{ "openapi": "3.0.1", "info": { "title": "AI News Content Crawler", "description": "This Apify actor searches Google News RSS for one or more country/language editions, collects article URLs, opens each news page, extracts clean text, and stores one dataset item per processed URL. It uses Google News RSS discovery with automatic HTTP fallback when browser rendering fails.", "version": "0.0", "x-build-id": "CIEJGWLccZH2tbjn2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ilborso~ai-news-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ilborso-ai-news-content-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ilborso~ai-news-content-crawler/runs": { "post": { "operationId": "runs-sync-ilborso-ai-news-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ilborso~ai-news-content-crawler/run-sync": { "post": { "operationId": "run-sync-ilborso-ai-news-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "searchQuery", "languageAndRegion" ], "properties": { "searchQuery": { "title": "Search query", "type": "string", "description": "Enter search query as you would write it to Google News search bar. You can use advanced operators such as intitle, inurl, site, exclude operator -, exact match with double-quotes, AND, OR and more." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of pages opened simultaneously in the Playwright browser. This value represents the maximum number of browser pages or tabs processed in parallel, not the number of system threads. Max value is capped to 50.", "default": 10 }, "languageAndRegion": { "title": "Language and region", "uniqueItems": true, "type": "array", "description": "Practical whitelist of commonly used Google News country/language pairs in the format CC:ll. This is not an official or complete list of all combinations supported by Google News.", "items": { "type": "string", "enum": [ "AR:es", "AT:de", "AU:en", "BE:fr", "BE:nl", "BG:bg", "BR:pt", "CA:en", "CA:fr", "CH:de", "CH:fr", "CH:it", "CL:es", "CO:es", "CZ:cs", "DE:de", "DK:da", "EE:et", "EG:ar", "ES:es", "FI:fi", "FR:fr", "GB:en", "GR:el", "HK:zh", "HR:hr", "HU:hu", "ID:id", "IE:en", "IL:he", "IN:en", "IN:hi", "IT:it", "JP:ja", "KR:ko", "LT:lt", "LV:lv", "MA:fr", "MX:es", "MY:en", "NG:en", "NL:nl", "NO:no", "NZ:en", "PE:es", "PH:en", "PK:en", "PL:pl", "PT:pt", "RO:ro", "RS:sr", "RU:ru", "SA:ar", "SE:sv", "SG:en", "SI:sl", "SK:sk", "TH:th", "TR:tr", "TW:zh", "UA:uk", "US:en", "VE:es", "VN:vi", "ZA:en" ] }, "default": [ "IT:it" ] }, "maxSites": { "title": "Max sites", "minimum": 1, "type": "integer", "description": "Maximum number of unique news sites returned for each language/region pair.", "default": 50 }, "daysBack": { "title": "Days back", "minimum": 1, "type": "integer", "description": "How many days back to search. chunkDays is always set equal to daysBack.", "default": 7 }, "decodeInterval": { "title": "Decode interval", "minimum": 1, "type": "integer", "description": "Interval passed to googlenewsdecoder. Usually keep 1.", "default": 1 } } }, "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 } } } } } } } } } }