{ "openapi": "3.0.1", "info": { "title": "Google News Scraper", "description": "Scrapes Google News RSS feeds for search queries and topic categories. Returns articles with decoded URLs, sentiment analysis, reading time, full-text extraction, and deduplication across queries.", "version": "1.0", "x-build-id": "d6X19AYuDWYyWlQ5O" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-google-news-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~google-news-scraper/runs": { "post": { "operationId": "runs-sync-brilliant_gum-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search Queries", "type": "array", "description": "List of search queries to scrape from Google News. Each query fetches up to maxArticlesPerQuery results. Example: [\"artificial intelligence\", \"climate change 2024\"]", "items": { "type": "string" } }, "query": { "title": "Single Search Query", "type": "string", "description": "Convenience field for a single query string. Use 'queries' for multiple queries. Ignored if 'queries' is provided." }, "language": { "title": "Language", "enum": [ "en", "ru", "de", "fr", "es", "it", "pt", "nl", "pl", "ja", "zh", "ar", "ko", "sv", "no", "da", "fi", "cs", "ro", "hu", "tr", "uk", "he", "id", "vi" ], "type": "string", "description": "Language for news results. Uses BCP 47 language tag.", "default": "en" }, "country": { "title": "Country", "enum": [ "US", "GB", "AU", "CA", "IN", "DE", "FR", "ES", "IT", "BR", "RU", "JP", "CN", "KR", "MX", "AR", "NL", "PL", "SE", "NO", "DK", "FI", "CZ", "RO", "HU", "TR", "UA", "IL", "ID", "VN", "ZA", "NG", "EG", "SA", "AE" ], "type": "string", "description": "Target country for news edition.", "default": "US" }, "maxArticlesPerQuery": { "title": "Max Articles Per Query", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of articles to collect per search query. Google News RSS returns up to 100 per request. For more, the actor rotates query variants.", "default": 100 }, "dateRange": { "title": "Date Range", "enum": [ "1h", "1d", "7d", "30d", "custom" ], "type": "string", "description": "Filter articles by publication date. Use 'custom' to specify startDate and endDate.", "default": "7d" }, "startDate": { "title": "Start Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Start date for custom date range. Format: YYYY-MM-DD. Only used when dateRange is 'custom'." }, "endDate": { "title": "End Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "End date for custom date range. Format: YYYY-MM-DD. Only used when dateRange is 'custom'." }, "topics": { "title": "Topic Categories", "uniqueItems": true, "type": "array", "description": "Scrape top stories for specific Google News topic categories. These use Google's curated topic feeds.", "items": { "type": "string", "enum": [ "world", "nation", "business", "technology", "sports", "entertainment", "health", "science" ] } }, "includeDuplicates": { "title": "Include Duplicates", "type": "boolean", "description": "If false (default), articles found in multiple queries are deduplicated by URL. If true, the same article may appear multiple times.", "default": false }, "includeFullText": { "title": "Include Full Article Text", "type": "boolean", "description": "Fetch and extract the full text of each article from its source URL. Significantly increases run time and may fail for paywalled sources.", "default": false }, "outputFormat": { "title": "Output Format", "enum": [ "articles", "topics", "both" ], "type": "string", "description": "Control what is saved to the dataset.", "default": "articles" }, "sortBy": { "title": "Sort Results By", "enum": [ "relevance", "date" ], "type": "string", "description": "How to order results in the dataset.", "default": "date" }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of concurrent HTTP requests. Lower values are more polite. Default is 5.", "default": 5 }, "requestTimeoutSecs": { "title": "Request Timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each HTTP request in seconds.", "default": 30 }, "retryCount": { "title": "Retry Count", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of times to retry failed requests before skipping.", "default": 3 } } }, "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 } } } } } } } } } }