DeltaForceOS Beginner Curriculum
/ LESSON 06 · 50m

Beginner Web Scraper Agent

/ Curriculum notes

This lesson is available as written curriculum now. Use the notes below with the matching PDF workbook in the resources library.

Collect clean data without turning scraping into chaos Workbook: /resources/web-scraper-agent.pdf Codex route: /resources/web-scraper-agent-codex-build-guide.pdf Claude Code route: /resources/web-scraper-agent-claude-code-build-guide.pdf

/ Choose your build route

Build this lesson inside Codex

Open the repo in Codex, let it inspect the files, then paste the prompt. Ask it to edit only the smallest set of files and verify before you deploy.

Before Codex
1. Open the project in Codex.
2. Confirm .env.local exists locally and is ignored by Git.
3. Open README.md and package.json so Codex can orient itself.
4. Do not paste private keys into the prompt.
Paste this prompt
Inspect this repo for the Beginner Web Scraper Agent build.

Outcome:
Build a scraper that reads pages, extracts structured data, dedupes results, and fails safely.

Tools:
Firecrawl, Playwright, Supabase, OpenAI, Python, Lighthouse, Vercel

Explain the files a beginner needs to understand before editing:
README.md, package.json, src, public, scripts, .env.local, and any Supabase files.

Then implement the smallest safe version, list required env names, run the build or focused tests, fix failures, and summarize changed files.

/ Transcript

Beginner Web Scraper Agent Outcome: Build a scraper that reads pages, extracts structured data, dedupes results, and fails safely. Tools: Firecrawl, Playwright, Supabase, OpenAI, Python, Lighthouse, Vercel Workbook: /resources/web-scraper-agent.pdf Codex route PDF: /resources/web-scraper-agent-codex-build-guide.pdf Claude Code route PDF: /resources/web-scraper-agent-claude-code-build-guide.pdf Build assignment: Scrape five public websites and produce one structured audit row per site. Use the lesson tabs to choose Codex or Claude Code, then post the proof in Skool.