turtlebasket/HomeHarvest
1
0
Fork 0
mirror of https://github.com/Bunsly/HomeHarvest.git synced 2026-03-04 19:44:29 -08:00
Code Issues Packages Projects Releases Wiki Activity

enh: property type (#102)

Browse Source
This commit is contained in:
Cullen Watson
2024-11-03 17:23:07 -06:00
committed by GitHub
parent 1f717bd9e3
commit 8e04f6b117
11 changed files with 274 additions and 241 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
homeharvest/__init__.py
View File

@@ -3,12 +3,13 @@ import pandas as pd
from .core.scrapers import ScraperInput
from .utils import process_result, ordered_properties, validate_input, validate_dates, validate_limit
from .core.scrapers.realtor import RealtorScraper
from .core.scrapers.models import ListingType
from .core.scrapers.models import ListingType, SearchPropertyType
def scrape_property(
location: str,
listing_type: str = "for_sale",
property_type: list[str] | None = None,
radius: float = None,
mls_only: bool = False,
past_days: int = None,
@@ -24,6 +25,7 @@ def scrape_property(
Scrape properties from Realtor.com based on a given location and listing type.
:param location: Location to search (e.g. "Dallas, TX", "85281", "2530 Al Lipscomb Way")
:param listing_type: Listing Type (for_sale, for_rent, sold, pending)
:param property_type: Property Type (single_family, multi_family, condos, condo_townhome_rowhome_coop, condo_townhome, townhomes, duplex_triplex, farm, land, mobile)
:param radius: Get properties within _ (e.g. 1.0) miles. Only applicable for individual addresses.
:param mls_only: If set, fetches only listings with MLS IDs.
:param proxy: Proxy to use for scraping
@@ -41,6 +43,7 @@ def scrape_property(
scraper_input = ScraperInput(
location=location,
listing_type=ListingType[listing_type.upper()],
property_type=[SearchPropertyType[prop.upper()] for prop in property_type] if property_type else None,
proxy=proxy,
radius=radius,
mls_only=mls_only,
@@ -63,4 +66,6 @@ def scrape_property(
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=FutureWarning)
return pd.concat(properties_dfs, ignore_index=True, axis=0)[ordered_properties].replace({"None": pd.NA, None: pd.NA, "": pd.NA})
return pd.concat(properties_dfs, ignore_index=True, axis=0)[ordered_properties].replace(
{"None": pd.NA, None: pd.NA, "": pd.NA}
)