Domain Extractor Grouper
Pricing
from $1.95 / 1,000 domain extracteds
Extract, normalize, and group root domains from URLs, emails, and mixed text. Export account-level domain groups, counts, source traces, and reports.
You can access the Domain Extractor Grouper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "p2PnbTkVk9hB3LOGB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~domain-extractor-grouper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-domain-extractor-grouper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/junipr~domain-extractor-grouper/runs": { "post": { "operationId": "runs-sync-junipr-domain-extractor-grouper", "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/junipr~domain-extractor-grouper/run-sync": { "post": { "operationId": "run-sync-junipr-domain-extractor-grouper", "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": { "inputItems": { "title": "Input Items", "type": "array", "description": "Strings or row objects to scan. Objects are read using URL, email, and text field mappings.", "default": [ { "sourceId": "lead-001", "website": "https://www.Example.com/pricing?utm_source=list", "email": "Sales@Example.com", "notes": "Parent brand example.com also owns help@support.example.com" }, { "sourceId": "lead-002", "website": "https://blog.vendor.co.uk/post", "email": "hello@Vendor.co.uk", "notes": "Partner portal: portal.partner.io" }, "Email ops@sub.example.com or visit https://docs.example.com/start." ] }, "text": { "title": "Fallback Text", "type": "string", "description": "Optional free text to scan when Input Items is empty.", "default": "" }, "urlFields": { "title": "URL Fields", "type": "array", "description": "Object fields treated as URLs, websites, or domain-like web properties.", "items": { "type": "string" }, "default": [ "url", "website", "site", "homepage", "sourceUrl", "profileUrl" ] }, "emailFields": { "title": "Email Fields", "type": "array", "description": "Object fields treated as email addresses or email lists.", "items": { "type": "string" }, "default": [ "email", "emails", "contactEmail", "ownerEmail", "supportEmail" ] }, "textFields": { "title": "Mixed Text Fields", "type": "array", "description": "Object fields scanned for URLs, emails, and bare domains inside mixed text.", "items": { "type": "string" }, "default": [ "text", "notes", "description", "body", "content", "message" ] }, "extractFromAllStringFields": { "title": "Scan All String Fields", "type": "boolean", "description": "When enabled, every unmapped string field is scanned as mixed text.", "default": false }, "includeSubdomains": { "title": "Include Subdomains", "type": "boolean", "description": "Include normalized subdomains observed for each root domain group.", "default": true }, "includeSamples": { "title": "Include Sample Matches", "type": "boolean", "description": "Include traceable sample matches in each dataset row.", "default": true }, "maxSamplesPerDomain": { "title": "Maximum Samples Per Domain", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum sample matches stored in each domain group row.", "default": 5 }, "knownMultiPartSuffixes": { "title": "Known Multi-Part Suffixes", "type": "array", "description": "Optional extra suffixes such as co.uk or com.au used when reducing hosts to root domains.", "items": { "type": "string" }, "default": [] }, "maxItems": { "title": "Maximum Items", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum input strings or rows to scan. Defaults low and is capped for predictable local utility runs.", "default": 100 }, "includeReport": { "title": "Generate Summary Report", "type": "boolean", "description": "Store domain groups, summary JSON, and a Markdown report in the default key-value store.", "default": true }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write a dry-run summary without PPE charges or dataset output.", "default": false }, "debug": { "title": "Debug Logging", "type": "boolean", "description": "Enable additional logs for troubleshooting field mapping and extraction decisions.", "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 Domain Extractor Grouper 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: