Google News (via Apify)

Registre officiel IA et agents

Google News for AI agents: headlines, sources, dates and article URLs, with time filters.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code
claude mcp add --transport http google-news-via-apify 'https://mcp.apify.com/?tools=automationnation/google-news-scraper' --header 'Authorization: <Your Apify API token, sent as '\''Bearer <token>'\''. Get it at https://console.apify.com/settings/integrations (free account).>'
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "google-news-via-apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=automationnation/google-news-scraper",
            "headers": {
                "Authorization": "<Your Apify API token, sent as 'Bearer <token>'. Get it at https://console.apify.com/settings/integrations (free account).>"
            }
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Google News Scraper & API: articles, sources and dates
  2. Quick facts
  3. Example input
  4. Run it from code
  5. Use it with AI agents (MCP)
  6. FAQ
  7. More from AutomationNation

Google News Scraper & API: articles, sources and dates

Google News Scraper is an Apify Actor that returns Google News results for any topic, company or keyword: headline, source, publish date, snippet and the article URL, with time filters (past hour to past year), sort by date and any country and language, up to 300 articles per search, at $1 per 1,000 articles.

Price: $1 per 1,000 articles ($0.80 on Gold and above) · Run it: https://apify.com/automationnation/google-news-scraper · Guide: https://retracn.github.io/automationnation-actors/google-news-scraper/

Quick facts

  • One row per article: headline, snippet, source, publish time (ISO) and the publisher's article URL.
  • Time filters: past hour, day, week, month or year; sort by relevance or date.
  • Any country and language, up to 300 articles per search.
  • Monitoring: with Only new results on, a scheduled run returns only articles earlier runs didn't (a Google Alerts feed you can use in code). Guide: https://retracn.github.io/automationnation-actors/guides/google-alerts-api/
  • Price: $1 per 1,000 articles; the free $5 monthly credit covers 5,000 articles.

Example input

{
  "queries": [
    "apple earnings"
  ],
  "time": "week",
  "maxResultsPerQuery": 30
}

Run it from code

REST API

curl -X POST "https://api.apify.com/v2/acts/automationnation~google-news-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"queries": ["apple earnings"], "time": "week", "maxResultsPerQuery": 30}'

Python — see examples/python_example.py

# pip install apify-client
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("automationnation/google-news-scraper").call(run_input={
  "queries": [
    "apple earnings"
  ],
  "time": "week",
  "maxResultsPerQuery": 30
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item.get("title"), item.get("source"), item.get("publishedAt"), item.get("url"))

JavaScript — see examples/node_example.mjs

// npm install apify-client
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('automationnation/google-news-scraper').call({
  "queries": [
    "apple earnings"
  ],
  "time": "week",
  "maxResultsPerQuery": 30
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
for (const item of items) console.log(item.title, item.source, item.publishedAt, item.url);

Use it with AI agents (MCP)

Hosted MCP server URL (Claude, ChatGPT, Cursor and other clients with remote MCP support):

https://mcp.apify.com?tools=automationnation/google-news-scraper

Local config for Claude Desktop / Cursor — mcp/claude_desktop_config.json:

{
  "mcpServers": {
    "google-news-scraper": {
      "command": "npx",
      "args": [
        "-y",
        "@apify/actors-mcp-server",
        "--tools",
        "automationnation/google-news-scraper"
      ],
      "env": {
        "APIFY_TOKEN": "YOUR_APIFY_TOKEN"
      }
    }
  }
}

FAQ

Is there an official Google News API? No. Google retired the Google News API years ago. Google News Scraper on Apify returns Google News results as data through Apify's API, clients and MCP.

Do I get the full article text? You get the headline, snippet, source, date and URL; pass the URLs to a content crawler for full text.

Is there a Google Alerts API? No. Google Alerts arrive by email or RSS only. Schedule this Actor with Only new results on to get each new article about your query as JSON, Slack, Sheets or a webhook.

More from AutomationNation


This repository holds usage examples. The scraper itself runs on the Apify platform; you need a free Apify account and API token. Examples are MIT licensed.

Questions fréquentes

Qu'est-ce que Google News (via Apify) ?

Google News for AI agents: headlines, sources, dates and article URLs, with time filters.

Comment installer Google News (via Apify) ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http google-news-via-apify 'https://mcp.apify.com/?tools=automationnation/google-news-scraper' --header 'Authorization: <Your Apify API token, sent as '\''Bearer <token>'\''. Get it at https://console.apify.com/settings/integrations (free account).>'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Google News (via Apify) ?

Oui. Il attend Authorization, à renseigner dans sa configuration.

Google News (via Apify) est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Google News (via Apify) ?

Il est publié par retracn. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.