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

Add foreclosure parameter (#55)

pull/65/head v0.3.12
robertomr100 2024-03-03 12:45:28 -05:00 committed by GitHub
parent 03198428de
commit ab6a0e3b6e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 40 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
README.md
View File

@ -1,6 +1,6 @@
<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.
**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).
@ -13,8 +13,6 @@
- **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_
@ -46,9 +44,9 @@ 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)}")
@ -57,7 +55,6 @@ properties.to_csv(filename, index=False)
print(properties.head())
```
## Output
```plaintext
>>> properties.head()
@ -94,37 +91,9 @@ 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
@ -175,21 +144,4 @@ 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 using a proxy as a parameter to scrape_property() to change your IP address.
---

2
homeharvest/__init__.py
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)

2
homeharvest/core/scrapers/__init__.py
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]:
...

20
homeharvest/core/scrapers/realtor/__init__.py
View File

@ -381,9 +381,16 @@ class RealtorScraper(Scraper):
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 'foreclosure' in variables and variables['foreclosure'] == True:
is_foreclosure = "foreclosure: true"
if 'foreclosure' in variables and variables['foreclosure'] == False:
is_foreclosure = "foreclosure: false"
if search_type == "comps": #: comps search, came from an address
query = """query Property_search(
$coordinates: [Float]!
@ -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,
@ -541,7 +552,7 @@ class RealtorScraper(Scraper):
search_variables = {
"offset": 0,
}
search_type = (
"comps"
if self.radius and location_type == "address"
@ -586,6 +597,9 @@ 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"]

5
pyproject.toml
View File

@ -1,8 +1,8 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.12"
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
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]

12
tests/test_realtor.py
View File

@ -139,3 +139,15 @@ 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)