{ "openapi": "3.0.1", "info": { "title": "Impressum Email Scraper (German Sites)", "description": "Scrape emails, phone numbers and social links from German websites' Impressum pages. Decodes obfuscated addresses, returns German phone numbers in E.164. Pay per contact found.", "version": "0.2", "x-build-id": "I39r9wYubNYfV795T" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sandy_yclept~impressum-email-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sandy_yclept-impressum-email-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sandy_yclept~impressum-email-scraper/runs": { "post": { "operationId": "runs-sync-sandy_yclept-impressum-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sandy_yclept~impressum-email-scraper/run-sync": { "post": { "operationId": "run-sync-sandy_yclept-impressum-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "List of German websites (domains or URLs) to pull Impressum contact details from. One record per URL is produced.", "default": [ { "url": "https://www.heise.de/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxContactPages": { "title": "Max contact subpages", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many contact-like subpages to crawl per site on top of the homepage. German sites put the legally required contact on /impressum, and it is crawled first; the default leaves room for /kontakt and the privacy page too.", "default": 6 }, "validateEmails": { "title": "Validate emails (MX + scoring)", "type": "boolean", "description": "Check each discovered email against its domain's MX records and attach a confidence score. Turn off for a faster run without deliverability checks.", "default": true }, "includeSocials": { "title": "Extract social profiles", "type": "boolean", "description": "Extract LinkedIn, X/Twitter, Facebook, Instagram, YouTube and TikTok profile links (share/intent URLs are filtered out).", "default": true }, "renderJs": { "title": "JavaScript rendering", "enum": [ "off", "auto", "on" ], "type": "string", "description": "Load pages in a real browser to reach contacts that are rendered by JavaScript. Off (default) is the fastest and cheapest. Auto scans without a browser first and only re-crawls a site in the browser when nothing was found — best accuracy/cost ratio. On always uses the browser. Auto and On require the run memory to be at least 2048 MB. Below 1024 MB the browser is not started and the run says so.", "default": "off" }, "phoneRegion": { "title": "Default phone region", "type": "string", "description": "ISO country code used to parse phone numbers written without an international prefix. Defaults to DE for German sites; change it for Austrian (AT) or Swiss (CH) targets.", "default": "DE" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy for fetching pages. Apify Proxy's datacenter IPs are included in every Apify plan, the Free plan too; residential proxies are billed separately. Left disabled, the Actor connects directly, and retries sites that refuse it through Apify Proxy (see below).", "default": { "useApifyProxy": false } }, "proxyFallback": { "title": "Retry refused sites through Apify Proxy", "type": "boolean", "description": "Every cloud run has a datacenter IP address, and some sites turn those away. A site that refuses or drops the direct connection is retried once through Apify Proxy's datacenter IPs (included in every Apify plan, the Free plan too), then once more directly. Sites that answer directly never go through the proxy, and robots.txt is respected either way. Has no effect when a proxy is configured above.", "default": 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 }, "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 } } } } } } } } } }