Compare commits

...

11 Commits

Author SHA1 Message Date
Zachary Hampton
f726548cc6 Update pyproject.toml 2023-10-18 09:35:48 -07:00
Zachary Hampton
fad7d670eb Update README.md 2023-10-18 08:37:42 -07:00
Zachary Hampton
89a6f93c9f Update pyproject.toml 2023-10-18 08:37:26 -07:00
Zachary Hampton
e1090b06e4 Update README.md 2023-10-17 20:22:25 -07:00
Cullen Watson
5036e74b60 Merge branch 'master' of https://github.com/ZacharyHampton/HomeHarvest 2023-10-09 11:30:17 -05:00
Cullen Watson
2cb544bc8d [chore] display clickable URLs in jupyter 2023-10-09 11:28:56 -05:00
Zachary Hampton
68cb365e03 Merge pull request #34 from ZacharyHampton/days_on_mls
[enh] days_on_mls attr
2023-10-09 09:04:59 -07:00
Cullen Watson
23876d5725 [chore] function types 2023-10-09 11:02:51 -05:00
Cullen Watson
b59d55f6b5 [enh] days_on_mls attr 2023-10-09 11:00:36 -05:00
Cullen Watson
3c3adb5f29 [docs] update video 2023-10-05 20:24:23 -05:00
Zachary Hampton
6ede8622cc - pending listing support
- removal of pending_or_contingent param
2023-10-05 11:43:00 -07:00
10 changed files with 138 additions and 59 deletions

View File

@@ -6,9 +6,9 @@
**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://calendly.com/zachary-products/15min)** *to work with us.*
*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/bunsly/15min)** *to work with us.*
Check out another project we wrote: ***[JobSpy](https://github.com/cullenwatson/JobSpy)** a Python package for job scraping*
Check out another project we wrote: ***[JobSpy](https://github.com/Bunsly/JobSpy)** a Python package for job scraping*
## HomeHarvest Features
@@ -20,7 +20,7 @@ Check out another project we wrote: ***[JobSpy](https://github.com/cullenwatson/
- **CLI**: For users who prefer command-line operations.
[Video Guide for HomeHarvest](https://youtu.be/JnV7eR2Ve2o) - _updated for release v0.2.7_
[Video Guide for HomeHarvest](https://youtu.be/J1qgNPgmSLI) - _updated for release v0.3.4_
![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
@@ -45,9 +45,8 @@ filename = f"HomeHarvest_{current_timestamp}.csv"
properties = scrape_property(
location="San Diego, CA",
listing_type="sold", # or (for_sale, for_rent)
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)
# pending_or_contingent=True # use on for_sale listings to find pending / contingent listings
# mls_only=True, # only fetch MLS listings
# proxy="http://user:pass@host:port" # use a proxy to change your IP address
)
@@ -69,7 +68,7 @@ positional arguments:
location Location to scrape (e.g., San Francisco, CA)
options:
-l {for_sale,for_rent,sold}, --listing_type {for_sale,for_rent,sold}
-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
@@ -81,9 +80,6 @@ options:
-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.
-c, --pending_or_contingent
If set, fetches only pending or contingent listings. Only applicable for for_sale listings from general area searches.
```
```bash
homeharvest "San Francisco, CA" -l for_rent -o excel -f HomeHarvest
@@ -110,6 +106,7 @@ Required
- 'for_rent'
- 'for_sale'
- 'sold'
- 'pending'
Optional
├── radius (decimal): Radius in miles to find comparable properties based on individual addresses.
@@ -117,8 +114,6 @@ 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)
|
├── pending_or_contingent (True/False): If set, fetches only pending or contingent listings. Only applicable for `for_sale listings` from general area searches.
├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
@@ -152,6 +147,7 @@ Property
│ └── lot_sqft
├── Property Listing Details:
│ ├── days_on_mls
│ ├── list_price
│ ├── list_date
│ ├── sold_price

View File

@@ -4,7 +4,9 @@
"cell_type": "code",
"execution_count": null,
"id": "cb48903e-5021-49fe-9688-45cd0bc05d0f",
"metadata": {},
"metadata": {
"is_executing": true
},
"outputs": [],
"source": [
"from homeharvest import scrape_property\n",
@@ -84,10 +86,34 @@
"outputs": [],
"source": [
"# check sold properties\n",
"scrape_property(\n",
"properties = scrape_property(\n",
" location=\"90210\",\n",
" listing_type=\"sold\"\n",
")"
" listing_type=\"sold\",\n",
" past_days=10\n",
")\n",
"display(properties)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "628c1ce2",
"metadata": {
"collapsed": false,
"is_executing": true,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"source": [
"# display clickable URLs\n",
"from IPython.display import display, HTML\n",
"properties['property_url'] = '<a href=\"' + properties['property_url'] + '\" target=\"_blank\">' + properties['property_url'] + '</a>'\n",
"\n",
"html = properties.to_html(escape=False)\n",
"truncate_width = f'<style>.dataframe td {{ max-width: 200px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }}</style>{html}'\n",
"display(HTML(truncate_width))"
]
}
],

View File

@@ -13,7 +13,6 @@ def scrape_property(
radius: float = None,
mls_only: bool = False,
past_days: int = None,
pending_or_contingent: bool = False,
proxy: str = None,
) -> pd.DataFrame:
"""
@@ -23,7 +22,6 @@ 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 pending_or_contingent: If set, fetches only pending or contingent listings. Only applicable for for_sale listings from general area searches.
:param proxy: Proxy to use for scraping
"""
validate_input(listing_type)
@@ -35,7 +33,6 @@ def scrape_property(
radius=radius,
mls_only=mls_only,
last_x_days=past_days,
pending_or_contingent=pending_or_contingent,
)
site = RealtorScraper(scraper_input)

View File

@@ -14,7 +14,7 @@ def main():
"--listing_type",
type=str,
default="for_sale",
choices=["for_sale", "for_rent", "sold"],
choices=["for_sale", "for_rent", "sold", "pending"],
help="Listing type to scrape",
)
@@ -60,13 +60,6 @@ def main():
help="If set, fetches only MLS listings.",
)
parser.add_argument(
"-c",
"--pending_or_contingent",
action="store_true",
help="If set, fetches only pending or contingent listings. Only applicable for for_sale listings from general area searches.",
)
args = parser.parse_args()
result = scrape_property(
@@ -76,7 +69,6 @@ def main():
proxy=args.proxy,
mls_only=args.mls_only,
past_days=args.days,
pending_or_contingent=args.pending_or_contingent,
)
if not args.filename:

View File

@@ -11,7 +11,6 @@ class ScraperInput:
mls_only: bool | None = None
proxy: str | None = None
last_x_days: int | None = None
pending_or_contingent: bool | None = None
class Scraper:
@@ -37,7 +36,6 @@ class Scraper:
self.radius = scraper_input.radius
self.last_x_days = scraper_input.last_x_days
self.mls_only = scraper_input.mls_only
self.pending_or_contingent = scraper_input.pending_or_contingent
def search(self) -> list[Property]:
...

View File

@@ -19,6 +19,7 @@ class SiteName(Enum):
class ListingType(Enum):
FOR_SALE = "FOR_SALE"
FOR_RENT = "FOR_RENT"
PENDING = "PENDING"
SOLD = "SOLD"
@@ -58,6 +59,7 @@ class Property:
last_sold_date: str | None = None
prc_sqft: int | None = None
hoa_fee: int | None = None
days_on_mls: int | None = None
description: Description | None = None
latitude: float | None = None

View File

@@ -4,6 +4,7 @@ homeharvest.realtor.__init__
This module implements the scraper for realtor.com
"""
from datetime import datetime
from typing import Dict, Union, Optional
from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -18,7 +19,6 @@ class RealtorScraper(Scraper):
ADDRESS_AUTOCOMPLETE_URL = "https://parser-external.geo.moveaws.com/suggest"
def __init__(self, scraper_input):
self.counter = 1
super().__init__(scraper_input)
def handle_location(self):
@@ -105,11 +105,29 @@ class RealtorScraper(Scraper):
)
able_to_get_lat_long = (
property_info
and property_info.get("address")
and property_info["address"].get("location")
and property_info["address"]["location"].get("coordinate")
property_info
and property_info.get("address")
and property_info["address"].get("location")
and property_info["address"]["location"].get("coordinate")
)
list_date_str = property_info["basic"]["list_date"].split("T")[0] if property_info["basic"].get(
"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
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
today = datetime.now()
days_on_mls = None
status = property_info["basic"]["status"].lower()
if list_date:
if status == "sold" and last_sold_date:
days_on_mls = (last_sold_date - list_date).days
elif status in ('for_sale', 'for_rent'):
days_on_mls = (today - list_date).days
if days_on_mls and days_on_mls < 0:
days_on_mls = None
listing = Property(
mls=mls,
@@ -119,17 +137,13 @@ class RealtorScraper(Scraper):
property_url=f"{self.PROPERTY_URL}{property_info['details']['permalink']}",
status=property_info["basic"]["status"].upper(),
list_price=property_info["basic"]["price"],
list_date=property_info["basic"]["list_date"].split("T")[0]
if property_info["basic"].get("list_date")
else None,
list_date=list_date,
prc_sqft=property_info["basic"].get("price")
/ property_info["basic"].get("sqft")
/ property_info["basic"].get("sqft")
if property_info["basic"].get("price")
and property_info["basic"].get("sqft")
else None,
last_sold_date=property_info["basic"]["sold_date"].split("T")[0]
if property_info["basic"].get("sold_date")
and property_info["basic"].get("sqft")
else None,
last_sold_date=last_sold_date,
latitude=property_info["address"]["location"]["coordinate"].get("lat")
if able_to_get_lat_long
else None,
@@ -149,6 +163,7 @@ class RealtorScraper(Scraper):
garage=property_info["details"].get("garage"),
stories=property_info["details"].get("stories"),
),
days_on_mls=days_on_mls
)
return [listing]
@@ -274,6 +289,10 @@ class RealtorScraper(Scraper):
last_sold_date
list_price
price_per_sqft
flags {
is_contingent
is_pending
}
description {
sqft
beds
@@ -335,17 +354,19 @@ class RealtorScraper(Scraper):
pending_or_contingent_param = (
"or_filters: { contingent: true, pending: true }"
if self.pending_or_contingent
if self.listing_type == ListingType.PENDING
else ""
)
listing_type = ListingType.FOR_SALE if self.listing_type == ListingType.PENDING else self.listing_type
if search_type == "comps": #: comps search, came from an address
query = """query Property_search(
$coordinates: [Float]!
$radius: String!
$offset: Int!,
) {
property_search(
home_search(
query: {
nearby: {
coordinates: $coordinates
@@ -353,13 +374,15 @@ class RealtorScraper(Scraper):
}
status: %s
%s
%s
}
%s
limit: 200
offset: $offset
) %s""" % (
self.listing_type.value.lower(),
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
sort_param,
results_query,
)
@@ -385,7 +408,7 @@ class RealtorScraper(Scraper):
limit: 200
offset: $offset
) %s""" % (
self.listing_type.value.lower(),
listing_type.value.lower(),
date_param,
pending_or_contingent_param,
sort_param,
@@ -415,7 +438,7 @@ class RealtorScraper(Scraper):
response = self.session.post(self.SEARCH_GQL_URL, json=payload)
response.raise_for_status()
response_json = response.json()
search_key = "home_search" if search_type == "area" else "property_search"
search_key = "home_search" if "home_search" in query else "property_search"
properties: list[Property] = []
@@ -430,7 +453,6 @@ class RealtorScraper(Scraper):
return {"total": 0, "properties": []}
for result in response_json["data"][search_key]["results"]:
self.counter += 1
mls = (
result["source"].get("id")
if "source" in result and isinstance(result["source"], dict)
@@ -447,13 +469,15 @@ class RealtorScraper(Scraper):
and result["location"]["address"].get("coordinate")
)
is_pending = result["flags"].get("is_pending") or result["flags"].get("is_contingent")
realty_property = Property(
mls=mls,
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']}",
status=result["status"].upper(),
status="PENDING" if is_pending else result["status"].upper(),
list_price=result["list_price"],
list_date=result["list_date"].split("T")[0]
if result.get("list_date")
@@ -470,8 +494,8 @@ class RealtorScraper(Scraper):
if able_to_get_lat_long
else None,
address=self._parse_address(result, search_type="general_search"),
#: neighborhoods=self._parse_neighborhoods(result),
description=self._parse_description(result),
days_on_mls=self.calculate_days_on_mls(result)
)
properties.append(realty_property)
@@ -582,7 +606,6 @@ class RealtorScraper(Scraper):
description_data = result.get("description", {})
if description_data is None or not isinstance(description_data, dict):
print("Warning: description_data is invalid!")
description_data = {}
style = description_data.get("type", "")
@@ -601,3 +624,22 @@ class RealtorScraper(Scraper):
garage=description_data.get("garage"),
stories=description_data.get("stories"),
)
@staticmethod
def calculate_days_on_mls(result: dict) -> Optional[int]:
list_date_str = result.get("list_date")
list_date = datetime.strptime(list_date_str.split("T")[0], "%Y-%m-%d") if list_date_str else None
last_sold_date_str = result.get("last_sold_date")
last_sold_date = datetime.strptime(last_sold_date_str, "%Y-%m-%d") if last_sold_date_str else None
today = datetime.now()
if list_date:
if result["status"] == 'sold':
if last_sold_date:
days = (last_sold_date - list_date).days
if days >= 0:
return days
elif result["status"] in ('for_sale', 'for_rent'):
days = (today - list_date).days
if days >= 0:
return days

View File

@@ -18,6 +18,7 @@ ordered_properties = [
"half_baths",
"sqft",
"year_built",
"days_on_mls",
"list_price",
"list_date",
"sold_price",

View File

@@ -1,9 +1,9 @@
[tool.poetry]
name = "homeharvest"
version = "0.3.3"
version = "0.3.6"
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/ZacharyHampton/HomeHarvest"
homepage = "https://github.com/Bunsly/HomeHarvest"
readme = "README.md"
[tool.poetry.scripts]

View File

@@ -7,14 +7,10 @@ from homeharvest.exceptions import (
def test_realtor_pending_or_contingent():
pending_or_contingent_result = scrape_property(
location="Surprise, AZ",
pending_or_contingent=True,
location="Surprise, AZ", listing_type="pending"
)
regular_result = scrape_property(
location="Surprise, AZ",
pending_or_contingent=False,
)
regular_result = scrape_property(location="Surprise, AZ", listing_type="for_sale")
assert all(
[
@@ -25,6 +21,35 @@ def test_realtor_pending_or_contingent():
assert len(pending_or_contingent_result) != len(regular_result)
def test_realtor_pending_comps():
pending_comps = scrape_property(
location="2530 Al Lipscomb Way",
radius=5,
past_days=180,
listing_type="pending",
)
for_sale_comps = scrape_property(
location="2530 Al Lipscomb Way",
radius=5,
past_days=180,
listing_type="for_sale",
)
sold_comps = scrape_property(
location="2530 Al Lipscomb Way",
radius=5,
past_days=180,
listing_type="sold",
)
results = [pending_comps, for_sale_comps, sold_comps]
assert all([result is not None for result in results])
#: assert all lengths are different
assert len(set([len(result) for result in results])) == len(results)
def test_realtor_comps():
result = scrape_property(
location="2530 Al Lipscomb Way",