{ "openapi": "3.0.1", "info": { "title": "Impressum Scraper: German Company Contacts & Directors", "description": "Extract Impressum contact data from German, Austrian and Swiss company websites: legal name, managing directors (Geschäftsführer), email, phone, address, VAT ID and register number (HRB/FN/CHE). $3 per 1,000 imprints with a contact; sites without one are free.", "version": "0.1", "x-build-id": "gKl8rlKnYJyUvjWhk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datagleaner~impressum-contacts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datagleaner-impressum-contacts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/datagleaner~impressum-contacts/runs": { "post": { "operationId": "runs-sync-datagleaner-impressum-contacts", "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/datagleaner~impressum-contacts/run-sync": { "post": { "operationId": "run-sync-datagleaner-impressum-contacts", "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": "Company websites, one per line. `firma.de`, `https://www.firma.de/` and a direct imprint URL such as `https://www.firma.de/impressum` all work. Leave empty to run 3 built-in DACH examples.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID (from another Actor)", "type": "string", "description": "Optional. Read company websites from this dataset, for example Google Maps Scraper results, and add them to the websites above. Each item's `website` (or `url`, `domain`, `site`, `homepage`, `link`, `companyWebsite`, `web`) is used; items without one are skipped. In an integration use `{{resource.defaultDatasetId}}`." }, "datasetField": { "title": "Website field in the dataset", "type": "string", "description": "Optional. Name of the field that holds the website when it is not one of the usual ones. Tried first." }, "maxDatasetItems": { "title": "Max websites from the dataset", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stops reading the dataset after this many distinct websites. Only used with a dataset ID.", "default": 1000 }, "onlyWithEmail": { "title": "Only sites with an email", "type": "boolean", "description": "Output only websites whose legal notice gave at least one email address. Sites without one are free either way.", "default": false }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 1, "maximum": 10, "type": "integer", "description": "Pages read per website: the home page, then the imprint link and, if there is none, the common imprint paths (/impressum, /imprint, /legal-notice, /mentions-legales). A path that returns 404 does not count.", "default": 3 }, "languageHint": { "title": "Language hint", "enum": [ "auto", "de", "en", "fr" ], "type": "string", "description": "Which language's imprint link and paths to try first. Auto picks German for .de, .at and .ch, French for .fr, .be and .lu, and English otherwise. All languages are parsed either way.", "default": "auto" }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many websites are processed at the same time. Each website gets at most one request at a time.", "default": 10 }, "delaySecs": { "title": "Delay between requests to one site (seconds)", "minimum": 0, "maximum": 30, "type": "number", "description": "Polite pause between two requests to the same website.", "default": 0.5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "How long to wait for each page before retrying.", "default": 20 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Defaults to no proxy. Turn on Apify Proxy if many sites answer 429 (rate limited), as Shopify shops sometimes do on shared cloud IPs." } } }, "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 } } } } } } } } } }