GDELT News Scraper & News Monitoring API (65+ Languages)

Search worldwide online news in 65+ languages through the official GDELT DOC 2.0 API. Headline, URL, outlet, country, time, and optional tone. No API key.

Hosted MCP Server

npx add-mcp 'https://mcp.apify.com?tools=dedicated_crest/gdelt-news-monitor'

Installs into Claude Code, Codex, Cursor and more

Documentation

GDELT News Scraper – Global News Monitor & Search API (dedicated_crest/gdelt-news-monitor) Actor

GDELT news scraper & news monitoring API: search worldwide online news in 65+ languages by keyword, site, country, language and theme. Headline, URL, outlet, country, language, time, tone. Deduplicated, no API key. Google Alerts alternative. $2/1,000.

Pricing

$2.00 / 1,000 articles

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the API section below.

Each client library has reference documentation the quickstart does not restate: JavaScript/TypeScript (npm install apify-client) and Python (pip install apify-client).

README

GDELT News Scraper – Global News Monitor & Search API

Search and monitor worldwide online news in 65+ languages through the official GDELT DOC 2.0 API. Enter keywords (and optionally sites, countries, languages, or GDELT themes) and get one deduplicated row per article: headline, URL, outlet domain, outlet country, language, time first seen, and optional tone or sentiment. No API key or login.

Price: $0.002 per unique article saved ($2 per 1,000). There is no start fee. Syndicated duplicates are removed before you are charged.

Try a run for free: New Apify accounts can use the Free plan, which includes $5 of platform usage credit each month and does not require a credit card, so a small test run is covered. Unused credit does not roll over.

Try it now: the form is pre-filled with artificial intelligence, English-language sources, the last 24 hours, and 15 articles. Click Start. GDELT allows about one request every 5 seconds and is sometimes busy, so a short run usually finishes in under a minute. The test run below took about 41 seconds, including one brief busy retry.

Buyer use cases

  1. Monitor news on a company or topic — set keywords to a brand, executive, product, or issue and timespan to 24h or 7d. Schedule the Actor daily and send new rows to Slack, email, or Google Sheets for a briefing.
  2. Adverse-media / KYC screening — search a company, supplier, or person, then set maxTone to a negative threshold (for example -2) or turn on sentiment to review negative coverage with outlet country and the time the article was first seen.
  3. Industry or country news feeds — combine a topic keyword with countries and languages (for example English-language coverage from US and UK) for research, comms, or a newsletter.

Real run results (11 Nov 2026)

Pre-filled input: keyword artificial intelligence, language English, timespan 24h, maxItems: 15 (run iFDRq0vm4YH5ibxcl, about 41 seconds at 10:03 AM PT, 15 articles saved, 66 duplicate headlines skipped and not charged). First 8 rows:

Seen (UTC)TitleOutletOutlet countryLanguage
2026-11-11 06:30US - China AI cooperation and competition: Bessentchinatechnews.comChinaEnglish
2026-11-11 06:30WhatsApp To Go Beyond Messaging With AI Integration, Digital Payments…freepressjournal.inIndiaEnglish
2026-11-11 06:30U. S. stocks slide Tuesday as sell - off in Nvidia extendsindiagazette.comIndiaEnglish
2026-11-11 06:30Which AI Collaborates Best with Humans? New Skillprint Experiment Exp…jamaicantimes.comJamaicaEnglish
2026-11-11 06:30Alleged spy plot targeting CEO Jensen Huang raises questions about Nv…thehindubusinessline.comIndiaEnglish
2026-11-11 06:30Combining AI with GIS to solve real - time farm problems - the Farmwi…thehindubusinessline.comIndiaEnglish
2026-11-11 06:30Google Expands Gemini 4 Carbon AI Access For Developers, Businesses W…freepressjournal.inIndiaEnglish
2026-11-11 06:30Asian shares mostly rise on AI chip demand despite Wall Street retrea…cecildaily.comUnited StatesEnglish

For AI agents

This Actor is dedicated_crest/gdelt-news-monitor. Call it through the Apify API, the official JavaScript or Python client, or Apify's MCP server. Send JSON input with:

  • keywords (array of strings): terms to match; multi-word entries are treated as phrases, for example ["acme corp"]
  • timespan (string): how far back to search, for example 24h or 7d (optional startDate / endDate for a custom range)
  • Optional filters: languages, countries, domains, excludeDomains, allKeywords, excludeKeywords, themes, minTone, maxTone, sentiment, maxItems
  • Leave fetchArticleMeta false for a fast first run

Each output row is one unique article. Stable fields include title, url, domain, sourceCountry, language, seenAt, sentiment, toneRange, socialImage, mobileUrl, query, and scrapedAt. sentiment is filled when Label sentiment is on. article (description, author, published time, site name, image, optional text snippet) is filled when Fetch article metadata is on.

Features

  • 🔎 Keywords (any), must-contain (all) and exclude terms; multi-word entries become exact phrases
  • 📰 Only / exclude specific news sites (e.g. reuters.com, bbc.co.uk)
  • 🌍 Source country and language filters (e.g. US, india, german, spanish)
  • 🏷️ GDELT themes (e.g. CYBER_ATTACK, ECON_BANKRUPTCY, ENV_CLIMATECHANGE) and a raw query box for any GDELT operator (near20:, imagetag:, …)
  • 🙂 Sentiment labels (negative / neutral / positive from GDELT's tone score) or min/max tone filters for "only very negative news"
  • ⏱️ Time span (30min … 3m) or exact start/end dates. Large ranges are split into time windows automatically, so you can get far more than GDELT's 250-per-query limit.
  • ♻️ URL canonicalization + syndicated-headline dedupe
  • 📝 Optional article metadata: meta description, author, published time, site name, image, optional opening-text snippet
  • 💵 Stops cleanly at your Maximum cost per run

How to use it

  1. Click Try for free.
  2. Enter keywords (and optionally sites, countries, languages).
  3. Choose a time span, e.g. 24h.
  4. Run it, or schedule hourly/daily and connect Slack, Google Sheets, email, Zapier, Make or n8n for alerts.

Input example

{
  "keywords": ["data breach", "ransomware"],
  "languages": ["english"],
  "countries": ["US", "UK"],
  "timespan": "24h",
  "sentiment": true,
  "maxItems": 500
}

Output example

Real output (query "data breach", English, with sentiment and article metadata):

{
  "title": "AI Enabled Ransomware, New Threat",
  "url": "https://www.livelaw.in/articles/ai-enabled-ransomware-new-threat-555141",
  "domain": "livelaw.in",
  "sourceCountry": "India",
  "language": "English",
  "seenAt": "2026-10-17T12:45:00Z",
  "sentiment": "negative",
  "toneRange": "< -1.5",
  "socialImage": "https://www.livelaw.in/h-upload/2026/10/16/706878-ransomware.jpg",
  "mobileUrl": "https://www.livelaw.in/amp/articles/ai-enabled-ransomware-new-threat-555141",
  "duplicateOf": null,
  "query": "\"data breach\" sourcelang:english",
  "scrapedAt": "2026-10-17T17:13:09.774Z",
  "article": {
    "fetchStatus": 200,
    "finalUrl": "https://www.livelaw.in/articles/ai-enabled-ransomware-new-threat-555141",
    "description": "Ransomware has always operated on this basic business model: Cryptically compromise someone",
    "author": "Pratham Tiwari",
    "publishedAt": "2026-10-17T15:00:19+05:30",
    "siteName": null,
    "image": "https://www.livelaw.in/h-upload/2026/10/16/706878-ransomware.jpg",
    "keywords": "Ransomware, Cybercrime, Information Technology Act, Cybersecurity Laws, Intermediary Liability, Digital Personal Data Protection Act, Electronic Evidence, Digital Forensics, AI Generated Deepfakes, Legal Framework",
    "text": null
  }
}

sentiment is present when Label sentiment is on. article is present when Fetch article metadata is on. duplicateOf is only filled when you turn off syndicated-duplicate removal.

Pricing

Pay per event: $0.002 per unique article ($2 per 1,000), no start fee. Duplicates are removed before charging. Set a Maximum cost per run and the Actor stops cleanly when it's reached.

How that compares with other news Actors on the Apify Store (free-tier list prices from the Store API, checked 18 Oct 2026):

ActorSourcePrice per 1,000 articlesStart fee
This ActorGDELT (65+ languages, outlet country)$2.00none
GDELT News Scraper (dami_studio)GDELT$2.00none
GDELT Global News Monitoring Scraper (scrapers_lat)GDELT$8.00none
GDELT News Scraper (logiover)GDELT$3.00$0.00005
Google News Scraper (data_xplorer)Google News$4.00none
Google News Scraper (automation-lab)Google News$2.30$0.005

Google News scrapers are a good fit for "what does Google show for this query". GDELT is a better fit for global, multilingual coverage with outlet country, language and tone filters.

Speed & limits (please read)

  • GDELT asks clients to send at most one request every 5 seconds and often answers "busy" (HTTP 429) under load. The Actor respects this and retries patiently, so a run usually takes 30 seconds to a few minutes, longer when GDELT is busy. Status messages show when it's waiting.
  • Each request returns up to 250 articles. Busy time ranges are split automatically.
  • Label sentiment runs 3 queries per time window (negative / neutral / positive), so it takes about 3× longer.
  • GDELT's DOC API covers roughly the last 3 months.

FAQ

Is this legal? Yes. The Actor uses GDELT's public, free DOC 2.0 API, which is intended for this kind of research and monitoring. Article metadata fetching only reads public page metadata. If you enable text snippets, respect publishers' copyright and terms.

Is it affiliated with GDELT or Google? No. The GDELT Project is an independent open data initiative. This Actor is not affiliated with or endorsed by it.

Feedback? Open an issue in the Issues tab.

Can I use it as a Google Alerts replacement? Yes. Schedule it hourly or daily with timespan matching the interval (e.g. 24h daily) and send new rows to Slack, email or Google Sheets.

Does it return the full article text? By default you get the headline, URL and GDELT metadata. Turn on Fetch article metadata to visit each article and add its meta description, author, published time, site name and image; with that on, Article text snippet length adds up to 5,000 characters of the opening paragraphs. Respect publishers' copyright.

Why did my run take several minutes? GDELT throttles all clients to about one request per 5 seconds and answers "busy" under load. The Actor waits and retries instead of failing; you are not charged for waiting.

How far back can I search? GDELT's DOC API covers roughly the last 3 months.

Related tools

Other Actors by the same developer that work well with this one:

⭐ Enjoying it?

If this Actor saved you time, a quick rating on its Apify Store page helps a lot, and it helps other people find it. Feedback or a missing feature? Open an issue on the Actor's Issues tab. Thank you!

Actor input Schema

keywords (type: array):

Articles that mention ANY of these keywords. Multi-word entries are searched as exact phrases, for example "artificial intelligence". GDELT requires words of 3+ characters (put short acronyms inside a quoted phrase).

allKeywords (type: array):

Every one of these terms must also appear in the article, for example 'regulation' or a company name.

excludeKeywords (type: array):

Drop articles that contain any of these words or phrases, for example sports or horoscope.

domains (type: array):

Only include these news site domains, for example reuters.com or bbc.co.uk. Leave empty for all sites.

excludeDomains (type: array):

News site domains to exclude, for example example.com.

countries (type: array):

Filter by country of the news outlet. Use FIPS 10-4 codes or names, for example US, UK, france, india, germany.

languages (type: array):

Filter by article language, for example english, spanish, german, french, chinese (or ISO-style codes like eng, spa).

themes (type: array):

Optional GDELT GKG theme codes, for example ECON_BANKRUPTCY, CYBER_ATTACK, ENV_CLIMATECHANGE.

query (type: string):

Optional raw GDELT DOC 2.0 operators, ANDed with the fields above, for example near20:"tesla recall" or imagetag:"protest".

timespan (type: string):

How far back to search, for example 30min, 6h, 24h, 7d, 2w, 3m. GDELT's DOC API covers roughly the last 3 months. Ignored when Start date is set.

startDate (type: string):

Optional start of a custom date range (ISO date or date-time, for example 2026-10-01 or 2026-10-01T08:00:00Z).

endDate (type: string):

Optional end of a custom date range (ISO date or date-time). Defaults to now.

sentiment (type: boolean):

If true, label each article negative, neutral, or positive using GDELT's tone score. This runs 3 GDELT queries per time window, so the run takes about 3× longer. Leave false for a fast first run.

minTone (type: integer):

If set, only articles with GDELT tone above this value (for example 5 = clearly positive). Disables sentiment labels.

maxTone (type: integer):

If set, only articles with GDELT tone below this value (for example -5 = clearly negative). Disables sentiment labels.

dedupeTitles (type: boolean):

If true (default), drop articles whose headline matches one already saved (wire stories republished by many sites). URLs are always deduplicated. Duplicates are not charged.

fetchArticleMeta (type: boolean):

If true, visit each article page to add meta description, author, published time, site name and image (1 extra request per article; some sites block bots). Leave false for a fast first run.

articleTextMaxChars (type: integer):

When metadata fetching is on, include up to N characters of the article's opening paragraphs (0 = none). Respect publishers' copyright.

sort (type: string):

Order GDELT returns articles in each time window: newest first (default), oldest first, relevance, most positive, or most negative.

maxItems (type: integer):

Maximum number of unique articles to save and charge for. Use a small number (for example 15) for a fast first run. The run also stops cleanly when your Maximum cost per run is reached.

Actor input object example

{
  "keywords": [
    "artificial intelligence"
  ],
  "languages": [
    "english"
  ],
  "timespan": "24h",
  "sentiment": false,
  "dedupeTitles": true,
  "fetchArticleMeta": false,
  "articleTextMaxChars": 0,
  "sort": "datedesc",
  "maxItems": 15
}

Actor output Schema

results (type: string):

News articles with title, URL, source domain, country, language, time seen and sentiment.

summary (type: string):

GDELT query used, date range, articles saved, requests and duplicates skipped.

API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

JavaScript example

import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "keywords": [
        "artificial intelligence"
    ],
    "languages": [
        "english"
    ],
    "maxItems": 15
};

// Run the Actor and wait for it to finish
const run = await client.actor("dedicated_crest/gdelt-news-monitor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

Python example

from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "keywords": ["artificial intelligence"],
    "languages": ["english"],
    "maxItems": 15,
}

# Run the Actor and wait for it to finish
run = client.actor("dedicated_crest/gdelt-news-monitor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

CLI example

echo '{
  "keywords": [
    "artificial intelligence"
  ],
  "languages": [
    "english"
  ],
  "maxItems": 15
}' |
apify call dedicated_crest/gdelt-news-monitor --silent --output-dataset

MCP server setup

{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,dedicated_crest/gdelt-news-monitor"
        }
    }
}

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an Authorization: Bearer <APIFY_API_TOKEN> header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/C0gVEJJhVsTMIFJmq/builds/8dfSHaVTVQkAPnFns/openapi.json