{ "openapi": "3.0.1", "info": { "title": "AI Website Categorization: IAB, Industry & Brand Safety", "description": "Classify domains with AI: IAB Content Taxonomy 3.1 category (Tier 1 and 2 IDs), industry, business model, language and brand safety flags for each website, plus parked, dead and redirected domain detection. Reads only public pages and respects robots.txt.", "version": "0.1", "x-build-id": "Sa0Wm9xV41rzbycoF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/messnomore~website-categorization/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-messnomore-website-categorization", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/messnomore~website-categorization/runs": { "post": { "operationId": "runs-sync-messnomore-website-categorization", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/messnomore~website-categorization/run-sync": { "post": { "operationId": "run-sync-messnomore-website-categorization", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "One domain or URL per entry, e.g. \"stripe.com\" or \"https://www.bbc.co.uk/news\" (up to 10,000 per run). Only the host name is used. Duplicates and invalid entries are skipped and never charged.", "items": { "type": "string" } }, "taxonomy": { "title": "Taxonomy", "enum": [ "iab_content_3", "custom" ], "type": "string", "description": "\"IAB Content Taxonomy 3.1\" returns the IAB Tier 1 and Tier 2 category (official IDs). \"IAB + my own labels\" also picks the best of your custom labels for each site (same price).", "default": "iab_content_3" }, "customLabels": { "title": "Custom labels", "type": "array", "description": "Used only with \"IAB + my own labels\": 2 to 100 labels (up to 80 characters each), e.g. \"SaaS\", \"E-commerce\", \"Agency\", \"News media\". Each site gets the best fitting label, or none when nothing fits.", "default": [], "items": { "type": "string" } }, "includeBrandSafety": { "title": "Brand safety flags", "type": "boolean", "description": "Flag sensitive topics (adult, gambling, alcohol and tobacco, weapons, hate speech, piracy, spam and malware, and the other IAB Sensitive Topics) with an overall risk level (none, low, medium, high).", "default": true }, "aiKnowledgeFallback": { "title": "Classify blocked or unreachable sites from AI knowledge", "type": "boolean", "description": "When a site blocks automated visitors, disallows them in robots.txt, or drops or stalls the connection (common on large sites), classify it from the AI model's own knowledge of that domain (the site is not visited again). Results are marked classificationSource = \"ai_knowledge\". Domains the model does not know stay unclassified.", "default": true }, "maxPagesPerDomain": { "title": "Pages per domain", "minimum": 1, "maximum": 3, "type": "integer", "description": "1 = homepage only (fastest). 2 = homepage + About page (recommended). 3 = also one products or services page. The price per domain is the same.", "default": 2 } } }, "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 } } } } } } } } } }