Compare commits

...

10 Commits

Author SHA1 Message Date
Cullen Watson
1f47fc3b7e fix: use enum value (#65) 2024-04-12 01:41:15 -05:00
Zachary Hampton
5c2498c62b - pending date, property type fields (#45)
- alt photos bug fix (#57)
2024-03-13 19:17:17 -07:00
Zachary Hampton
d775540afd - location bug fix 2024-03-06 16:31:06 -07:00
Cullen Watson
5ea9a6f6b6 docs: readme 2024-03-03 11:49:27 -06:00
robertomr100
ab6a0e3b6e Add foreclosure parameter (#55) 2024-03-03 11:45:28 -06:00
Zachary Hampton
03198428de Merge pull request #48 from Bunsly/for_rent_url
fix: rent url
2024-01-09 13:12:30 -07:00
Cullen Watson
70fa071318 fix: rent url 2024-01-08 12:46:31 -06:00
Cullen Watson
f7e74cf535 Merge pull request #44 from Bunsly/fix_postal_search
fix postal search to search just by zip
2023-12-02 00:40:13 -06:00
Cullen Watson
e17b976923 fix postal search to search just by zip 2023-12-02 00:39:28 -06:00
Zachary Hampton
ad13b55ea6 Update README.md 2023-11-30 11:48:48 -07:00
9 changed files with 109 additions and 119 deletions

View File

@@ -1,24 +1,16 @@
<img src="https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/d1a2bf8b-09f5-4c57-b33a-0ada8a34f12d" width="400">
**HomeHarvest** is a simple, yet comprehensive, real estate scraping library that extracts and formats data in the style of MLS listings.
[![Try with Replit](https://replit.com/badge?caption=Try%20with%20Replit)](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
**HomeHarvest** is a real estate scraping library that extracts and formats data in the style of MLS listings.
**Not technical?** Try out the web scraping tool on our site at [tryhomeharvest.com](https://tryhomeharvest.com).
*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com)** *to work with us.*
Check out another project we wrote: ***[JobSpy](https://github.com/Bunsly/JobSpy)** a Python package for job scraping*
## HomeHarvest Features
- **Source**: Fetches properties directly from **Realtor.com**.
- **Data Format**: Structures data to resemble MLS listings.
- **Export Flexibility**: Options to save as either CSV or Excel.
- **Usage Modes**:
- **Python**: For those who'd like to integrate scraping into their Python scripts.
- **CLI**: For users who prefer command-line operations.
[Video Guide for HomeHarvest](https://youtu.be/J1qgNPgmSLI) - _updated for release v0.3.4_
@@ -27,7 +19,7 @@ Check out another project we wrote: ***[JobSpy](https://github.com/Bunsly/JobSpy
## Installation
```bash
pip install homeharvest
pip install -U homeharvest
```
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
@@ -50,9 +42,9 @@ properties = scrape_property(
# date_from="2023-05-01", # alternative to past_days
# date_to="2023-05-28",
# foreclosure=True
# mls_only=True, # only fetch MLS listings
# proxy="http://user:pass@host:port" # use a proxy to change your IP address
)
print(f"Number of properties: {len(properties)}")
@@ -61,7 +53,6 @@ properties.to_csv(filename, index=False)
print(properties.head())
```
## Output
```plaintext
>>> properties.head()
@@ -98,37 +89,9 @@ Optional
├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
├── foreclosure (True/False): If set, fetches only foreclosures
└── proxy (string): In format 'http://user:pass@host:port'
```
### CLI
```
usage: homeharvest [-l {for_sale,for_rent,sold}] [-o {excel,csv}] [-f FILENAME] [-p PROXY] [-d DAYS] [-r RADIUS] [-m] [-c] location
Home Harvest Property Scraper
positional arguments:
location Location to scrape (e.g., San Francisco, CA)
options:
-l {for_sale,for_rent,sold,pending}, --listing_type {for_sale,for_rent,sold,pending}
Listing type to scrape
-o {excel,csv}, --output {excel,csv}
Output format
-f FILENAME, --filename FILENAME
Name of the output file (without extension)
-p PROXY, --proxy PROXY
Proxy to use for scraping
-d DAYS, --days DAYS Sold/listed in last _ days filter.
-r RADIUS, --radius RADIUS
Get comparable properties within _ (e.g., 0.0) miles. Only applicable for individual addresses.
