mirror of
https://github.com/Bunsly/HomeHarvest.git
synced 2026-03-05 20:14:30 -08:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
93a1cbe17f | ||
|
|
49d27943c4 | ||
|
|
05fca9b7e6 |
42
README.md
42
README.md
@@ -20,8 +20,24 @@
|
|||||||
pip install --force-reinstall homeharvest
|
pip install --force-reinstall homeharvest
|
||||||
```
|
```
|
||||||
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
|
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
|
||||||
|
|
||||||
## Usage
|
## Usage
|
||||||
|
|
||||||
|
### CLI
|
||||||
|
|
||||||
|
```bash
|
||||||
|
homeharvest "San Francisco, CA" --site_name zillow realtor.com redfin --listing_type for_rent --output excel --filename HomeHarvest
|
||||||
|
```
|
||||||
|
|
||||||
|
This will scrape properties from the specified sites for the given location and listing type, and save the results to an Excel file named `HomeHarvest.xlsx`.
|
||||||
|
|
||||||
|
By default:
|
||||||
|
- If `--site_name` is not provided, it will scrape from all available sites.
|
||||||
|
- If `--listing_type` is left blank, the default is `for_sale`, other options are `for_rent` or `sold`.
|
||||||
|
- The `--output` default format is `excel`, options are `csv` or `excel`.
|
||||||
|
- If `--filename` is left blank, the default is `HomeHarvest_<current_timestamp>`
|
||||||
|
|
||||||
|
### Python
|
||||||
```py
|
```py
|
||||||
from homeharvest import scrape_property
|
from homeharvest import scrape_property
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
@@ -35,16 +51,17 @@ properties: pd.DataFrame = scrape_property(
|
|||||||
#: Note, to export to CSV or Excel, use properties.to_csv() or properties.to_excel().
|
#: Note, to export to CSV or Excel, use properties.to_csv() or properties.to_excel().
|
||||||
print(properties)
|
print(properties)
|
||||||
```
|
```
|
||||||
|
|
||||||
## Output
|
## Output
|
||||||
```py
|
```py
|
||||||
>>> properties.head()
|
>>> properties.head()
|
||||||
street city ... mls_id description
|
property_url site_name listing_type apt_min_price apt_max_price ...
|
||||||
0 420 N Scottsdale Rd Tempe ... NaN NaN
|
0 https://www.redfin.com/AZ/Tempe/1003-W-Washing... redfin for_rent 1666.0 2750.0 ...
|
||||||
1 1255 E University Dr Tempe ... NaN NaN
|
1 https://www.redfin.com/AZ/Tempe/VELA-at-Town-L... redfin for_rent 1665.0 3763.0 ...
|
||||||
2 1979 E Rio Salado Pkwy Tempe ... NaN NaN
|
2 https://www.redfin.com/AZ/Tempe/Camden-Tempe/a... redfin for_rent 1939.0 3109.0 ...
|
||||||
3 548 S Wilson St Tempe ... None None
|
3 https://www.redfin.com/AZ/Tempe/Emerson-Park/a... redfin for_rent 1185.0 1817.0 ...
|
||||||
4 945 E Playa Del Norte Dr Unit 4027 Tempe ... NaN NaN
|
4 https://www.redfin.com/AZ/Tempe/Rio-Paradiso-A... redfin for_rent 1470.0 2235.0 ...
|
||||||
[5 rows x 23 columns]
|
[5 rows x 41 columns]
|
||||||
```
|
```
|
||||||
|
|
||||||
### Parameters for `scrape_properties()`
|
### Parameters for `scrape_properties()`
|
||||||
@@ -104,7 +121,14 @@ Property
|
|||||||
│ └── bldg_min_area (int)
|
│ └── bldg_min_area (int)
|
||||||
|
|
||||||
└── Apartment Details (for property type: apartment):
|
└── Apartment Details (for property type: apartment):
|
||||||
└── apt_min_price (int)
|
├── apt_min_beds: int
|
||||||
|
├── apt_max_beds: int
|
||||||
|
├── apt_min_baths: float
|
||||||
|
├── apt_max_baths: float
|
||||||
|
├── apt_min_price: int
|
||||||
|
├── apt_max_price: int
|
||||||
|
├── apt_min_sqft: int
|
||||||
|
├── apt_max_sqft: int
|
||||||
```
|
```
|
||||||
## Supported Countries for Property Scraping
|
## Supported Countries for Property Scraping
|
||||||
|
|
||||||
|
|||||||
@@ -68,10 +68,10 @@ def get_ordered_properties(result: Property) -> list[str]:
|
|||||||
"year_built",
|
"year_built",
|
||||||
"agent_name",
|
"agent_name",
|
||||||
"mls_id",
|
"mls_id",
|
||||||
"description",
|
|
||||||
"img_src",
|
"img_src",
|
||||||
"latitude",
|
"latitude",
|
||||||
"longitude",
|
"longitude",
|
||||||
|
"description",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
57
homeharvest/cli.py
Normal file
57
homeharvest/cli.py
Normal file
@@ -0,0 +1,57 @@
|
|||||||
|
import argparse
|
||||||
|
import datetime
|
||||||
|
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(
|
||||||
|
"--site_name",
|
||||||
|
type=str,
|
||||||
|
nargs="*",
|
||||||
|
default=None,
|
||||||
|
help="Site name(s) to scrape from (e.g., realtor.com zillow)",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--listing_type",
|
||||||
|
type=str,
|
||||||
|
default="for_sale",
|
||||||
|
choices=["for_sale", "for_rent", "sold"],
|
||||||
|
help="Listing type to scrape",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--output",
|
||||||
|
type=str,
|
||||||
|
default="excel",
|
||||||
|
choices=["excel", "csv"],
|
||||||
|
help="Output format",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--filename",
|
||||||
|
type=str,
|
||||||
|
default=None,
|
||||||
|
help="Name of the output file (without extension)",
|
||||||
|
)
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
result = scrape_property(args.location, args.site_name, args.listing_type)
|
||||||
|
|
||||||
|
if not args.filename:
|
||||||
|
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||||
|
args.filename = f"HomeHarvest_{timestamp}"
|
||||||
|
|
||||||
|
if args.output == "excel":
|
||||||
|
output_filename = f"{args.filename}.xlsx"
|
||||||
|
result.to_excel(output_filename, index=False)
|
||||||
|
print(f"Excel file saved as {output_filename}")
|
||||||
|
elif args.output == "csv":
|
||||||
|
output_filename = f"{args.filename}.csv"
|
||||||
|
result.to_csv(output_filename, index=False)
|
||||||
|
print(f"CSV file saved as {output_filename}")
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
@@ -188,7 +188,9 @@ class ZillowScraper(Scraper):
|
|||||||
else None,
|
else None,
|
||||||
"img_src": result.get("imgSrc"),
|
"img_src": result.get("imgSrc"),
|
||||||
"price_per_sqft": int(home_info["price"] // home_info["livingArea"])
|
"price_per_sqft": int(home_info["price"] // home_info["livingArea"])
|
||||||
if "livingArea" in home_info and "price" in home_info
|
if "livingArea" in home_info
|
||||||
|
and home_info["livingArea"] != 0
|
||||||
|
and "price" in home_info
|
||||||
else None,
|
else None,
|
||||||
}
|
}
|
||||||
property_obj = Property(**property_data)
|
property_obj = Property(**property_data)
|
||||||
|
|||||||
@@ -1,11 +1,14 @@
|
|||||||
[tool.poetry]
|
[tool.poetry]
|
||||||
name = "homeharvest"
|
name = "homeharvest"
|
||||||
version = "0.2.2"
|
version = "0.2.3"
|
||||||
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
|
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
|
||||||
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
|
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
|
||||||
homepage = "https://github.com/ZacharyHampton/HomeHarvest"
|
homepage = "https://github.com/ZacharyHampton/HomeHarvest"
|
||||||
readme = "README.md"
|
readme = "README.md"
|
||||||
|
|
||||||
|
[tool.poetry.scripts]
|
||||||
|
homeharvest = "homeharvest.cli:main"
|
||||||
|
|
||||||
[tool.poetry.dependencies]
|
[tool.poetry.dependencies]
|
||||||
python = "^3.10"
|
python = "^3.10"
|
||||||
requests = "^2.31.0"
|
requests = "^2.31.0"
|
||||||
@@ -18,4 +21,4 @@ pytest = "^7.4.2"
|
|||||||
|
|
||||||
[build-system]
|
[build-system]
|
||||||
requires = ["poetry-core"]
|
requires = ["poetry-core"]
|
||||||
build-backend = "poetry.core.masonry.api"
|
build-backend = "poetry.core.masonry.api"
|
||||||
Reference in New Issue
Block a user