Automation library · Data collection

Web site scraper for LLMs with Airtop

Started by someone submitting a form, and works across Google Docs and Google Sheets. 18 steps, 1 branch: a working afternoon to understand properly.

Medium

18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 2Logic 5Service 11

The steps in the order they run, from what starts it.

  1. 1On form submissionForm triggerStarts it
  2. 2When Executed by Another WorkflowExecute Workflow triggerStarts it
  3. 3Unify paramsSetLogic
  4. 4Create SpreadsheetGoogle SheetsService
  5. 5Info to upload into spreadsheetSetLogic
  6. 6Load info to spreadsheetGoogle SheetsService
  7. 7Scrape webpageAirtopService
  8. 8Create Google DocsGoogle DocsService
  9. 9Write scraped contentGoogle DocsService
  10. 10Should scrape more?IfLogic
  11. 11Read scraped webpagesGoogle SheetsService
  12. 12Retrieve links to scrapeAirtopService
  13. 13Filter links to insert to SheetsCodeLogic
  14. 14Insert new linksGoogle SheetsService
  15. 15Scrape webpage1AirtopService
  16. 16Update with new scraped contentGoogle DocsService
  17. 17Flag scraped linkSetLogic
  18. 18Insert flagGoogle SheetsService

How it's built

Starts on
Someone submitting a form
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
Google Docs, Google Sheets
Model
None. This is plumbing, not judgement

Questions

What does it need to run?

An n8n account, plus your own Google Docs and Google Sheets accounts. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone submitting a form.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 18 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 18 steps before you point it at anything that matters.