All projects
Data & scraping · December 2025
Employee Scraper — AI employee data collection (GPT-4)
A Python tool for automated collection of employee data from company websites using an AI agent (GPT-4). It takes a URL, extracts structured data (name, role, contacts) and exports it to Google Sheets. Available as a CLI and a Python library.
What was built:
- AI agent on agency-swarm (GPT-4) with tools: entity extraction without brittle per-site CSS selectors
- Classic page parsing: requests + BeautifulSoup, HTML cleanup, URL validation
- Output to Google Sheets (gspread + OAuth2)
- CLI (poetry run scrape) and Python API (EmployeeScraper)
- Modular architecture: the agent is decoupled from scraping and output logic
- pytest tests with a fixture page
Use cases: lead generation, recruiting, market research — saves hours of manual contact gathering.
Role: full-cycle development — architecture, AI agent, scraping, Google Sheets integration.
Project screens
Screen 1 
Screen 2 
Screen 3 
Screen 4