[chore]: clean up
Cullen Watson
parent
f8c0dd766d
commit
51bde20c3c
155
README.md
155
README.md
|
|
@ -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.
|
||||
**HomeHarvest** is a simple, yet comprehensive, real estate scraping library that extracts and formats data in the style of MLS listings.
|
||||
|
||||
[](https://replit.com/@ZacharyHampton/HomeHarvestDemo)
|
||||
|
||||
|
|
@ -11,10 +11,14 @@
|
|||
|
||||
Check out another project we wrote: ***[JobSpy](https://github.com/cullenwatson/JobSpy)** – a Python package for job scraping*
|
||||
|
||||
## Features
|
||||
## HomeHarvest Features
|
||||
|
||||
- Scrapes properties from **Zillow**, **Realtor.com** & **Redfin** simultaneously
|
||||
- Aggregates the properties in a Pandas DataFrame
|
||||
- **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**:
|
||||
- **CLI**: For users who prefer command-line operations.
|
||||
- **Python**: For those who'd like to integrate scraping into their Python scripts.
|
||||
|
||||
[Video Guide for HomeHarvest](https://youtu.be/JnV7eR2Ve2o) - _updated for release v0.2.7_
|
||||
|
||||
|
|
@ -29,21 +33,6 @@ pip install homeharvest
|
|||
|
||||
## Usage
|
||||
|
||||
### Python
|
||||
|
||||
```py
|
||||
from homeharvest import scrape_property
|
||||
import pandas as pd
|
||||
|
||||
properties: pd.DataFrame = scrape_property(
|
||||
location="85281",
|
||||
listing_type="for_rent" # for_sale / sold
|
||||
)
|
||||
|
||||
#: Note, to export to CSV or Excel, use properties.to_csv() or properties.to_excel().
|
||||
print(properties)
|
||||
```
|
||||
|
||||
### CLI
|
||||
|
||||
```
|
||||
|
|
@ -55,7 +44,6 @@ positional arguments:
|
|||
location Location to scrape (e.g., San Francisco, CA)
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
-l {for_sale,for_rent,sold}, --listing_type {for_sale,for_rent,sold}
|
||||
Listing type to scrape
|
||||
-o {excel,csv}, --output {excel,csv}
|
||||
|
|
@ -72,104 +60,107 @@ options:
|
|||
> homeharvest "San Francisco, CA" -l for_rent -o excel -f HomeHarvest
|
||||
```
|
||||
|
||||
## Output
|
||||
### Python
|
||||
|
||||
```py
|
||||
>>> properties.head()
|
||||
property_url site_name listing_type apt_min_price apt_max_price ...
|
||||
0 https://www.redfin.com/AZ/Tempe/1003-W-Washing... redfin for_rent 1666.0 2750.0 ...
|
||||
1 https://www.redfin.com/AZ/Tempe/VELA-at-Town-L... redfin for_rent 1665.0 3763.0 ...
|
||||
2 https://www.redfin.com/AZ/Tempe/Camden-Tempe/a... redfin for_rent 1939.0 3109.0 ...
|
||||
3 https://www.redfin.com/AZ/Tempe/Emerson-Park/a... redfin for_rent 1185.0 1817.0 ...
|
||||
4 https://www.redfin.com/AZ/Tempe/Rio-Paradiso-A... redfin for_rent 1470.0 2235.0 ...
|
||||
[5 rows x 41 columns]
|
||||
from homeharvest import scrape_property
|
||||
from datetime import datetime
|
||||
|
||||
# Generate filename based on current timestamp
|
||||
current_timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"output/{current_timestamp}.csv"
|
||||
|
||||
properties = scrape_property(
|
||||
location="San Diego, CA",
|
||||
listing_type="sold", # for_sale, for_rent
|
||||
)
|
||||
print(f"Number of properties: {len(properties)}")
|
||||
properties.to_csv(filename, index=False)
|
||||
```
|
||||
|
||||
### Parameters for `scrape_properties()`
|
||||
|
||||
## Output
|
||||
```plaintext
|
||||
>>> properties.head()
|
||||
MLS MLS # Status Style ... COEDate LotSFApx PrcSqft Stories
|
||||
0 SDCA 230018348 SOLD CONDOS ... 2023-10-03 290110 803 2
|
||||
1 SDCA 230016614 SOLD TOWNHOMES ... 2023-10-03 None 838 3
|
||||
2 SDCA 230016367 SOLD CONDOS ... 2023-10-03 30056 649 1
|
||||
3 MRCA NDP2306335 SOLD SINGLE_FAMILY ... 2023-10-03 7519 661 2
|
||||
4 SDCA 230014532 SOLD CONDOS ... 2023-10-03 None 752 1
|
||||
[5 rows x 22 columns]
|
||||
```
|
||||
|
||||
### Parameters for `scrape_property()`
|
||||
```
|
||||
Required
|
||||
├── location (str): address in various formats e.g. just zip, full address, city/state, etc.
|
||||
└── listing_type (enum): for_rent, for_sale, sold
|
||||
Optional
|
||||
├── site_name (list[enum], default=all three sites): zillow, realtor.com, redfin
|
||||
├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
|
||||
└── keep_duplicates (bool, default=False): whether to keep or remove duplicate properties based on address
|
||||
├── radius_for_comps (float): Radius in miles to find comparable properties based on individual addresses.
|
||||
├── sold_last_x_days (int): Number of past days to filter sold properties.
|
||||
├── proxy (str): in format 'http://user:pass@host:port'
|
||||
```
|
||||
|
||||
### Property Schema
|
||||
```plaintext
|
||||
Property
|
||||
├── Basic Information:
|
||||
│ ├── property_url (str)
|
||||
│ ├── site_name (enum): zillow, redfin, realtor.com
|
||||
│ ├── listing_type (enum): for_sale, for_rent, sold
|
||||
│ └── property_type (enum): house, apartment, condo, townhouse, single_family, multi_family, building
|
||||
│ ├── property_url (str)
|
||||
│ ├── mls (str)
|
||||
│ ├── mls_id (str)
|
||||
│ └── status (str)
|
||||
|
||||
├── Address Details:
|
||||
│ ├── street_address (str)
|
||||
│ ├── city (str)
|
||||
│ ├── state (str)
|
||||
│ ├── zip_code (str)
|
||||
│ ├── unit (str)
|
||||
│ └── country (str)
|
||||
│ ├── street (str)
|
||||
│ ├── unit (str)
|
||||
│ ├── city (str)
|
||||
│ ├── state (str)
|
||||
│ └── zip (str)
|
||||
|
||||
├── House for Sale Features:
|
||||
│ ├── tax_assessed_value (int)
|
||||
│ ├── lot_area_value (float)
|
||||
│ ├── lot_area_unit (str)
|
||||
│ ├── stories (int)
|
||||
│ ├── year_built (int)
|
||||
│ └── price_per_sqft (int)
|
||||
├── Property Description:
|
||||
│ ├── style (str)
|
||||
│ ├── beds (int)
|
||||
│ ├── baths_full (int)
|
||||
│ ├── baths_half (int)
|
||||
│ ├── sqft (int)
|
||||
│ ├── lot_sqft (int)
|
||||
│ ├── sold_price (int)
|
||||
│ ├── year_built (int)
|
||||
│ ├── garage (float)
|
||||
│ └── stories (int)
|
||||
|
||||
├── Building for Sale and Apartment Details:
|
||||
│ ├── bldg_name (str)
|
||||
│ ├── beds_min (int)
|
||||
│ ├── beds_max (int)
|
||||
│ ├── baths_min (float)
|
||||
│ ├── baths_max (float)
|
||||
│ ├── sqft_min (int)
|
||||
│ ├── sqft_max (int)
|
||||
│ ├── price_min (int)
|
||||
│ ├── price_max (int)
|
||||
│ ├── area_min (int)
|
||||
│ └── unit_count (int)
|
||||
├── Property Listing Details:
|
||||
│ ├── list_price (int)
|
||||
│ ├── list_date (str)
|
||||
│ ├── last_sold_date (str)
|
||||
│ ├── prc_sqft (int)
|
||||
│ └── hoa_fee (int)
|
||||
|
||||
├── Miscellaneous Details:
|
||||
│ ├── mls_id (str)
|
||||
│ ├── agent_name (str)
|
||||
│ ├── img_src (str)
|
||||
│ ├── description (str)
|
||||
│ ├── status_text (str)
|
||||
│ └── posted_time (str)
|
||||
|
||||
└── Location Details:
|
||||
├── latitude (float)
|
||||
└── longitude (float)
|
||||
├── Location Details:
|
||||
│ ├── latitude (float)
|
||||
│ ├── longitude (float)
|
||||
│ └── neighborhoods (str)
|
||||
```
|
||||
## Supported Countries for Property Scraping
|
||||
|
||||
* **Zillow**: contains listings in the **US** & **Canada**
|
||||
* **Realtor.com**: mainly from the **US** but also has international listings
|
||||
* **Redfin**: listings mainly in the **US**, **Canada**, & has expanded to some areas in **Mexico**
|
||||
|
||||
### Exceptions
|
||||
The following exceptions may be raised when using HomeHarvest:
|
||||
|
||||
- `InvalidSite` - valid options: `zillow`, `redfin`, `realtor.com`
|
||||
- `InvalidListingType` - valid options: `for_sale`, `for_rent`, `sold`
|
||||
- `NoResultsFound` - no properties found from your input
|
||||
- `GeoCoordsNotFound` - if Zillow scraper is not able to derive geo-coordinates from the location you input
|
||||
|
||||
## Frequently Asked Questions
|
||||
|
||||
---
|
||||
|
||||
**Q: Encountering issues with your queries?**
|
||||
**A:** Try a single site and/or broaden the location. If problems persist, [submit an issue](https://github.com/ZacharyHampton/HomeHarvest/issues).
|
||||
**Q: Encountering issues with your searches?**
|
||||
**A:** Try to broaden the location. 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 the real estate site for sending too many requests. Currently, **Zillow** is particularly aggressive with blocking. We recommend:
|
||||
**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 to change your IP address.
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
import pandas as pd
|
||||
from typing import Union
|
||||
import concurrent.futures
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
|
|
@ -7,7 +6,7 @@ from .core.scrapers import ScraperInput
|
|||
from .utils import process_result, ordered_properties
|
||||
from .core.scrapers.realtor import RealtorScraper
|
||||
from .core.scrapers.models import ListingType, Property, SiteName
|
||||
from .exceptions import InvalidSite, InvalidListingType
|
||||
from .exceptions import InvalidListingType
|
||||
|
||||
|
||||
_scrapers = {
|
||||
|
|
@ -15,10 +14,7 @@ _scrapers = {
|
|||
}
|
||||
|
||||
|
||||
def _validate_input(site_name: str, listing_type: str) -> None:
|
||||
if site_name.lower() not in _scrapers:
|
||||
raise InvalidSite(f"Provided site, '{site_name}', does not exist.")
|
||||
|
||||
def _validate_input(listing_type: str) -> None:
|
||||
if listing_type.upper() not in ListingType.__members__:
|
||||
raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
|
||||
|
||||
|
|
@ -27,7 +23,7 @@ def _scrape_single_site(location: str, site_name: str, listing_type: str, radius
|
|||
"""
|
||||
Helper function to scrape a single site.
|
||||
"""
|
||||
_validate_input(site_name, listing_type)
|
||||
_validate_input(listing_type)
|
||||
|
||||
scraper_input = ScraperInput(
|
||||
location=location,
|
||||
|
|
@ -40,6 +36,7 @@ def _scrape_single_site(location: str, site_name: str, listing_type: str, radius
|
|||
|
||||
site = _scrapers[site_name.lower()](scraper_input)
|
||||
results = site.search()
|
||||
print(f"found {len(results)}")
|
||||
|
||||
properties_dfs = [process_result(result) for result in results]
|
||||
if not properties_dfs:
|
||||
|
|
@ -50,22 +47,19 @@ def _scrape_single_site(location: str, site_name: str, listing_type: str, radius
|
|||
|
||||
def scrape_property(
|
||||
location: str,
|
||||
#: site_name: Union[str, list[str]] = "realtor.com",
|
||||
listing_type: str = "for_sale",
|
||||
radius: float = None,
|
||||
sold_last_x_days: int = None,
|
||||
proxy: str = None,
|
||||
) -> pd.DataFrame:
|
||||
"""
|
||||
Scrape property from various sites from a given location and listing type.
|
||||
Scrape properties from Realtor.com based on a given location and listing type.
|
||||
|
||||
:param sold_last_x_days: Sold in last x days
|
||||
:param radius: Radius in miles to find comparable properties on individual addresses
|
||||
:param keep_duplicates:
|
||||
:param proxy:
|
||||
:param location: US Location (e.g. 'San Francisco, CA', 'Cook County, IL', '85281', '2530 Al Lipscomb Way')
|
||||
:param site_name: Site name or list of site names (e.g. ['realtor.com', 'zillow'], 'redfin')
|
||||
:param listing_type: Listing type (e.g. 'for_sale', 'for_rent', 'sold')
|
||||
:param listing_type: Listing type (e.g. 'for_sale', 'for_rent', 'sold'). Default is 'for_sale'.
|
||||
:param radius: Radius in miles to find comparable properties on individual addresses. Optional.
|
||||
:param sold_last_x_days: Number of past days to filter sold properties. Optional.
|
||||
:param proxy: Proxy IP address to be used for scraping. Optional.
|
||||
:returns: pd.DataFrame containing properties
|
||||
"""
|
||||
site_name = "realtor.com"
|
||||
|
|
|
|||
|
|
@ -38,7 +38,8 @@ def main():
|
|||
|
||||
parser.add_argument(
|
||||
"-r",
|
||||
"--radius",
|
||||
"--sold-properties-radius",
|
||||
dest="sold_properties_radius", # This makes sure the parsed argument is stored as radius_for_comps in args
|
||||
type=float,
|
||||
default=None,
|
||||
help="Get comparable properties within _ (eg. 0.0) miles. Only applicable for individual addresses."
|
||||
|
|
@ -46,7 +47,7 @@ def main():
|
|||
|
||||
args = parser.parse_args()
|
||||
|
||||
result = scrape_property(args.location, args.listing_type, proxy=args.proxy)
|
||||
result = scrape_property(args.location, args.listing_type, radius_for_comps=args.radius_for_comps, proxy=args.proxy)
|
||||
|
||||
if not args.filename:
|
||||
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
|
|
|
|||
|
|
@ -32,39 +32,34 @@ class Address:
|
|||
|
||||
|
||||
@dataclass
|
||||
class Agent:
|
||||
name: str
|
||||
phone: str | None = None
|
||||
email: str | None = None
|
||||
class Description:
|
||||
style: str | None = None
|
||||
beds: int | None = None
|
||||
baths_full: int | None = None
|
||||
baths_half: int | None = None
|
||||
sqft: int | None = None
|
||||
lot_sqft: int | None = None
|
||||
sold_price: int | None = None
|
||||
year_built: int | None = None
|
||||
garage: float | None = None
|
||||
stories: int | None = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class Property:
|
||||
property_url: str | None = None
|
||||
property_url: str
|
||||
mls: str | None = None
|
||||
mls_id: str | None = None
|
||||
status: str | None = None
|
||||
style: str | None = None
|
||||
|
||||
beds: int | None = None
|
||||
baths_full: int | None = None
|
||||
baths_half: int | None = None
|
||||
list_price: int | None = None
|
||||
list_date: str | None = None
|
||||
sold_price: int | None = None
|
||||
last_sold_date: str | None = None
|
||||
prc_sqft: float | None = None
|
||||
est_sf: int | None = None
|
||||
lot_sf: int | None = None
|
||||
hoa_fee: int | None = None
|
||||
|
||||
address: Address | None = None
|
||||
|
||||
yr_blt: int | None = None
|
||||
list_price: int | None = None
|
||||
list_date: str | None = None
|
||||
last_sold_date: str | None = None
|
||||
prc_sqft: int | None = None
|
||||
hoa_fee: int | None = None
|
||||
description: Description | None = None
|
||||
|
||||
latitude: float | None = None
|
||||
longitude: float | None = None
|
||||
|
||||
stories: int | None = None
|
||||
prkg_gar: float | None = None
|
||||
|
||||
neighborhoods: Optional[str] = None
|
||||
|
|
|
|||
|
|
@ -2,38 +2,26 @@
|
|||
homeharvest.realtor.__init__
|
||||
~~~~~~~~~~~~
|
||||
|
||||
This module implements the scraper for relator.com
|
||||
This module implements the scraper for realtor.com
|
||||
"""
|
||||
from ..models import Property, Address, ListingType
|
||||
from typing import Dict, Union, Optional
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
|
||||
from .. import Scraper
|
||||
from ....exceptions import NoResultsFound
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from ..models import Property, Address, ListingType, Description
|
||||
|
||||
|
||||
class RealtorScraper(Scraper):
|
||||
SEARCH_URL = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
|
||||
PROPERTY_URL = "https://www.realtor.com/realestateandhomes-detail/"
|
||||
ADDRESS_AUTOCOMPLETE_URL = "https://parser-external.geo.moveaws.com/suggest"
|
||||
|
||||
def __init__(self, scraper_input):
|
||||
self.counter = 1
|
||||
super().__init__(scraper_input)
|
||||
self.search_url = (
|
||||
"https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
|
||||
)
|
||||
|
||||
def handle_location(self):
|
||||
headers = {
|
||||
"authority": "parser-external.geo.moveaws.com",
|
||||
"accept": "*/*",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
"origin": "https://www.realtor.com",
|
||||
"referer": "https://www.realtor.com/",
|
||||
"sec-ch-ua": '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"',
|
||||
"sec-ch-ua-mobile": "?0",
|
||||
"sec-ch-ua-platform": '"Windows"',
|
||||
"sec-fetch-dest": "empty",
|
||||
"sec-fetch-mode": "cors",
|
||||
"sec-fetch-site": "cross-site",
|
||||
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36",
|
||||
}
|
||||
|
||||
params = {
|
||||
"input": self.location,
|
||||
"client_id": self.listing_type.value.lower().replace("_", "-"),
|
||||
|
|
@ -42,9 +30,8 @@ class RealtorScraper(Scraper):
|
|||
}
|
||||
|
||||
response = self.session.get(
|
||||
"https://parser-external.geo.moveaws.com/suggest",
|
||||
self.ADDRESS_AUTOCOMPLETE_URL,
|
||||
params=params,
|
||||
headers=headers,
|
||||
)
|
||||
response_json = response.json()
|
||||
|
||||
|
|
@ -70,22 +57,19 @@ class RealtorScraper(Scraper):
|
|||
stories
|
||||
}
|
||||
address {
|
||||
address_validation_code
|
||||
city
|
||||
country
|
||||
county
|
||||
line
|
||||
postal_code
|
||||
state_code
|
||||
street_direction
|
||||
street_name
|
||||
street_number
|
||||
street_name
|
||||
street_suffix
|
||||
street_post_direction
|
||||
unit_value
|
||||
unit
|
||||
unit_descriptor
|
||||
zip
|
||||
city
|
||||
state_code
|
||||
postal_code
|
||||
location {
|
||||
coordinate {
|
||||
lat
|
||||
lon
|
||||
}
|
||||
}
|
||||
}
|
||||
basic {
|
||||
baths
|
||||
|
|
@ -113,25 +97,24 @@ class RealtorScraper(Scraper):
|
|||
"variables": variables,
|
||||
}
|
||||
|
||||
response = self.session.post(self.search_url, json=payload)
|
||||
response = self.session.post(self.SEARCH_URL, json=payload)
|
||||
response_json = response.json()
|
||||
|
||||
property_info = response_json["data"]["property"]
|
||||
|
||||
return [
|
||||
Property(
|
||||
property_url="https://www.realtor.com/realestateandhomes-detail/"
|
||||
+ property_info["details"]["permalink"],
|
||||
stories=property_info["details"]["stories"],
|
||||
mls_id=property_id,
|
||||
property_url=f"{self.PROPERTY_URL}{property_info['details']['permalink']}",
|
||||
address=self._parse_address(property_info, search_type="handle_address"),
|
||||
description=self._parse_description(property_info)
|
||||
)
|
||||
]
|
||||
|
||||
def general_search(self, variables: dict, search_type: str, return_total: bool = False) -> list[Property] | int:
|
||||
def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, list[Property]]]:
|
||||
"""
|
||||
Handles a location area & returns a list of properties
|
||||
"""
|
||||
|
||||
results_query = """{
|
||||
count
|
||||
total
|
||||
|
|
@ -141,86 +124,87 @@ class RealtorScraper(Scraper):
|
|||
status
|
||||
last_sold_price
|
||||
last_sold_date
|
||||
hoa {
|
||||
fee
|
||||
}
|
||||
list_price
|
||||
price_per_sqft
|
||||
description {
|
||||
sqft
|
||||
beds
|
||||
baths_full
|
||||
baths_half
|
||||
beds
|
||||
lot_sqft
|
||||
sqft
|
||||
sold_price
|
||||
year_built
|
||||
garage
|
||||
sold_price
|
||||
type
|
||||
sub_type
|
||||
name
|
||||
stories
|
||||
}
|
||||
source {
|
||||
raw {
|
||||
area
|
||||
status
|
||||
style
|
||||
}
|
||||
last_update_date
|
||||
contract_date
|
||||
id
|
||||
listing_id
|
||||
name
|
||||
type
|
||||
listing_href
|
||||
community_id
|
||||
management_id
|
||||
corporation_id
|
||||
subdivision_status
|
||||
spec_id
|
||||
plan_id
|
||||
tier_rank
|
||||
feed_type
|
||||
}
|
||||
hoa {
|
||||
fee
|
||||
}
|
||||
location {
|
||||
address {
|
||||
street_number
|
||||
street_name
|
||||
street_suffix
|
||||
unit
|
||||
city
|
||||
country
|
||||
line
|
||||
postal_code
|
||||
state_code
|
||||
state
|
||||
postal_code
|
||||
coordinate {
|
||||
lon
|
||||
lat
|
||||
}
|
||||
street_direction
|
||||
street_name
|
||||
street_number
|
||||
street_post_direction
|
||||
street_suffix
|
||||
unit
|
||||
}
|
||||
neighborhoods {
|
||||
name
|
||||
name
|
||||
}
|
||||
}
|
||||
list_price
|
||||
price_per_sqft
|
||||
style_category_tags {
|
||||
exterior
|
||||
}
|
||||
source {
|
||||
id
|
||||
}
|
||||
}
|
||||
}
|
||||
}"""
|
||||
|
||||
sold_date_param = ('sold_date: { min: "$today-%sD" }' % self.sold_last_x_days
|
||||
if self.listing_type == ListingType.SOLD and self.sold_last_x_days is not None
|
||||
if self.listing_type == ListingType.SOLD and self.sold_last_x_days
|
||||
else "")
|
||||
sort_param = ('sort: [{ field: sold_date, direction: desc }]'
|
||||
if self.listing_type == ListingType.SOLD
|
||||
else 'sort: [{ field: list_date, direction: desc }]')
|
||||
|
||||
if search_type == "area":
|
||||
if search_type == "comps":
|
||||
print('general - comps')
|
||||
query = (
|
||||
"""query Property_search(
|
||||
$coordinates: [Float]!
|
||||
$radius: String!
