{ "openapi": "3.0.1", "info": { "title": "Impressum Scraper – German, Austrian & Swiss Company Data", "description": "Extract company data from the Impressum (imprint / legal notice) of any DE, AT or CH website: company name, legal form, managing directors, HRB/HRA/FN register number and court, USt-IdNr/UID VAT ID, address, phone, fax and email. No Google search. Pay only when an imprint is found.", "version": "0.1", "x-build-id": "zbta4JdrQ0jrRwd5y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~imprint-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-imprint-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~imprint-scraper/runs": { "post": { "operationId": "runs-sync-gazidev-imprint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~imprint-scraper/run-sync": { "post": { "operationId": "run-sync-gazidev-imprint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Websites (domains or URLs)", "type": "array", "description": "Company websites from Germany, Austria or Switzerland, e.g. `muster-gmbh.de` or `https://www.firma.at/`. `https://` is added automatically. You can also give the imprint URL directly. Each domain is processed once and returns one row.", "default": [ "heise.de", "zotter.at", "kaffeemacher.ch" ], "items": { "type": "string" } }, "bulkText": { "title": "Bulk list (paste text or CSV)", "type": "string", "description": "Paste a big list: one domain per line, comma/semicolon separated, or a whole CSV export (the first cell that looks like a domain/URL in each row is used)." }, "sourceFileUrl": { "title": "Bulk list file URL (TXT/CSV)", "type": "string", "description": "Public URL of a .txt or .csv file with domains/URLs (e.g. a Google Sheets 'publish to web' CSV link)." }, "onlyFound": { "title": "Save only websites with an imprint", "type": "boolean", "description": "Leave out rows for websites where no usable imprint was found (unreachable, blocked, no Impressum). Those rows are free either way.", "default": false }, "includeRawSnippet": { "title": "Include raw imprint text", "type": "boolean", "description": "Add `rawSnippet`: the first 1,500 characters of the imprint block the fields were read from, so you can verify or post-process them (e.g. with an LLM).", "default": true }, "maxSites": { "title": "Max websites", "minimum": 0, "type": "integer", "description": "Stop after this many websites (0 = no limit). Useful to test a big list cheaply.", "default": 0 }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 2, "maximum": 15, "type": "integer", "description": "Homepage + imprint candidates (links named Impressum/Imprint/Legal notice, then common paths like `/impressum`). 6 is enough for almost every site. The price per website is the same whatever you choose.", "default": 6 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages disallowed by the site's robots.txt and honor its Crawl-delay. Recommended. Note: Shopify shops disallow `/policies/` by default, so their legal notice is then reported as disallowed.", "default": true }, "minDelayPerHostSecs": { "title": "Delay between requests to the same host (seconds)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Politeness throttle: minimum gap between two requests to the same website (a larger robots.txt Crawl-delay wins, up to 10 s).", "default": 1 }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many different websites are processed at the same time. Requests to one website are always sequential.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "Per-request timeout. Failed requests are retried.", "default": 20 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Not needed for most sites.", "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 } } } } } } } } } }