Mark Kalsbeek
c6328cee46
Van Oord: postcode is in the first .elementor-heading-title on detail pages. Van Herk: postcode extracted via regex from <title> tag; also pick up kamers and energielabel from the features list which were previously ignored. Test output now includes woonoppervlak and energielabel fields. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
27 lines
754 B
Python
27 lines
754 B
Python
import sys
|
|
|
|
sys.path.insert(0, "../src")
|
|
|
|
import logging
|
|
|
|
from cache import * # noqa: F401 — must be before adapter imports
|
|
|
|
from adapters import SCRAPERS
|
|
|
|
logging.basicConfig(
|
|
stream=sys.stdout,
|
|
level=logging.INFO, # debug costs too many tokens
|
|
format="%(asctime)s %(levelname)s %(name)s — %(message)s",
|
|
datefmt="%Y-%m-%dT%H:%M:%S",
|
|
)
|
|
|
|
# --- change this to test a different adapter ---
|
|
ADAPTER = SCRAPERS['post']
|
|
|
|
if __name__ == "__main__":
|
|
print(f"Testing adapter: {ADAPTER.__name__}")
|
|
listings = ADAPTER()
|
|
print(f"Got {len(listings)} listings\n")
|
|
for l in listings:
|
|
print(f" {l.adres}, {l.postcode}, {l.stad} — €{l.prijs} — {l.kamers} rooms — {l.woonoppervlak}m2 — {l.energielabel} — {l.url}")
|