Google News Scraper
Pricing
from $1.00 / 1,000 articles
Scrapes Google News search results, topics and top stories by country and language, with the real article link, publisher and publish time; optional full article text.
You can access the Google News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "IpVbtgEMYm1WiEE9W" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mina_safwat~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mina_safwat-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/mina_safwat~google-news-scraper/runs": { "post": { "operationId": "runs-sync-mina_safwat-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/mina_safwat~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-mina_safwat-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": "Words to search Google News for, one query per line. Google's search operators work too, such as \"exact phrase\", -exclude, OR, site:reuters.com or intitle:tesla.", "default": [], "items": { "type": "string" } }, "startUrls": { "title": "Google News links", "type": "array", "description": "Google News pages to read, one per line: a search (news.google.com/search?q=…), a topic (news.google.com/topics/…), a section such as Business or Technology, a publication, or the top stories page (news.google.com). A link that names its own edition (hl, gl and ceid in the address) keeps it; others use the country and language below. Story (\"Full coverage\") pages and single article links have no article list and are listed in FAILED_INPUTS.", "default": [], "items": { "type": "string" } }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code of the Google News edition, such as US, GB, DE, IN or EG. If Google has no edition for this country and language, it serves its nearest one and the run's status message says which.", "default": "US" }, "language": { "title": "Language", "type": "string", "description": "Language code of the edition, such as en, de, fr, ar or pt-BR. Each country offers only its own languages: Egypt has ar, India has en and hi, Switzerland has de and fr.", "default": "en" }, "timeRange": { "title": "Published within", "enum": [ "any", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Only articles published in this period. For links other than searches the period is applied to the feed's articles after reading it.", "default": "any" }, "dateFrom": { "title": "Published from (date)", "type": "string", "description": "Only articles published on or after this day (US Pacific calendar day), such as 2026-09-01. Use either this pair of dates or \"Published within\", not both." }, "dateTo": { "title": "Published to (date)", "type": "string", "description": "Only articles published on or before this day, such as 2026-09-30. Days are Google's US Pacific calendar days." }, "maxResults": { "title": "Max articles per query or link", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stops after this many articles for each query or link. A Google News feed holds about 100 articles; above 100, searches are read day by day, newest first, so they can reach thousands (up to a year back unless you set dates). Topic, section and top stories links stop at the 30-100 articles Google lists.", "default": 100 }, "includeArticleText": { "title": "Add full article text", "type": "boolean", "description": "Adds articleText, wordCount, description, imageUrl and authors to each row. Paywalled or script-only pages give no text; their row is still saved, with those fields empty, and is not charged the article-text event.", "default": 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 } } } } } } } } }}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: