"""Scraper layer for the yunke data-mirror system.

Scrapers sit between the session layer (:mod:`app.session.yunke_client`) and
the persistence layer (a LATER task). Each scraper is an async generator that
walks one upstream list endpoint and yields **normalized dicts** —
snake_case keys matching the target ORM model columns, plus a ``raw_json`` key
holding the original upstream record verbatim.

Persistence (upsert into ORM tables) is intentionally out of scope here: it is
Task 1.7. Keeping scrapers pure producers lets us test ingestion logic against
``respx`` fixtures without a database.
"""