{ "openapi": "3.0.1", "info": { "title": "German Imprint Scraper + Email Validation", "description": "AI-powered Apify Actor that scrapes Impressum pages on German websites and extracts decision-makers (Geschäftsführer, Vorstand), validated B2B emails, company addresses, VAT IDs, and Handelsregister numbers. Structured JSON output for B2B lead generation, sales prospecting, and CRM enrichment.", "version": "1.3", "x-build-id": "Jfq7LJV6Vv7vQfF1v" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/winningsolutions~german-imprint-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-winningsolutions-german-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/winningsolutions~german-imprint-scraper/runs": { "post": { "operationId": "runs-sync-winningsolutions-german-imprint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/winningsolutions~german-imprint-scraper/run-sync": { "post": { "operationId": "run-sync-winningsolutions-german-imprint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "targetUrls" ], "properties": { "targetUrls": { "title": "Target URLs", "type": "array", "description": "Websites to scrape. Each item must be an object with a `url` key, for example `{ \"url\": \"https://example.de\" }`. The Console uses the request-list editor; API and MCP callers should use the same JSON shape. At least one valid URL is required.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "skipResultsWithoutEmail": { "title": "Skip Results Without Email", "type": "boolean", "description": "If true, rows without a non-empty `email` are not written to the default dataset. Error rows are still saved. Use for lead lists where an email is mandatory.", "default": false }, "maxRetries": { "title": "Max Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times to retry failed HTTP or scrape steps for a URL (0 to 10). Does not change which fields are extracted.", "default": 3 }, "timeout": { "title": "Request Timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Per-request timeout in seconds for HTTP-style steps (5 to 60).", "default": 5 }, "validateEmail": { "title": "Validate Email Addresses", "type": "boolean", "description": "If true, runs deliverability-oriented checks on extracted emails and sets `email_status` (e.g. DELIVERABLE, UNDELIVERABLE). Extra usage fees apply when enabled. If false, `email_status` may still be present but reflects no full validation pass.", "default": false }, "disableImprintUrl": { "title": "Disable Imprint URL", "type": "boolean", "description": "If true, omits `imprint_url` and `imprint_status` from each dataset row for privacy or leaner exports. Same business logic runs; only the stored fields change.", "default": false }, "disableContactPerson": { "title": "Disable Contact Person", "type": "boolean", "description": "If true, omits the whole `contact_person` object from each dataset row.", "default": false }, "disableCompanyName": { "title": "Disable Company Name", "type": "boolean", "description": "If true, omits `company_name` from each dataset row.", "default": false }, "disableCompanyAddress": { "title": "Disable Company Address", "type": "boolean", "description": "If true, omits `company_address` from each dataset row.", "default": false }, "disablePhoneNumber": { "title": "Disable Phone Number", "type": "boolean", "description": "If true, omits `phone_number` from each dataset row.", "default": false }, "disableEmail": { "title": "Disable Email", "type": "boolean", "description": "If true, omits `email` and `email_status` from each dataset row.", "default": false }, "disableRegisterNumber": { "title": "Disable Register Number", "type": "boolean", "description": "If true, omits `register_number` (Handelsregister) from each dataset row.", "default": false }, "disableVatId": { "title": "Disable VAT ID (Umsatzsteuer-Identifikationsnummer)", "type": "boolean", "description": "If true, omits `vat_id` from each dataset row.", "default": false }, "performanceMax": { "title": "PerformanceMAX", "type": "boolean", "description": "High-throughput mode: higher internal concurrency (about 3x faster for large lists). Requires at least 2 GB Actor memory. Leave false on the 1 GB memory tier to avoid out-of-memory failures.", "default": false }, "useHeadlessBrowser": { "title": "Use headless browser only", "type": "boolean", "description": "Programmatic flag. If true, force browser-based scraping path for all URLs instead of axios-first mode.", "default": false }, "enableAxiosRetry": { "title": "Enable axios-first with browser fallback", "type": "boolean", "description": "Programmatic flag. If true, run axios-first scraping with optional browser fallback retries.", "default": true }, "retryOptions": { "title": "Retry options", "type": "object", "description": "Programmatic flag. Controls retry trigger criteria used by axios-first mode.", "properties": { "requireEmail": { "title": "Require email for retry", "type": "boolean", "description": "Trigger retry when email is missing.", "default": true }, "requireContactPerson": { "title": "Require contact person for retry", "type": "boolean", "description": "Trigger retry when contact person is missing.", "default": true }, "requireAnyField": { "title": "Require any field for retry", "type": "boolean", "description": "Trigger retry if no relevant fields are found at all.", "default": false }, "minFieldsRequired": { "title": "Minimum fields before skip retry", "type": "integer", "description": "Minimum extracted fields before retry is skipped.", "minimum": 1, "maximum": 10, "default": 3 } }, "additionalProperties": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify Proxy or custom proxy URLs. Use when sites block datacenter IPs. Shape matches Apify's proxy editor (`useApifyProxy`, optional `proxyUrls`, `groups`, `countryCode`). Proxy usage is included in the base cost as documented for this Actor." } } }, "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 } } }, "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 } } } } } } } } } }