WISE Scraper

WISE teaches an AI coding agent structured, repeatable web scraping for JS-rendered sites. The goal is a working scraping project built from shipped WISE assets.

Rule 0 — Orient before acting. Before opening a browser or writing any code, read references/guide.md § Big Picture to understand what you're building and what decisions you need to make. Only then start exploration.

Orient → Explore → Evidence → Choose tier → Exploit → JSONL → Assemble

1. Orient — read the schema, templates, and runner options; understand what's shipped
2. Explore — inspect the live site with agent-browser, test selectors, map navigation
3. Evidence — record selector proof and DOM observations before designing the exploit
4. Choose tier — prefer shipped plumbing, escalate only when justified; ask about runtime preference if unclear
5. Exploit — assemble a profile from template fragments, run it, extend with hooks or task-local code
6. Process — JSONL is the intermediate truth; assemble markdown/CSV/JSON later

Use when: JS-rendered sites, pagination, UI state, filter combos, structured repeatable output. Not when: a stable API/export exists, or static curl is clearly enough.