Amazon Product Data Scraping using AI to Google Sheets - n8n Workflow

Market Researchers: Individuals needing continuous, structured data feeds on competitor products or pricing.
E-commerce Analysts: Users who want to track changes in product URLs, titles, and categories on Amazon.
Automation Enthusiasts: Those looking for advanced n8n templates combining scheduling, AI, custom code, and Google services.
Data Engineers: Professionals seeking a robust, scheduled n8n trigger mechanism for web data extraction projects.

Keeping track of products and pricing on massive platforms like Amazon requires continuous monitoring, which manual methods cannot sustain. This innovative n8n workflow solves this by utilizing advanced AI scraping technology (ScrapeGraphAI) combined with the reliability of n8n. The core value of this n8n template is its ability to handle complex website structures like Amazon, extracting key product details—such as titles, URLs, and categories—using natural language prompts, and delivering clean, ready-to-analyze data straight to Google Sheets. This automation runs on an automated n8n trigger, ensuring your data is always fresh, making this a highly valuable addition to your suite of n8n templates.

This comprehensive n8n workflow operates in four distinct phases:

1. Scheduled Execution (n8n Trigger): The process begins with the Automated Schedule Trigger n8n node, which initiates the entire n8n workflow based on a predefined schedule (e.g., daily or hourly). This ensures continuous data capture.


2. AI Data Extraction: The workflow proceeds to the AI-Powered Amazon Product Scraper n8n node. This uses the ScrapeGraphAI integration to navigate the specified Amazon search URL (for 'keyboard' products) and intelligently scrape the desired data fields (title, url, category) based on a natural language prompt.


3. Data Cleaning and Formatting: The raw JSON output from the AI is passed to the Data Formatting and Processing custom Code n8n node. This essential step filters the result, extracting the specific array of products and mapping them into a standardized, clean format suitable for spreadsheet rows. This ensures compatibility before saving.


4. Storage: Finally, the cleaned data is sent to the Google Sheets Data Storage n8n node. Configured to the 'Append' operation, this node safely adds all the newly scraped product entries as new rows in your target Google Sheet document, completing the automated n8n workflow cycle.

To deploy this powerful n8n workflow template, follow these steps:

1. Import the JSON: Copy the provided JSON code and import it directly into your n8n instance via the Workflows section. This installs the core n8n workflow structure.


2. Set up ScrapeGraphAI Credentials: Select the AI-Powered Amazon Product Scraper n8n node. You must configure and connect your ScrapeGraphAI API credentials, as this is a community n8n node requiring an API key.


3. Set up Google Sheets Credentials: Select the Google Sheets Data Storage n8n node. Connect your Google Sheets OAuth2 API credentials. Ensure the service account has write access to the desired Google Sheet.


4. Configure Target Spreadsheet: In the Google Sheets n8n node, specify the Document ID (URL) of your desired spreadsheet and confirm the Sheet Name (e.g., 'Sheet1').


5. Activate the n8n Trigger: Review the Automated Schedule Trigger n8n node parameters and set your preferred running frequency (e.g., daily). Once configuration is complete, set the overall n8n workflow to 'Active'.

Automated Schedule Trigger (n8n Trigger):
Function: Starts the entire n8n workflow at specific, recurring times.
Key Configuration: Scheduled rule is set, allowing users to define the interval for automated execution.
AI-Powered Amazon Product Scraper (ScrapeGraphAI n8n node):
Function: The primary scraping agent. It uses an AI model to intelligently extract structured data from the complex Amazon search results page.
Key Configuration: websiteUrl is set to the Amazon keyboard search page; userPrompt provides explicit instructions on the required data schema ({title, url, category}).
Data Formatting and Processing (Code n8n node):
Function: Takes the AI's structured JSON output, extracts the nested 'products' array, and maps each item to a standardized title, url, and category object, cleaning the data for the next n8n node.
Key Configuration: Custom JavaScript ensures only the necessary fields are returned in the expected input format for Google Sheets.
Google Sheets Data Storage (Google Sheets n8n node):
Function: Connects to the user's Google Drive and appends the processed product data as new rows, maintaining a continuous record.
Key Configuration: Operation is set to 'append'; requires DocumentId (spreadsheet URL) and uses automatic column mapping for title, url, and category fields.