{ "openapi": "3.0.1", "info": { "title": "Polish REGON Scraper - GUS Business Registry (no API key)", "description": "Scrape Poland's REGON (GUS) registry anonymously: look up by NIP/REGON/KRS, discover companies by address + PKD, and get local units (jednostki lokalne) as separate rows. No API key required.", "version": "1.0", "x-build-id": "LPDzCfJLJzIoxg9YL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/regdata~polish-regon-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-regdata-polish-regon-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/regdata~polish-regon-scraper/runs": { "post": { "operationId": "runs-sync-regdata-polish-regon-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/regdata~polish-regon-scraper/run-sync": { "post": { "operationId": "run-sync-regdata-polish-regon-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchMode": { "title": "Search mode", "enum": [ "byAddress", "nip", "regon", "krs" ], "type": "string", "description": "How to search: discover all entities at an address (with optional PKD), or look up specific NIP / REGON / KRS numbers.", "default": "byAddress" }, "identifiers": { "title": "Identifiers (NIP / REGON / KRS)", "type": "array", "description": "List of identifiers to look up. Only used when search mode is nip / regon / krs.", "items": { "type": "string" } }, "voivodeship": { "title": "Województwo (voivodeship)", "type": "string", "description": "Region name (e.g. \"Łódzkie\") or TERYT code. Required for address search. Diacritics optional." }, "county": { "title": "Powiat (county)", "type": "string", "description": "County name or TERYT code within the voivodeship." }, "municipality": { "title": "Gmina (municipality)", "type": "string", "description": "Municipality name or TERYT code within the county." }, "city": { "title": "Miejscowość (city)", "type": "string", "description": "City/town name or TERYT code within the municipality." }, "street": { "title": "Ulica (street, optional)", "type": "string", "description": "Optional street name or code to narrow the address search." }, "nameFragment": { "title": "Name fragment (optional)", "type": "string", "description": "Optional company-name fragment filter for address search." }, "pkd": { "title": "PKD code (optional)", "type": "string", "description": "Optional PKD activity code to filter the address search server-side (e.g. \"62.01.Z\")." }, "pkdSections": { "title": "Filter - PKD sections (A-U)", "type": "array", "description": "Keep only records with a PKD code in these PKD 2007 sections. C=Manufacturing, G=Trade, H=Transport, etc. Requires fetchPkd.", "items": { "type": "string" } }, "pkdCodes": { "title": "Filter - PKD code prefixes", "type": "array", "description": "Keep only records whose PKD code starts with one of these (e.g. \"10\", \"62.01\"). Requires fetchPkd.", "items": { "type": "string" } }, "pkdMatch": { "title": "PKD match mode", "enum": [ "any", "main" ], "type": "string", "description": "'main' = only the main (przeważająca) PKD must match; 'any' = any reported PKD may match.", "default": "any" }, "legalForms": { "title": "Filter - legal form", "type": "array", "description": "Keep only entities whose legal form contains one of these phrases (e.g. \"spółka z ograniczoną\", \"spółka akcyjna\").", "items": { "type": "string" } }, "fetchFullReport": { "title": "Fetch full report", "type": "boolean", "description": "Fetch each entity's full REGON report (legal form, ownership, dates, contact, full address). Adds one request per record.", "default": true }, "fetchPkd": { "title": "Fetch PKD codes", "type": "boolean", "description": "Additionally fetch each entity's PKD activity codes (main + secondary).", "default": true }, "includeLocalUnits": { "title": "Include local units (jednostki lokalne)", "type": "boolean", "description": "Include local units as separate rows (recordType=LOCAL_UNIT, with parentRegon). Address search returns these natively; identifier search expands them.", "default": true }, "maxResults": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Maximum records to emit (0 = unlimited). Bounds cost on large regions.", "default": 0 }, "minIntervalMs": { "title": "Min interval between requests (ms)", "minimum": 0, "type": "integer", "description": "Politeness delay between requests. The site allows ~3/s; keep >= 350ms to avoid the conditional CAPTCHA.", "default": 350 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Residential PL proxies recommended for large/volume runs to avoid the conditional CAPTCHA.", "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 } } } } } } } } } }