{ "openapi": "3.0.1", "info": { "title": "Connecticut Business Registry Scraper — SOTS", "description": "Search Connecticut's full business registry by name or account number, or stream new registrations since a date. Normalized records from data.ct.gov: status, account number, registration date, mailing address, ownership certifications. Complete registry, not only active companies. No proxy needed.", "version": "0.8", "x-build-id": "wB65IXwEskp7ZIGfY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ai-lead-gen-tools~us-ct-sots/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ai-lead-gen-tools-us-ct-sots", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ai-lead-gen-tools~us-ct-sots/runs": { "post": { "operationId": "runs-sync-ai-lead-gen-tools-us-ct-sots", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ai-lead-gen-tools~us-ct-sots/run-sync": { "post": { "operationId": "run-sync-ai-lead-gen-tools-us-ct-sots", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "search", "new" ], "type": "string", "description": "\"search\" looks companies up by the terms and account numbers you provide. \"new\" ignores them and returns companies registered after the last run — put the actor on a schedule and you get a new-registrations feed.", "default": "search" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Company names or fragments. Matching is case-insensitive and finds the term anywhere in the name, so \"TESLA\" also returns \"TESLA MOTORS CT LLC\". Minimum 2 characters. Every matched company is de-duplicated, so paying once per company.", "items": { "type": "string", "minLength": 2, "maxLength": 80 } }, "accountNumbers": { "title": "Account numbers", "type": "array", "description": "Exact Connecticut business account numbers, e.g. \"0123456\". Fastest path: one request per number, no name matching. This is the same value returned in the sourceId and documentNumber fields.", "items": { "type": "string", "pattern": "^[0-9A-Za-z-]{1,20}$" } }, "status": { "title": "Status filter (optional)", "type": "string", "description": "Restrict results to one registry status, matched exactly and case-sensitively: \"Active\", \"Forfeited\", \"Dissolved\", \"Withdrawn\", \"Revoked\", \"Cancelled\", \"Merged\", \"Expired Reservation\", \"Rejected\" and 18 other values. Leave empty for the full registry — only about 35% of Connecticut rows are Active." }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Hard cap on the number of company records saved to the dataset. Each saved record is charged.", "default": 100 }, "sinceDays": { "title": "Feed window (days back)", "minimum": 1, "maximum": 400, "type": "integer", "description": "Used in \"new\" mode when no explicit start date is set: how many days to look back on the first run. Later runs continue from the cursor saved in the key-value store. Connecticut published 4 808 registrations in the last 30 days when measured.", "default": 7 }, "sinceDate": { "title": "Feed start date (optional)", "type": "string", "description": "Explicit start date in \"new\" mode, format YYYY-MM-DD. Leave empty to use the saved cursor, or the window above on the first run." }, "maxPagesPerTerm": { "title": "Max pages per search term", "minimum": 1, "maximum": 100, "type": "integer", "description": "The source returns at most 1000 rows per request. This caps how many pages a single term may page through, so a very broad term cannot run away.", "default": 10 }, "includeRaw": { "title": "Include raw source row", "type": "boolean", "description": "Attach the untouched source row to every record under the `raw` field, including the composer `mailing_address` string and the export timestamp create_dt. Useful for auditing the address split.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel requests to the state's API. Keep it modest to stay polite to a public dataset.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Per-request timeout before a retry is attempted.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Not needed: the dataset is a public JSON API and answers directly from Apify. Enable only if you have a specific reason to route the traffic.", "default": { "useApifyProxy": false } }, "runBudgetSecs": { "title": "Run budget (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "How long this run may take before it stops and returns what it has. Leave it empty (recommended) and the run uses the whole timeout you set for it. Set a number only to stop earlier. Stopping early is not a failure: the run summary reports it and you get the records found so far." } } }, "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 } } } } } } } } } }