{ "openapi": "3.0.1", "info": { "title": "Google News Scraper", "description": "Extract full Google News articles with text, images & metadata. 95%+ success rate, multi-region support, smart content extraction with automatic fallbacks. Production-ready & cost-optimized", "version": "1.0", "x-build-id": "PmNO7EZdvkb0f6fJV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xmolodtsov~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xmolodtsov-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xmolodtsov~google-news-scraper/runs": { "post": { "operationId": "runs-sync-xmolodtsov-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xmolodtsov~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-xmolodtsov-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search Query", "type": "string", "description": "A search term to find news articles on Google News. For scraping multiple queries in one run, use the Queries field below instead." }, "queries": { "title": "Queries", "type": "array", "description": "A list of search queries to scrape. Each item can be a plain string (e.g. \"tesla\") or an object with a \"query\" field and optional passthrough fields that get merged into each output article. Takes precedence over the Search Query field above." }, "maxItemsPerUrl": { "title": "Articles per Query", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of articles to scrape for each query. Lower values are cheaper and faster.", "default": 50 }, "maxItems": { "title": "Total Articles Limit", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Optional cap on the total number of articles across all queries. Once reached, remaining queries are skipped. Leave at 0 for unlimited.", "default": 0 }, "fetchArticleDetails": { "title": "Fetch Full Article Content", "type": "boolean", "description": "When enabled, the scraper visits each article URL to extract full text, images, and metadata. Disable for a fast, low-cost run that returns RSS metadata only (title, source, date, link).", "default": true }, "region": { "title": "Country/Region", "enum": [ "US", "GB", "CA", "AU", "DE", "IT", "ES", "MX" ], "type": "string", "description": "Country for regional news results. Affects which articles and sources Google News returns.", "default": "US" }, "language": { "title": "Language", "enum": [ "en-US", "en-GB", "en-CA", "en-AU", "de-DE", "it-IT", "es-ES", "es-MX" ], "type": "string", "description": "Language for news content. Controls which language articles are returned in.", "default": "en-US" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Only include articles published on or after this date. Defaults to the last 30 days if not set." }, "dateTo": { "title": "Date To", "type": "string", "description": "Only include articles published on or before this date. Defaults to today if not set." }, "disableBrowserFallback": { "title": "Disable Browser Fallback", "type": "boolean", "description": "Skip Playwright browser fallback for articles and URL resolution that fail via HTTP. Reduces cost but may return fewer articles. Articles that cannot be fetched via HTTP will be skipped.", "default": false }, "topics": { "title": "Topics", "type": "array", "description": "Google News topic names to fetch (e.g. \"business\", \"technology\"). Used alongside or instead of a search query to browse topic feeds.", "items": { "type": "string" }, "default": [] }, "topicsHashed": { "title": "Topics (Hashed)", "type": "array", "description": "Google News topic hashes for direct topic RSS feed URLs. Use this if you know the internal hash for a Google News topic section.", "items": { "type": "string" }, "default": [] }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for the scraper. Defaults to Apify Proxy, which is required for Google News URL resolution.", "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 } } }, "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 } } } } } } } } } }