Automated Product Data Extraction from Webpage Screenshots

somdn_product_page

This n8n workflow automates the process of capturing full-page screenshots from specified URLs in a Google Sheet, extracting all visible data from the screenshots using Dumpling AI, and then analyzing the text with GPT-4 to identify structured product information. The workflow begins with a trigger when a new URL is added to the Google Sheet, followed by Dumpling AI capturing a screenshot and extracting visual data. The screenshot is downloaded and saved to Google Drive, while the extracted URL is logged back in the sheet. Next, GPT-4 analyzes the screenshot text to identify product details such as name, price, ratings, deals, and buying options. Each product is then split into individual records and stored in a separate Google Sheet for further analysis or reporting. This workflow is especially useful for eCommerce scraping, market research, and competitive analysis, allowing users to automate the collection and organization of product data from webpages without manual effort.

Node Count

11 – 20 Nodes

Nodes Used

@n8n/n8n-nodes-langchain.openAi, googleDrive, googleSheets, googleSheetsTrigger, httpRequest, splitOut, stickyNote

Reviews

There are no reviews yet.

Be the first to review “Automated Product Data Extraction from Webpage Screenshots”

Your email address will not be published. Required fields are marked *