Compare commits

...

8 Commits

Author SHA1 Message Date
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
7 changed files with 72 additions and 81 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
@@ -180,20 +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
## 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

@@ -158,7 +158,8 @@ 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"),
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", [])),
style=property_info["basic"].get("type", "").upper(),
beds=property_info["basic"].get("beds"),
@@ -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
@@ -383,6 +384,12 @@ 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 +399,7 @@ class RealtorScraper(Scraper):
) {
home_search(
query: {
%s
nearby: {
coordinates: $coordinates
radius: $radius
@@ -404,6 +412,7 @@ class RealtorScraper(Scraper):
limit: 200
offset: $offset
) %s""" % (
is_foreclosure,
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
@@ -420,6 +429,7 @@ class RealtorScraper(Scraper):
) {
home_search(
query: {
%s
city: $city
county: $county
postal_code: $postal_code
@@ -432,6 +442,7 @@ class RealtorScraper(Scraper):
limit: 200
offset: $offset
) %s""" % (
is_foreclosure,
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
@@ -440,7 +451,7 @@ class RealtorScraper(Scraper):
)
else: #: general search, came from an address
query = (
"""query Property_search(
"""query Property_search(
$property_id: [ID]!
$offset: Int!,
) {
@@ -451,7 +462,7 @@ class RealtorScraper(Scraper):
limit: 1
offset: $offset
) %s"""
% results_query
% results_query
)
payload = {
@@ -467,12 +478,12 @@ 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 +498,10 @@ 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 +514,7 @@ 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 +578,20 @@ 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 +600,9 @@ 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"]
@@ -673,7 +695,6 @@ 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",
]

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 = "0.3.13"
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)