{ "openapi": "3.0.1", "info": { "title": "Gelbe Seiten Business Scraper", "description": "Search Gelbe Seiten by business category and city or postal code, and collect structured business listings. Results include names, categories, addresses, phone numbers, websites and ratings; optional detail-page visits add email, opening hours and coordinates. Duplicate businesses are removed.", "version": "0.1", "x-build-id": "eKdAVaRbIhp6WYOf8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/axiomworks~gelbe-seiten-business-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-axiomworks-gelbe-seiten-business-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/axiomworks~gelbe-seiten-business-scraper/runs": { "post": { "operationId": "runs-sync-axiomworks-gelbe-seiten-business-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/axiomworks~gelbe-seiten-business-scraper/run-sync": { "post": { "operationId": "run-sync-axiomworks-gelbe-seiten-business-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searches": { "title": "Searches: list of {query, location} objects", "type": "array", "description": "Required unless startUrls is given. Array of objects, each {\"query\": German category or keyword, \"location\": city or postal code}. Example: [{\"query\":\"zahnarzt\",\"location\":\"muenchen\"},{\"query\":\"restaurants\",\"location\":\"80331\"}]. Entries without a query or location are skipped. All searches share the maxItems budget. Missing or blocked targets return no rows and guidance." }, "startUrls": { "title": "Start URLs: Gelbe Seiten search or business pages", "type": "array", "description": "Optional. Gelbe Seiten URLs: search pages like https://www.gelbeseiten.de/suche/zahnarzt/muenchen (category and city read from the URL) or single business pages like https://www.gelbeseiten.de/gsbiz/. Processed together with 'searches', sharing the maxItems budget. Other hosts are skipped with a warning.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "businessIds": { "title": "Business IDs: Gelbe Seiten UUIDs", "type": "array", "description": "Gelbe Seiten business UUIDs, e.g. ba862339-6447-4091-92d9-50b38785b57b. Alternative to searches or startUrls; all targets share maxItems. Business IDs always fetch detail pages. Missing or blocked businesses produce no row and a status message. Default empty.", "default": [], "items": { "type": "string" } }, "sortBy": { "title": "Sort by", "enum": [ "relevanz", "bewertung", "entfernung" ], "type": "string", "description": "Result order for searches: 'relevanz' (relevance, default), 'bewertung' (rating) or 'entfernung' (distance). Example: \"bewertung\".", "default": "relevanz" }, "maxItems": { "title": "Max items: total businesses, 1-5000", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Total businesses to return across all searches and URLs (shared budget), 1-5000, default 50. Run stops once this many are saved. Example: 20. Use maxItemsPerSearch to split it between searches.", "default": 50 }, "includeDetails": { "title": "Include details", "type": "boolean", "description": "true (default) opens each business page to add email, openingHours, latitude/longitude (one extra request per business, slower). false returns only listing-card fields (name, address, phone, website, rating) and is faster.", "default": true }, "requireEmail": { "title": "Only businesses with email", "type": "boolean", "description": "true returns only businesses that publish an email; forces includeDetails on. Skipped businesses do not count toward maxItems, so the run may scan many pages. Default false.", "default": false }, "requireWebsite": { "title": "Only businesses with website", "type": "boolean", "description": "true returns only businesses that list a website. Skipped businesses do not count toward maxItems. Default false.", "default": false }, "requirePhone": { "title": "Only businesses with phone", "type": "boolean", "description": "true returns only businesses that list a phone number. Skipped businesses do not count toward maxItems. Default false.", "default": false }, "minRating": { "title": "Minimum rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Minimum average rating, 0-5 (e.g. 4). When above 0, unrated businesses are skipped. 0 (default) means no filter.", "default": 0 }, "maxItemsPerSearch": { "title": "Max items per search", "minimum": 0, "type": "integer", "description": "Cap per single search or search URL, so one broad search cannot use the whole maxItems budget. Example: 25. 0 (default) means no cap.", "default": 0 }, "enableAiEnrichment": { "title": "AI enrichment", "type": "boolean", "description": "Opt in to companyType ('sme', 'chain' or 'institution') classification by a third-party AI processor. Default false leaves companyType null. Successful enrichment is charged separately; AI errors leave companyType null.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings, e.g. {\"useApifyProxy\":true}. Datacenter by default; blocked requests are retried on a fresh session. If a search returns 0 results because of blocking, add \"apifyProxyGroups\":[\"RESIDENTIAL\"].", "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 } } } } } } } } } }