add scrapers: Van Daal (API), Van Silfhout (SSR) for Delft

- fetch_vandaal: OG Online API, covers Delft/Rijswijk/Den Haag area,
  includes is_bought→verkocht status mapping
- fetch_vansilfhout: HTML scraper, all listings on single page,
  extracts postcode from embedded JS variable (objectZipcode)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-04 21:39:02 +02:00
parent c92ddb5812
commit d310a7a560
4 changed files with 210 additions and 3 deletions

View File

@@ -244,6 +244,69 @@ def fetch_moerman() -> list[RawListing]:
return listings
# ---------------------------------------------------------------------------
# Van Daal Makelaardij (Delft)
# ---------------------------------------------------------------------------
# OG Online / realtime-listings platform.
_VANDAAL_BASE = "https://www.vandaalmakelaardij.nl"
_VANDAAL_SKIP = {"rented", "rented_ur"}
_VANDAAL_STATUS_MAP = {
"available": "beschikbaar",
"under_bid": "onder_bod",
"under_option": "onder_bod",
"is_bought": "verkocht",
"sold": "verkocht",
"sold_ur": "verkocht",
}
def fetch_vandaal() -> list[RawListing]:
data = fetch_json(
f"{_VANDAAL_BASE}/nl/realtime-listings/consumer",
headers={"X-Requested-With": "XMLHttpRequest"},
)
listings = []
for item in data:
if not item.get("isSales"):
continue
if item.get("statusOrig") in _VANDAAL_SKIP:
continue
if item.get("salesPrice", 0) > config.MAX_PRICE:
continue
postcode = (item.get("zipcode") or "").replace(" ", "") or None
perceel = item.get("plotSurface") or None
if perceel == 0:
perceel = None
raw_year = item.get("dateOfConstruction") or ""
bouwjaar = int(raw_year) if raw_year.isdigit() else None
listings.append(RawListing(
url=_VANDAAL_BASE + item["url"],
source_makelaar="vandaal",
status=_VANDAAL_STATUS_MAP.get(item.get("statusOrig", ""), "beschikbaar"),
adres=item.get("address") or None,
postcode=postcode,
stad=item.get("city") or None,
prijs=item.get("salesPrice") or None,
woningtype=item.get("type") or None,
woonoppervlak=item.get("livingSurface") or None,
perceeloppervlak=perceel,
kamers=item.get("rooms") or None,
slaapkamers=item.get("bedrooms") or None,
bouwjaar=bouwjaar,
energielabel=item.get("energyLabel") or None,
hero_image_url=item.get("photo") or None,
))
log.info("vandaal: %d koopwoningen opgehaald", len(listings))
return listings
# ---------------------------------------------------------------------------
# SCRAPERS — exporteer hier alle actieve API adapters
# ---------------------------------------------------------------------------
@@ -252,4 +315,5 @@ SCRAPERS = {
'bjornd': fetch_bjornd,
'ooms': fetch_ooms,
'moerman': fetch_moerman,
'vandaal': fetch_vandaal,
}