{ "openapi": "3.0.1", "info": { "title": "Impressum Scraper DACH - Company Data from Imprint Pages", "description": "Turn a list of German, Austrian and Swiss company websites (or a Google Maps / Gelbe Seiten dataset) into legal company data from the Impressum: legal name, legal form, address, register court and number (HRB, FN, CHE), VAT ID, company phone and e-mail. Pay only for found Impressum pages.", "version": "0.1", "x-build-id": "XyVx0hnatuAfemLn9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aidnurs~impressum-enricher/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aidnurs-impressum-enricher", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aidnurs~impressum-enricher/runs": { "post": { "operationId": "runs-sync-aidnurs-impressum-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aidnurs~impressum-enricher/run-sync": { "post": { "operationId": "run-sync-aidnurs-impressum-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Company websites or domains", "type": "array", "description": "Company homepages or bare domains (frosta.de, https://www.manner.com). The Actor finds the Impressum link on the homepage and reads it. Duplicates (same domain with or without www) are checked once.", "default": [ "https://www.frosta.de", "https://www.manner.com", "https://www.appenzeller.ch" ], "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID from a Google Maps / Gelbe Seiten / Herold scraper", "type": "string", "description": "Run any business directory or Google Maps scraper, copy its dataset ID and paste it here. The company website is read from the field website, websiteUrl, web, homepage, domain or url (Google Maps place links and social profiles are skipped). Items without a website are skipped for free." }, "websiteField": { "title": "Website field in the dataset (optional)", "type": "string", "description": "Name of the dataset field that holds the website, if it is not one of the usual names above." }, "maxItems": { "title": "Max websites", "minimum": 1, "type": "integer", "description": "Maximum number of websites to check. You only pay for websites where an Impressum with company data was found.", "default": 1000 }, "includePersonNames": { "title": "Include names of managing directors / owners", "type": "boolean", "description": "Names of Geschäftsführer, Vorstand and owners are personal data under GDPR. Off by default: you get only their count. Turn on only if you have a lawful basis to process them.", "default": false }, "includePersonalContacts": { "title": "Include personal e-mails and mobile numbers", "type": "boolean", "description": "Off by default: only company inboxes (info@, office@, kontakt@ ...) and landline numbers are returned; personal addresses (anna.huber@, gmail) and mobile numbers are left out.", "default": false }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many websites are checked at the same time (1-10). Each website gets one request at a time.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed: company websites answer any visitor. The Actor never bypasses captchas or bot protection.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }