Quick Overview
This workflow collects a university homepage URL and a target field, country, and degree level, then uses Firecrawl to verify the official site, find and validate a matching program page and faculty/staff directory URL on the same domain, and logs the outcome to Google Sheets.
How it works
- Receives submissions from an n8n form with the university homepage URL, target field, country, and degree level.
- Normalizes the homepage URL, extracts the official domain, and validates that all required inputs are present.
- Uses Firecrawl Scrape to analyze the homepage and confirm it is an official degree-granting university site in the selected country.
- Uses Firecrawl Search to query the official domain for program/department pages, then deduplicates and ranks candidates to pick the best match.
- Uses Firecrawl Scrape to extract content from the best candidate page and verifies the target field and requested degree level appear in the page evidence.
- Uses Firecrawl Search to find and score a faculty/staff directory page on the same official domain and selects the best directory URL.
- Appends either a verified result (program URL + faculty source URL) or a failure status to a Google Sheets spreadsheet.
Setup
- Create a Firecrawl API credential using HTTP Header Auth and ensure it can access the Firecrawl Scrape and Search endpoints.
- Connect Google Sheets OAuth credentials and select the target spreadsheet and worksheet used to append results.
- Ensure the Google Sheet has columns for University Name, Target Field, Degree, Country, Program URL, Faculty Source URL, and Status.
- Enable the form trigger and share the generated form link with users who will submit discovery requests.