Skip to content

Added fall-back to address for missing numbers #128

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wtfloris merged 5 commits into from
Mar 26, 2026
+25 −22
Merged

Added fall-back to address for missing numbers #128

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
32cd9af
Added fall-back to address for missing numbers
RobertoRoos Mar 11, 2026
ae41152
Fixed test + address fallthrough
RobertoRoos Mar 11, 2026
1637300
Also added new address method to Funda
RobertoRoos Mar 11, 2026
fa1cec4
Also did Vesteda for new address method
RobertoRoos Mar 11, 2026
4da9d0e
Reverted most changed back compared to master
RobertoRoos Mar 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 23 additions & 21 deletions hestia/hestia_utils/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ def address(self) -> str:
@address.setter
def address(self, address: str) -> None:
self._address = address

@property
def city(self) -> str:
return self._parsed_city
Expand Down Expand Up @@ -430,17 +430,30 @@ def parse_pararius(self, r: requests.models.Response):
continue
if re.search(r"^[0-9]", address_raw): # Filter "1e Foobarstraat 5", etc.
continue
if not re.search(r"[0-9]", address_raw):

price_text = price_main.get_text(" ", strip=True).replace("\xa0", " ")
# If unable to cast to int, the price is not available so skip the listing
try:
m = re.search(r"(\d[\d\.,]*)", price_text)
if not m:
continue
home.price = int(m.group(1).replace(".", "").replace(",", ""))
except Exception:
continue

# Most Pararius titles are prefixed with a property type; strip when present.
parts = address_raw.split()
if parts and parts[0].lower() in {"appartement", "huis", "studio", "kamer", "woning", "woonhuis", "flat", "house", "room", "apartment"}:
address = " ".join(parts[1:]).strip()
else:
address = address_raw.strip()
ignored = {"appartement", "huis", "studio", "kamer", "woning", "woonhuis", "flat", "house", "room", "apartment"}
address = address_raw.strip()
first, _, address_rest = address.partition(" ")
if first.lower() in ignored:
address = address_rest

if not re.search(r"[0-9]", address):
continue
# Quite a lot of listings on Pararius don't include the house number
# Instead of skipping them, just rely on the amount of rent
# This will still distinguish most houses in the database
address += f" [€{home.price}]"

home.address = address

city_raw = subtitle.get_text(" ", strip=True)
Expand All @@ -453,17 +466,6 @@ def parse_pararius(self, r: requests.models.Response):
continue
home.url = ("https://www.pararius.com" + href) if href.startswith("/") else href

price_text = price_main.get_text(" ", strip=True).replace("\xa0", " ")

# If unable to cast to int, the price is not available so skip the listing
try:
m = re.search(r"(\d[\d\.,]*)", price_text)
if not m:
continue
home.price = int(m.group(1).replace(".", "").replace(",", ""))
except Exception:
continue

sqm_el = res.select_one(".illustrated-features__item--surface-area")
if sqm_el:
sqm_match = re.search(r"(\d+)", sqm_el.get_text(" ", strip=True))
Expand All @@ -484,7 +486,7 @@ def parse_funda(self, r: requests.models.Response):
continue

home = Home(agency="funda")

home.address = f"{res['_source']['address']['street_name']} {res['_source']['address']['house_number']}"
if "house_number_suffix" in res["_source"]["address"].keys():
suffix = res["_source"]["address"]["house_number_suffix"]
Expand Down
3 changes: 2 additions & 1 deletion tests/test_parsers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -627,7 +627,8 @@ def test_filters_no_house_number(self, mock_response):
html = f"<html>{self._make_listing_html(address='Appartement Kerkstraat')}</html>"
r = mock_response(html)
results = HomeResults("pararius", r)
assert len(results.homes) == 0
assert len(results.homes) == 1
assert results[0].address == "Kerkstraat [€1500]" # < improvised number!

def test_filters_address_starting_with_number(self, mock_response):
"""Addresses where the raw content starts with a digit (no type prefix) are filtered."""
Expand Down
Loading