-m, --mls_only If set, fetches only MLS listings.
```
```bash
homeharvest "San Francisco, CA" -l for_rent -o excel -f HomeHarvest
```
### Property Schema
@@ -161,6 +124,7 @@ Property
│ ├── days_on_mls
│ ├── list_price
│ ├── list_date
│ ├── pending_date
│ ├── sold_price
│ ├── last_sold_date
│ ├── price_per_sqft
@@ -180,20 +144,3 @@ 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
## Frequently Asked Questions
---
**Q: Encountering issues with your searches?**
**A:** Try to broaden the parameters you're using. If problems persist, [submit an issue](https://github.com/ZacharyHampton/HomeHarvest/issues).
---
**Q: Received a Forbidden 403 response code?**
**A:** This indicates that you have been blocked by Realtor.com for sending too many requests. We recommend:
- Waiting a few seconds between requests.
- Trying a VPN or useing a proxy as a parameter to scrape_property() to change your IP address.
---

View File

@@ -15,6 +15,7 @@ def scrape_property(
proxy: str = None,
date_from: str = None,
date_to: str = None,
foreclosure: bool = None,
) -> pd.DataFrame:
"""
Scrape properties from Realtor.com based on a given location and listing type.
@@ -38,6 +39,7 @@ def scrape_property(
last_x_days=past_days,
date_from=date_from,
date_to=date_to,
foreclosure=foreclosure,
)
site = RealtorScraper(scraper_input)

View File

@@ -13,6 +13,7 @@ class ScraperInput:
last_x_days: int | None = None
date_from: str | None = None
date_to: str | None = None
foreclosure: bool | None = None
class Scraper:
@@ -40,6 +41,7 @@ class Scraper:
self.mls_only = scraper_input.mls_only
self.date_from = scraper_input.date_from
self.date_to = scraper_input.date_to
self.foreclosure = scraper_input.foreclosure
def search(self) -> list[Property]:
...

View File

@@ -23,6 +23,27 @@ class ListingType(Enum):
SOLD = "SOLD"
class PropertyType(Enum):
APARTMENT = "APARTMENT"
BUILDING = "BUILDING"
COMMERCIAL = "COMMERCIAL"
CONDO_TOWNHOME = "CONDO_TOWNHOME"
CONDO_TOWNHOME_ROWHOME_COOP = "CONDO_TOWNHOME_ROWHOME_COOP"
CONDO = "CONDO"
CONDOS = "CONDOS"
COOP = "COOP"
DUPLEX_TRIPLEX = "DUPLEX_TRIPLEX"
FARM = "FARM"
INVESTMENT = "INVESTMENT"
LAND = "LAND"
MOBILE = "MOBILE"
MULTI_FAMILY = "MULTI_FAMILY"
RENTAL = "RENTAL"
SINGLE_FAMILY = "SINGLE_FAMILY"
TOWNHOMES = "TOWNHOMES"
OTHER = "OTHER"
@dataclass
class Address:
street: str | None = None
@@ -36,7 +57,7 @@ class Address:
class Description:
primary_photo: str | None = None
alt_photos: list[str] | None = None
style: str | None = None
style: PropertyType | None = None
beds: int | None = None
baths_full: int | None = None
baths_half: int | None = None
@@ -58,6 +79,7 @@ class Property:
list_price: int | None = None
list_date: str | None = None
pending_date: str | None = None
last_sold_date: str | None = None
prc_sqft: int | None = None
hoa_fee: int | None = None

View File

@@ -9,7 +9,7 @@ from typing import Dict, Union, Optional
from concurrent.futures import ThreadPoolExecutor, as_completed
from .. import Scraper
from ..models import Property, Address, ListingType, Description
from ..models import Property, Address, ListingType, Description, PropertyType
class RealtorScraper(Scraper):
@@ -84,11 +84,10 @@ class RealtorScraper(Scraper):
garage
permalink
}
primary_photo {
href
}
photos {
href
media {
photos {
href
}
}
}
}"""
@@ -120,9 +119,11 @@ class RealtorScraper(Scraper):
"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
last_sold_date = datetime.strptime(last_sold_date_str, "%Y-%m-%d") if last_sold_date_str else None
pending_date = datetime.strptime(pending_date_str, "%Y-%m-%d") if pending_date_str else None
today = datetime.now()
days_on_mls = None
@@ -150,6 +151,7 @@ class RealtorScraper(Scraper):
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,
@@ -158,8 +160,7 @@ class RealtorScraper(Scraper):
else None,
address=self._parse_address(property_info, search_type="handle_listing"),
description=Description(
