{ "openapi": "3.0.1", "info": { "title": "Impressum Scraper - Company, VAT ID & Register Number Extractor", "description": "For DACH B2B lead lists and KYB checks: an Impressum API that finds the legal notice (imprint, mentions légales, aviso legal, 特定商取引法) of each website and returns name, legal form, address, phone, email, directors, register number and court, VAT ID with a format check, each with its source line.", "version": "0.1", "x-build-id": "Da8zmUKFCfvtry4Af" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neverempty~impressum-company-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neverempty-impressum-company-data-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neverempty~impressum-company-data-extractor/runs": { "post": { "operationId": "runs-sync-neverempty-impressum-company-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neverempty~impressum-company-data-extractor/run-sync": { "post": { "operationId": "run-sync-neverempty-impressum-company-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "websites": { "title": "Websites (domains or legal notice URLs)", "type": "array", "description": "Websites whose legal notice you want read, one per line (1 to 500 per run). Give a domain (example.de) and the Actor finds the Impressum / imprint / legal notice / mentions légales / aviso legal / note legali / 特定商取引法に基づく表記 page from the home page links or the usual addresses (/impressum, /imprint, /legal-notice, /legal …). Give a full URL with a path (https://example.de/impressum) and that page is read as the legal notice. Checked in production on German, Austrian and Swiss sites; French, Spanish, Italian and Japanese notices are read by rules that have not been confirmed in production yet (best effort). Pages whose text appears only after JavaScript runs cannot be read. Only the sites you list are read, at most 5 pages per site, and each site's robots.txt is followed. The same site given twice is read and charged once. If this is empty, the example site www.hetzner.com is read and nothing is charged.", "items": { "type": "string" } }, "includePersonNames": { "title": "Include names of persons", "type": "boolean", "description": "Legal notices name managing directors, owners and the person responsible for content; for sole traders the business name is often a personal name. Turn this off to leave out representatives, contentResponsible, and any company name that carries no legal form (GmbH, Ltd, SAS …). You are responsible for using personal data lawfully (GDPR, rules on unsolicited marketing).", "default": true }, "maxConcurrency": { "title": "Websites read at the same time", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many websites are read in parallel (1 to 8).", "default": 4 }, "requestTimeoutSecs": { "title": "Time limit per request (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "How long to wait for one page to answer (5 to 60 seconds). HTTP 429, 500, 502, 503 and 504 are asked again up to two more times.", "default": 20 } } }, "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 } } } } } } } } } }