Extract Website Intelligence & Classify Ecommerce URLs with Gemini & Firecrawl to Google Sheets

Go to Workflow
0 views
Built by Dinakar Selvakumar Dinakar Selvakumar
Created on June 07, 2026

Description

Description

This n8n template automates website analysis and ecommerce URL classification using AI. It scrapes a website, extracts business intelligence, maps all internal pages, and categorises them into products, categories, or non-commerce pages. All outputs are saved in Google Sheets for easy access.

Use cases

Lead enrichment for sales and marketing teams
Ecommerce product & category discovery
Competitor website analysis
Website audits and content mapping
Market and industry research

How it works

A user submits a website URL via an n8n form.
The homepage is scraped and cleaned.
AI extracts company insights (value proposition, industry, audience, B2B/B2C).
Firecrawl maps all internal URLs.
URLs are enriched with metadata.
AI classifies each URL as product, category, or other.
Results are written into structured Google Sheets tabs.

How to use

Import the workflow into n8n.
Connect Google Sheets, Firecrawl, and AI credentials.
Update the Google Sheets document links.
Open the form URL and submit a website.
Let the workflow run and review the results in Sheets.

Requirements

n8n (self-hosted or cloud)
Firecrawl API key
Google Gemini or compatible LLM credentials
Google Sheets account

Customising this workflow

Change AI prompts to match your niche (SaaS, ecommerce, services).
Add filters to exclude unwanted URLs (blogs, legal pages, etc.).
Extend Sheets with scoring, tagging, or lead qualification logic.
Replace the LLM with another supported model if needed.

What this template demonstrates

End-to-end website intelligence extraction
Safe, rule-based AI classification (no hallucinations)
Scalable URL processing with batching
Clean data pipelines into Google Sheets
Practical AI usage for real business workflows

This template is designed to work out-of-the-box for website intelligence, ecommerce mapping, and lead research.

Feel free to reach out for custom implementation or enhancements:

📧 Email: @[email protected]

Nodes Used (4)

Code
n8n-nodes-base.code
Google Gemini
@n8n/n8n-nodes-langchain.googleGemini
Google Sheets
n8n-nodes-base.googleSheets
HTTP Request
n8n-nodes-base.httpRequest