{ "openapi": "3.0.1", "info": { "title": "AI Crawler Checker: GPTBot, robots.txt & llms.txt Policy Audit", "description": "Check which AI crawlers each website blocks in robots.txt (GPTBot, ClaudeBot, Google-Extended, PerplexityBot), plus llms.txt and TDM opt-out signals.", "version": "0.1", "x-build-id": "hVkd0MYIk1f9VWoi8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/adastra-connect~ai-crawler-policy-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-adastra-connect-ai-crawler-policy-auditor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/adastra-connect~ai-crawler-policy-auditor/runs": { "post": { "operationId": "runs-sync-adastra-connect-ai-crawler-policy-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/adastra-connect~ai-crawler-policy-auditor/run-sync": { "post": { "operationId": "run-sync-adastra-connect-ai-crawler-policy-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or URLs", "type": "array", "description": "Organizational public domains or URLs without personal data. Input paths are omitted. Private/internal destinations and literal IPs are blocked.", "items": { "type": "string" }, "default": [ "www.nytimes.com", "www.theguardian.com", "en.wikipedia.org" ] }, "testPath": { "title": "Additional path to test", "type": "string", "description": "Evaluate this path in addition to /. This path is never fetched. Example: /news/.", "default": "" }, "bots": { "title": "Bot tokens to check", "type": "array", "description": "Leave empty for all registered tokens. Unknown tokens are evaluated as custom bots with mixed purpose.", "items": { "type": "string" }, "default": [] }, "includeRaw": { "title": "Include robots directives", "type": "boolean", "description": "Include up to 50 KB of reconstructed robots directives. Comments are omitted; nonstandard paths are fingerprinted.", "default": false }, "maxResults": { "title": "Maximum billable rows", "minimum": 1, "type": "integer", "description": "Hard cap on domain rows or individual change rows across the run.", "default": 100 }, "concurrency": { "title": "Concurrent domains", "minimum": 1, "maximum": 20, "type": "integer", "description": "Different hosts in parallel; one active request at a time per destination host.", "default": 5 }, "requestDelayMs": { "title": "Request delay (ms)", "minimum": 0, "type": "integer", "description": "Minimum spacing between requests to one host. Default 250 ms; a larger Crawl-delay for this auditor takes precedence.", "default": 250 }, "monitorMode": { "title": "Monitor policy changes", "type": "boolean", "description": "Compare with compact snapshots in the named ai-crawler-policy-auditor-state store. First run saves baselines.", "default": false }, "monitorKey": { "title": "Monitoring namespace", "type": "string", "description": "Keep the same value across scheduled runs. Separate values create independent baselines. Avoid overlapping runs in one namespace.", "default": "default" }, "emitBaselineOnFirstRun": { "title": "Emit baseline fields", "type": "boolean", "description": "Emit one change-shaped row for each meaningful initial field. Baseline rows carry baseline: true.", "default": false } } }, "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 } } } } } } } } } }