Google News Scraper
Under maintenancePricing
from $2.50 / 1,000 per news records
Google News Scraper
Under maintenancePricing
from $2.50 / 1,000 per news records
You can access the Google News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "bJnvlDBmWlS4rU157" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/knowten~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-knowten-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/knowten~google-news-scraper/runs": { "post": { "operationId": "runs-sync-knowten-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/knowten~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-knowten-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": [ "region_language" ], "properties": { "keywords": { "title": "Keywords", "type": "array", "description": "Search terms to look for, one per line (e.g. 'bitcoin'). Google News search operators such as quotes are supported.", "items": { "type": "string" }, "default": [] }, "topic": { "title": "Topic", "enum": [ "", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "type": "string", "description": "Optional Google News headline section to pull in addition to the keywords.", "default": "" }, "timeframe": { "title": "Timeframe", "enum": [ "", "1h", "1d", "7d", "1m", "1y" ], "type": "string", "description": "How far back to search. Only applies to keyword searches; topic feeds always return current headlines.", "default": "1y" }, "region_language": { "title": "Region and Language", "enum": [ "AR:es-419", "AU:en", "AT:de", "BE:fr", "BE:nl", "BO:es-419", "BR:pt-419", "CA:en", "CA:fr", "CL:es-419", "CO:es-419", "CR:es-419", "CU:es-419", "CZ:cs", "DO:es-419", "EC:es-419", "EG:ar", "SV:es-419", "FR:fr", "DE:de", "GR:el", "GT:es-419", "HN:es-419", "HK:zh-Hant", "HU:hu", "IN:en", "IN:hi", "ID:id", "IE:en", "IL:he", "IT:it", "JP:ja", "LV:lv", "LB:ar", "LT:lt", "MY:en", "MX:es-419", "NL:nl", "NZ:en", "NI:es-419", "NG:en", "NO:no", "PA:es-419", "PY:es-419", "PE:es-419", "PH:en", "PL:pl", "PT:pt-150", "PR:es-419", "RO:ro", "RU:ru", "SA:ar", "SN:fr", "RS:sr", "SG:en", "SK:sk", "ZA:en", "KR:ko", "ES:es", "SE:sv", "CH:de", "CH:fr", "TW:zh-Hant", "TH:th", "TR:tr", "UA:uk", "AE:ar", "GB:en", "US:en", "US:es-419", "UY:es-419", "VE:es-419", "VN:vi" ], "type": "string", "description": "Select the country and language for the news results.", "default": "US:en" }, "maxArticles": { "title": "Max articles per keyword/topic", "minimum": 1, "type": "integer", "description": "Maximum number of articles to collect for each keyword and topic. Google caps a single feed at ~100 results, so enable Deep Extraction to go beyond that - to reach thousands, set this to the number you want (e.g. 5000) AND turn Deep Extraction on.", "default": 20 }, "extractDeep": { "title": "Deep Extraction (Time-Chunking)", "type": "boolean", "description": "Splits the timeframe into parallel after:/before: windows so a keyword can return far more than the ~100 articles a single Google News feed provides. The number of windows scales automatically with \"Max articles per keyword/topic\" (more articles requested = more, narrower windows). Works with any Timeframe, including \"Any time\" (which falls back to a 5-year lookback so it has something to slice). For best results on niche keywords, pick a broader Timeframe so each window has more articles to find.", "default": false }, "decodeUrls": { "title": "Decode URLs", "type": "boolean", "description": "Resolve each Google News redirect link to the publisher's real article URL. Adds one request per article.", "default": true }, "fetchArticleContent": { "title": "Fetch article description and image", "type": "boolean", "description": "Visit each article to read its description and cover image. This is the slowest stage - turn it off for a much faster run that returns feed data only (title, URL, source, publish date).", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many requests to run in parallel. Lower this if you hit rate limits, raise it for more speed on larger memory settings.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used for all requests. Strongly recommended: Google throttles the URL-decoding endpoint per IP, and some publishers block datacenter traffic.", "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 } } } } } } } } }}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: