{ "openapi": "3.0.1", "info": { "title": "AI Crawler Access Checker: GPTBot, ClaudeBot, robots.txt", "description": "Bulk-check which AI crawlers (GPTBot, ClaudeBot, PerplexityBot...) each domain allows or blocks in robots.txt. Pay per domain, EN/ES, no API keys.", "version": "0.1", "x-build-id": "Gb38cx2pXhggjZYTC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/atalaya-ai~ai-crawler-access-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-atalaya-ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/atalaya-ai~ai-crawler-access-checker/runs": { "post": { "operationId": "runs-sync-atalaya-ai-ai-crawler-access-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/atalaya-ai~ai-crawler-access-checker/run-sync": { "post": { "operationId": "run-sync-atalaya-ai-ai-crawler-access-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "domains" ], "properties": { "domains": { "title": "Domains to check", "minItems": 1, "maxItems": 5000, "type": "array", "description": "Domains or website URLs, one per line (for example `example.com` or `https://www.example.com/pricing`). Only the host is used; each host is checked once (`example.com` and `www.example.com` are different hosts). Up to 5,000 per run. Free Apify plans check up to 25 domains per run.", "items": { "type": "string" } }, "crawlers": { "title": "AI crawlers to check (optional)", "type": "array", "description": "Leave empty to check all supported AI crawlers. Or list a subset by robots.txt token (case-insensitive): GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, Googlebot, Google-Extended, Applebot, Applebot-Extended, CCBot, Meta-ExternalAgent, Meta-ExternalFetcher, Amazonbot, Amzn-SearchBot, Amzn-User, Bytespider, DuckAssistBot. Unknown tokens are ignored and listed in the run summary.", "default": [], "items": { "type": "string" } }, "paths": { "title": "Extra paths to test (optional)", "type": "array", "description": "The site root `/` is always tested. Add paths such as `/blog/` or `/pricing` to see whether each crawler may fetch them too (up to 20). The deciding robots.txt rule is reported per path.", "default": [], "items": { "type": "string" } }, "language": { "title": "Language of the verdict", "enum": [ "en", "es" ], "type": "string", "description": "Language of the one-line `verdict`, the `topFix` and status messages. All other fields (crawler names, statuses, rules) are language-neutral.", "default": "en" }, "checkLlmsTxt": { "title": "Also check llms.txt and llms-full.txt", "type": "boolean", "description": "Adds two small requests per domain to report whether /llms.txt and /llms-full.txt exist. Turn off for the fastest robots.txt-only check. The price per domain is the same either way.", "default": true }, "maxConcurrency": { "title": "Domains checked in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many different domains are checked at the same time (1-20). Requests to one domain are always sent one at a time with a short pause, whatever this value is.", "default": 10 } } }, "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 } } } } } } } } } }