Compare commits

...

4 Commits

Author SHA1 Message Date
zachary
68a3438c6e - single home return type bug fix 2025-05-05 12:29:36 -07:00
zachary
a3c5e9060e - updated queries 2025-05-03 13:55:56 -07:00
zachary
d06595fe56 - updated queries 2025-05-03 13:28:12 -07:00
zachary
e378feeefe - bug fixes 2025-04-12 18:34:35 -07:00
5 changed files with 42 additions and 22 deletions

View File

@@ -25,6 +25,7 @@ class SiteName(Enum):
class SearchPropertyType(Enum):
SINGLE_FAMILY = "single_family"
APARTMENT = "apartment"
CONDOS = "condos"
CONDO_TOWNHOME_ROWHOME_COOP = "condo_townhome_rowhome_coop"
CONDO_TOWNHOME = "condo_townhome"

View File

@@ -121,7 +121,10 @@ class RealtorScraper(Scraper):
property_info = response_json["data"]["home"]
if self.return_type != ReturnType.raw:
return [self.process_property(property_info)]
else:
return [property_info]
@staticmethod
def process_advertisers(advertisers: list[dict] | None) -> Advertisers | None:
@@ -257,7 +260,7 @@ class RealtorScraper(Scraper):
sort_param = (
"sort: [{ field: sold_date, direction: desc }]"
if self.listing_type == ListingType.SOLD
else "sort: [{ field: list_date, direction: desc }]"
else "" #: "sort: [{ field: list_date, direction: desc }]" #: prioritize normal fractal sort from realtor
)
pending_or_contingent_param = (
@@ -448,6 +451,7 @@ class RealtorScraper(Scraper):
"county": location_info.get("county"),
"state_code": location_info.get("state_code"),
"postal_code": location_info.get("postal_code"),
}
if self.foreclosure:

View File

@@ -36,6 +36,13 @@ _SEARCH_HOMES_DATA_BASE = """{
sqft
__typename
}
photos(https: true) {
title
href
tags {
label
}
}
list_price
__typename
}
@@ -90,12 +97,17 @@ _SEARCH_HOMES_DATA_BASE = """{
}
}
tax_record {
cl_id
public_record_id
last_update_date
apn
tax_parcel_id
}
primary_photo(https: true) {
href
}
photos(https: true) {
title
href
tags {
label
@@ -220,7 +232,7 @@ HOMES_DATA = """%s
}""" % _SEARCH_HOMES_DATA_BASE
SEARCH_HOMES_DATA = """%s
current_estimates {
current_estimates {
__typename
source {
__typename
@@ -232,7 +244,7 @@ SEARCH_HOMES_DATA = """%s
estimateLow: estimate_low
date
isBestHomeValue: isbest_homevalue
}
}
}""" % _SEARCH_HOMES_DATA_BASE
GENERAL_RESULTS_QUERY = """{

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.4.6"
version = "0.4.9"
description = "Real estate scraping library"
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
homepage = "https://github.com/Bunsly/HomeHarvest"

View File

@@ -292,11 +292,14 @@ def test_phone_number_matching():
def test_return_type():
results = {
"pandas": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100),
"pydantic": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic"),
"raw": scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
"pandas": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100)],
"pydantic": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic")],
"raw": [
scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
scrape_property(location="66642", listing_type="for_rent", limit=100, return_type="raw"),
],
}
assert isinstance(results["pandas"], pd.DataFrame)
assert isinstance(results["pydantic"][0], Property)
assert isinstance(results["raw"][0], dict)
assert all(isinstance(result, pd.DataFrame) for result in results["pandas"])
assert all(isinstance(result[0], Property) for result in results["pydantic"])
assert all(isinstance(result[0], dict) for result in results["raw"])