frequency": "Unclear at this time.",
624
+ "description": "Google-GeminiNotebook fetches individual URLs that users add as sources in Gemini Notebook so Google can analyze and summarize their content. More info can be found at https://knownagents.com/agents/google-gemininotebook"
625
+ },
549
626
  "Google-NotebookLM": {
550
627
  "operator": "Unclear at this time.",
551
628
  "respect": "Unclear at this time.",
552
629
  "function": "AI Assistants",
553
630
  "frequency": "Unclear at this time.",
554
- "description": "Google-NotebookLM is an AI-powered research and note-taking assistant that helps users synthesize information from uploaded sources like documents, transcripts, or web co… More info can be found at https://knownagents.com/agents/google-notebooklm"
631
+ "description": "Google-NotebookLM is Google's former Gemini Notebook fetcher identifier that continues to retrieve source URLs users add to their notebooks. More info can be found at https://knownagents.com/agents/google-notebooklm"
555
632
  },
556
633
  "GoogleAgent-Mariner": {
557
634
  "operator": "Google",
@@ -595,6 +672,48 @@
595
672
  "frequency": "No information.",
596
673
  "description": "Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies."
597
674
  },
675
+ "Grok Bot": {
676
+ "operator": "Unclear at this time.",
677
+ "respect": "Unclear at this time.",
678
+ "function": "AI Agents",
679
+ "frequency": "Unclear at this time.",
680
+ "description": "Grok Bot is a personal AI agent created by xAI that runs on a persistent cloud computer with a browser, filesystem, and terminal. It completes multi-step tasks across app… More info can be found at https://knownagents.com/agents/grok-bot"
681
+ },
682
+ "GrokAppAndroid": {
683
+ "operator": "[xAI](https://x.ai)",
684
+ "respect": "Unclear at this time.",
685
+ "function": "AI Search Crawlers",
686
+ "frequency": "Unclear at this time.",
687
+ "description": "Grok AI is an advanced AI assistant built by xAI that leverages real-time web and X data to produce context-aware, multimodal responses."
688
+ },
689
+ "GrokBot": {
690
+ "operator": "[xAI](https://x.ai)",
691
+ "respect": "Unclear at this time.",
692
+ "function": "AI Search Crawlers",
693
+ "frequency": "Unclear at this time.",
694
+ "description": "Used to collect publicly available web content to support the training of Grok AI models."
695
+ },
696
+ "Haiku-SearchBot": {
697
+ "operator": "Unclear at this time.",
698
+ "respect": "Unclear at this time.",
699
+ "function": "AI Assistants",
700
+ "frequency": "Unclear at this time.",
701
+ "description": "Haiku-SearchBot retrieves webpages in response to user requests through Haiku's legal AI services. More info can be found at https://knownagents.com/agents/haiku-searchbot"
702
+ },
703
+ "HarkBot": {
704
+ "operator": "Unclear at this time.",
705
+ "respect": "Unclear at this time.",
706
+ "function": "AI Agents",
707
+ "frequency": "Unclear at this time.",
708
+ "description": "HarkBot visits web pages on behalf of signed-in Hark users as Hark carries out research, form-filling, and account actions. More info can be found at https://knownagents.com/agents/harkbot"
709
+ },
710
+ "HatchFeed": {
711
+ "operator": "[Meta](https://agent.meta.ai)",
712
+ "respect": "No",
713
+ "function": "AI Assistants",
714
+ "frequency": "Unclear at this time.",
715
+ "description": "HatchFeed is the link-preview fetcher of Meta's Muse AI agent; https://agent.meta.ai in its user agent redirects to muse.ai. It fetches a page and its Open Graph images when Muse needs them for a user."
716
+ },
598
717
  "HenkBot": {
599
718
  "operator": "Unclear at this time.",
600
719
  "respect": "Unclear at this time.",
@@ -602,6 +721,13 @@
602
721
  "frequency": "Unclear at this time.",
603
722
  "description": "Henkbot crawls the web on behalf of Valyu, an AI search infrastructure provider that indexes content for use in AI-powered retrieval pipelines. More info can be found at https://knownagents.com/agents/henkbot"
604
723
  },
724
+ "Hunyuan": {
725
+ "operator": "[Tencent](https://hunyuan.tencent.com)",
726
+ "respect": "Unclear at this time.",
727
+ "function": "Hunyuan is a training crawler operated by Tencent.",
728
+ "frequency": "Unclear at this time.",
729
+ "description": "Hunyuan is a training crawler operated by Tencent. Its job is to read public web pages and feed that content into a machine-learning pipeline that trains future versions of the model."
730
+ },
605
731
  "iAskBot": {
606
732
  "operator": "Unclear at this time.",
607
733
  "respect": "Unclear at this time.",
@@ -651,6 +777,13 @@
651
777
  "operator": "[img2dataset](https://github.com/rom1504/img2dataset)",
652
778
  "respect": "Unclear at this time."
653
779
  },
780
+ "Instinct": {
781
+ "operator": "Unclear at this time.",
782
+ "respect": "Unclear at this time.",
783
+ "function": "AI Agents",
784
+ "frequency": "Unclear at this time.",
785
+ "description": "Instinct is a personal AI agent that uses a phone and computer to complete everyday tasks such as ordering groceries, booking travel, arranging appointments, and communic… More info can be found at https://knownagents.com/agents/instinct"
786
+ },
654
787
  "ISSCyberRiskCrawler": {
655
788
  "description": "Used to train machine learning based models to quantify cyber risk.",
656
789
  "frequency": "No information.",
@@ -749,6 +882,13 @@
749
882
  "frequency": "Defined per-user.",
750
883
  "description": "Lightpanda is a custom-built headless browser designed for AI and automation."
751
884
  },
885
+ "Liner-User": {
886
+ "operator": "Unclear at this time.",
887
+ "respect": "Unclear at this time.",
888
+ "function": "AI Assistants",
889
+ "frequency": "Unclear at this time.",
890
+ "description": "Liner-User fetches web content for Liner to answer user questions with cited information. More info can be found at https://knownagents.com/agents/liner-user"
891
+ },
752
892
  "LinerBot": {
753
893
  "operator": "Unclear at this time.",
754
894
  "respect": "Unclear at this time.",
@@ -812,6 +952,13 @@
812
952
  "frequency": "Unhinged, more than 1 per second.",
813
953
  "description": "As per their documentation, \"The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses.\""
814
954
  },
955
+ "MiniMaxAgent": {
956
+ "operator": "Unclear at this time.",
957
+ "respect": "Unclear at this time.",
958
+ "function": "AI Agents",
959
+ "frequency": "Unclear at this time.",
960
+ "description": "MiniMaxAgent browses and uses online information to complete complex user-directed tasks in MiniMax Agent. More info can be found at https://knownagents.com/agents/minimax-agent"
961
+ },
815
962
  "MistralAI-Index": {
816
963
  "operator": "Mistral AI",
817
964
  "respect": "Yes",
@@ -840,6 +987,13 @@
840
987
  "description": "MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response.",
841
988
  "respect": "Yes"
842
989
  },
990
+ "MoonshotBot": {
991
+ "operator": "[Kimi](https://www.kimi.ai/)",
992
+ "respect": "Unclear at this time.",
993
+ "function": "MoonshotBot is a training crawler.",
994
+ "frequency": "Unclear at this time.",
995
+ "description": "MoonshotBot is a training crawler operated by Kimi. Its job is to read public web pages and feed that content into a machine-learning pipeline that trains future versions of the model."
996
+ },
843
997
  "Mozilla-Tabstack": {
844
998
  "operator": "Mozilla that performs programmatic, AI-driven interactions with web content through Tabstack",
845
999
  "respect": "Yes",
@@ -847,6 +1001,13 @@
847
1001
  "frequency": "On demand via API.",
848
1002
  "description": "Mozilla-Tabstack is an AI agent operated by Mozilla that performs programmatic, AI-driven interactions with web content through Tabstack. More info can be found at https://knownagents.com/agents/mozilla-tabstack"
849
1003
  },
1004
+ "Muse": {
1005
+ "operator": "Unclear at this time.",
1006
+ "respect": "Unclear at this time.",
1007
+ "function": "AI Agents",
1008
+ "frequency": "Unclear at this time.",
1009
+ "description": "Muse is a personal AI agent created by Meta that uses a web browser and connected apps to complete multi-step tasks such as filling out forms, booking travel, sending ema… More info can be found at https://knownagents.com/agents/muse"
1010
+ },
850
1011
  "MyCentralAIScraperBot": {
851
1012
  "operator": "Unclear at this time.",
852
1013
  "respect": "Unclear at this time.",
@@ -861,6 +1022,13 @@
861
1022
  "frequency": "Unclear at this time.",
862
1023
  "description": "'Naget revolutionizes content discovery through an AI-powered ecosystem that transforms how we generate, organize, share, and discover valuable content.' (https://naget.com/) User-agent string links https://naget.ai/bot which yields 404."
863
1024
  },
1025
+ "nbot": {
1026
+ "operator": "[NBot](https://nbot.ai)",
1027
+ "respect": "Unclear at this time.",
1028
+ "function": "AI Search Crawlers",
1029
+ "frequency": "Unclear at this time.",
1030
+ "description": "NBot uses advanced AI to scan news outlets, industry blogs, newsletters, and social media."
1031
+ },
864
1032
  "netEstate Imprint Crawler": {
865
1033
  "operator": "netEstate",
866
1034
  "respect": "Unclear at this time.",
@@ -887,7 +1055,7 @@
887
1055
  "respect": "Unclear at this time.",
888
1056
  "function": "AI Agents",
889
1057
  "frequency": "Unclear at this time.",
890
- "description": "Nova Act is an AI agent created by Amazon that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a… More info can be found at https://knownagents.com/agents/novaact"
1058
+ "description": "NovaAct is Amazon's browser-using agent for navigating websites and completing multi-step tasks on behalf of users. More info can be found at https://knownagents.com/agents/novaact"
891
1059
  },
892
1060
  "OAI-AdsBot": {
893
1061
  "operator": "[OpenAI](https://openai.com)",
@@ -959,12 +1127,19 @@
959
1127
  "frequency": "The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address.",
960
1128
  "description": "Compiles data on businesses and business professionals that is structured using AI and machine learning."
961
1129
  },
1130
+ "Payhawk Invoice Fetching Agent": {
1131
+ "operator": "Payhawk that retrieves invoices from supplier websites for users and attaches them to expense records",
1132
+ "respect": "Unclear at this time.",
1133
+ "function": "AI Agents",
1134
+ "frequency": "Unclear at this time.",
1135
+ "description": "Payhawk Invoice Fetching Agent is a browser agent operated by Payhawk that retrieves invoices from supplier websites for users and attaches them to expense records. More info can be found at https://knownagents.com/agents/payhawk-invoice-fetching-agent"
1136
+ },
962
1137
  "Perplexity-User": {
963
1138
  "operator": "[Perplexity](https://www.perplexity.ai/)",
964
1139
  "respect": "[No](https://docs.perplexity.ai/guides/bots)",
965
1140
  "function": "AI Assistants",
966
1141
  "frequency": "Only when prompted by a user.",
967
- "description": "Perplexity-User supports user actions within Perplexity. When users ask Perplexity a question, it might visit a web page to help provide an accurate answer and include a … More info can be found at https://knownagents.com/agents/perplexity-user"
1142
+ "description": "Perplexity-User retrieves webpages in response to user requests so Perplexity can answer questions using current information from those pages. More info can be found at https://knownagents.com/agents/perplexity-user"
968
1143
  },
969
1144
  "PerplexityBot": {
970
1145
  "operator": "[Perplexity](https://www.perplexity.ai/)",
@@ -985,7 +1160,7 @@
985
1160
  "respect": "Unclear at this time.",
986
1161
  "function": "AI Assistants",
987
1162
  "frequency": "No explicit frequency provided.",
988
- "description": "Phind is an AI-powered answer engine designed for developers, offering technical answers and code examples. It uses real-time web search and specialized AI models to prov… More info can be found at https://knownagents.com/agents/phindbot"
1163
+ "description": "PhindBot retrieves web pages to support Phind's developer-focused search and answer engine, which uses current web information to answer technical questions. More info can be found at https://knownagents.com/agents/phindbot"
989
1164
  },
990
1165
  "Poggio-Citations": {
991
1166
  "operator": "Poggio, a company that provides AI sales enablement tools for creating tailored narratives, business cases, and account plan…",
@@ -1071,6 +1246,13 @@
1071
1246
  "operator": "[Zyte](https://www.zyte.com)",
1072
1247
  "respect": "Unclear at this time."
1073
1248
  },
1249
+ "ScryBot": {
1250
+ "operator": "[Scry](https://scry.io/)",
1251
+ "respect": "Unclear at this time.",
1252
+ "function": "Used with AI agents to scrape data for answers to queries",
1253
+ "frequency": "No information.",
1254
+ "description": "An AI agent companion that allows you to enhance answers by scraping data"
1255
+ },
1074
1256
  "SemrushBot-OCOB": {
1075
1257
  "operator": "[Semrush](https://www.semrush.com/)",
1076
1258
  "respect": "[Yes](https://www.semrush.com/bot/)",
@@ -1225,6 +1407,13 @@
1225
1407
  "frequency": "Unclear at this time.",
1226
1408
  "description": "Description unavailable from knownagents.com More info can be found at https://knownagents.com/agents/wrtnbot"
1227
1409
  },
1410
+ "xAI-Grok": {
1411
+ "operator": "[xAI](https://x.ai/)",
1412
+ "respect": "Unclear at this time.",
1413
+ "function": "xAI-Grok is an xAI crawler token associated with Grok content collection.",
1414
+ "frequency": "Unclear at this time.",
1415
+ "description": "xAI-Grok is an xAI crawler token associated with Grok content collection. It is classified as training because it performs automated collection rather than a user-triggered fetch."
1416
+ },
1228
1417
  "YaK": {
1229
1418
  "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)",
1230
1419
  "respect": "Unclear at this time.",
@@ -1246,6 +1435,13 @@
1246
1435
  "frequency": "No information.",
1247
1436
  "description": "Retrieves data used for YandexGPT quick answers features."
1248
1437
  },
1438
+ "YiBot": {
1439
+ "operator": "[01.ai](https://01.ai/), an AI company founded by Kai-Fu Lee.",
1440
+ "respect": "Unclear at this time.",
1441
+ "function": "This bot crawls the web to gather data and content for indexation and AI model training.",
1442
+ "frequency": "Unclear at this time.",
1443
+ "description": "YiBot/1.0 is an advanced artificial intelligence platform designed to enhance interaction and engagement across various applications. Its architecture allows for seamless integration into websites and applications, providing users with a responsive and intuitive interface."
1444
+ },
1249
1445
  "YiyanBot": {
1250
1446
  "operator": "Baidu that fetches web content for the yiyan",
1251
1447
  "respect": "Unclear at this time.",
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: django-bots
3
- Version: 1.2.2
3
+ Version: 1.2.4
4
4
  Summary: User-agent parsing, crawler detection and AI bot blocking for Django.
5
5
  Author-email: M4p4 <homejr@protonmail.com>
6
6
  License-Expression: MIT
@@ -1,3 +0,0 @@
1
- {
2
- "ai_robots_txt": "v2.0"
3
- }
File without changes
File without changes
File without changes