{ "openapi": "3.0.1", "info": { "title": "AI Crawler Checker: robots.txt GPTBot, ClaudeBot & llms.txt", "description": "Bulk check which AI crawlers a website allows or blocks in robots.txt: GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended and 18 more. Adds llms.txt, Content-Signal, meta robots and a verdict (training vs AI search). Misses are free.", "version": "0.1", "x-build-id": "uNVkiJVpULhCRYfRw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/swillz~ai-crawler-access-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-swillz-ai-crawler-access-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/swillz~ai-crawler-access-checker/runs": { "post": { "operationId": "runs-sync-swillz-ai-crawler-access-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/swillz~ai-crawler-access-checker/run-sync": { "post": { "operationId": "run-sync-swillz-ai-crawler-access-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "domains": { "title": "Domains or website URLs", "type": "array", "description": "Sites to check, e.g. [\"nytimes.com\",\"https://www.stripe.com\"]. A bare domain is checked at https:// and follows redirects (e.g. to www). Each host is checked once.", "items": { "type": "string" } }, "bots": { "title": "AI crawlers to check", "type": "array", "description": "Leave empty to check all 23 known crawlers: OpenAI, Anthropic, Perplexity, Google, Microsoft, Apple, Meta, Amazon, DuckDuckGo, Mistral, Common Crawl, ByteDance, Cohere and Diffbot.", "items": { "type": "string", "enum": [ "GPTBot", "OAI-SearchBot", "ChatGPT-User", "ClaudeBot", "Claude-SearchBot", "Claude-User", "anthropic-ai", "PerplexityBot", "Perplexity-User", "Google-Extended", "Googlebot", "Bingbot", "Applebot", "Applebot-Extended", "Meta-ExternalAgent", "Meta-ExternalFetcher", "Amazonbot", "DuckAssistBot", "MistralAI-User", "CCBot", "Bytespider", "cohere-ai", "Diffbot" ], "enumTitles": [ "GPTBot (OpenAI, training)", "OAI-SearchBot (OpenAI, search)", "ChatGPT-User (OpenAI, user)", "ClaudeBot (Anthropic, training)", "Claude-SearchBot (Anthropic, search)", "Claude-User (Anthropic, user)", "anthropic-ai (Anthropic, training)", "PerplexityBot (Perplexity, search)", "Perplexity-User (Perplexity, user)", "Google-Extended (Google, training)", "Googlebot (Google, search engine)", "Bingbot (Microsoft, search engine)", "Applebot (Apple, search)", "Applebot-Extended (Apple, training)", "Meta-ExternalAgent (Meta, training)", "Meta-ExternalFetcher (Meta, user)", "Amazonbot (Amazon, search)", "DuckAssistBot (DuckDuckGo, search)", "MistralAI-User (Mistral, user)", "CCBot (Common Crawl, training)", "Bytespider (ByteDance, training)", "cohere-ai (Cohere, training)", "Diffbot (Diffbot, training)" ] } }, "customUserAgents": { "title": "Extra user-agent tokens", "type": "array", "description": "Any other crawler tokens to check against robots.txt, e.g. [\"YouBot\",\"Timpibot\"]. Up to 20.", "items": { "type": "string" } }, "testPath": { "title": "Path to test", "type": "string", "description": "Path the bot rules are evaluated for (and the page whose meta robots is read). Default \"/\" (the whole site). Use e.g. \"/blog/\" to check a section.", "default": "/" }, "checkLlmsTxt": { "title": "Check llms.txt and llms-full.txt", "type": "boolean", "description": "Look for /llms.txt (title, summary, sections, link count) and /llms-full.txt.", "default": true }, "checkHomepage": { "title": "Check page meta robots", "type": "boolean", "description": "Fetch the tested page (only if robots.txt allows generic crawlers) and report meta robots, X-Robots-Tag, noindex, noai and noimageai.", "default": true }, "includeBotDetails": { "title": "Include per-bot details", "type": "boolean", "description": "Add the bots array (operator, purpose, access, matched user-agent and rule for each crawler). Turn off for compact rows; the blocked/allowed lists stay.", "default": true }, "datasetId": { "title": "Read domains from a dataset", "type": "string", "description": "Optional dataset ID from another Actor run (e.g. a lead list or Google Maps scrape). Domains are read from domainField." }, "domainField": { "title": "Dataset field with the domain", "type": "string", "description": "Field to read from datasetId, e.g. \"website\". Auto-detected from domain, website, url and similar if empty." }, "maxDomains": { "title": "Max domains", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many unique domains (1-100000). Default 1000.", "default": 1000 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Sites checked in parallel (1-30). Default 10.", "default": 10 }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "Per HTTP request (3-60). Default 15.", "default": 15 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }