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

enh: add agent name/phone (#66)

pull/68/head^2 v0.3.16
Cullen Watson 2024-04-16 14:55:44 -05:00 committed by GitHub
parent 1f47fc3b7e
commit 0bdf56568e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
13 changed files with 407 additions and 158 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
.pre-commit-config.yaml Normal file
View File

@ -0,0 +1,21 @@
---
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.2.0
hooks:
- id: trailing-whitespace
- id: end-of-file-fixer
- id: check-added-large-files
- id: check-yaml
- repo: https://github.com/adrienverge/yamllint
rev: v1.29.0
hooks:
- id: yamllint
verbose: true # create awareness of linter findings
args: ["-d", "{extends: relaxed, rules: {line-length: {max: 120}}}"]
- repo: https://github.com/psf/black
rev: 24.2.0
hooks:
- id: black
language_version: python
args: [--line-length=120, --quiet]

1
README.md
View File

@ -143,4 +143,3 @@ The following exceptions may be raised when using HomeHarvest:
- `InvalidListingType` - valid options: `for_sale`, `for_rent`, `sold`
- `InvalidDate` - date_from or date_to is not in the format YYYY-MM-DD

8
homeharvest/cli.py
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(
"-l",
@ -35,9 +33,7 @@ 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")
parser.add_argument(
"-d",
"--days",

33
homeharvest/core/scrapers/__init__.py
View File

@ -1,5 +1,6 @@
from dataclasses import dataclass
import requests
import uuid
from .models import Property, ListingType, SiteName
@ -27,6 +28,12 @@ class Scraper:
if not session:
self.session = requests.Session()
self.session.headers.update(
{
"auth": f"Bearer {self.get_access_token()}",
"apollographql-client-name": "com.move.Realtor-apollo-ios",
}
)
else:
self.session = session
@ -43,12 +50,26 @@ class Scraper:
self.date_to = scraper_input.date_to
self.foreclosure = scraper_input.foreclosure
def search(self) -> list[Property]:
...
def search(self) -> list[Property]: ...
@staticmethod
def _parse_home(home) -> Property:
...
def _parse_home(home) -> Property: ...
def handle_location(self):
...
def handle_location(self): ...
def get_access_token(self):
url = "https://graph.realtor.com/auth/token"
payload = f'{{"client_app_id":"rdc_mobile_native,24.20.4.149916,iphone","device_id":"{str(uuid.uuid4()).upper()}","grant_type":"device_mobile"}}'
headers = {
"Host": "graph.realtor.com",
"x-client-version": "24.20.4.149916",
"accept": "*/*",
"content-type": "Application/json",
"user-agent": "Realtor.com/24.20.4.149916 CFNetwork/1410.0.3 Darwin/22.6.0",
"accept-language": "en-US,en;q=0.9",
}
response = requests.post(url, headers=headers, data=payload)
data = response.json()
return data["access_token"]

8
homeharvest/core/scrapers/models.py
View File

@ -69,6 +69,12 @@ class Description:
stories: int | None = None
@dataclass
class Agent:
name: str | None = None
phone: str | None = None
@dataclass
class Property:
property_url: str
@ -89,3 +95,5 @@ class Property:
latitude: float | None = None
longitude: float | None = None
neighborhoods: Optional[str] = None
agents: list[Agent] = None

196
homeharvest/core/scrapers/realtor/__init__.py
View File

@ -4,18 +4,21 @@ homeharvest.realtor.__init__
This module implements the scraper for realtor.com
"""
from datetime import datetime
from typing import Dict, Union, Optional
from concurrent.futures import ThreadPoolExecutor, as_completed
from .. import Scraper
from ..models import Property, Address, ListingType, Description, PropertyType
from ..models import Property, Address, ListingType, Description, PropertyType, Agent
class RealtorScraper(Scraper):
SEARCH_GQL_URL = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
PROPERTY_URL = "https://www.realtor.com/realestateandhomes-detail/"
PROPERTY_GQL = "https://graph.realtor.com/graphql"
ADDRESS_AUTOCOMPLETE_URL = "https://parser-external.geo.moveaws.com/suggest"
NUM_PROPERTY_WORKERS = 20
def __init__(self, scraper_input):
super().__init__(scraper_input)
@ -110,15 +113,17 @@ class RealtorScraper(Scraper):
)
able_to_get_lat_long = (
property_info
and property_info.get("address")
and property_info["address"].get("location")
and property_info["address"]["location"].get("coordinate")
property_info
and property_info.get("address")
and property_info["address"].get("location")
and property_info["address"]["location"].get("coordinate")
)
list_date_str = (
property_info["basic"]["list_date"].split("T")[0] if property_info["basic"].get("list_date") else None
)
last_sold_date_str = (
property_info["basic"]["sold_date"].split("T")[0] if property_info["basic"].get("sold_date") else None
)
list_date_str = property_info["basic"]["list_date"].split("T")[0] if property_info["basic"].get(
"list_date") else None
last_sold_date_str = property_info["basic"]["sold_date"].split("T")[0] if property_info["basic"].get(
"sold_date") else None
pending_date_str = property_info["pending_date"].split("T")[0] if property_info.get("pending_date") else None
list_date = datetime.strptime(list_date_str, "%Y-%m-%d") if list_date_str else None
@ -131,33 +136,31 @@ class RealtorScraper(Scraper):
if list_date:
if status == "sold" and last_sold_date:
days_on_mls = (last_sold_date - list_date).days
elif status in ('for_sale', 'for_rent'):
elif status in ("for_sale", "for_rent"):
days_on_mls = (today - list_date).days
if days_on_mls and days_on_mls < 0:
days_on_mls = None
listing = Property(
mls=mls,
mls_id=property_info["source"].get("listing_id")
if "source" in property_info and isinstance(property_info["source"], dict)
else None,
mls_id=(
property_info["source"].get("listing_id")
if "source" in property_info and isinstance(property_info["source"], dict)
else None
),
property_url=f"{self.PROPERTY_URL}{property_info['details']['permalink']}",
status=property_info["basic"]["status"].upper(),
list_price=property_info["basic"]["price"],
list_date=list_date,
prc_sqft=property_info["basic"].get("price")
/ property_info["basic"].get("sqft")
if property_info["basic"].get("price")
and property_info["basic"].get("sqft")
else None,
prc_sqft=(
property_info["basic"].get("price") / property_info["basic"].get("sqft")
if property_info["basic"].get("price") and property_info["basic"].get("sqft")
else None
),
last_sold_date=last_sold_date,
pending_date=pending_date,
latitude=property_info["address"]["location"]["coordinate"].get("lat")
if able_to_get_lat_long
else None,
longitude=property_info["address"]["location"]["coordinate"].get("lon")
if able_to_get_lat_long
else None,
latitude=property_info["address"]["location"]["coordinate"].get("lat") if able_to_get_lat_long else None,
longitude=property_info["address"]["location"]["coordinate"].get("lon") if able_to_get_lat_long else None,
address=self._parse_address(property_info, search_type="handle_listing"),
description=Description(
alt_photos=self.process_alt_photos(property_info.get("media", {}).get("photos", [])),
@ -172,7 +175,7 @@ class RealtorScraper(Scraper):
garage=property_info["details"].get("garage"),
stories=property_info["details"].get("stories"),
),
days_on_mls=days_on_mls
days_on_mls=days_on_mls,
)
return [listing]
@ -281,16 +284,12 @@ class RealtorScraper(Scraper):
Property(
mls_id=property_id,
property_url=f"{self.PROPERTY_URL}{property_info['details']['permalink']}",
