fix: simplify fields

pull/13/head
Cullen Watson 2023-09-19 21:13:20 -05:00
parent e8d9235ee6
commit f6054e8746
11 changed files with 276 additions and 329 deletions

View File

@ -23,9 +23,7 @@ def _validate_input(site_name: str, listing_type: str) -> None:
raise InvalidSite(f"Provided site, '{site_name}', does not exist.")
if listing_type.upper() not in ListingType.__members__:
raise InvalidListingType(
f"Provided listing type, '{listing_type}', does not exist."
)
raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
def _get_ordered_properties(result: Property) -> list[str]:
@ -35,34 +33,26 @@ def _get_ordered_properties(result: Property) -> list[str]:
"listing_type",
"property_type",
"status_text",
"currency",
"price",
"apt_min_price",
"apt_max_price",
"apt_min_sqft",
"apt_max_sqft",
"apt_min_beds",
"apt_max_beds",
"apt_min_baths",
"apt_max_baths",
"baths_min",
"baths_max",
"beds_min",
"beds_max",
"sqft_min",
"sqft_max",
"price_min",
"price_max",
"unit_count",
"tax_assessed_value",
"square_feet",
"price_per_sqft",
"beds",
"baths",
"lot_area_value",
"lot_area_unit",
"street_address",
"unit",
"address_one",
"address_two",
"city",
"state",
"zip_code",
"country",
"posted_time",
"bldg_min_beds",
"bldg_min_baths",
"bldg_min_area",
"bldg_unit_count",
"area_min",
"bldg_name",
"stories",
"year_built",
@ -86,12 +76,11 @@ def _process_result(result: Property) -> pd.DataFrame:
prop_data["property_type"] = None
if "address" in prop_data:
address_data = prop_data["address"]
prop_data["street_address"] = address_data.street_address
prop_data["unit"] = address_data.unit
prop_data["address_one"] = address_data.address_one
prop_data["address_two"] = address_data.address_two
prop_data["city"] = address_data.city
prop_data["state"] = address_data.state
prop_data["zip_code"] = address_data.zip_code
prop_data["country"] = address_data.country
del prop_data["address"]
@ -101,9 +90,7 @@ def _process_result(result: Property) -> pd.DataFrame:
return properties_df
def _scrape_single_site(
location: str, site_name: str, listing_type: str, proxy: str = None
) -> pd.DataFrame:
def _scrape_single_site(location: str, site_name: str, listing_type: str, proxy: str = None) -> pd.DataFrame:
"""
Helper function to scrape a single site.
"""
@ -120,9 +107,7 @@ def _scrape_single_site(
results = site.search()
properties_dfs = [_process_result(result) for result in results]
properties_dfs = [
df.dropna(axis=1, how="all") for df in properties_dfs if not df.empty
]
properties_dfs = [df.dropna(axis=1, how="all") for df in properties_dfs if not df.empty]
if not properties_dfs:
return pd.DataFrame()
@ -158,9 +143,7 @@ def scrape_property(
else:
with ThreadPoolExecutor() as executor:
futures = {
executor.submit(
_scrape_single_site, location, s_name, listing_type, proxy
): s_name
executor.submit(_scrape_single_site, location, s_name, listing_type, proxy): s_name
for s_name in site_name
}
@ -175,14 +158,12 @@ def scrape_property(
final_df = pd.concat(results, ignore_index=True)
columns_to_track = ["street_address", "city", "unit"]
columns_to_track = ["address_one", "address_two", "city"]
#: validate they exist, otherwise create them
for col in columns_to_track:
if col not in final_df.columns:
final_df[col] = None
final_df = final_df.drop_duplicates(
subset=["street_address", "city", "unit"], keep="first"
)
final_df = final_df.drop_duplicates(subset=columns_to_track, keep="first")
return final_df

View File

@ -5,9 +5,7 @@ from homeharvest import scrape_property
def main():
parser = argparse.ArgumentParser(description="Home Harvest Property Scraper")
parser.add_argument(
"location", type=str, help="Location to scrape (e.g., San Francisco, CA)"
)
parser.add_argument("location", type=str, help="Location to scrape (e.g., San Francisco, CA)")
parser.add_argument(
"-s",
@ -44,15 +42,11 @@ def main():
help="Name of the output file (without extension)",
)
parser.add_argument(
"-p", "--proxy", type=str, default=None, help="Proxy to use for scraping"
)
parser.add_argument("-p", "--proxy", type=str, default=None, help="Proxy to use for scraping")
args = parser.parse_args()
result = scrape_property(
args.location, args.site_name, args.listing_type, proxy=args.proxy
)
result = scrape_property(args.location, args.site_name, args.listing_type, proxy=args.proxy)
if not args.filename:
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")

View File

@ -19,10 +19,7 @@ class Scraper:
self.session = requests.Session()
if scraper_input.proxy:
proxy_url = scraper_input.proxy
proxies = {
"http": proxy_url,
"https": proxy_url
}
proxies = {"http": proxy_url, "https": proxy_url}
self.session.proxies.update(proxies)
self.listing_type = scraper_input.listing_type
self.site_name = scraper_input.site_name

View File

@ -1,5 +1,6 @@
from dataclasses import dataclass
from enum import Enum
from typing import Tuple
class SiteName(Enum):
@ -56,12 +57,11 @@ class PropertyType(Enum):
@dataclass
class Address:
street_address: str
city: str
state: str
zip_code: str
unit: str | None = None
country: str | None = None
address_one: str | None = None
address_two: str | None = "#"
city: str | None = None
state: str | None = None
zip_code: str | None = None
@dataclass
@ -73,12 +73,7 @@ class Property:
property_type: PropertyType | None = None
# house for sale
price: int | None = None
tax_assessed_value: int | None = None
currency: str | None = None
square_feet: int | None = None
beds: int | None = None
baths: float | None = None
lot_area_value: float | None = None
lot_area_unit: str | None = None
stories: int | None = None
@ -90,23 +85,25 @@ class Property:
img_src: str | None = None
description: str | None = None
status_text: str | None = None
latitude: float | None = None
longitude: float | None = None
posted_time: str | None = None
# building for sale
bldg_name: str | None = None
bldg_unit_count: int | None = None
bldg_min_beds: int | None = None
bldg_min_baths: float | None = None
bldg_min_area: int | None = None
area_min: int | None = None
# apt
apt_min_beds: int | None = None
apt_max_beds: int | None = None
apt_min_baths: float | None = None
apt_max_baths: float | None = None
apt_min_price: int | None = None
apt_max_price: int | None = None
apt_min_sqft: int | None = None
apt_max_sqft: int | None = None
beds_min: int | None = None
beds_max: int | None = None
baths_min: float | None = None
baths_max: float | None = None
sqft_min: int | None = None
sqft_max: int | None = None
price_min: int | None = None
price_max: int | None = None
unit_count: int | None = None
latitude: float | None = None
longitude: float | None = None

View File

@ -1,16 +1,23 @@
import json
"""
homeharvest.realtor.__init__
~~~~~~~~~~~~
This module implements the scraper for relator.com
"""
from ..models import Property, Address
from .. import Scraper
from typing import Any, Generator
from ....exceptions import NoResultsFound
from ....utils import parse_address_two, parse_unit
from ....utils import parse_address_one, parse_address_two
from concurrent.futures import ThreadPoolExecutor, as_completed
class RealtorScraper(Scraper):
def __init__(self, scraper_input):
self.counter = 1
super().__init__(scraper_input)
self.search_url = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
self.search_url = (
"https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
)
def handle_location(self):
headers = {
@ -50,6 +57,9 @@ class RealtorScraper(Scraper):
return result[0]
def handle_address(self, property_id: str) -> list[Property]:
"""
Handles a specific address & returns one property
"""
query = """query Property($property_id: ID!) {
property(id: $property_id) {
property_id
@ -108,43 +118,45 @@ class RealtorScraper(Scraper):
response_json = response.json()
property_info = response_json["data"]["property"]
street_address, unit = parse_address_two(property_info["address"]["line"])
address_one, address_two = parse_address_one(property_info["address"]["line"])
return [
Property(
site_name=self.site_name,
address=Address(
street_address=street_address,
address_one=address_one,
address_two=address_two,
city=property_info["address"]["city"],
state=property_info["address"]["state_code"],
zip_code=property_info["address"]["postal_code"],
unit=unit,
country="USA",
),
property_url="https://www.realtor.com/realestateandhomes-detail/"
+ property_info["details"]["permalink"],
beds=property_info["basic"]["beds"],
baths=property_info["basic"]["baths"],
stories=property_info["details"]["stories"],
year_built=property_info["details"]["year_built"],
square_feet=property_info["basic"]["sqft"],
price_per_sqft=property_info["basic"]["price"]
// property_info["basic"]["sqft"]
if property_info["basic"]["sqft"] is not None
and property_info["basic"]["price"] is not None
price_per_sqft=property_info["basic"]["price"] // property_info["basic"]["sqft"]
if property_info["basic"]["sqft"] is not None and property_info["basic"]["price"] is not None
else None,
price=property_info["basic"]["price"],
mls_id=property_id,
listing_type=self.listing_type,
lot_area_value=property_info["public_record"]["lot_size"]
if property_info["public_record"] is not None
else None,
beds_min=property_info["basic"]["beds"],
beds_max=property_info["basic"]["beds"],
baths_min=property_info["basic"]["baths"],
baths_max=property_info["basic"]["baths"],
sqft_min=property_info["basic"]["sqft"],
sqft_max=property_info["basic"]["sqft"],
price_min=property_info["basic"]["price"],
price_max=property_info["basic"]["price"],
)
]
def handle_area(
self, variables: dict, return_total: bool = False
) -> list[Property] | int:
def handle_area(self, variables: dict, return_total: bool = False) -> list[Property] | int:
"""
Handles a location area & returns a list of properties
"""
query = (
"""query Home_search(
$city: String,
@ -237,17 +249,15 @@ class RealtorScraper(Scraper):
return []
for result in response_json["data"]["home_search"]["results"]:
street_address, unit = parse_address_two(
result["location"]["address"]["line"]
)
self.counter += 1
address_one, _ = parse_address_one(result["location"]["address"]["line"])
realty_property = Property(
address=Address(
street_address=street_address,
address_one=address_one,
city=result["location"]["address"]["city"],
state=result["location"]["address"]["state_code"],
zip_code=result["location"]["address"]["postal_code"],
unit=parse_unit(result["location"]["address"]["unit"]),
country="USA",
address_two=parse_address_two(result["location"]["address"]["unit"]),
),
latitude=result["location"]["address"]["coordinate"]["lat"]
if result
@ -264,20 +274,22 @@ class RealtorScraper(Scraper):
and "lon" in result["location"]["address"]["coordinate"]
else None,
site_name=self.site_name,
property_url="https://www.realtor.com/realestateandhomes-detail/"
+ result["property_id"],
beds=result["description"]["beds"],
baths=result["description"]["baths"],
property_url="https://www.realtor.com/realestateandhomes-detail/" + result["property_id"],
stories=result["description"]["stories"],
year_built=result["description"]["year_built"],
square_feet=result["description"]["sqft"],
price_per_sqft=result["price_per_sqft"],
price=result["list_price"],
mls_id=result["property_id"],
listing_type=self.listing_type,
lot_area_value=result["description"]["lot_sqft"],
beds_min=result["description"]["beds"],
beds_max=result["description"]["beds"],
baths_min=result["description"]["baths"],
baths_max=result["description"]["baths"],
sqft_min=result["description"]["sqft"],
sqft_max=result["description"]["sqft"],
price_min=result["list_price"],
price_max=result["list_price"],
)
properties.append(realty_property)
return properties

View File

@ -1,7 +1,13 @@
"""
homeharvest.redfin.__init__
~~~~~~~~~~~~
This module implements the scraper for redfin.com
"""
import json
from typing import Any
from .. import Scraper
from ....utils import parse_address_two, parse_unit
from ....utils import parse_address_two, parse_address_one
from ..models import Property, Address, PropertyType, ListingType, SiteName
from ....exceptions import NoResultsFound
@ -12,9 +18,7 @@ class RedfinScraper(Scraper):
self.listing_type = scraper_input.listing_type
def _handle_location(self):
url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(
self.location
)
url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(self.location)
response = self.session.get(url)
response_json = json.loads(response.text.replace("{}&&", ""))
@ -28,9 +32,7 @@ class RedfinScraper(Scraper):
return "address" #: address, needs to be handled differently
if "exactMatch" not in response_json["payload"]:
raise NoResultsFound(
"No results found for location: {}".format(self.location)
)
raise NoResultsFound("No results found for location: {}".format(self.location))
if response_json["payload"]["exactMatch"] is not None:
target = response_json["payload"]["exactMatch"]
@ -45,39 +47,30 @@ class RedfinScraper(Scraper):
return home[key]["value"]
if not single_search:
street_address, unit = parse_address_two(get_value("streetLine"))
unit = parse_unit(get_value("streetLine"))
address = Address(
street_address=street_address,
address_one=parse_address_one(get_value("streetLine"))[0],
address_two=parse_address_one(get_value("streetLine"))[1],
city=home.get("city"),
state=home.get("state"),
zip_code=home.get("zip"),
unit=unit,
country="USA",
)
else:
address_info = home.get("streetAddress")
street_address, unit = parse_address_two(address_info.get("assembledAddress"))
address_one, address_two = parse_address_one(address_info.get("assembledAddress"))
address = Address(
street_address=street_address,
address_one=address_one,
address_two=address_two,
city=home.get("city"),
state=home.get("state"),
zip_code=home.get("zip"),
unit=unit,
country="USA",
)
url = "https://www.redfin.com{}".format(home["url"])
#: property_type = home["propertyType"] if "propertyType" in home else None
lot_size_data = home.get("lotSize")
if not isinstance(lot_size_data, int):
lot_size = (
lot_size_data.get("value", None)
if isinstance(lot_size_data, dict)
else None
)
lot_size = lot_size_data.get("value", None) if isinstance(lot_size_data, dict) else None
else:
lot_size = lot_size_data
@ -86,26 +79,24 @@ class RedfinScraper(Scraper):
listing_type=self.listing_type,
address=address,
property_url=url,
beds=home["beds"] if "beds" in home else None,
baths=home["baths"] if "baths" in home else None,
beds_min=home["beds"] if "beds" in home else None,
beds_max=home["beds"] if "beds" in home else None,
baths_min=home["baths"] if "baths" in home else None,
baths_max=home["baths"] if "baths" in home else None,
price_min=get_value("price"),
price_max=get_value("price"),
sqft_min=get_value("sqFt"),
sqft_max=get_value("sqFt"),
stories=home["stories"] if "stories" in home else None,
agent_name=get_value("listingAgent"),
description=home["listingRemarks"] if "listingRemarks" in home else None,
year_built=get_value("yearBuilt")
if not single_search
else home["yearBuilt"],
square_feet=get_value("sqFt"),
year_built=get_value("yearBuilt") if not single_search else home["yearBuilt"],
lot_area_value=lot_size,
property_type=PropertyType.from_int_code(home.get("propertyType")),
price_per_sqft=get_value("pricePerSqFt"),
price=get_value("price"),
mls_id=get_value("mlsId"),
latitude=home["latLong"]["latitude"]
if "latLong" in home and "latitude" in home["latLong"]
else None,
longitude=home["latLong"]["longitude"]
if "latLong" in home and "longitude" in home["latLong"]
else None,
latitude=home["latLong"]["latitude"] if "latLong" in home and "latitude" in home["latLong"] else None,
longitude=home["latLong"]["longitude"] if "latLong" in home and "longitude" in home["latLong"] else None,
)
def _handle_rentals(self, region_id, region_type):
@ -125,12 +116,10 @@ class RedfinScraper(Scraper):
address_info = home_data.get("addressInfo", {})
centroid = address_info.get("centroid", {}).get("centroid", {})
address = Address(
street_address=address_info.get("formattedStreetLine", None),
city=address_info.get("city", None),
state=address_info.get("state", None),
zip_code=address_info.get("zip", None),
unit=None,
country="US" if address_info.get("countryCode", None) == 1 else None,
address_one=parse_address_one(address_info.get("formattedStreetLine"))[0],
city=address_info.get("city"),
state=address_info.get("state"),
zip_code=address_info.get("zip"),
)
price_range = rental_data.get("rentPriceRange", {"min": None, "max": None})
@ -143,20 +132,20 @@ class RedfinScraper(Scraper):
site_name=SiteName.REDFIN,
listing_type=ListingType.FOR_RENT,
address=address,
apt_min_beds=bed_range.get("min", None),
apt_min_baths=bath_range.get("min", None),
apt_max_beds=bed_range.get("max", None),
apt_max_baths=bath_range.get("max", None),
description=rental_data.get("description", None),
latitude=centroid.get("latitude", None),
longitude=centroid.get("longitude", None),
apt_min_price=price_range.get("min", None),
apt_max_price=price_range.get("max", None),
apt_min_sqft=sqft_range.get("min", None),
apt_max_sqft=sqft_range.get("max", None),
img_src=home_data.get("staticMapUrl", None),
posted_time=rental_data.get("lastUpdated", None),
bldg_name=rental_data.get("propertyName", None),
description=rental_data.get("description"),
latitude=centroid.get("latitude"),
longitude=centroid.get("longitude"),
baths_min=bath_range.get("min"),
baths_max=bath_range.get("max"),
beds_min=bed_range.get("min"),
beds_max=bed_range.get("max"),
price_min=price_range.get("min"),
price_max=price_range.get("max"),
sqft_min=sqft_range.get("min"),
sqft_max=sqft_range.get("max"),
img_src=home_data.get("staticMapUrl"),
posted_time=rental_data.get("lastUpdated"),
bldg_name=rental_data.get("propertyName"),
)
properties_list.append(property_)
@ -175,16 +164,15 @@ class RedfinScraper(Scraper):
building["address"]["streetType"],
]
)
street_address, unit = parse_address_two(street_address)
return Property(
site_name=self.site_name,
property_type=PropertyType("BUILDING"),
address=Address(
street_address=street_address,
address_one=parse_address_one(street_address)[0],
city=building["address"]["city"],
state=building["address"]["stateOrProvinceCode"],
zip_code=building["address"]["postalCode"],
unit=parse_unit(
address_two=parse_address_two(
" ".join(
[
building["address"]["unitType"],
@ -195,7 +183,7 @@ class RedfinScraper(Scraper):
),
property_url="https://www.redfin.com{}".format(building["url"]),
listing_type=self.listing_type,
bldg_unit_count=building["numUnitsForSale"],
unit_count=building["numUnitsForSale"],
)
def handle_address(self, home_id: str):
@ -206,7 +194,6 @@ class RedfinScraper(Scraper):
https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId=147337694&accessLevel=3
https://www.redfin.com/stingray/api/home/details/belowTheFold?propertyId=147337694&accessLevel=3
"""
url = "https://www.redfin.com/stingray/api/home/details/aboveTheFold?propertyId={}&accessLevel=3".format(
home_id
)
@ -214,9 +201,7 @@ class RedfinScraper(Scraper):
response = self.session.get(url)
response_json = json.loads(response.text.replace("{}&&", ""))
parsed_home = self._parse_home(
response_json["payload"]["addressSectionInfo"], single_search=True
)
parsed_home = self._parse_home(response_json["payload"]["addressSectionInfo"], single_search=True)
return [parsed_home]
def search(self):
@ -235,10 +220,7 @@ class RedfinScraper(Scraper):
url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}&sold_within_days=30&num_homes=100000"
response = self.session.get(url)
response_json = json.loads(response.text.replace("{}&&", ""))
homes = [
self._parse_home(home) for home in response_json["payload"]["homes"]
] + [
self._parse_building(building)
for building in response_json["payload"]["buildings"].values()
homes = [self._parse_home(home) for home in response_json["payload"]["homes"]] + [
self._parse_building(building) for building in response_json["payload"]["buildings"].values()
]
return homes

View File

@ -1,7 +1,13 @@
"""
homeharvest.zillow.__init__
~~~~~~~~~~~~
This module implements the scraper for zillow.com
"""
import re
import json
from .. import Scraper
from ....utils import parse_address_two, parse_unit
from ....utils import parse_address_one, parse_address_two
from ....exceptions import GeoCoordsNotFound, NoResultsFound
from ..models import Property, Address, ListingType, PropertyType
@ -13,12 +19,13 @@ class ZillowScraper(Scraper):
if not self.is_plausible_location(self.location):
raise NoResultsFound("Invalid location input: {}".format(self.location))
if self.listing_type == ListingType.FOR_SALE:
self.url = f"https://www.zillow.com/homes/for_sale/{self.location}_rb/"
elif self.listing_type == ListingType.FOR_RENT:
self.url = f"https://www.zillow.com/homes/for_rent/{self.location}_rb/"
else:
self.url = f"https://www.zillow.com/homes/recently_sold/{self.location}_rb/"
listing_type_to_url_path = {
ListingType.FOR_SALE: "for_sale",
ListingType.FOR_RENT: "for_rent",
ListingType.SOLD: "recently_sold",
}
self.url = f"https://www.zillow.com/homes/{listing_type_to_url_path[self.listing_type]}/{self.location}_rb/"
def is_plausible_location(self, location: str) -> bool:
url = (
@ -31,9 +38,7 @@ class ZillowScraper(Scraper):
return response.json()["results"] != []
def search(self):
resp = self.session.get(
self.url, headers=self._get_headers()
)
resp = self.session.get(self.url, headers=self._get_headers())
resp.raise_for_status()
content = resp.text
@ -43,9 +48,7 @@ class ZillowScraper(Scraper):
re.DOTALL,
)
if not match:
raise NoResultsFound(
"No results were found for Zillow with the given Location."
)
raise NoResultsFound("No results were found for Zillow with the given Location.")
json_str = match.group(1)
data = json.loads(json_str)
@ -130,9 +133,7 @@ class ZillowScraper(Scraper):
"wants": {"cat1": ["mapResults"]},
"isDebugRequest": False,
}
resp = self.session.put(
url, headers=self._get_headers(), json=payload
)
resp = self.session.put(url, headers=self._get_headers(), json=payload)
resp.raise_for_status()
a = resp.json()
return self._parse_properties(resp.json())
@ -146,87 +147,71 @@ class ZillowScraper(Scraper):
if "hdpData" in result:
home_info = result["hdpData"]["homeInfo"]
address_data = {
"street_address": parse_address_two(home_info["streetAddress"])[0],
"unit": parse_unit(home_info["unit"])
if "unit" in home_info
else None,
"address_one": parse_address_one(home_info["streetAddress"])[0],
"address_two": parse_address_two(home_info["unit"]) if "unit" in home_info else "#",
"city": home_info["city"],
"state": home_info["state"],
"zip_code": home_info["zipcode"],
"country": home_info["country"],
}
property_data = {
"site_name": self.site_name,
"address": Address(**address_data),
"property_url": f"https://www.zillow.com{result['detailUrl']}",
"beds": int(home_info["bedrooms"])
if "bedrooms" in home_info
else None,
"baths": home_info.get("bathrooms"),
"square_feet": int(home_info["livingArea"])
if "livingArea" in home_info
else None,
"currency": home_info["currency"],
"price": home_info.get("price"),
"tax_assessed_value": int(home_info["taxAssessedValue"])
if "taxAssessedValue" in home_info
else None,
"property_type": PropertyType(home_info["homeType"]),
"listing_type": ListingType(
home_info["statusType"]
if "statusType" in home_info
else self.listing_type
property_obj = Property(
site_name=self.site_name,
address=Address(**address_data),
property_url=f"https://www.zillow.com{result['detailUrl']}",
tax_assessed_value=int(home_info["taxAssessedValue"]) if "taxAssessedValue" in home_info else None,
property_type=PropertyType(home_info["homeType"]),
listing_type=ListingType(
home_info["statusType"] if "statusType" in home_info else self.listing_type
),
"lot_area_value": round(home_info["lotAreaValue"], 2)
if "lotAreaValue" in home_info
else None,
"lot_area_unit": home_info.get("lotAreaUnit"),
"latitude": result["latLong"]["latitude"],
"longitude": result["latLong"]["longitude"],
"status_text": result.get("statusText"),
"posted_time": result["variableData"]["text"]
status_text=result.get("statusText"),
posted_time=result["variableData"]["text"]
if "variableData" in result
and "text" in result["variableData"]
and result["variableData"]["type"] == "TIME_ON_INFO"
else None,
"img_src": result.get("imgSrc"),
"price_per_sqft": int(home_info["price"] // home_info["livingArea"])
if "livingArea" in home_info
and home_info["livingArea"] != 0
and "price" in home_info
price_min=home_info.get("price"),
price_max=home_info.get("price"),
beds_min=int(home_info["bedrooms"]) if "bedrooms" in home_info else None,
beds_max=int(home_info["bedrooms"]) if "bedrooms" in home_info else None,
baths_min=home_info.get("bathrooms"),
baths_max=home_info.get("bathrooms"),
sqft_min=int(home_info["livingArea"]) if "livingArea" in home_info else None,
sqft_max=int(home_info["livingArea"]) if "livingArea" in home_info else None,
price_per_sqft=int(home_info["price"] // home_info["livingArea"])
if "livingArea" in home_info and home_info["livingArea"] != 0 and "price" in home_info
else None,
}
property_obj = Property(**property_data)
latitude=result["latLong"]["latitude"],
longitude=result["latLong"]["longitude"],
lot_area_value=round(home_info["lotAreaValue"], 2) if "lotAreaValue" in home_info else None,
lot_area_unit=home_info.get("lotAreaUnit"),
img_src=result.get("imgSrc"),
)
properties_list.append(property_obj)
elif "isBuilding" in result:
price = result["price"]
building_data = {
"property_url": f"https://www.zillow.com{result['detailUrl']}",
"site_name": self.site_name,
"property_type": PropertyType("BUILDING"),
"listing_type": ListingType(result["statusType"]),
"img_src": result["imgSrc"],
"price": int(price.replace("From $", "").replace(",", ""))
if "From $" in price
else None,
"apt_min_price": int(
price.replace("$", "").replace(",", "").replace("+/mo", "")
)
if "+/mo" in price
else None,
"address": self._extract_address(result["address"]),
"bldg_min_beds": result["minBeds"],
"currency": "USD",
"bldg_min_baths": result["minBaths"],
"bldg_min_area": result.get("minArea"),
"bldg_unit_count": result["unitCount"],
"bldg_name": result.get("communityName"),
"status_text": result["statusText"],
"latitude": result["latLong"]["latitude"],
"longitude": result["latLong"]["longitude"],
}
building_obj = Property(**building_data)
price_string = result["price"].replace("$", "").replace(",", "").replace("+/mo", "")
match = re.search(r"(\d+)", price_string)
price_value = int(match.group(1)) if match else None
building_obj = Property(
property_url=f"https://www.zillow.com{result['detailUrl']}",
site_name=self.site_name,
property_type=PropertyType("BUILDING"),
listing_type=ListingType(result["statusType"]),
img_src=result["imgSrc"],
address=self._extract_address(result["address"]),
baths_min=result["minBaths"],
area_min=result.get("minArea"),
bldg_name=result.get("communityName"),
status_text=result["statusText"],
beds_min=result["minBeds"],
price_min=price_value if "+/mo" in result["price"] else None,
price_max=price_value if "+/mo" in result["price"] else None,
latitude=result["latLong"]["latitude"],
longitude=result["latLong"]["longitude"],
unit_count=result["unitCount"],
)
properties_list.append(building_obj)
return properties_list
@ -241,43 +226,41 @@ class ZillowScraper(Scraper):
else property_data["hdpUrl"]
)
address_data = property_data["address"]
street_address, unit = parse_address_two(address_data["streetAddress"])
address_one, address_two = parse_address_one(address_data["streetAddress"])
address = Address(
street_address=street_address,
unit=unit,
address_one=address_one,
address_two=address_two if address_two else "#",
city=address_data["city"],
state=address_data["state"],
zip_code=address_data["zipcode"],
country=property_data.get("country"),
)
property_type = property_data.get("homeType", None)
return Property(
site_name=self.site_name,
address=address,
property_url=url,
beds=property_data.get("bedrooms", None),
baths=property_data.get("bathrooms", None),
year_built=property_data.get("yearBuilt", None),
price=property_data.get("price", None),
tax_assessed_value=property_data.get("taxAssessedValue", None),
property_type=PropertyType(property_type),
listing_type=self.listing_type,
address=address,
year_built=property_data.get("yearBuilt"),
tax_assessed_value=property_data.get("taxAssessedValue"),
lot_area_value=property_data.get("lotAreaValue"),
lot_area_unit=property_data["lotAreaUnits"].lower() if "lotAreaUnits" in property_data else None,
agent_name=property_data.get("attributionInfo", {}).get("agentName"),
stories=property_data.get("resoFacts", {}).get("stories"),
mls_id=property_data.get("attributionInfo", {}).get("mlsId"),
beds_min=property_data.get("bedrooms"),
beds_max=property_data.get("bedrooms"),
baths_min=property_data.get("bathrooms"),
baths_max=property_data.get("bathrooms"),
price_min=property_data.get("price"),
price_max=property_data.get("price"),
sqft_min=property_data.get("livingArea"),
sqft_max=property_data.get("livingArea"),
price_per_sqft=property_data.get("resoFacts", {}).get("pricePerSquareFoot"),
latitude=property_data.get("latitude"),
longitude=property_data.get("longitude"),
img_src=property_data.get("streetViewTileImageUrlMediumAddress"),
currency=property_data.get("currency", None),
lot_area_value=property_data.get("lotAreaValue"),
lot_area_unit=property_data["lotAreaUnits"].lower()
if "lotAreaUnits" in property_data
else None,
agent_name=property_data.get("attributionInfo", {}).get("agentName", None),
stories=property_data.get("resoFacts", {}).get("stories", None),
description=property_data.get("description", None),
mls_id=property_data.get("attributionInfo", {}).get("mlsId", None),
price_per_sqft=property_data.get("resoFacts", {}).get(
"pricePerSquareFoot", None
),
square_feet=property_data.get("livingArea", None),
property_type=PropertyType(property_type),
listing_type=self.listing_type,
description=property_data.get("description"),
)
def _extract_address(self, address_str):
@ -290,7 +273,7 @@ class ZillowScraper(Scraper):
if len(parts) != 3:
raise ValueError(f"Unexpected address format: {address_str}")
street_address = parts[0].strip()
address_one = parts[0].strip()
city = parts[1].strip()
state_zip = parts[2].split(" ")
@ -303,14 +286,13 @@ class ZillowScraper(Scraper):
else:
raise ValueError(f"Unexpected state/zip format in address: {address_str}")
street_address, unit = parse_address_two(street_address)
address_one, address_two = parse_address_one(address_one)
return Address(
street_address=street_address,
address_one=address_one,
address_two=address_two if address_two else "#",
city=city,
unit=unit,
state=state,
zip_code=zip_code,
country="USA",
)
@staticmethod

View File

@ -1,9 +1,9 @@
import re
def parse_address_two(street_address: str) -> tuple:
def parse_address_one(street_address: str) -> tuple:
if not street_address:
return street_address, None
return street_address, "#"
apt_match = re.search(
r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+|SUITE\s*[\dA-Z]+)$",
@ -13,36 +13,26 @@ def parse_address_two(street_address: str) -> tuple:
if apt_match:
apt_str = apt_match.group().strip()
cleaned_apt_str = re.sub(
r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I
)
cleaned_apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I)
main_address = street_address.replace(apt_str, "").strip()
return main_address, cleaned_apt_str
else:
return street_address, None
return street_address, "#"
def parse_unit(street_address: str):
def parse_address_two(street_address: str):
if not street_address:
return None
return "#"
apt_match = re.search(
r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+)$",
r"(APT\s*[\dA-Z]+|#[\dA-Z]+|UNIT\s*[\dA-Z]+|LOT\s*[\dA-Z]+|SUITE\s*[\dA-Z]+)$",
street_address,
re.I,
)
if apt_match:
apt_str = apt_match.group().strip()
apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*)", "#", apt_str, flags=re.I)
apt_str = re.sub(r"(APT\s*|UNIT\s*|LOT\s*|SUITE\s*)", "#", apt_str, flags=re.I)
return apt_str
else:
return None
if __name__ == "__main__":
print(parse_address_two("4303 E Cactus Rd Apt 126"))
print(parse_address_two("1234 Elm Street apt 2B"))
print(parse_address_two("1234 Elm Street UNIT 3A"))
print(parse_address_two("1234 Elm Street unit 3A"))
print(parse_address_two("1234 Elm Street SuIte 3A"))
return "#"

View File

@ -9,15 +9,9 @@ from homeharvest.exceptions import (
def test_redfin():
results = [
scrape_property(
location="2530 Al Lipscomb Way", site_name="redfin", listing_type="for_sale"
),
scrape_property(
location="Phoenix, AZ, USA", site_name=["redfin"], listing_type="for_rent"
),
scrape_property(
location="Dallas, TX, USA", site_name="redfin", listing_type="sold"
),
scrape_property(location="2530 Al Lipscomb Way", site_name="redfin", listing_type="for_sale"),
scrape_property(location="Phoenix, AZ, USA", site_name=["redfin"], listing_type="for_rent"),
scrape_property(location="Dallas, TX, USA", site_name="redfin", listing_type="sold"),
scrape_property(location="85281", site_name="redfin"),
]

24
tests/test_utils.py Normal file
View File

@ -0,0 +1,24 @@
from homeharvest.utils import parse_address_one, parse_address_two
def test_parse_address_one():
test_data = [
("4303 E Cactus Rd Apt 126", ("4303 E Cactus Rd", "#126")),
("1234 Elm Street apt 2B", ("1234 Elm Street", "#2B")),
("1234 Elm Street UNIT 3A", ("1234 Elm Street", "#3A")),
("1234 Elm Street unit 3A", ("1234 Elm Street", "#3A")),
("1234 Elm Street SuIte 3A", ("1234 Elm Street", "#3A")),
]
for input_data, (exp_addr_one, exp_addr_two) in test_data:
address_one, address_two = parse_address_one(input_data)
assert address_one == exp_addr_one
assert address_two == exp_addr_two
def test_parse_address_two():
test_data = [("Apt 126", "#126"), ("apt 2B", "#2B"), ("UNIT 3A", "#3A"), ("unit 3A", "#3A"), ("SuIte 3A", "#3A")]
for input_data, expected in test_data:
output = parse_address_two(input_data)
assert output == expected

View File

@ -9,15 +9,9 @@ from homeharvest.exceptions import (
def test_zillow():
results = [
scrape_property(
location="2530 Al Lipscomb Way", site_name="zillow", listing_type="for_sale"
),
scrape_property(
location="Phoenix, AZ, USA", site_name=["zillow"], listing_type="for_rent"
),
scrape_property(
location="Dallas, TX, USA", site_name="zillow", listing_type="sold"
),
scrape_property(location="2530 Al Lipscomb Way", site_name="zillow", listing_type="for_sale"),
scrape_property(location="Phoenix, AZ, USA", site_name=["zillow"], listing_type="for_rent"),
scrape_property(location="Dallas, TX, USA", site_name="zillow", listing_type="sold"),
scrape_property(location="85281", site_name="zillow"),
]