Data extraction and transformation from web pages to structured content

• Automate content extraction from multiple web pages for marketing analysis
• Transform HTML content into markdown format for easier readability
• Extract links and metadata for SEO purposes
• Batch process URLs to optimize data retrieval and reduce server load

Initiate the workflow with a manual trigger Wait for a specified duration before processing URLs Retrieve URLs from a connected data source Split the URLs into manageable batches for processing Send requests to extract markdown content and links from each URL Store the retrieved data in a structured format for further use

1. 1
   Import the workflow template into your n8n instance
2. 2
   Connect your data source containing the URLs to the 'Get urls from own data source' node
3. 3
   Update the authorization token in the HTTP request node
4. 4
   Configure the output settings to your preferred data storage solution
5. 5
   Test the workflow by triggering it manually