{ "openapi": "3.0.1", "info": { "title": "North Data Scraper - European Company Register Data", "description": "Scrape European company data from North Data: register number and court, address, legal form, status, founding date, purpose, officers, yearly revenue, earnings and total assets, plus register events. Search by name or paste company URLs. Export to Excel, CSV, JSON or API.", "version": "0.1", "x-build-id": "46189AerzMNwWFRJQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pshivam~northdata-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pshivam-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pshivam~northdata-scraper/runs": { "post": { "operationId": "runs-sync-pshivam-northdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pshivam~northdata-scraper/run-sync": { "post": { "operationId": "run-sync-pshivam-northdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One entry per search, e.g. \"Siemens\", \"Aumann AG\" or \"bakery Hamburg\". Each search returns up to 45 companies (the most North Data shows for one search). Add a legal form or a city to narrow it down. Leave empty if you paste company URLs below.", "items": { "type": "string" } }, "startUrls": { "title": "Company or search URLs", "type": "array", "description": "North Data company pages (https://www.northdata.com/Siemens AG, München/HRB 6684) or search pages (https://www.northdata.com/siemens). A company page is always scraped in full.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "countries": { "title": "Only these countries", "type": "array", "description": "Keep only companies from these countries. Pick from the list or type a name or a two-letter code (DE, GB). Leave empty for every country.", "items": { "type": "string", "enumSuggestedValues": [ "Austria", "Belgium", "Croatia", "Cyprus", "Czech Republic", "Denmark", "Estonia", "Finland", "France", "Germany", "Greece", "Ireland", "Israel", "Lithuania", "Luxembourg", "Malta", "Netherlands", "Norway", "Poland", "Portugal", "Romania", "Slovakia", "Spain", "Sweden", "Switzerland", "Ukraine", "United Kingdom" ] } }, "onlyActive": { "title": "Only active companies", "type": "boolean", "description": "Skip companies that are terminated, dissolved or in liquidation.", "default": false }, "includeDetails": { "title": "Open each company for full details", "type": "boolean", "description": "On: register IDs, address, founding date, purpose, officers, yearly figures and events. Off: a much faster, cheaper run with what the search list shows (name, city, country, register number, status).", "default": true }, "includeFinancials": { "title": "Include yearly figures", "type": "boolean", "description": "Revenue, earnings, equity, total assets and employees per year, where North Data shows them. Turn off for a smaller result.", "default": true }, "includeOfficers": { "title": "Include officers", "type": "boolean", "description": "Managing directors and other officers with their role, as listed on the company's North Data page. Large companies have over a hundred.", "default": true }, "includeEvents": { "title": "Include register events", "type": "boolean", "description": "The company's latest publications and register events (annual reports, role changes, capital changes), newest first, up to 50.", "default": false }, "onlyNew": { "title": "Only new companies", "type": "boolean", "description": "Skip companies that earlier runs of this same search already returned, so you never get or pay for the same company twice. Turn it on for a scheduled run or a saved task. The first run works as usual and remembers what it returned, in your key-value store 'northdata-scraper-only-new'.", "default": false }, "maxItems": { "title": "Maximum companies", "minimum": 1, "type": "integer", "description": "Stop after this many companies. You are charged per company.", "default": 100 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "North Data accepts only about 10 pages a minute from one address. With Apify Proxy (on by default) every page goes out through an address of its own, so 100 companies take about 2 minutes. Switch it off to run from one address: about 10 minutes per 100 companies.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Pages loaded at the same time. With Apify Proxy each of them goes out through an address of its own (about 85 MB of memory each): 16 addresses at 2 pages a second stay under North Data's limit of about 10 pages a minute for one address. Without a proxy that limit rules and at most 4 are used.", "default": 16 } } }, "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 } } } } } } } } } }