Scrape books from URL with Dumpling AI, clean HTML, save to Sheets, email as CSV
n8n8 modulesv1.0Who is this for? This workflow is ideal for virtual assistants, researchers, developers, automation specialists, and data analysts who need to regularly extract and organize structured product information (like books) from a website. It’s especially useful for those working with catalog-based websites who want to automate extraction and delivery of clean, sorted data. --- 🧩 What problem is this solving? Manually copying product listings like book titles and prices from a website into a spreadshe
At a glance
Scrape books from URL with Dumpling AI, clean HTML, save to Sheets, email as CSV is a ready-made n8n workflow you import as a workflow JSON file — no build required. It connects Gmail, Slack, Google Sheets, Google Drive. It's free to download. Follow the 5-step import below to go live in minutes.
- Platform
- n8n
- Connects
- Gmail, Slack, Google Sheets, Google Drive, Dropbox
- Modules
- 8
- Price
- Free
- Version
- v1.0
About this workflow
Who is this for? This workflow is ideal for virtual assistants, researchers, developers, automation specialists, and data analysts who need to regularly extract and organize structured product information (like books) from a website. It’s especially useful for those working with catalog-based websites who want to automate extraction and delivery of clean, sorted data. --- 🧩 What problem is this solving? Manually copying product listings like book titles and prices from a website into a spreadsheet is slow and repetitive. This automation solves that problem by scraping content using Dumpling AI, extracting the right data using CSS selectors, and formatting it into a clean CSV file that is sent to your email—all triggered automatically when a new URL is added to Google Sheets. --- ⚙️ What this workflow does This template automates an entire content scraping and delivery process: - Watches a Google Sheet for new URLs - Scrapes the HTML content of the given webpage using Dumpling AI - Uses CSS selectors in the HTML node to extract each book from the page - Splits the HTML array into individual items - Extracts the book title and price from each HTML block - Sorts the books in descending order based on price - Converts the sorted data to a CSV file - Sends the CSV via email using Gmail --- 🛠️ Setup 1. Google Sheets - Create a sheet titled something like URLs - Add your product listing URLs (e.g., - Connect the Google Sheets trigger node to your sheet - Ensure you have proper credentials connected 2. Dumpling AI - Create an account at Dumpling AI - Generate your API key - Set the HTTP Method to POST and pass the URL dynamically from the Google Sheet - Use Header Auth to include your API key in the request header - Make sure "cleaned": "True" is included in the body for optimized HTML output 3. HTML Node - The first HTML node extracts the main book container blocks using: .row > li - The second HTML node parses out the individual fields: - title: h3 > a (via the title attribute) - price: .pricecolor 4. Sort Node - Sorts books by price in descending order - Note: price is extracted as a string, ensure it's parsable if you plan to use numeric filtering later 5. Convert to CSV - The JSON data is passed into a Convert node and transformed into a CSV file 6. Gmail - Sends the CSV as an attachment to a designated email --- 🔄 How to customize this workflow - Extract more data: Add more CSS selectors in the second HTML node to pull fields like author, availability, or product links - Switch destinations: Replace Gmail with Slack, Google Drive, Dropbox, or another platform - Adjust sorting: Sort alphabetically or based on another extracted value - Use a different source: As long as the site structure is consistent, this can scrape any listing-like page - Trigger differently: Use a webhook, form submission, or schedule trigger instead of Google Sheets --- ⚠️ Dependencies and Notes - This workflow uses Dumpling AI to perform the web scraping. This requires an API key and uses credits per request. - The HTML node depends on valid CSS selectors. If the site layout changes, the selectors may need to be updated. - Ensure you’re not scraping content from websites that prohibit automated scraping.
How to import this n8n workflow
- 1
Download the workflow JSON file after purchase.
- 2
Open n8n → click the menu → Import from File.
- 3
Select the downloaded JSON and import.
- 4
Set up credentials for each node that requires them.
- 5
Click Execute Workflow to test, then activate.
Setup guide
Setup guide included
Purchase to unlock the full step-by-step guide
Related N8n workflows
Save new Quaderno invoices to Dropbox
Find local GMB leads with 1-star reviews using Apify and Google Sheets
Send leads to Google Sheets and to your iOS device for new Facebook Lead Ads leads
Research Kuaishou creator videos from a keyword with JustOneAPI
Automated stock analysis reports with technical & news sentiment using GPT-4o
✍️ AI agent to create Linkedin posts for blog promotion with GPT-4o
Automated book summarization with DeepSeek AI, Qdrant Vector DB & Google Drive
YouTube Videos to Viral X Threads by Keywords (using Gemini & Claude)
Reviews
No reviews yet
Be the first to buy and share your experience.
Leave a review
Sign in to share your experience with this workflow.
Create a free account to purchase workflows.
- JSON blueprint — instant download
- Setup guide PDF included
- 5 downloads · valid 30 days
- Works with n8n
Need help setting this up?
Book a 3-hour live setup session with an Agility consultant.
- Configure live on Google Meet / Zoom
- Free follow-up if workflow has defects
- Platform expert assigned to you