Google News Scraper
Pricing
from $4.00 / 1,000 results
Go to Apify Store
Google News Scraper
Pricing
from $4.00 / 1,000 results
You can access the Google News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "tb7wdGAf0f2LGUxDC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/excellent_mustang~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-excellent_mustang-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/excellent_mustang~google-news-scraper/runs": { "post": { "operationId": "runs-sync-excellent_mustang-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/excellent_mustang~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-excellent_mustang-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": "Keyword or phrase to search Google News for. Supports Google News operators, e.g. \"tesla OR rivian\", \"\\\"supply chain\\\"\", \"intitle:earnings\". Leave empty to use a Topic instead, or to scrape Top Stories." }, "topic": { "title": "Topic section", "enum": [ "", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "type": "string", "description": "Scrape one of Google News' built-in headline sections instead of running a keyword search. Ignored when a Search query is set.", "default": "" }, "publisher": { "title": "Limit to publisher", "type": "string", "description": "Only return articles from this domain, e.g. \"reuters.com\" or \"bbc.co.uk\". Applied as a site: filter on top of your query." }, "language": { "title": "Language", "enum": [ "en", "es", "fr", "de", "it", "pt", "nl", "sv", "no", "da", "fi", "pl", "cs", "sk", "hu", "ro", "bg", "el", "tr", "ru", "uk", "ar", "he", "fa", "hi", "bn", "ta", "te", "mr", "gu", "kn", "ml", "th", "vi", "id", "ms", "ja", "ko", "zh-CN", "zh-TW" ], "type": "string", "description": "Article language (the Google News 'hl' parameter).", "default": "en" }, "region": { "title": "Region / edition", "enum": [ "US", "GB", "CA", "AU", "IE", "NZ", "IN", "SG", "PH", "MY", "ZA", "NG", "KE", "DE", "AT", "CH", "FR", "BE", "NL", "ES", "MX", "AR", "CL", "CO", "PE", "IT", "PT", "BR", "SE", "NO", "DK", "FI", "PL", "CZ", "SK", "HU", "RO", "BG", "GR", "TR", "RU", "UA", "IL", "AE", "SA", "EG", "JP", "KR", "CN", "TW", "HK", "TH", "VN", "ID", "PK", "BD" ], "type": "string", "description": "Country edition of Google News (the 'gl' parameter). Different editions surface different outlets for the same query.", "default": "US" }, "additionalMarkets": { "title": "Additional markets", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Run the same query against extra editions in one go, as REGION:language pairs (e.g. \"GB:en\", \"DE:de\", \"JP:ja\"). Results are merged and de-duplicated. Ideal for tracking how a story is covered across countries.", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "Published after", "type": "string", "description": "Only return articles published on or after this date (YYYY-MM-DD). Google News honours this back to roughly the last 12 months for most queries." }, "dateTo": { "title": "Published before", "type": "string", "description": "Only return articles published on or before this date (YYYY-MM-DD)." }, "maxItems": { "title": "Maximum articles", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Total number of articles to return across all feeds. Google News serves up to ~100 items per feed, so add more markets to go beyond that.", "default": 50 }, "resolveArticleUrls": { "title": "Resolve real publisher URLs", "type": "boolean", "description": "Convert each opaque news.google.com/rss/articles/... link into the actual publisher URL (e.g. https://www.reuters.com/...). Strongly recommended — without it you only get Google redirect links. Adds roughly 10 seconds per 100 articles.", "default": true }, "includeImages": { "title": "Fetch article thumbnails", "type": "boolean", "description": "Look up each article's og:image on the publisher's own page. Requires URL resolution. Typically finds a thumbnail for around two thirds of articles — some publishers block non-browser traffic — and noticeably increases run time.", "default": false }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Parallel HTTP requests. The default is a good balance; raise it only if you are scraping thousands of articles and using a proxy.", "default": 10 }, "enrichmentTimeoutSecs": { "title": "Enrichment time budget (seconds)", "minimum": 10, "maximum": 900, "type": "integer", "description": "Hard ceiling on URL resolution and image lookup combined. When the budget runs out the Actor stops enriching and returns what it already has, rather than running long.", "default": 150 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Google News RSS is reachable without a proxy, so this is off by default. Enable Apify Proxy if you are running very large jobs or scraping from a blocked network.", "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 } } }, "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: