n8n SEO FAQ Generator for Websites using GPT-5 Nano and Google Sheets

This n8n workflow automates the generation of SEO-optimized FAQ content for websites. It leverages a Google Sheet as the input source for website URLs and an OpenAI model (presumably GPT-5 Nano, as hinted by the directory name) to generate relevant questions and answers. The generated content is then written back to the Google Sheet.

What it does

This workflow streamlines the process of creating FAQ content by:

1. Triggering the workflow: The workflow can be executed manually or on a schedule.
2. Reading website URLs from Google Sheets: It fetches a list of website URLs from a specified Google Sheet.
3. Limiting processing: It limits the number of URLs processed in a single run (currently set to 1).
4. Looping through URLs: For each URL, it performs the following steps:
   • Fetching website content: It makes an HTTP request to the URL to retrieve the website's content.
   • Parsing XML content (if applicable): If the fetched content is XML, it parses it.
   • Extracting relevant text: It uses a Code node to extract specific text content from the website's HTML, focusing on paragraphs and headings, and cleans it up.
   • Generating FAQs with OpenAI: It sends the extracted website content to OpenAI to generate a list of 5 frequently asked questions and their answers in JSON format.
   • Parsing OpenAI response: It parses the JSON response from OpenAI to extract the generated FAQs.
   • Structuring FAQ data: It uses a Code node to format the generated questions and answers into a structured format suitable for Google Sheets.
   • Writing FAQs back to Google Sheets: It appends the generated FAQs (questions and answers) to the same Google Sheet, marking the original URL as "processed".
5. Handling errors: If any step encounters an error, the workflow stops and reports the error.
6. Sending email notifications (optional/placeholder): A Gmail node is present, suggesting the possibility of sending email notifications, though its exact configuration for this purpose is not fully defined in the provided JSON.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n instance: A running n8n instance to import and execute the workflow.
• Google Sheets Account: Access to a Google Sheet with a list of website URLs. The workflow expects a sheet named "FAQ" with columns for URL, Question, Answer, and Status.
• OpenAI API Key: An OpenAI API key with access to the GPT model used for content generation.
• Gmail Account (optional): If you intend to use the Gmail node for notifications, a configured Gmail credential.

Setup/Usage

1. Import the workflow:
   • Copy the provided JSON content.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the "Import from JSON" button and paste the copied JSON.
2. Configure Credentials:
   • Google Sheets: Set up a Google Sheets credential. Ensure it has read/write access to the spreadsheet you'll be using.
   • OpenAI: Set up an OpenAI credential with your API key.
   • Gmail (optional): If you plan to use the Gmail node, configure a Gmail credential.
3. Prepare your Google Sheet:
   • Create a new Google Sheet (or use an existing one).
   • Rename the first sheet to "FAQ".
   • Add the following header columns in the first row: URL, Question, Answer, Status.
   • Populate the URL column with the website URLs for which you want to generate FAQs. Leave Question, Answer, and Status blank initially.
4. Activate the workflow:
   • Enable the workflow in n8n.
   • You can execute it manually by clicking "Execute Workflow" or configure the "Schedule Trigger" node to run at a specific interval.
5. Monitor the output: The generated FAQs will be appended to your Google Sheet, and the Status column for processed URLs will be updated.

Note: The workflow currently processes one URL at a time due to the "Limit" node being set to 1. Adjust this value if you wish to process more URLs concurrently. The "Code" nodes contain JavaScript logic for extracting and formatting data, which you might need to adjust based on the specific structure of the websites you are targeting or the desired output format.