{ "openapi": "3.0.1", "info": { "title": "US Business Formation Scraper — New LLC & Company Leads", "description": "Scrape newly registered US businesses & LLCs from state open-data registries (CO, OR, CT, PA). Get business name, entity type, formation date, status, registered agent and address — filter by date, type & keyword, with monitoring for only-new filings. Keyless, no browser.", "version": "0.1", "x-build-id": "oKwFZWTQAhgletFxu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~us-business-formation-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-us-business-formation-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~us-business-formation-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-us-business-formation-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~us-business-formation-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-us-business-formation-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "states": { "title": "States (only these 5 have data)", "type": "array", "description": "Pick any subset of the 5 supported state registries: New York, Colorado, Pennsylvania, Connecticut, Oregon. These are the only US states that publish a clean, queryable open-data business registry with formation dates — you can only choose from this list, so there are no empty runs. Leave empty to scrape all 5. More states added on request.", "items": { "type": "string", "enum": [ "Colorado", "Oregon", "Connecticut", "Pennsylvania", "New York" ] }, "default": [ "Colorado", "Oregon", "Connecticut", "Pennsylvania", "New York" ] }, "registeredAfter": { "title": "Registered after (YYYY-MM-DD)", "type": "string", "description": "Only return businesses registered/formed on or after this date — the key to fresh, high-intent leads. Leave empty for all (newest first). Example: 2026-05-01." }, "entityTypes": { "title": "Entity types", "type": "array", "description": "Keep only these entity types (matched flexibly across each state's wording). Leave empty for all types.", "items": { "type": "string", "enum": [ "LLC", "Corporation", "Nonprofit", "Partnership", "Sole Proprietorship", "Trade Name" ] }, "default": [] }, "keyword": { "title": "Keyword (optional)", "type": "string", "description": "Full-text filter on the registry (matches business name and other indexed fields). Leave empty to return all." }, "statusActiveOnly": { "title": "Active businesses only", "type": "boolean", "description": "Drop businesses whose status is clearly inactive (dissolved, revoked, expired, withdrawn…). Keeps active and unknown-status records.", "default": false }, "maxResultsPerState": { "title": "Max results per state", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Cap the number of business records collected per state.", "default": 500 }, "maxResults": { "title": "Max results (whole run)", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Global cap on the total number of business records emitted in this run, across all states.", "default": 1000 }, "deduplicateResults": { "title": "Deduplicate results", "type": "boolean", "description": "Emit each business only once per run (keyed by state + registry number).", "default": true }, "monitorMode": { "title": "Monitoring mode — only new filings", "type": "boolean", "description": "Remember filings already returned and emit ONLY businesses not seen in previous runs (new registrations). Pairs with Apify Schedules to capture fresh leads daily.", "default": false }, "monitorStoreName": { "title": "Monitor store name", "type": "string", "description": "Named key-value store holding the 'already seen' filing ids for monitoring mode. Use a different name per tracked scope.", "default": "business-formation-monitor" }, "socrataAppToken": { "title": "Socrata app token (optional)", "type": "string", "description": "Optional Socrata app token to raise the open-data API throttling limit on very large runs. Not required for normal use." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum states fetched in parallel.", "default": 4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. State open-data APIs are clean, so the default Apify proxy is plenty.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }