{ "openapi": "3.0.1", "info": { "title": "North Data Scraper - EU Company Register & Officers", "description": "Scrape North Data for European company register records: court and number (HRB, Companies House, Siren, KVK), EUID, LEI, address, officers, published financials and events. Search by legal name or paste a profile URL. Fast HTTP crawl on Apify, no login.", "version": "0.1", "x-build-id": "0SRqQTsFbMdbChweL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawloop~northdata-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawloop-northdata-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawloop~northdata-scraper/runs": { "post": { "operationId": "runs-sync-crawloop-northdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawloop~northdata-scraper/run-sync": { "post": { "operationId": "run-sync-crawloop-northdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Company names or keywords", "type": "array", "description": "Legal names work best (e.g. Bayerische Motoren Werke). A short keyword such as BMW also matches clubs and similarly named firms. Anonymous search returns at most 45 companies per query (15 per page).", "items": { "type": "string" } }, "startUrls": { "title": "North Data URLs", "type": "array", "description": "Company profile URLs and/or search URLs. Profile pages are scraped directly; search pages are paginated. Person pages are skipped.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "language": { "title": "Language", "enum": [ "en", "de" ], "type": "string", "description": "North Data locale for labels (roles, event names, metric titles). Register numbers are the same in both.", "default": "en" }, "fetchProfiles": { "title": "Open each company page", "type": "boolean", "description": "On (default): fetch the profile and return officers, financial series, EUID/LEI, purpose and register events. Off: return only search-hit identity (name, city, register label, URL) — cheaper and faster.", "default": true }, "includeOfficers": { "title": "Include officers", "type": "boolean", "description": "Managing directors, board members and other registered officers with role, city and person URL.", "default": true }, "includeFinancials": { "title": "Include published financials", "type": "boolean", "description": "Year-by-year revenue, earnings and similar series when North Data publishes figures. Many SMEs have none.", "default": true }, "includeEvents": { "title": "Include register events", "type": "boolean", "description": "Dated register history: registration, capital changes, management changes, mergers.", "default": true }, "includePublications": { "title": "Include publication feed", "type": "boolean", "description": "Up to 25 recent patent, trademark and bulletin items from the profile feed. Makes rows larger.", "default": false }, "maxItems": { "title": "Maximum companies", "minimum": 0, "type": "integer", "description": "Hard cap across all queries and URLs. You are charged per dataset row.", "default": 20 }, "requestDelaySecs": { "title": "Delay between requests (seconds)", "minimum": 0, "type": "number", "description": "Polite pause between HTTP requests. Keep at 0.4 or higher for longer crawls.", "default": 0.4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Datacenter is enough for public North Data HTML. Leave Apify Proxy off for a local run.", "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 } } } } } } } } } }