What you build: a no-code workflow that scrapes a web page (or a list of pages) and saves the cleaned content to a spreadsheet.
Who it is for: anyone who copies information off websites by hand. No code.
Time: about 10 minutes.
Free build prompt: it is yours when you join the free daily Beginners in AI newsletter.
Copying details off web pages into a spreadsheet is the kind of dull job worth automating once and forgetting. So here is a simple Gumloop workflow that scrapes a page and saves what matters, which you can point at one URL or a whole list.
What will you build?
A web scraping workflow. You give it a URL, it pulls the page content, an AI step cleans it down to the fields you want, and the result lands in a Google Sheet. Feed it a list and it scrapes them all.
What do you need to start?
- A free Gumloop account.
- A URL (or a sheet of URLs) to scrape.
- A Google Sheet to write results to, if you want them saved.
How does it work?
Four nodes in a line, the AI step doing the tidying.
| Node | What it does |
|---|---|
| Input | The URL you paste in |
| Website Scraper | Pulls the page content |
| Ask AI | Cleans it to the fields you want |
| Output | Returns or saves the result |
How do you build it, step by step?
Start a New Workflow and type:
Take a URL, scrape the page content, use AI to pull out the title,
price, and description, and save them as a row in a Google Sheet.How do you set the model to Claude?
Open the AI step or agent and pick the model. For careful work I use Claude 4.8 Opus, the “Smartest” option; a faster model saves credits on simple runs.
How do you run it?
Click Run and paste a URL, or connect a sheet of URLs to scrape them in one go. Check the first few results, then let it work through the list.
Want this scraper without building it?
Grab the free build prompt for this workflow. Subscribe to the daily newsletter and it is waiting on the thank-you page. Paste it into Gumloop and run.
A working AI automation you can copy, every morning
Free daily newsletter. Built for people who want to use AI well, not chase every model.
Free forever. Unsubscribe anytime.
What can go wrong?
- Blocked sites. Some pages block scrapers. Test on a normal page first.
- Wrong fields. Name exactly what you want in the prompt, or you get too much. Be specific.
- Respect the rules. Scrape public pages and follow each site’s terms. The AI Automation hub has more.
Common questions
Do I need to code a scraper?
No. The Website Scraper node does the pulling, and you describe what to keep in plain English.
Can it scrape many pages?
Yes. Feed a list of URLs from a sheet and it works through them.
Where do results go?
Wherever you point the output: back to you, or saved as rows in a Google Sheet.
Is scraping allowed?
Stick to public pages and follow each site’s terms of use. Do not scrape behind logins you should not.
Does it use Claude?
The cleaning step can. Claude 4.8 Opus is the “Smartest” model option.
Sources
Last reviewed: June 2026. Gumloop changes often; check the official docs above if a button has moved.
You may also like
- AI Automation for Beginners (the hub)
- How to use Claude AI
- The AI Tools Directory
- Start Here: the beginner path
- The AI Glossary
- The daily Beginners in AI newsletter
Want a head start? Book a 2-hour live AI crash course
A private, beginner-friendly session across Claude, ChatGPT, Gemini, Grok, and the wider landscape. Walk away knowing which tools fit your work and how to use them.
Book the 2-hour crash course · $125 →