{ "openapi": "3.0.1", "info": { "title": "US Business Registry Scraper — New Companies by State", "description": "Search US state business registries from official open-data portals: company name, registry ID, entity type, status, registration date, address and registered agent. Filter by state, city, name and registration date to pull newly formed companies as fresh leads. No API key.", "version": "0.1", "x-build-id": "MmrIbPq1UVCGcYOKh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/publicdata~us-business-registry-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-publicdata-us-business-registry-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/publicdata~us-business-registry-scraper/runs": { "post": { "operationId": "runs-sync-publicdata-us-business-registry-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/publicdata~us-business-registry-scraper/run-sync": { "post": { "operationId": "run-sync-publicdata-us-business-registry-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Which registries to query. Only CO, CT, OR, TX, NY and DE are supported; an unsupported code is an error, never a silent fallback. Empty = all six. Oregon note: the state publishes one row per associated name and this Actor reads only the PRINCIPAL PLACE OF BUSINESS rows, so 559,186 of Oregon's 564,236 companies are reachable and the 5,050 that publish no such row are returned by no filter (measured live 2026-08-21).", "items": { "type": "string", "enum": [ "CO", "CT", "OR", "TX", "NY", "DE" ], "enumTitles": [ "Colorado", "Connecticut", "Oregon", "Texas", "New York", "Delaware" ] } }, "query": { "title": "Company name contains", "type": "string", "description": "Free-text match on the business name, e.g. 'solar', 'dental', 'logistics'. Leave empty to list everything matching the other filters." }, "registeredAfter": { "title": "Registered after (YYYY-MM-DD)", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Keep entities whose registration date is on/after this date — this is how you pull newly formed companies as fresh B2B leads. Must be a real calendar date in YYYY-MM-DD form: 2026-13-45 has the right shape but does not exist, and the run stops with a message instead of quietly exporting nothing. What the date means differs by state: formation date in CO/CT/OR, first franchise-tax liability in TX, licence start in DE, and the filing date of the document in NY (a filings feed — keep 'New registrations only' on to restrict it to formations)." }, "registeredBefore": { "title": "Registered before (YYYY-MM-DD)", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only entities whose registration date is on/before this date. Same validation as 'Registered after': it must be a real calendar date, and it must not fall before 'Registered after'." }, "city": { "title": "City", "type": "string", "description": "Filter on the city of the address the state publishes: principal address (CO), business address (CT, DE), principal place of business (OR), taxpayer address (TX), and in NY the address the entity designates for service of process — which is often its registered agent's, so NY city results skew to Albany. Every row reports which one it carries in 'addressType'." }, "entityType": { "title": "Entity type contains", "type": "string", "description": "Legal form, e.g. 'Limited Liability Company', 'Nonprofit', 'Corporation'. It is a CONTAINS match on the type name, exactly like the company-name filter: 'corp' finds every corporation type, and a short fragment also matches inside a longer word - 'AB' matches 330,577 Oregon rows because it is inside 'LiABility'. Use a whole word. Colorado and Texas publish codes instead of names: a term that IS one of the codes they publish (DLLC, CL, and also the ones the portals leave undocumented such as CO 'FO' or TX 'AB') matches that code exactly, so the entityType of an exported row always works as input; any other term is matched against the code LABELS and never against the code text, which is why a Colorado 'Limited Partnership' query returns 43,890 rows and not the 58,377 that included DLLP/FLLP limited liability partnerships. Connecticut's own vocabulary is LLC / Stock / Non-Stock / Limited Partnership / LLP - an LLP is not a Limited Partnership and the two terms return different rows. Delaware publishes a licence activity ('GENERAL SERVICES', 'RESIDENT CONTRACTOR'), not a legal form." }, "activeOnly": { "title": "Active entities only", "type": "boolean", "description": "Drop entities the state reports as not active: status (CO, CT), right-to-transact code (TX, 194,522 of 3,415,044 rows), dissolution/termination/surrender/merger filings (NY), expired licences (DE). Oregon publishes no status column — its dataset is active registrations by construction.", "default": true }, "newRegistrationsOnly": { "title": "New registrations only (New York)", "type": "boolean", "description": "New York publishes a rolling 30-day feed of ALL filings, so most rows are biennial statements of long-established companies. With this on, only formation and authority filings are kept (24,524 of 95,549 rows). No effect on the other five states, which publish entity records.", "default": true }, "includeRaw": { "title": "Include raw record", "type": "boolean", "description": "Add the untouched state record alongside the normalised fields.", "default": false }, "maxItems": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Hard cap on rows exported (and charged) across all states. 0 = unlimited.", "default": 500 } } }, "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 } } } } } } } } } }