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

[enh] date_to and date_from

pull/40/head
Cullen Watson 2023-11-03 18:35:41 -05:00
parent c597a78191
commit 4edad901c5
8 changed files with 108 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
README.md
View File

@ -46,7 +46,11 @@ filename = f"HomeHarvest_{current_timestamp}.csv"
properties = scrape_property(
location="San Diego, CA",
listing_type="sold", # or (for_sale, for_rent, pending)
past_days=30, # sold in last 30 days - listed in last x days if (for_sale, for_rent)
past_days=30, # sold in last 30 days - listed in last 30 days if (for_sale, for_rent)
# date_from="2023-05-01", # alternative to past_days
# date_to="2023-05-28",
# mls_only=True, # only fetch MLS listings
# proxy="http://user:pass@host:port" # use a proxy to change your IP address
)
@ -57,34 +61,6 @@ properties.to_csv(filename, index=False)
print(properties.head())
```
### 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
```
## Output
```plaintext
@ -115,11 +91,45 @@ Optional
├── past_days (integer): Number of past days to filter properties. Utilizes 'last_sold_date' for 'sold' listing types, and 'list_date' for others (for_rent, for_sale).
│ Example: 30 (fetches properties listed/sold in the last 30 days)
│
├── date_range (string tuple): Start and end dates to filter properties listed or sold, both dates are required.
} (use this to get properties in chunks as there's a 10k result limit)
│ Format for both must be "YYYY-MM-DD".
│ Example: ("2023-05-01", "2023-05-15") (fetches properties listed/sold between these dates)
│
├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
│
└── 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
```plaintext
Property

11
homeharvest/__init__.py
View File

@ -1,10 +1,9 @@
import warnings
import pandas as pd
from .core.scrapers import ScraperInput
from .utils import process_result, ordered_properties, validate_input
from .utils import process_result, ordered_properties, validate_input, validate_dates
from .core.scrapers.realtor import RealtorScraper
from .core.scrapers.models import ListingType
from .exceptions import InvalidListingType, NoResultsFound
def scrape_property(
@ -14,6 +13,8 @@ def scrape_property(
mls_only: bool = False,
past_days: int = None,
proxy: str = None,
date_from: str = None,
date_to: str = None,
) -> pd.DataFrame:
"""
Scrape properties from Realtor.com based on a given location and listing type.
@ -22,9 +23,11 @@ def scrape_property(
:param radius: Get properties within _ (e.g. 1.0) miles. Only applicable for individual addresses.
:param mls_only: If set, fetches only listings with MLS IDs.
:param past_days: Get properties sold or listed (dependent on your listing_type) in the last _ days.
:param date_from, date_to: Get properties sold or listed (dependent on your listing_type) between these dates. format: 2021-01-28
:param proxy: Proxy to use for scraping
"""
validate_input(listing_type)
validate_dates(date_from, date_to)
scraper_input = ScraperInput(
location=location,
@ -33,6 +36,8 @@ def scrape_property(
radius=radius,
mls_only=mls_only,
last_x_days=past_days,
date_from=date_from,
date_to=date_to,
)
site = RealtorScraper(scraper_input)
@ -40,7 +45,7 @@ def scrape_property(
properties_dfs = [process_result(result) for result in results]
if not properties_dfs:
raise NoResultsFound("no results found for the query")
return pd.DataFrame()
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=FutureWarning)

4
homeharvest/core/scrapers/__init__.py
View File

@ -11,6 +11,8 @@ class ScraperInput:
mls_only: bool | None = None
proxy: str | None = None
last_x_days: int | None = None
date_from: str | None = None
date_to: str | None = None
class Scraper:
@ -36,6 +38,8 @@ class Scraper:
self.radius = scraper_input.radius
self.last_x_days = scraper_input.last_x_days
self.mls_only = scraper_input.mls_only
self.date_from = scraper_input.date_from
self.date_to = scraper_input.date_to
def search(self) -> list[Property]:
...

26
homeharvest/core/scrapers/realtor/__init__.py
View File

@ -9,7 +9,6 @@ from typing import Dict, Union, Optional
from concurrent.futures import ThreadPoolExecutor, as_completed
from .. import Scraper
from ....exceptions import NoResultsFound
from ..models import Property, Address, ListingType, Description
@ -38,7 +37,7 @@ class RealtorScraper(Scraper):
result = response_json["autocomplete"]
if not result:
raise NoResultsFound("No results found for location: " + self.location)
return None
return result[0]
@ -336,15 +335,17 @@ class RealtorScraper(Scraper):
}
}"""
date_param = (
'sold_date: { min: "$today-%sD" }' % self.last_x_days
if self.listing_type == ListingType.SOLD and self.last_x_days
else (
'list_date: { min: "$today-%sD" }' % self.last_x_days
if self.last_x_days
else ""
)
)
date_param = ""
if self.listing_type == ListingType.SOLD:
if self.date_from and self.date_to:
date_param = f'sold_date: {{ min: "{self.date_from}", max: "{self.date_to}" }}'
elif self.last_x_days:
date_param = f'sold_date: {{ min: "$today-{self.last_x_days}D" }}'
else:
if self.date_from and self.date_to:
date_param = f'list_date: {{ min: "{self.date_from}", max: "{self.date_to}" }}'
elif self.last_x_days:
date_param = f'list_date: {{ min: "$today-{self.last_x_days}D" }}'
sort_param = (
"sort: [{ field: sold_date, direction: desc }]"
@ -509,6 +510,9 @@ class RealtorScraper(Scraper):
def search(self):
location_info = self.handle_location()
if not location_info:
return []
location_type = location_info["area_type"]
search_variables = {

5
homeharvest/exceptions.py
View File

@ -1,6 +1,5 @@
class InvalidListingType(Exception):
"""Raised when a provided listing type is does not exist."""
class NoResultsFound(Exception):
"""Raised when no results are found for the given location"""
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 """

20
homeharvest/utils.py
View File

@ -1,6 +1,7 @@
from .core.scrapers.models import Property, ListingType
import pandas as pd
from .exceptions import InvalidListingType
from datetime import datetime
from .core.scrapers.models import Property, ListingType
from .exceptions import InvalidListingType, InvalidDate
ordered_properties = [
"property_url",
@ -70,3 +71,18 @@ def validate_input(listing_type: str) -> None:
raise InvalidListingType(
f"Provided listing type, '{listing_type}', does not exist."
)
def validate_dates(date_from: str | None, date_to: str | None) -> None:
if (date_from is not None and date_to is None) or (date_from is None and date_to is not None):
raise InvalidDate("Both date_from and date_to must be provided.")
if date_from and date_to:
try:
date_from_obj = datetime.strptime(date_from, "%Y-%m-%d")
date_to_obj = datetime.strptime(date_to, "%Y-%m-%d")
if date_to_obj < date_from_obj:
raise InvalidDate("date_to must be after date_from.")
except ValueError as e:
raise InvalidDate(f"Invalid date format or range")

2
pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.7"
version = "0.3.8"
description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
homepage = "https://github.com/Bunsly/HomeHarvest"

26
tests/test_realtor.py
View File

@ -1,7 +1,6 @@
from homeharvest import scrape_property
from homeharvest.exceptions import (
InvalidListingType,
NoResultsFound,
)
@ -85,6 +84,20 @@ def test_realtor_last_x_days_sold():
) and len(days_result_30) != len(days_result_10)
def test_realtor_date_range_sold():
days_result_30 = scrape_property(
location="Dallas, TX", listing_type="sold", date_from="2023-05-01", date_to="2023-05-28"
)
days_result_60 = scrape_property(
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)
def test_realtor_single_property():
results = [
scrape_property(
@ -117,15 +130,12 @@ def test_realtor():
assert all([result is not None for result in results])
bad_results = []
try:
bad_results += [
scrape_property(
def test_realtor_bad_address():
bad_results = scrape_property(
location="abceefg ju098ot498hh9",
listing_type="for_sale",
)
]
except (InvalidListingType, NoResultsFound):
if len(bad_results) == 0:
assert True
assert all([result is None for result in bad_results])