{ "openapi": "3.0.1", "info": { "title": "Google News Scraper Fast (Full Article + AI/RAG Markdown)", "description": "Ultra-fast Google News scraper & URL decoder. Extracts real publisher URLs (decodes CBMi/Fbv4je links), multi-source story clusters, OpenGraph images, and full-article AI/RAG-ready Markdown + chunks across 85+ country/language editions with zero proxy requirement.", "version": "1.0", "x-build-id": "WbZJDGWkdPMIyMAx1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/church_of_loujess~google-news-scraper-fast/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-church_of_loujess-google-news-scraper-fast", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/church_of_loujess~google-news-scraper-fast/runs": { "post": { "operationId": "runs-sync-church_of_loujess-google-news-scraper-fast", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/church_of_loujess~google-news-scraper-fast/run-sync": { "post": { "operationId": "run-sync-church_of_loujess-google-news-scraper-fast", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Search Keywords (Bulk)", "type": "array", "description": "List of search keywords or queries for Google News (e.g. ['Artificial Intelligence', 'OpenAI', 'NVIDIA']). Supports Google search operators like site:reuters.com or intitle:AI.", "default": [ "Artificial Intelligence", "OpenAI" ], "items": { "type": "string" } }, "keyword": { "title": "Single Search Keyword (Legacy Compatibility)", "type": "string", "description": "Single search keyword (compatible with data_xplorer/google-news-scraper-fast). Merged automatically with 'keywords'." }, "topics": { "title": "Google News Topic Feeds (Optional)", "type": "array", "description": "Optional official Google News Topic sections to scrape in addition to keywords (e.g. ['TOP_STORIES', 'TECHNOLOGY', 'BUSINESS', 'WORLD', 'SCIENCE', 'HEALTH', 'SPORTS', 'ENTERTAINMENT', 'NATION']).", "default": [], "items": { "type": "string" } }, "timeframe": { "title": "Time Period (timeframe)", "enum": [ "1h", "6h", "12h", "1d", "7d", "30d", "1y", "all" ], "type": "string", "description": "Time filter for Google News search (e.g. '1h' = past hour, '1d' = past 24 hours, '7d' = past 7 days, '30d' = past 30 days, '1y' = past year, 'all' = anytime).", "default": "7d" }, "region_language": { "title": "Region & Language Edition (region_language)", "type": "string", "description": "Google News Country & Language edition in 'COUNTRY:lang' format (e.g. 'US:en', 'GB:en', 'CA:en', 'AU:en', 'DE:de', 'FR:fr', 'ES:es', 'JP:ja', 'BR:pt-419', 'IN:en').", "default": "US:en" }, "maxArticles": { "title": "Max Articles per Keyword / Topic", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum number of articles to extract per keyword or topic (default: 20, 0 = up to 100 per feed).", "default": 20 }, "decodeGoogleNewsUrls": { "title": "Decode Real Publisher URLs (Fbv4je / CBMi Decoder)", "type": "boolean", "description": "Automatically decode opaque 'news.google.com/rss/articles/CBMi...' redirect URLs into the actual target publisher URL (e.g. reuters.com, techcrunch.com).", "default": true }, "extractArticleContent": { "title": "Extract Full Article Markdown & RAG Chunks", "type": "boolean", "description": "Fetch the decoded publisher webpage and extract OpenGraph thumbnail image, author, clean full-article Markdown, and token-bounded AI/RAG chunks.", "default": true }, "chunkSizeWords": { "title": "RAG Chunk Size (Words)", "minimum": 50, "maximum": 2000, "type": "integer", "description": "Target word count per RAG chunk when extractArticleContent is enabled.", "default": 250 }, "proxyConfiguration": { "title": "Proxy Configuration (Optional)", "type": "object", "description": "Optional proxy configuration. Works out-of-the-box with direct connections at zero proxy cost.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }