Google News Scraper
Pricing
from $1.00 / 1,000 results
Go to Apify Store
Google News Scraper
Scrape Google News in real-time. Supports keyword search, date filters, full-text article extraction, and image extraction.
Google News Scraper
Pricing
from $1.00 / 1,000 results
Scrape Google News in real-time. Supports keyword search, date filters, full-text article extraction, and image extraction.
You can access the Google News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "oBJ8PT4XSUf2uY6PF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/crawlerbros~google-news-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-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/crawlerbros~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-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", "required": [ "queries" ], "properties": { "queries": { "title": "Search Queries", "minItems": 1, "type": "array", "description": "One or more search keywords. Each query is processed separately. Results are deduplicated across queries.", "items": { "type": "string" } }, "maxResultsPerQuery": { "title": "Max Results Per Query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of articles to return per query.", "default": 20 }, "language": { "title": "Language", "type": "string", "description": "2-letter BCP-47 language code for Google News results (e.g. 'en', 'de', 'fr', 'es').", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "ISO 3166-1 alpha-2 country code for regional news (e.g. 'US', 'GB', 'DE', 'IN').", "default": "US" }, "dateRange": { "title": "Date Range", "enum": [ "1h", "6h", "1d", "7d", "1m", "1y", "any" ], "type": "string", "description": "Filter articles by recency. Ignored if dateFrom/dateTo are set.", "default": "any" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Filter articles published on or after this date (YYYY-MM-DD). Overrides dateRange." }, "dateTo": { "title": "Date To", "type": "string", "description": "Filter articles published on or before this date (YYYY-MM-DD). Use with dateFrom." }, "siteFilter": { "title": "Site Filter", "type": "string", "description": "Restrict results to a specific domain (e.g. 'reuters.com', 'bbc.com')." }, "excludeWords": { "title": "Exclude Words", "type": "array", "description": "Words or phrases to exclude from results.", "items": { "type": "string" } }, "extractFullText": { "title": "Extract Full Article Text", "type": "boolean", "description": "Fetch each article and extract the full body text using trafilatura. Uses Playwright to render the article page.", "default": false }, "includeImages": { "title": "Include Article Images", "type": "boolean", "description": "Extract the main og:image URL from each article page. Uses Playwright to render the article page.", "default": false }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of parallel browser pages (for full text/images). Higher = faster but more memory.", "default": 5 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Google News Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: