{ "openapi": "3.0.1", "info": { "title": "Impressum Scraper", "description": "Extract Impressum data from German, Austrian and Swiss websites: company name, legal form, managing directors, register court and HRB number, VAT ID, tax number, address, phone, fax and email. B2B leads in bulk via API, export to CSV or Excel, schedule runs, connect n8n, Make or Zapier.", "version": "0.1", "x-build-id": "59WmwuV3kB0xMaL05" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lergassy~impressum-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lergassy-impressum-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lergassy~impressum-scraper/runs": { "post": { "operationId": "runs-sync-lergassy-impressum-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lergassy~impressum-scraper/run-sync": { "post": { "operationId": "run-sync-lergassy-impressum-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "websites" ], "properties": { "websites": { "title": "🔍 Websites", "type": "array", "description": "Company websites to read the Impressum from — one per line. A bare domain (muster-gmbh.de), a full URL (https://www.muster-gmbh.de/) or a direct link to the Impressum page all work. Duplicates are removed. Each website gives one row: the company data, or a free row saying why there is none.", "items": { "type": "string" } }, "validateVatId": { "title": "💯 Check VAT ID in EU VIES ($)", "type": "boolean", "description": "Paid add-on: checks every VAT ID found (DE…, ATU…, other EU) against the official EU VIES service and adds vatIdValid (true/false), plus the registered name and address where the member state shares them (Germany does not). Charged only when VIES gives a definite answer. Swiss CHE numbers are not in VIES and are skipped.", "default": false }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 2, "maximum": 10, "type": "integer", "description": "How many pages to open per website at most while looking for the Impressum: the home page, the Impressum / Imprint / Legal notice link, then the usual paths (/impressum, /imprint, …). 4 finds it on almost every site; raise it for unusual sites. Minimum 2 (home page + Impressum).", "default": 4 }, "includeRawText": { "title": "Include Impressum text", "type": "boolean", "description": "Adds impressumText: the plain text of the Impressum block (up to 20,000 characters), for your own parsing or an AI model. Off by default to keep exports small.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed: websites are opened directly, and a site that blocks that is retried through a residential address automatically. Set a proxy only if you must use your own." } } }, "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 } } } } } } } } } }