address=self._parse_address(
property_info, search_type="handle_address"
),
address=self._parse_address(property_info, search_type="handle_address"),
description=self._parse_description(property_info),
)
]
def general_search(
self, variables: dict, search_type: str
) -> Dict[str, Union[int, list[Property]]]:
def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, list[Property]]]:
"""
Handles a location area & returns a list of properties
"""
@ -380,17 +379,15 @@ class RealtorScraper(Scraper):
)
pending_or_contingent_param = (
"or_filters: { contingent: true, pending: true }"
if self.listing_type == ListingType.PENDING
else ""
"or_filters: { contingent: true, pending: true }" if self.listing_type == ListingType.PENDING else ""
)
listing_type = ListingType.FOR_SALE if self.listing_type == ListingType.PENDING else self.listing_type
is_foreclosure = ""
if variables.get('foreclosure') is True:
if variables.get("foreclosure") is True:
is_foreclosure = "foreclosure: true"
elif variables.get('foreclosure') is False:
elif variables.get("foreclosure") is False:
is_foreclosure = "foreclosure: false"
if search_type == "comps": #: comps search, came from an address
@ -453,7 +450,7 @@ class RealtorScraper(Scraper):
)
else: #: general search, came from an address
query = (
"""query Property_search(
"""query Property_search(
$property_id: [ID]!
$offset: Int!,
) {
@ -464,7 +461,7 @@ class RealtorScraper(Scraper):
limit: 1
offset: $offset
) %s"""
% results_query
% results_query
)
payload = {
@ -480,64 +477,72 @@ class RealtorScraper(Scraper):
properties: list[Property] = []
if (
response_json is None
or "data" not in response_json
or response_json["data"] is None
or search_key not in response_json["data"]
or response_json["data"][search_key] is None
or "results" not in response_json["data"][search_key]
response_json is None
or "data" not in response_json
or response_json["data"] is None
or search_key not in response_json["data"]
or response_json["data"][search_key] is None
or "results" not in response_json["data"][search_key]
):
return {"total": 0, "properties": []}
for result in response_json["data"][search_key]["results"]:
mls = (
result["source"].get("id")
if "source" in result and isinstance(result["source"], dict)
else None
)
def process_property(result: dict) -> Property | None:
mls = result["source"].get("id") if "source" in result and isinstance(result["source"], dict) else None
if not mls and self.mls_only:
continue
return
able_to_get_lat_long = (
result
and result.get("location")
and result["location"].get("address")
and result["location"]["address"].get("coordinate")
result
and result.get("location")
and result["location"].get("address")
and result["location"]["address"].get("coordinate")
)
is_pending = result["flags"].get("is_pending") or result["flags"].get("is_contingent")
if is_pending and self.listing_type != ListingType.PENDING:
continue
return
property_id = result["property_id"]
agents = self.get_agents(property_id)
realty_property = Property(
mls=mls,
mls_id=result["source"].get("listing_id")
if "source" in result and isinstance(result["source"], dict)
else None,
property_url=f"{self.PROPERTY_URL}{result['property_id']}" if self.listing_type != ListingType.FOR_RENT else f"{self.PROPERTY_URL}M{result['property_id']}?listing_status=rental",
mls_id=(
result["source"].get("listing_id")
if "source" in result and isinstance(result["source"], dict)
else None
),
property_url=(
f"{self.PROPERTY_URL}{property_id}"
if self.listing_type != ListingType.FOR_RENT
else f"{self.PROPERTY_URL}M{property_id}?listing_status=rental"
),
status="PENDING" if is_pending else result["status"].upper(),
list_price=result["list_price"],
list_date=result["list_date"].split("T")[0]
if result.get("list_date")
else None,
list_date=result["list_date"].split("T")[0] if result.get("list_date") else None,
prc_sqft=result.get("price_per_sqft"),
last_sold_date=result.get("last_sold_date"),
hoa_fee=result["hoa"]["fee"]
if result.get("hoa") and isinstance(result["hoa"], dict)
else None,
latitude=result["location"]["address"]["coordinate"].get("lat")
if able_to_get_lat_long
else None,
longitude=result["location"]["address"]["coordinate"].get("lon")
if able_to_get_lat_long
else None,
hoa_fee=result["hoa"]["fee"] if result.get("hoa") and isinstance(result["hoa"], dict) else None,
latitude=result["location"]["address"]["coordinate"].get("lat") if able_to_get_lat_long else None,
longitude=result["location"]["address"]["coordinate"].get("lon") if able_to_get_lat_long else None,
address=self._parse_address(result, search_type="general_search"),
description=self._parse_description(result),
days_on_mls=self.calculate_days_on_mls(result)
days_on_mls=self.calculate_days_on_mls(result),
agents=agents,
)
properties.append(realty_property)
return realty_property
with ThreadPoolExecutor(max_workers=self.NUM_PROPERTY_WORKERS) as executor:
futures = [
executor.submit(process_property, result) for result in response_json["data"][search_key]["results"]
]
for future in as_completed(futures):
result = future.result()
if result:
properties.append(result)
return {
"total": response_json["data"][search_key]["total"],
@ -558,18 +563,14 @@ class RealtorScraper(Scraper):
search_type = (
"comps"
if self.radius and location_type == "address"
else "address"
if location_type == "address" and not self.radius
else "area"
else "address" if location_type == "address" and not self.radius else "area"
)
if location_type == "address":
if not self.radius: #: single address search, non comps
property_id = location_info["mpr_id"]
search_variables |= {"property_id": property_id}
gql_results = self.general_search(
search_variables, search_type=search_type
)
gql_results = self.general_search(search_variables, search_type=search_type)
if gql_results["total"] == 0:
listing_id = self.get_latest_listing_id(property_id)
if listing_id is None:
@ -603,7 +604,7 @@ class RealtorScraper(Scraper):
}
if self.foreclosure:
search_variables['foreclosure'] = self.foreclosure
search_variables["foreclosure"] = self.foreclosure
result = self.general_search(search_variables, search_type=search_type)
total = result["total"]
@ -624,6 +625,19 @@ class RealtorScraper(Scraper):
return homes
def get_agents(self, property_id: str) -> list[Agent]:
payload = f'{{"query":"query GetHome($property_id: ID!) {{\\n home(property_id: $property_id) {{\\n __typename\\n\\n consumerAdvertisers: consumer_advertisers {{\\n __typename\\n type\\n advertiserId: advertiser_id\\n name\\n phone\\n type\\n href\\n slogan\\n photo {{\\n __typename\\n href\\n }}\\n showRealtorLogo: show_realtor_logo\\n hours\\n }}\\n\\n\\n }}\\n}}\\n","variables":{{"property_id":"{property_id}"}}}}'
response = self.session.post(self.PROPERTY_GQL, data=payload)
data = response.json()
try:
ads = data["data"]["home"]["consumerAdvertisers"]
except (KeyError, TypeError):
return []
agents = [Agent(name=ad["name"], phone=ad["phone"]) for ad in ads]
return agents
@staticmethod
def _parse_neighborhoods(result: dict) -> Optional[str]:
neighborhoods_list = []
@ -646,17 +660,19 @@ class RealtorScraper(Scraper):
def _parse_address(self, result: dict, search_type):
if search_type == "general_search":
address = result['location']['address']
address = result["location"]["address"]
else:
address = result["address"]
return Address(
street=" ".join([
self.handle_none_safely(address.get('street_number')),
self.handle_none_safely(address.get('street_direction')),
self.handle_none_safely(address.get('street_name')),
self.handle_none_safely(address.get('street_suffix')),
]).strip(),
street=" ".join(
[
self.handle_none_safely(address.get("street_number")),
self.handle_none_safely(address.get("street_direction")),
self.handle_none_safely(address.get("street_name")),
self.handle_none_safely(address.get("street_suffix")),
]
).strip(),
unit=address["unit"],
city=address["city"],
state=address["state_code"],
@ -705,12 +721,12 @@ class RealtorScraper(Scraper):
today = datetime.now()
if list_date:
if result["status"] == 'sold':
if result["status"] == "sold":
if last_sold_date:
days = (last_sold_date - list_date).days
if days >= 0:
return days
elif result["status"] in ('for_sale', 'for_rent'):
elif result["status"] in ("for_sale", "for_rent"):
days = (today - list_date).days
if days >= 0:
return days

3
homeharvest/exceptions.py
View File

@ -1,5 +1,6 @@
class InvalidListingType(Exception):
"""Raised when a provided listing type is does not exist."""
class InvalidDate(Exception):
"""Raised when only one of date_from or date_to is provided or not in the correct format. ex: 2023-10-23 """
"""Raised when only one of date_from or date_to is provided or not in the correct format. ex: 2023-10-23"""

15
homeharvest/utils.py
View File

@ -31,6 +31,9 @@ ordered_properties = [
"stories",
"hoa_fee",
"parking_garage",
"agent",
"broker",
"broker_phone",
"primary_photo",
"alt_photos",
]
@ -48,6 +51,14 @@ def process_result(result: Property) -> pd.DataFrame:
prop_data["state"] = address_data.state
prop_data["zip_code"] = address_data.zip
if "agents" in prop_data:
agents = prop_data["agents"]
if agents:
prop_data["agent"] = agents[0].name
if len(agents) > 1:
prop_data["broker"] = agents[1].name
prop_data["broker_phone"] = agents[1].phone
prop_data["price_per_sqft"] = prop_data["prc_sqft"]
description = result.description
@ -72,9 +83,7 @@ def process_result(result: Property) -> pd.DataFrame:
def validate_input(listing_type: str) -> None:
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 validate_dates(date_from: str | None, date_to: str | None) -> None:

197
poetry.lock generated
View File

@ -11,6 +11,17 @@ files = [
{file = "certifi-2023.7.22.tar.gz", hash = "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082"},
]
[[package]]
name = "cfgv"
version = "3.4.0"
description = "Validate configuration and produce human readable error messages."
optional = false
python-versions = ">=3.8"
files = [
{file = "cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9"},
{file = "cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560"},
]
[[package]]
name = "charset-normalizer"
version = "3.3.0"
@ -121,6 +132,17 @@ files = [
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]]
name = "distlib"
version = "0.3.8"
description = "Distribution utilities"
optional = false
python-versions = "*"
files = [
{file = "distlib-0.3.8-py2.py3-none-any.whl", hash = "sha256:034db59a0b96f8ca18035f36290806a9a6e6bd9d1ff91e45a7f172eb17e51784"},
{file = "distlib-0.3.8.tar.gz", hash = "sha256:1530ea13e350031b6312d8580ddb6b27a104275a31106523b8f123787f494f64"},
]
[[package]]
name = "exceptiongroup"
version = "1.1.3"
@ -135,6 +157,36 @@ files = [
[package.extras]
test = ["pytest (>=6)"]
[[package]]
name = "filelock"
version = "3.13.4"
description = "A platform independent file lock."
optional = false
python-versions = ">=3.8"
files = [
{file = "filelock-3.13.4-py3-none-any.whl", hash = "sha256:404e5e9253aa60ad457cae1be07c0f0ca90a63931200a47d9b6a6af84fd7b45f"},
{file = "filelock-3.13.4.tar.gz", hash = "sha256:d13f466618bfde72bd2c18255e269f72542c6e70e7bac83a0232d6b1cc5c8cf4"},
]
[package.extras]
docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
typing = ["typing-extensions (>=4.8)"]
[[package]]
name = "identify"
version = "2.5.35"
description = "File identification library for Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "identify-2.5.35-py2.py3-none-any.whl", hash = "sha256:c4de0081837b211594f8e877a6b4fad7ca32bbfc1a9307fdd61c28bfe923f13e"},
{file = "identify-2.5.35.tar.gz", hash = "sha256:10a7ca245cfcd756a554a7288159f72ff105ad233c7c4b9c6f0f4d108f5f6791"},
]
[package.extras]
license = ["ukkonen"]
[[package]]
name = "idna"
version = "3.4"
@ -157,6 +209,20 @@ files = [
{file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
]
[[package]]
name = "nodeenv"
version = "1.8.0"
description = "Node.js virtual environment builder"
optional = false
python-versions = ">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*"
files = [
{file = "nodeenv-1.8.0-py2.py3-none-any.whl", hash = "sha256:df865724bb3c3adc86b3876fa209771517b0cfe596beff01a92700e0e8be4cec"},
{file = "nodeenv-1.8.0.tar.gz", hash = "sha256:d51e0c37e64fbf47d017feac3145cdbb58836d7eee8c6f6d3b6880c5456227d2"},
]
[package.dependencies]
setuptools = "*"
[[package]]
name = "numpy"
version = "1.26.0"
@ -277,6 +343,21 @@ sql-other = ["SQLAlchemy (>=1.4.36)"]
test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
xml = ["lxml (>=4.8.0)"]
[[package]]
name = "platformdirs"
version = "4.2.0"
description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
optional = false
python-versions = ">=3.8"
files = [
{file = "platformdirs-4.2.0-py3-none-any.whl", hash = "sha256:0614df2a2f37e1a662acbd8e2b25b92ccf8632929bc6d43467e17fe89c75e068"},
{file = "platformdirs-4.2.0.tar.gz", hash = "sha256:ef0cc731df711022c174543cb70a9b5bd22e5a9337c8624ef2c2ceb8ddad8768"},
]
[package.extras]
docs = ["furo (>=2023.9.10)", "proselint (>=0.13)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"]
test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)"]
[[package]]
name = "pluggy"
version = "1.3.0"
@ -292,6 +373,24 @@ files = [
dev = ["pre-commit", "tox"]
testing = ["pytest", "pytest-benchmark"]
[[package]]
name = "pre-commit"
version = "3.7.0"
description = "A framework for managing and maintaining multi-language pre-commit hooks."
optional = false
python-versions = ">=3.9"
files = [
{file = "pre_commit-3.7.0-py2.py3-none-any.whl", hash = "sha256:5eae9e10c2b5ac51577c3452ec0a490455c45a0533f7960f993a0d01e59decab"},
{file = "pre_commit-3.7.0.tar.gz", hash = "sha256:e209d61b8acdcf742404408531f0c37d49d2c734fd7cff2d6076083d191cb060"},
]
[package.dependencies]
cfgv = ">=2.0.0"
identify = ">=1.0.0"
nodeenv = ">=0.11.1"
pyyaml = ">=5.1"
virtualenv = ">=20.10.0"
[[package]]
name = "pytest"
version = "7.4.2"
@ -339,6 +438,66 @@ files = [
{file = "pytz-2023.3.post1.tar.gz", hash = "sha256:7b4fddbeb94a1eba4b557da24f19fdf9db575192544270a9101d8509f9f43d7b"},
]
[[package]]
name = "pyyaml"
version = "6.0.1"
description = "YAML parser and emitter for Python"
optional = false
python-versions = ">=3.6"
files = [
{file = "PyYAML-6.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d858aa552c999bc8a8d57426ed01e40bef403cd8ccdd0fc5f6f04a00414cac2a"},
{file = "PyYAML-6.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd66fc5d0da6d9815ba2cebeb4205f95818ff4b79c3ebe268e75d961704af52f"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f003ed9ad21d6a4713f0a9b5a7a0a79e08dd0f221aff4525a2be4c346ee60aab"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afd7e57eddb1a54f0f1a974bc4391af8bcce0b444685d936840f125cf046d5bd"},
{file = "PyYAML-6.0.1-cp36-cp36m-win32.whl", hash = "sha256:fca0e3a251908a499833aa292323f32437106001d436eca0e6e7833256674585"},
{file = "PyYAML-6.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:f22ac1c3cac4dbc50079e965eba2c1058622631e526bd9afd45fedd49ba781fa"},
{file = "PyYAML-6.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b1275ad35a5d18c62a7220633c913e1b42d44b46ee12554e5fd39c70a243d6a3"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18aeb1bf9a78867dc38b259769503436b7c72f7a1f1f4c93ff9a17de54319b27"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:596106435fa6ad000c2991a98fa58eeb8656ef2325d7e158344fb33864ed87e3"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa90d3f661d43131ca170712d903e6295d1f7a0f595074f151c0aed377c9b9c"},
{file = "PyYAML-6.0.1-cp37-cp37m-win32.whl", hash = "sha256:9046c58c4395dff28dd494285c82ba00b546adfc7ef001486fbf0324bc174fba"},
{file = "PyYAML-6.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:4fb147e7a67ef577a588a0e2c17b6db51dda102c71de36f8549b6816a96e1867"},
{file = "PyYAML-6.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d4c7e777c441b20e32f52bd377e0c409713e8bb1386e1099c2415f26e479595"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c8098ddcc2a85b61647b2590f825f3db38891662cfc2fc776415143f599bb859"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
]
[[package]]
name = "requests"
version = "2.31.0"
@ -360,6 +519,22 @@ urllib3 = ">=1.21.1,<3"
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "setuptools"
version = "69.5.1"
description = "Easily download, build, install, upgrade, and uninstall Python packages"
optional = false
python-versions = ">=3.8"
files = [
{file = "setuptools-69.5.1-py3-none-any.whl", hash = "sha256:c636ac361bc47580504644275c9ad802c50415c7522212252c033bd15f301f32"},
{file = "setuptools-69.5.1.tar.gz", hash = "sha256:6c1fccdac05a97e598fb0ae3bbed5904ccb317337a51139dcd51453611bbb987"},
]
[package.extras]
docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
testing = ["build[virtualenv]", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.9)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "mypy (==1.9)", "packaging (>=23.2)", "pip (>=19.1)", "pytest (>=6,!=8.1.1)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (>=0.2.1)", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
testing-integration = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "packaging (>=23.2)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
[[package]]
name = "six"
version = "1.16.0"
@ -410,7 +585,27 @@ secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.
socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
zstd = ["zstandard (>=0.18.0)"]
[[package]]
name = "virtualenv"
version = "20.25.1"
description = "Virtual Python Environment builder"
optional = false
python-versions = ">=3.7"
files = [
{file = "virtualenv-20.25.1-py3-none-any.whl", hash = "sha256:961c026ac520bac5f69acb8ea063e8a4f071bcc9457b9c1f28f6b085c511583a"},
{file = "virtualenv-20.25.1.tar.gz", hash = "sha256:e08e13ecdca7a0bd53798f356d5831434afa5b07b93f0abdf0797b7a06ffe197"},
]
[package.dependencies]
distlib = ">=0.3.7,<1"
filelock = ">=3.12.2,<4"
platformdirs = ">=3.9.1,<5"
[package.extras]
docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.2)", "sphinx-argparse (>=0.4)", "sphinxcontrib-towncrier (>=0.2.1a0)", "towncrier (>=23.6)"]
test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8)", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10)"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.10,<3.13"
content-hash = "018a1a6afb2d7f4c764b9e1926145d7d8d630ffa43f7786e062cbfd9a9a845a0"
content-hash = "371781da268d5f61d6e798c023777f337b620e9b07a48c316825d7b998b63f02"

3
pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.15"
version = "0.3.16"
description = "Real estate scraping library"
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
homepage = "https://github.com/Bunsly/HomeHarvest"
@ -17,6 +17,7 @@ pandas = "^2.1.1"
[tool.poetry.group.dev.dependencies]
pytest = "^7.4.2"
pre-commit = "^3.7.0"
[build-system]
requires = ["poetry-core"]

60
tests/test_realtor.py
View File

@ -1,22 +1,12 @@
from homeharvest import scrape_property
from homeharvest.exceptions import (
InvalidListingType,
)
def test_realtor_pending_or_contingent():
pending_or_contingent_result = scrape_property(
location="Surprise, AZ", listing_type="pending"
)
pending_or_contingent_result = scrape_property(location="Surprise, AZ", listing_type="pending")
regular_result = scrape_property(location="Surprise, AZ", listing_type="for_sale")
assert all(
[
result is not None
for result in [pending_or_contingent_result, regular_result]
]
)
assert all([result is not None for result in [pending_or_contingent_result, regular_result]])
assert len(pending_or_contingent_result) != len(regular_result)
@ -71,17 +61,13 @@ def test_realtor_comps():
def test_realtor_last_x_days_sold():
days_result_30 = scrape_property(
location="Dallas, TX", listing_type="sold", past_days=30
)
days_result_30 = scrape_property(location="Dallas, TX", listing_type="sold", past_days=30)
days_result_10 = scrape_property(
location="Dallas, TX", listing_type="sold", past_days=10
)
days_result_10 = scrape_property(location="Dallas, TX", listing_type="sold", past_days=10)
assert all(
[result is not None for result in [days_result_30, days_result_10]]
) and len(days_result_30) != len(days_result_10)
assert all([result is not None for result in [days_result_30, days_result_10]]) and len(days_result_30) != len(
days_result_10
)
def test_realtor_date_range_sold():
@ -93,9 +79,9 @@ def test_realtor_date_range_sold():
location="Dallas, TX", listing_type="sold", date_from="2023-04-01", date_to="2023-06-10"
)
assert all(
[result is not None for result in [days_result_30, days_result_60]]
) and len(days_result_30) < len(days_result_60)
assert all([result is not None for result in [days_result_30, days_result_60]]) and len(days_result_30) < len(
days_result_60
)
def test_realtor_single_property():
@ -119,12 +105,8 @@ def test_realtor():
location="2530 Al Lipscomb Way",
listing_type="for_sale",
),
scrape_property(
location="Phoenix, AZ", listing_type="for_rent"
), #: does not support "city, state, USA" format
scrape_property(
location="Dallas, TX", listing_type="sold"
), #: does not support "city, state, USA" format
scrape_property(location="Phoenix, AZ", listing_type="for_rent"), #: does not support "city, state, USA" format
scrape_property(location="Dallas, TX", listing_type="sold"), #: does not support "city, state, USA" format
scrape_property(location="85281"),
]
@ -142,21 +124,21 @@ def test_realtor_city():
def test_realtor_bad_address():
bad_results = scrape_property(
location="abceefg ju098ot498hh9",
listing_type="for_sale",
)
location="abceefg ju098ot498hh9",
listing_type="for_sale",
)
if len(bad_results) == 0:
assert True
def test_realtor_foreclosed():
foreclosed = scrape_property(
location="Dallas, TX", listing_type="for_sale", past_days=100, foreclosure=True
)
foreclosed = scrape_property(location="Dallas, TX", listing_type="for_sale", past_days=100, foreclosure=True)
not_foreclosed = scrape_property(
location="Dallas, TX", listing_type="for_sale", past_days=100, foreclosure=False
)
not_foreclosed = scrape_property(location="Dallas, TX", listing_type="for_sale", past_days=100, foreclosure=False)
assert len(foreclosed) != len(not_foreclosed)
def test_realtor_agent():
scraped = scrape_property(location="Detroit, MI", listing_type="for_sale")
assert scraped["agent"].nunique() > 1