{ "openapi": "3.0.1", "info": { "title": "German Impressum Scraper - Leads from DE, AT & CH Websites", "description": "Extract Impressum data from German, Austrian and Swiss websites: directors, email, phone, address, HRB, VAT ID. Google search built in. CSV, Excel, JSON, XML.", "version": "0.1", "x-build-id": "k7dF3n54biWSLcgt3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~german-impressum-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-german-impressum-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~german-impressum-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-german-impressum-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~german-impressum-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-german-impressum-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Websites", "type": "array", "description": "Websites to read the Impressum from. A homepage is enough (the Actor finds the Impressum link itself), and a direct Impressum URL works too. Paste a list or upload a file with one URL per line.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchTerms": { "title": "Google search terms", "type": "array", "description": "Find websites through Google instead of (or on top of) a URL list. One query per entry, for example 'steuerberater münchen' or 'dachdecker köln'. Every organic result is visited and its Impressum read.", "items": { "type": "string" } }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 10 items (preview). Paid users: Optional, max 1,000,000" }, "googleCountry": { "title": "Google country", "enum": [ "de", "at", "ch" ], "type": "string", "description": "Which Google market to search. Germany, Austria and Switzerland return different local websites for the same query.", "default": "de" }, "resultsPerSearchTerm": { "title": "Google results per search term", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many organic Google results to visit per search term (Google serves 10 per page, 100 at most).", "default": 30 }, "skipDirectories": { "title": "Skip directories and portals", "type": "boolean", "description": "Skip business directories, marketplaces, social networks, city portals and government sites that show up in Google (Gelbe Seiten, Das Örtliche, Jameda, Wikipedia and similar). Their Impressum describes the portal, not a lead.", "default": true }, "excludeDomains": { "title": "Exclude domains", "type": "array", "description": "Domains you never want in the results, for example existing customers or competitors (example.de).", "items": { "type": "string" } }, "onlyWithEmail": { "title": "Only leads with an email address", "type": "boolean", "description": "Drop companies whose Impressum shows no email address. Dropped rows are never charged.", "default": false }, "checkEmailMx": { "title": "Check the email domain's mail server", "type": "boolean", "description": "Look up the MX record of each email domain and report in emailMxValid whether the domain can receive mail at all. Free, and adds well under a second per lead.", "default": true }, "includeFailedWebsites": { "title": "Add websites without an Impressum to the dataset", "type": "boolean", "description": "Also write one row per website that could not be read (unreachable, blocked, no Impressum), with the reason in the error column. These rows are never charged. They are always listed in the key-value store record FAILED_WEBSITES either way.", "default": false }, "maxConcurrency": { "title": "Parallel websites", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many websites are read at the same time.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "How long to wait for each page before giving up on it.", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Most company websites answer without a proxy. Switch one on if many websites block the run.", "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 } } } } } } } } } }