robots.txt Parser & AI Crawler Block Checker
Pricing
$11.00 / 1,000 robots.txt ai policy rows
Go to Apify Store
robots.txt Parser & AI Crawler Block Checker
Try Input: 1 domain ≈ USD 0.011/row. From USD 11/1k. Paste domain and Start.
robots.txt Parser & AI Crawler Block Checker
Pricing
$11.00 / 1,000 robots.txt ai policy rows
Try Input: 1 domain ≈ USD 0.011/row. From USD 11/1k. Paste domain and Start.
You can access the robots.txt Parser & AI Crawler Block Checker programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "TAbBWVgeJ3uWZahkN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/taroyamada~robotstxt-ai-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-taroyamada-robotstxt-ai-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/taroyamada~robotstxt-ai-checker/runs": { "post": { "operationId": "runs-sync-taroyamada-robotstxt-ai-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/taroyamada~robotstxt-ai-checker/run-sync": { "post": { "operationId": "run-sync-taroyamada-robotstxt-ai-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", "type": "array", "description": "List of domains to analyze robots.txt for AI crawler policies. Max 500.", "items": { "type": "string" } }, "delivery": { "title": "Delivery Mode", "enum": [ "dataset", "webhook" ], "type": "string", "description": "How to deliver results. 'dataset' saves to Apify Dataset, 'webhook' sends to a URL. In demoMode, delivery is always dataset.", "default": "dataset" }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Webhook URL to send results to (only used when delivery is 'webhook'). Works with Slack, Discord, or any HTTP endpoint." }, "snapshotKey": { "title": "Snapshot Key", "type": "string", "description": "Record key for change snapshots inside the fixed robotstxt-ai-checker-state Key-Value Store.", "default": "robotstxt-snapshots" }, "datasetMode": { "title": "Dataset Mode", "enum": [ "all", "changes_only" ], "type": "string", "description": "all emits every result. changes_only emits only changed results and emits zero rows and zero charges when nothing changed.", "default": "changes_only" }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of parallel requests. Higher = faster but may trigger rate limits.", "default": 5 }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "If true, runs without saving results or sending webhooks. Useful for testing.", "default": false }, "demoMode": { "title": "Demo Mode", "type": "boolean", "description": "If true, checks only 1 domain, returns compact policy fields, and disables webhook/snapshot writes.", "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 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for robots.txt Parser & AI Crawler Block Checker from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: