turtlebasket
/
HomeHarvest
mirror of https://github.com/Bunsly/HomeHarvest.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat(redfin): rental support

pull/9/head
Cullen Watson 2023-09-19 11:58:20 -05:00
parent 02d112eea0
commit 1fc2d8c549
6 changed files with 92 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -3,4 +3,5 @@
**/__pycache__/
**/.pytest_cache/
*.pyc
/.ipynb_checkpoints/
/.ipynb_checkpoints/
*.csv

3
homeharvest/__init__.py
View File

@ -38,6 +38,9 @@ def get_ordered_properties(result: Property) -> list[str]:
"currency",
"price",
"apt_min_price",
"apt_max_price",
"apt_min_sqft",
"apt_max_sqft",
"tax_assessed_value",
"square_feet",
"price_per_sqft",

3
homeharvest/core/scrapers/models.py
View File

@ -103,3 +103,6 @@ class Property:
# apt
apt_min_price: int | None = None
apt_max_price: int | None = None
apt_min_sqft: int | None = None
apt_max_sqft: int | None = None

91
homeharvest/core/scrapers/redfin/__init__.py
View File

@ -2,7 +2,7 @@ import json
from typing import Any
from .. import Scraper
from ....utils import parse_address_two, parse_unit
from ..models import Property, Address, PropertyType
from ..models import Property, Address, PropertyType, ListingType, SiteName
from ....exceptions import NoResultsFound
@ -108,6 +108,64 @@ class RedfinScraper(Scraper):
else None,
)
def _handle_rentals(self, region_id, region_type):
url = f"https://www.redfin.com/stingray/api/v1/search/rentals?al=1&isRentals=true&region_id={region_id}&region_type={region_type}"
response = self.session.get(url)
response.raise_for_status() # This will raise an error if the response contains an HTTP error status.
homes = response.json()
properties_list = []
for home in homes["homes"]:
home_data = home["homeData"]
rental_data = home["rentalExtension"]
property_url = f"https://www.redfin.com{home_data.get('url', '')}"
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,
)
price_range = rental_data.get("rentPriceRange", {"min": None, "max": None})
bed_range = rental_data.get("bedRange", {"min": None, "max": None})
bath_range = rental_data.get("bathRange", {"min": None, "max": None})
sqft_range = rental_data.get("sqftRange", {"min": None, "max": None})
property_ = Property(
property_url=property_url,
site_name=SiteName.REDFIN,
listing_type=ListingType.FOR_RENT,
address=address,
square_feet=sqft_range.get("min", None),
beds=bed_range.get("min", None),
baths=bath_range.get("min", 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),
)
properties_list.append(property_)
if not properties_list:
raise NoResultsFound("No rentals found for the given location.")
return properties_list
def _parse_building(self, building: dict) -> Property:
street_address = " ".join(
[
@ -168,18 +226,19 @@ class RedfinScraper(Scraper):
home_id = region_id
return self.handle_address(home_id)
url = "https://www.redfin.com/stingray/api/gis?al=1&region_id={}&region_type={}".format(
region_id, region_type
)
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()
]
return homes
if self.listing_type == ListingType.FOR_RENT:
return self._handle_rentals(region_id, region_type)
elif self.listing_type == ListingType.FOR_SALE:
url = f"https://www.redfin.com/stingray/api/gis?al=1&region_id={region_id}&region_type={region_type}"
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()
]
return homes
else:
# Handle other cases, maybe raise an error if the listing type is not recognized.
pass

10
homeharvest/core/scrapers/zillow/__init__.py
View File

@ -22,14 +22,14 @@ class ZillowScraper(Scraper):
self.url = f"https://www.zillow.com/homes/recently_sold/{self.location}_rb/"
def is_plausible_location(self, location: str) -> bool:
url = ('https://www.zillowstatic.com/autocomplete/v3/suggestions?q={'
'}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render').format(
location
)
url = (
"https://www.zillowstatic.com/autocomplete/v3/suggestions?q={"
"}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render"
).format(location)
response = self.session.get(url)
return response.json()['results'] != []
return response.json()["results"] != []
def search(self):
resp = self.session.get(self.url, headers=self._get_headers())

7
tests/test_redfin.py
View File

@ -15,9 +15,10 @@ def test_redfin():
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"
),
# TODO
# scrape_property(
# location="Dallas, TX, USA", site_name="redfin", listing_type="sold"
# ),
scrape_property(location="85281", site_name="redfin"),
]