{ "openapi": "3.0.1", "info": { "title": "Gelbe Seiten Scraper - German B2B Business Directory", "description": "Scrape Gelbe Seiten (gelbeseiten.de) by category and city: business name, category, address, PLZ, phone, website, rating, reviews and opening hours. Reads district pages to go beyond 50 per city. Duplicates free, respects robots.txt.", "version": "0.1", "x-build-id": "4CvCKLWVfVZ3FfMd8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aidnurs~gelbeseiten-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aidnurs-gelbeseiten-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aidnurs~gelbeseiten-scraper/runs": { "post": { "operationId": "runs-sync-aidnurs-gelbeseiten-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aidnurs~gelbeseiten-scraper/run-sync": { "post": { "operationId": "run-sync-aidnurs-gelbeseiten-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "branchen": { "title": "Categories (Branchen)", "type": "array", "description": "Business categories as written on Gelbe Seiten, one per line (\"Elektriker\", \"Friseur\", \"Steuerberater\", \"Heizung & Sanitär\"). Every category is combined with every city below.", "items": { "type": "string" } }, "orte": { "title": "Cities (Orte)", "type": "array", "description": "German cities or towns, one per line (\"Berlin\", \"München\", \"Köln\"). A district works too: \"Berlin Bezirk Mitte\", \"München Stadtteil Schwabing\".", "items": { "type": "string" } }, "startUrls": { "title": "Gelbe Seiten URLs", "type": "array", "description": "Optional. Listing URLs like https://www.gelbeseiten.de/branchen/elektriker/berlin or single business pages like https://www.gelbeseiten.de/gsbiz/. Search pages (/suche) are closed by robots.txt and skipped.", "items": { "type": "string" } }, "maxItems": { "title": "Max businesses", "minimum": 1, "type": "integer", "description": "Maximum number of businesses to save in this run. You only pay for unique businesses saved to the dataset.", "default": 500 }, "includeDistricts": { "title": "Include district pages", "type": "boolean", "description": "A Gelbe Seiten city page shows at most 50 businesses. For big cities the Actor also reads the district pages the city page links to (Berlin Bezirke, Munich Stadtteile...) to get many more. Duplicates are removed and free.", "default": true }, "includeDetails": { "title": "Include opening hours and details", "type": "boolean", "description": "Open every business page to add weekly opening hours, GPS coordinates, full description, services, payment methods and last update date. Slower (one extra page per business), same price.", "default": false }, "includeEmails": { "title": "Include business e-mail", "type": "boolean", "description": "Add the business e-mail when it is a role mailbox (info@, kontakt@, office@...). Personal-looking addresses (first.last@, private mail providers) are never returned. B2B use only: comply with GDPR and UWG, no unsolicited e-mail marketing.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed. If Gelbe Seiten blocks the run, the Actor switches to Apify Proxy when it is enabled here.", "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 }, "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 } } } } } } } } } }