primary_photo=property_info["primary_photo"].get("href", "").replace("s.jpg", "od-w480_h360_x2.webp?w=1080&q=75"),
alt_photos=self.process_alt_photos(property_info.get("photos", [])),
alt_photos=self.process_alt_photos(property_info.get("media", {}).get("photos", [])),
style=property_info["basic"].get("type", "").upper(),
beds=property_info["basic"].get("beds"),
baths_full=property_info["basic"].get("baths_full"),
@@ -288,7 +289,7 @@ class RealtorScraper(Scraper):
]
def general_search(
self, variables: dict, search_type: str
self, variables: dict, search_type: str
) -> Dict[str, Union[int, list[Property]]]:
"""
Handles a location area & returns a list of properties
@@ -297,6 +298,7 @@ class RealtorScraper(Scraper):
count
total
results {
pending_date
property_id
list_date
status
@@ -309,6 +311,7 @@ class RealtorScraper(Scraper):
is_pending
}
description {
type
sqft
beds
baths_full
@@ -383,6 +386,12 @@ class RealtorScraper(Scraper):
)
listing_type = ListingType.FOR_SALE if self.listing_type == ListingType.PENDING else self.listing_type
is_foreclosure = ""
if variables.get('foreclosure') is True:
is_foreclosure = "foreclosure: true"
elif variables.get('foreclosure') is False:
is_foreclosure = "foreclosure: false"
if search_type == "comps": #: comps search, came from an address
query = """query Property_search(
@@ -392,6 +401,7 @@ class RealtorScraper(Scraper):
) {
home_search(
query: {
%s
nearby: {
coordinates: $coordinates
radius: $radius
@@ -404,6 +414,7 @@ class RealtorScraper(Scraper):
limit: 200
offset: $offset
) %s""" % (
is_foreclosure,
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
@@ -420,6 +431,7 @@ class RealtorScraper(Scraper):
) {
home_search(
query: {
%s
city: $city
county: $county
postal_code: $postal_code
@@ -432,6 +444,7 @@ class RealtorScraper(Scraper):
limit: 200
offset: $offset
) %s""" % (
is_foreclosure,
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
@@ -440,7 +453,7 @@ class RealtorScraper(Scraper):
)
else: #: general search, came from an address
query = (
"""query Property_search(
"""query Property_search(
$property_id: [ID]!
$offset: Int!,
) {
@@ -451,7 +464,7 @@ class RealtorScraper(Scraper):
limit: 1
offset: $offset
) %s"""
% results_query
% results_query
)
payload = {
@@ -467,12 +480,12 @@ 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": []}
@@ -487,10 +500,10 @@ class RealtorScraper(Scraper):
continue
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")
@@ -503,7 +516,7 @@ class RealtorScraper(Scraper):
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']}",
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",
status="PENDING" if is_pending else result["status"].upper(),
list_price=result["list_price"],
list_date=result["list_date"].split("T")[0]
@@ -567,12 +580,20 @@ class RealtorScraper(Scraper):
return gql_results["properties"]
else: #: general search, comps (radius)
if not location_info.get("centroid"):
return []
coordinates = list(location_info["centroid"].values())
search_variables |= {
"coordinates": coordinates,
"radius": "{}mi".format(self.radius),
}
elif location_type == "postal_code":
search_variables |= {
"postal_code": location_info.get("postal_code"),
}
else: #: general search, location
search_variables |= {
"city": location_info.get("city"),
@@ -581,6 +602,9 @@ class RealtorScraper(Scraper):
"postal_code": location_info.get("postal_code"),
}
if self.foreclosure:
search_variables['foreclosure'] = self.foreclosure
result = self.general_search(search_variables, search_type=search_type)
total = result["total"]
homes = result["properties"]
@@ -641,7 +665,6 @@ class RealtorScraper(Scraper):
@staticmethod
def _parse_description(result: dict) -> Description:
description_data = result.get("description", {})
if description_data is None or not isinstance(description_data, dict):
@@ -661,7 +684,7 @@ class RealtorScraper(Scraper):
return Description(
primary_photo=primary_photo,
