{ "openapi": "3.0.1", "info": { "title": "German Imprint Scraper with Decision Makers Names Extraction", "description": "An Actor that automatically locates and scrapes key contact details from German website imprint pages (Impressum). It extracts information such as company name, address, phone numbers, emails, and decision-makers (Entscheider, Entscheidungsträger)", "version": "0.12", "x-build-id": "dh0To0IdNCv7IKrAR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dominic-quaiser~imprint-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dominic-quaiser-imprint-contact-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dominic-quaiser~imprint-contact-scraper/runs": { "post": { "operationId": "runs-sync-dominic-quaiser-imprint-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dominic-quaiser~imprint-contact-scraper/run-sync": { "post": { "operationId": "run-sync-dominic-quaiser-imprint-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites to Scrape", "type": "array", "description": "Enter the homepage URLs of the websites you want to process. The actor will automatically navigate each site to find its specific imprint page.", "default": [ { "url": "https://www.katjes.de/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "fieldsToExtract": { "title": "Data to Extract", "uniqueItems": true, "type": "array", "description": "Choose the specific pieces of information you want to collect from the imprint pages.", "items": { "type": "string", "enum": [ "company_name", "business_address", "phone_number", "fax_number", "emails", "register_number", "vat_id", "social_media", "decision_makers" ], "enumTitles": [ "Company Name (Firmenname)", "Business Address (Geschäftsadresse)", "Phone Number (Telefonnummer)", "Fax Number (Faxnummer)", "Email Address (E-Mail-Adresse)", "Register Number (Handelsregisternummer)", "VAT ID (Umsatzsteuer-ID)", "Social Media (Soziale Medien)", "Decision Makers (Entscheidungsträger—Geschäftsführer, Vorstand)" ] }, "default": [ "company_name", "business_address", "phone_number", "emails", "social_media" ] }, "headlessBrowser": { "title": "Headless Browser Usage", "enum": [ "headlessBrowserOn", "headlessBrowserAuto", "headlessBrowserOff" ], "type": "string", "description": "Configure how the headless browser is used for fetching pages. Auto mode uses HTTP first with browser fallback (recommended for best performance).", "default": "headlessBrowserAuto" }, "metaData": { "title": "Include Metadata", "type": "boolean", "description": "When enabled, the output will include extra technical details. This is useful for troubleshooting or detailed analysis.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Specifies proxy servers that will be used by the scraper in order to hide its origin.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }