{ "openapi": "3.0.1", "info": { "title": "EU Impressum & Legal Notice Extractor: VAT, Register, Directors", "description": "Extract legal company details from EU Impressum / mentions légales / aviso legal / note legali / colofon pages: legal name, form, address, directors, VAT ID (VIES-checked), trade register, email, phone. Per-field confidence. $0.003 per site found.", "version": "1.0", "x-build-id": "9RqXuFSU2pNfAfDsh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/southern-data~legal-notice-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-southern-data-legal-notice-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/southern-data~legal-notice-extractor/runs": { "post": { "operationId": "runs-sync-southern-data-legal-notice-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/southern-data~legal-notice-extractor/run-sync": { "post": { "operationId": "run-sync-southern-data-legal-notice-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", "type": "array", "description": "One per line: \"mymuesli.com\", \"https://www.eataly.it/\", a direct link to the legal page (\"https://acme.de/impressum\" — read first), or an email address (its website is read). Duplicates are removed. Facebook / Instagram / marketplace links are not company websites and are listed as rowStatus=invalid_input (free).", "items": { "type": "string" } }, "websitesFileUrl": { "title": "…or a link to a website list (CSV / TXT / Google Sheet)", "type": "string", "description": "Public URL of a .txt or .csv file, or a Google Sheets link shared as \"Anyone with the link can view\". Uses the column headed website / url / domain / homepage / email if there is one; otherwise the column with the most websites. Up to 100,000 rows." }, "checkVies": { "title": "Check VAT IDs in the EU VIES register", "type": "boolean", "description": "Look up each EU VAT ID found in the European Commission's official VIES service (free, public). Adds viesStatus (valid / invalid / unavailable) and, where the member state discloses it, the registered name and address (Germany and Spain never do). Swiss CHE numbers are not in VIES. Turn off for slightly faster runs.", "default": true }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 1, "maximum": 8, "type": "integer", "description": "Pages read on each website: the homepage, then the legal-notice link (Impressum, mentions légales, aviso legal, note legali, colofon…) or, if none is linked, the usual paths such as /impressum. 4 is enough for nearly all sites; up to 8. The price is per website, not per page.", "default": 4 }, "defaultCountry": { "title": "Default country (optional)", "type": "string", "description": "Optional 2-letter code (DE, AT, CH, FR, IT, ES, NL…). Only used for .com / .eu / .shop sites that don't reveal their country, to read local phone numbers and pick the right legal-notice paths. Country domains and the VAT prefix take priority." }, "maxWebsites": { "title": "Max websites (0 = all)", "minimum": 0, "type": "integer", "description": "Read only the first N websites — handy for a cheap trial on a big file. The rest are skipped (not charged) and listed in the REMAINING record.", "default": 0 }, "maxConcurrency": { "title": "Websites read in parallel", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many different websites are read at the same time (pages within one website are always read one at a time, politely). 8 is a good default for 512 MB memory.", "default": 8 }, "pageTimeoutSecs": { "title": "Page timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Give up on a page that hasn't loaded in this time. A homepage timeout makes the website 'unreachable' (free). Each website stops after 2 minutes in total.", "default": 30 }, "selfTest": { "title": "Self-test (health check)", "type": "boolean", "description": "Ignore the inputs above and run the built-in health check instead: VAT/register/name rules, a full crawl of a test website, a VIES lookup and two live sites. Writes a SELF_TEST record, adds no dataset rows, charges nothing, and FAILS the run if anything is broken — schedule it daily as a free monitor.", "default": 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 } } } } } } } } } }