AI News Extractor & Summarizer Agent

Unlock Automated News Intelligence with this AI Agent

This AI Agent empowers you to stay ahead of the curve without the manual grind. It demonstrates powerful abilities in automated web scraping, designed to monitor specific news websites (even those without RSS feeds). Leveraging OpenAI's GPT-4, it intelligently processes extracted articles, showcasing its skills in content summarization and technical keyword identification. Finally, it automatically archives this curated intelligence into your NocoDB database or any other system you connect. Perfect for busy professionals who need to distill news efficiently.

Key Features & Benefits

• Scheduled Web Scraping: Automatically fetches news from your target website(s) on a customizable schedule (e.g., weekly).
• Recency Filtering: Focuses only on the latest articles published within a defined period (e.g., last 7 days).
• AI-Powered Summarization: Utilizes OpenAI (GPT-4) for its summarization ability, creating brief, easy-to-digest summaries of each article, saving you reading time.
• Intelligent Keyword Extraction: Employs OpenAI's keyword extraction ability to identify and list the most relevant technical keywords from article content, aiding in trend analysis and content strategy.
• Automated Data Archiving: Seamlessly stores extracted titles, links, dates, AI-generated summaries, and keywords into a NocoDB database or your chosen destination.
• Customizable & Extensible: Easily adapt CSS selectors for different websites and integrate with various other n8n nodes for further actions.
• Time-Saving Automation: Frees you from manual news checking and data compilation, allowing you to focus on strategic tasks.

• An n8n instance (Cloud or self-hosted).
• OpenAI API Key with access to a GPT-4 model (e.g., gpt-4-1106-preview or newer).
• NocoDB instance and API token (or credentials for your chosen database/destination).
• Basic understanding of CSS selectors for adapting to different website structures.

1. Download the n8n workflow JSON file.
2. Import the workflow into your n8n instance.
3. Configure the 'Schedule Trigger each week' node for your desired monitoring frequency.
4. In the 'Retrieve the web page for further processsing' HTTP Request node, update the URL to your target news site.
5. Crucially, adjust the CSS selectors in the 'Extract the HTML with the right css class', 'Extract date', and 'Extract individual posts' HTML nodes to match the structure of your target website. Use browser developer tools to identify the correct selectors.
6. In the 'Summary' and 'Keywords' OpenAI nodes, select your configured OpenAI API credential. Review and customize the prompts if needed to refine the AI's output.
7. Configure the 'NocoDB news database' node with your NocoDB instance URL, API token, Project ID, and Table ID. Map the fields according to your database schema. Alternatively, replace this node with your preferred data storage solution (e.g., Google Sheets, Airtable, Email).
8. Review the JavaScript code in the 'Select posts of last 7 days' node to adjust the article lookback period if necessary (ensure it aligns with your schedule trigger frequency).
9. Test the workflow with a single execution to ensure all nodes are configured correctly.
10. Activate the workflow for ongoing automated news extraction and AI processing.