Search Google News

When to use this

Use it to track coverage of a brand, person or topic. Google News' search operators work in query: quotes, OR, -word, site:reuters.com, intitle:, before: and after: (YYYY-MM-DD). date_posted keeps only recent articles.

region and language pick the Google News edition, US English by default. Leave language out for the region's own edition (DE gives German); a language Google News has no edition for in that region is a 400.

Articles come in Google News' order, most relevant first; sort by published_at for the newest. Each one links through Google News (google_news_url opens the article in a browser): Google encrypts the publisher's own URL in that link, so we can't return it. No pagination: one call returns everything Google News lists, up to about 100.

Parameters

All parameters go in the query string.

Example request

Replace YOUR_API_KEY with your key, or set LURKAPI_KEY for the code. Get a free key.

curl "https://api.lurkapi.com/v1/google/news?query=nvidia" \
  -H "x-api-key: YOUR_API_KEY"

const params = new URLSearchParams({
  query: "nvidia",
});
const res = await fetch(`https://api.lurkapi.com/v1/google/news?${params}`, {
  headers: { "x-api-key": process.env.LURKAPI_KEY },
});
const data = await res.json();
if (!data.success) throw new Error(`${data.code}: ${data.error}`);
console.log(data.articles);

import os
import requests

res = requests.get(
    "https://api.lurkapi.com/v1/google/news",
    params={
        "query": "nvidia",
    },
    headers={"x-api-key": os.environ["LURKAPI_KEY"]},
    timeout=60,
)
data = res.json()
if not data["success"]:
    raise RuntimeError(f"{data['code']}: {data['error']}")
print(data["articles"])

Example response

A real response from this endpoint, captured from the live API and trimmed to a couple of items. Strings over 96 characters (mostly signed media URLs) are cut short and end in ….

{
  "success": true,
  "credits_remaining": 999999,
  "credits_charged": 1,
  "articles": [
    {
      "title": "Nvidia launches new open models to run agents in the enterprise and on PCs",
      "source": "TechCrunch",
      "source_url": "https://techcrunch.com",
      "google_news_url": "https://news.google.com/rss/articles/CBMirgFBVV95cUxPNThVa0RMWlZyclBfYi0…",
      "published_at": "2026-10-19T15:37:09.000Z"
    },
    {
      "title": "Exclusive | Nvidia-Backed Startup doubleAI Launches Model to Pare Cost of Compute",
      "source": "WSJ",
      "source_url": "https://www.wsj.com",
      "google_news_url": "https://news.google.com/rss/articles/CBMirwFBVV95cUxNODZ3djBBc0dFbnhMb2N…",
      "published_at": "2026-10-19T12:00:00.000Z"
    }
  ]
}

Response fields

Every field of a successful response. [] marks a list: a[].b is the b of each item in a. nullable fields can be null; optional fields can be missing.

Caching and freshness

Responses are cached for up to 10 minutes, so a repeat call within that window can return the same data. It still costs 1 credit.

Errors

Errors return { success: false, error, code, docs } with the HTTP status below. Validation errors, 401/402/429 rejections and 5xx failures are free; not_found is charged (how charging works). All error codes.

Use it in Claude

Once LurkAPI is connected to Claude, this endpoint is the google_news tool. Ask in plain English, for example:

Use LurkAPI's google_news with query "nvidia" and summarize what you find.

Claude calls google_news with arguments like these, and each call costs 1 credit:

{
  "query": "nvidia"
}

Tool results are compact to save tokens: no nulls or empty lists, one URL per image or video, transcripts as plain text unless you pass timestamps=true. A result over 45,000 characters comes in parts: its _note gives the offset for the rest, and later parts are free for 15 minutes. trim=false returns the full response.