Automated news extraction and summarization from a website to a database

• Automate the collection of news articles from websites without RSS feeds.
• Generate summaries and keywords for news articles to enhance content discoverability.
• Store extracted news data in a structured database for easy access and analysis.

Schedule a weekly trigger to initiate the workflow. Retrieve the HTML content from the target news website. Extract article links and publication dates using CSS selectors. Filter articles from the last seven days. Fetch individual article content and generate summaries and keywords using OpenAI. Merge and format the extracted data for database storage. Store the processed data in a NocoDB database.

1. 1
   Import the workflow template into n8n.
2. 2
   Configure the OpenAI and NocoDB credentials.
3. 3
   Adjust the CSS selectors as needed for the target website.
4. 4
   Set the desired schedule for the workflow trigger.
5. 5
   Run the workflow to start extracting and storing news articles.