Automated Product Data Extraction from Google Sheets using AI Scraper - n8n Workflow

E-commerce Analysts: Needing to quickly collect competitor pricing or product descriptions.
Marketing Teams: Compiling product catalogs from various vendor websites.
Automation Enthusiasts: Seeking practical n8n templates that combine spreadsheet operations with advanced web scraping via API.
Data Engineers: Looking for a reliable, structured web scraping solution integrated into their existing n8n node environment.

Managing vast lists of website URLs and manually extracting specific data points like product name, price, and description is time-consuming and prone to errors. This powerful n8n workflow template solves this challenge by completely automating the ingestion and extraction pipeline.

It leverages the Google Sheets n8n trigger to watch for new entries. Once a new URL is detected, it utilizes an HTTP request to send the URL to Dumpling AI, an intelligent scraping service capable of returning highly structured JSON data based on a predefined schema. This ensures that the extracted data is clean and ready for immediate use. This robust n8n workflow is perfect for scalable data collection operations, drastically reducing manual effort.

This n8n workflow operates in four main stages:

1. Triggering the Automation: The n8n trigger, configured as a Watch New Website URL in Google Sheets node, constantly monitors a specified Google Sheet for newly added rows. Each new row is expected to contain a website URL to be scraped.


2. AI-Powered Extraction: The data from the triggering row (specifically the Website column) is passed to the Extract Product Info with Dumpling AI n8n node (an HTTP Request node). This n8n node calls the Dumpling AI API, defining a structured schema requesting productName, price, review, and productDescription.


3. Itemization: The API response often contains a list of results. The Split Extracted Products n8n node is essential here, as it processes the results array, splitting the output into individual data items. This ensures that if the page yielded multiple products, each product is processed as its own row.


4. Final Data Storage: The final clean, structured data item is then passed to the Append Product Info to Google Sheets n8n node, which writes the extracted details (Product Name, Price, and Description) into a dedicated output sheet named 'product details'. This completes the automated cycle of the n8n workflow.

To use this powerful n8n workflow template, follow these setup steps:

1. Import the JSON: Copy the provided JSON code and paste it into your self-hosted or cloud n8n instance.


2. Google Sheets Credentials (Trigger): Set up a Google Sheets Trigger credential. In the Watch New Website URL in Google Sheets n8n trigger node, connect your account and specify the spreadsheet and sheet name where you will be adding the source website URLs.


3. Google Sheets Credentials (Output): Set up a standard Google Sheets OAuth2 credential for the final Append Product Info to Google Sheets n8n node. Ensure the target sheet (product details) exists and has columns matching the extracted fields (productName, price, etc.).


4. Dumpling AI Credentials: This n8n workflow requires an API key for Dumpling AI. Create an 'HTTP Header Auth' credential in n8n. This credential must contain the API key required to successfully execute the HTTP Request n8n node.


5. Activation: Once credentials and document IDs are set, activate the n8n workflow. It will now run on the schedule set by the n8n trigger.

Watch New Website URL in Google Sheets (Google Sheets Trigger):
Function: Serves as the primary n8n trigger, initiating the process when a new row (containing a website URL) is detected in the source sheet.
Key Configuration: Monitors for the rowAdded event. Polling is set to 'every minute'.

Extract Product Info with Dumpling AI (HTTP Request):
Function: Executes the AI scraping logic. It sends the input URL to the Dumpling AI extraction endpoint.
Key Configuration: Uses a POST method. The jsonBody explicitly defines the desired structured output schema for product fields (productName, price, productDescription).

Split Extracted Products (Split Out):
Function: Ensures data cleanliness by taking the potentially complex array output from the AI scraper and splitting it so that each extracted product becomes an individual item in the n8n workflow stream.
Key Configuration: Splits the data based on the results field.

Append Product Info to Google Sheets (Google Sheets):
Function: The final action n8n node, writing the cleaned, structured product data back into the dedicated 'product details' sheet.
Key Configuration: Operation set to append. Data fields are mapped using expressions like ={{ $json.price }} to ensure the correct values are inserted into the columns.