📰 Google News API: News Search Results in Clean JSON

The efficient, reliable, and developer-friendly way to use the Google News API.

Actor page: apify.com/johnvc/GoogleNewsAPI Input schema: apify.com/johnvc/GoogleNewsAPI/input-schema

The Google News API searches Google News and returns clean, structured JSON, one item per page of results. Each item carries the search parameters, search metadata (total results, pages processed), and a news_results array where every article includes title, link, source, snippet, and ranking position. Supports location targeting, country and language filtering, safe search, duplicate filtering, and pagination control.

Video Walkthrough

Quick Start

Prerequisites

• Python 3.11 or higher
• An Apify account and API key (get a free key here)

1. Clone the repository

   bash

   Copy

   git clone https://github.com/johnisanerd/Apify-Google-News-Scraper.git
   cd Apify-Google-News-Scraper
   

2. Install dependencies with UV

   bash

   Copy

   # Install UV if you do not have it:
   curl -LsSf https://astral.sh/uv/install.sh | sh
   
   # Install project dependencies:
   uv sync
   

3. Configure your API key

   bash

   Copy

   cp .env.example .env
   # Edit .env and add your Apify API key
   # Get your free API key at: https://apify.com?fpr=9n7kx3
   

4. Run the example

   bash

   Copy

   uv run python google-news-scraper.py
   

Alternative: set the API key directly

export APIFY_API_TOKEN="your_api_key_here"
uv run python google-news-scraper.py

Why Use This Google News API?

Real-time coverage at scale. Google News aggregates tens of thousands of publishers. Instead of maintaining a client for each outlet, you query the aggregated index and get ranked results across all of them in a single call.

Geo-targeted results. Filter by country code (gl), language (hl), Google domain, and location string for precise control over the geographic and linguistic scope.

Configurable depth. Set max_pages for a quick headline snapshot or a deeper sweep. Each page is returned as a discrete item, easy to stream, filter, or load into a pipeline.

Predictable, pay-per-use pricing. A small per-run setup fee plus a per-page fee, with no subscription. You control cost with the page limit.

Consistent JSON output. Every article comes back with the same fields (title, link, source, snippet, position), so there is no schema variance between publishers.

Easy to automate. Call it from Python in a few lines, or load it as an MCP tool so assistants like Claude and Cursor can pull fresh news for you on demand.

Features

Core Capabilities

• Aggregated news search across thousands of publishers in one call
• Location targeting by country code (gl), language (hl), and Google domain
• Safe search and duplicate filtering toggles
• Auto-correction control with nfpr for exact-match queries
• Pagination control with a configurable page cap

Data Quality

• One item per page with a stable structure
• news_results array with title, link, source, snippet, and position per article
• Search metadata (total results, pages processed) on every item
• Echoed search parameters so each item is self-describing
• Consistent JSON shape across every query

Usage Examples

Basic search

{
  "q": "artificial intelligence",
  "max_pages": 1
}

Geo-targeted search with language filtering

{
  "q": "artificial intelligence breakthroughs",
  "google_domain": "google.com",
  "gl": "us",
  "hl": "en",
  "safe": "off",
  "max_pages": 2
}

Input Parameters

Output Format

A real result for artificial intelligence (one item per page; the news_results array is trimmed to a single article here, and search_information carries additional fields).

{
  "search_parameters": {
    "q": "artificial intelligence",
    "gl": "us",
    "hl": "en",
    "safe": "off",
    "nfpr": "0",
    "filter": "0",
    "max_pages": 1
  },
  "search_metadata": {
    "total_results": 9,
    "news_count": 9,
    "pages_processed": 1,
    "max_pages_set": 1,
    "pagination_limit_reached": false
  },
  "search_information": {
    "query_displayed": "artificial intelligence"
  },
  "search_timestamp": "2026-05-29T11:27:03",
  "page_number": 1,
  "news_results": [
    {
      "position": 1,
      "title": "Improving multimodal wearable sensing for healthcare with artificial intelligence",
      "link": "https://www.nature.com/articles/s41587-026-03134-z",
      "source": "Nature",
      "snippet": "This Comment explores artificial intelligence-driven strategies to accelerate the clinical translation of multimodal wearable sensors."
    }
  ]
}

Each page item echoes the search_parameters you sent, reports search_metadata (total results and pages processed), and lists every article in news_results with its ranking position, title, link, source, and snippet.

Use as an MCP tool

You can load the Google News API as an MCP tool so assistants call it for you. The MCP server URL preloads just this one Actor:

https://mcp.apify.com/?tools=actors,docs,johnvc/GoogleNewsAPI

Authenticate with OAuth in the browser when offered, or with your Apify API token (the same APIFY_API_TOKEN used by the Python example). Get a token at https://console.apify.com/settings/integrations and a free Apify account at https://apify.com?fpr=9n7kx3 .

Install in Claude Cowork Desktop

Cowork is the desktop app's automation mode. To give it the Google News API as a tool, add the Apify MCP server as a connector.

1. Open the Claude desktop app and go to Settings → Connectors (or Settings → Developer → Edit Config to edit claude_desktop_config.json directly).
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
2. Add the Apify MCP server, preloaded with only this Actor:

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.apify.com/?tools=actors,docs,johnvc/GoogleNewsAPI"
      ]
    }
  }
}

3. Restart the app. When Cowork first calls the tool, complete the OAuth prompt in your browser, or add your Apify API token in the connector settings to skip OAuth.
4. In a Cowork chat, confirm the tool is available and ask it to run the Google News API.

Download the desktop app and start a free trial: https://claude.ai/referral/uIlpa7nPLg More help: https://docs.apify.com/platform/integrations/claude-desktop

Install in Claude Code

Claude Code is the command-line tool. Add the Actor's MCP server with one command:

claude mcp add --transport http apify \
  "https://mcp.apify.com/?tools=actors,docs,johnvc/GoogleNewsAPI"

To use a token instead of browser OAuth:

claude mcp add --transport http apify \
  "https://mcp.apify.com/?tools=actors,docs,johnvc/GoogleNewsAPI" \
  --header "Authorization: Bearer YOUR_APIFY_TOKEN"

Then verify with claude mcp list, or run /mcp inside a session. Ask Claude Code to call the Google News API.

Try Claude Code free: https://claude.ai/referral/uIlpa7nPLg Claude Code MCP docs: https://code.claude.com/docs/en/mcp

Install in Claude (website)

On claude.ai you add Apify as a connector, then enable just this Actor's tool.

1. Go to Settings → Connectors → Browse connectors and search for Apify MCP server. Install it (enable or update if prompted).
2. When connecting, authenticate with your Apify API token, and enable the tool johnvc/GoogleNewsAPI.
3. In any chat, open + → Connectors and turn on Apify.
4. Alternatively, choose Add custom connector and paste the full MCP URL https://mcp.apify.com/?tools=actors,docs,johnvc/GoogleNewsAPI, using OAuth when prompted.
5. Ask Claude to run the Google News API.

Open Claude on the web: https://claude.ai/referral/uIlpa7nPLg

Install in Cursor