A powerful automated tool for extracting real-time news articles, metadata, and full-text content from Google News across various regions and languages.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install apify-google-news
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install apify-google-news using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Google News Scraper?
The Google News Scraper is a specialized skill designed to bridge the gap between raw news feeds and actionable data. By integrating this capability through Openclaw Skills, users can programmatically search and extract news articles including their full content, enriched descriptions, and comprehensive metadata. This tool eliminates the complexity of manual scraping by providing a structured API-driven approach to monitoring global headlines.
Built on the Apify platform, this skill supports granular filtering by region and language, making it an essential asset for developers building news aggregators, sentiment analysis tools, or automated research agents. It handles the heavy lifting of navigating Google News search results and extracting clean, readable text from diverse source websites.
Google News Scraper Use Cases
- Monitoring real-time industry trends and brand mentions for competitive intelligence.
- Automating the creation of localized news digests for specific geographic regions.
- Gathering high-quality textual data for training or fine-tuning NLP and LLM models.
- Tracking the spread of specific news topics across different languages and timeframes.
How Google News Scraper Works
- Initialize the process by sending a POST request with your search queries and filter parameters to start an asynchronous run.
- Poll the execution status using the unique run ID until the scraper marks the task as succeeded.
- Retrieve the final dataset in JSON format, containing all scraped articles and their associated metadata.
Google News Scraper Setup
To use this skill, you must first obtain an API token from the Apify platform and configure your environment.
# Set your API token in the environment
export APIFY_API_TOKEN='your_apify_api_token'
# Example of starting a run via curl
curl -X POST "https://api.apify.com/v2/acts/futurizerush~google-news-scraper/runs?token=$APIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"searchQueries": ["AI"], "region": "us", "language": "en"}'
Google News Scraper Data Schema & Taxonomy
The skill returns a structured JSON array where each item represents a news article. Key fields include:
| Field | Description |
|---|---|
title |
The headline of the news article. |
articleUrl |
The direct URL to the full article on the publisher's site. |
source |
The name of the news organization. |
pubDate |
The publication date string. |
articleContent |
Object containing content (up to 2000 chars) and token counts. |
enrichedDescription |
A cleaned summary of the article content. |
timestamp |
ISO 8601 formatted date for easy parsing. |
Google News Scraper Advanced Features
- Temporal filtering using the dateFilter parameter to capture news from the last hour, day, week, or month.
- Multi-query support allowing for the extraction of several distinct topics in a single execution cycle.
- Deep content extraction providing up to 2000 characters of the article body for immediate analysis.
- Regional and language localization supporting codes like 'tw' for Taiwan and 'zh-TW' for Traditional Chinese.
- Automated token counting for article content to assist with LLM context window management.
SKILL.md
Loading
Related Openclaw Skills
Google Maps Scraper
A powerful automation skill for extracting comprehensive business data and contact information directly from Google Maps.
Feishu Sheet Reader
An automated data extraction tool that reads and processes Feishu spreadsheet content via the Feishu API.
YouTube Email Scraper
An automated tool to extract email addresses and contact information from YouTube channels by keywords or direct URLs.
Threads Replies Scraper
A high-performance scraping tool for extracting public replies, comments, and engagement metrics from Meta Threads posts without requiring a login.
Threads Scraper
A powerful data extraction tool for Meta Threads that allows users to scrape posts, monitor hashtags, and analyze engagement metrics without requiring an account login.
AI GIF Compressor
An AI-powered optimization tool that converts and compresses heavy GIF, MP4, and WebM files into lightweight, web-ready MP4s using cloud GPU acceleration.
Featured*