alt_photos=RealtorScraper.process_alt_photos(result.get("photos")),
style=style,
style=PropertyType(style) if style else None,
beds=description_data.get("beds"),
baths_full=description_data.get("baths_full"),
baths_half=description_data.get("baths_half"),
@@ -673,7 +696,6 @@ class RealtorScraper(Scraper):
stories=description_data.get("stories"),
)
@staticmethod
def calculate_days_on_mls(result: dict) -> Optional[int]:
list_date_str = result.get("list_date")

View File

@@ -5,8 +5,6 @@ from .exceptions import InvalidListingType, InvalidDate
ordered_properties = [
"property_url",
"primary_photo",
"alt_photos",
"mls",
"mls_id",
"status",
@@ -33,6 +31,8 @@ ordered_properties = [
"stories",
"hoa_fee",
"parking_garage",
"primary_photo",
"alt_photos",
]
@@ -53,7 +53,7 @@ def process_result(result: Property) -> pd.DataFrame:
description = result.description
prop_data["primary_photo"] = description.primary_photo
prop_data["alt_photos"] = ", ".join(description.alt_photos)
prop_data["style"] = description.style
prop_data["style"] = description.style.value
prop_data["beds"] = description.beds
prop_data["full_baths"] = description.baths_full
prop_data["half_baths"] = description.baths_half

29
poetry.lock generated
View File

@@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
[[package]]
name = "certifi"
@@ -121,17 +121,6 @@ files = [
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]]
name = "et-xmlfile"
version = "1.1.0"
description = "An implementation of lxml.xmlfile for the standard library"
optional = false
python-versions = ">=3.6"
files = [
{file = "et_xmlfile-1.1.0-py3-none-any.whl", hash = "sha256:a2ba85d1d6a74ef63837eed693bcb89c3f752169b0e3e7ae5b16ca5e1b3deada"},
{file = "et_xmlfile-1.1.0.tar.gz", hash = "sha256:8eb9e2bc2f8c97e37a2dc85a09ecdcdec9d8a396530a6d5a33b30b9a92da0c5c"},
]
[[package]]
name = "exceptiongroup"
version = "1.1.3"
@@ -209,20 +198,6 @@ files = [
{file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"},
]
[[package]]
name = "openpyxl"
version = "3.1.2"
description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
optional = false
python-versions = ">=3.6"
files = [
{file = "openpyxl-3.1.2-py2.py3-none-any.whl", hash = "sha256:f91456ead12ab3c6c2e9491cf33ba6d08357d802192379bb482f1033ade496f5"},
{file = "openpyxl-3.1.2.tar.gz", hash = "sha256:a6f5977418eff3b2d5500d54d9db50c8277a368436f4e4f8ddb1be3422870184"},
]
[package.dependencies]
et-xmlfile = "*"
[[package]]
name = "packaging"
version = "23.2"
@@ -438,4 +413,4 @@ zstd = ["zstandard (>=0.18.0)"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.10,<3.13"
content-hash = "09ad811d74a42363ff4c3ccd012d8f73c89d7d978e5a6445b0f3d2e231922f1b"
content-hash = "018a1a6afb2d7f4c764b9e1926145d7d8d630ffa43f7786e062cbfd9a9a845a0"

View File

@@ -1,8 +1,8 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.10"
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
version = "0.3.15"
description = "Real estate scraping library"
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
homepage = "https://github.com/Bunsly/HomeHarvest"
readme = "README.md"
@@ -13,7 +13,6 @@ homeharvest = "homeharvest.cli:main"
python = ">=3.10,<3.13"
requests = "^2.31.0"
pandas = "^2.1.1"
openpyxl = "^3.1.2"
[tool.poetry.group.dev.dependencies]

View File

@@ -131,6 +131,15 @@ def test_realtor():
assert all([result is not None for result in results])
def test_realtor_city():
results = scrape_property(
location="Atlanta, GA",
listing_type="for_sale",
)
assert results is not None and len(results) > 0
def test_realtor_bad_address():
bad_results = scrape_property(
location="abceefg ju098ot498hh9",
@@ -139,3 +148,15 @@ def test_realtor_bad_address():
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
)
not_foreclosed = scrape_property(
location="Dallas, TX", listing_type="for_sale", past_days=100, foreclosure=False
)
assert len(foreclosed) != len(not_foreclosed)