|
||||
$offset: Int!,
|
||||
) {
|
||||
property_search(
|
||||
query: {
|
||||
nearby: {
|
||||
coordinates: $coordinates
|
||||
radius: $radius
|
||||
}
|
||||
status: %s
|
||||
%s
|
||||
}
|
||||
%s
|
||||
limit: 200
|
||||
offset: $offset
|
||||
) %s""" % (
|
||||
self.listing_type.value.lower(),
|
||||
sold_date_param,
|
||||
sort_param,
|
||||
results_query
|
||||
)
|
||||
)
|
||||
else:
|
||||
print('general - not comps')
|
||||
query = (
|
||||
"""query Home_search(
|
||||
$city: String,
|
||||
|
|
@ -238,60 +222,27 @@ class RealtorScraper(Scraper):
|
|||
status: %s
|
||||
%s
|
||||
}
|
||||
%s
|
||||
limit: 200
|
||||
offset: $offset
|
||||
) %s"""
|
||||
% (
|
||||
self.listing_type.value.lower(),
|
||||
sold_date_param,
|
||||
sort_param,
|
||||
results_query
|
||||
)
|
||||
)
|
||||
elif search_type == "comp_address":
|
||||
query = (
|
||||
"""query Property_search(
|
||||
$coordinates: [Float]!
|
||||
$radius: String!
|
||||
$offset: Int!,
|
||||
) {
|
||||
property_search(
|
||||
query: {
|
||||
nearby: {
|
||||
coordinates: $coordinates
|
||||
radius: $radius
|
||||
}
|
||||
%s
|
||||
}
|
||||
limit: 200
|
||||
offset: $offset
|
||||
) %s""" % (sold_date_param, results_query))
|
||||
else:
|
||||
query = (
|
||||
"""query Property_search(
|
||||
$property_id: [ID]!
|
||||
$offset: Int!,
|
||||
) {
|
||||
property_search(
|
||||
query: {
|
||||
property_id: $property_id
|
||||
%s
|
||||
}
|
||||
limit: 200
|
||||
offset: $offset
|
||||
) %s""" % (sold_date_param, results_query))
|
||||
|
||||
payload = {
|
||||
"query": query,
|
||||
"variables": variables,
|
||||
}
|
||||
|
||||
response = self.session.post(self.search_url, json=payload)
|
||||
response = self.session.post(self.SEARCH_URL, json=payload)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
search_key = "home_search" if search_type == "area" else "property_search"
|
||||
|
||||
if return_total:
|
||||
return response_json["data"][search_key]["total"]
|
||||
search_key = "property_search" if search_type == "comps" else "home_search"
|
||||
|
||||
properties: list[Property] = []
|
||||
|
||||
|
|
@ -303,7 +254,7 @@ class RealtorScraper(Scraper):
|
|||
or response_json["data"][search_key] is None
|
||||
or "results" not in response_json["data"][search_key]
|
||||
):
|
||||
return []
|
||||
return {"total": 0, "properties": []}
|
||||
|
||||
for result in response_json["data"][search_key]["results"]:
|
||||
self.counter += 1
|
||||
|
|
@ -312,122 +263,131 @@ class RealtorScraper(Scraper):
|
|||
if "source" in result and isinstance(result["source"], dict)
|
||||
else None
|
||||
)
|
||||
mls_id = (
|
||||
result["source"].get("listing_id")
|
||||
if "source" in result and isinstance(result["source"], dict)
|
||||
else None
|
||||
)
|
||||
|
||||
if not mls_id:
|
||||
if not mls:
|
||||
continue
|
||||
# not type
|
||||
|
||||
neighborhoods_list = []
|
||||
neighborhoods = result["location"].get("neighborhoods", [])
|
||||
|
||||
if neighborhoods:
|
||||
for neighborhood in neighborhoods:
|
||||
name = neighborhood.get("name")
|
||||
if name:
|
||||
neighborhoods_list.append(name)
|
||||
|
||||
neighborhoods_str = (
|
||||
", ".join(neighborhoods_list) if neighborhoods_list else None
|
||||
)
|
||||
|
||||
able_to_get_lat_long = result and result.get("location") and result["location"].get("address") and result["location"]["address"].get("coordinate")
|
||||
|
||||
realty_property = Property(
|
||||
property_url="https://www.realtor.com/realestateandhomes-detail/"
|
||||
+ result["property_id"],
|
||||
mls=mls,
|
||||
mls_id=mls_id,
|
||||
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(),
|
||||
style=result["description"]["type"].upper(),
|
||||
beds=result["description"]["beds"],
|
||||
baths_full=result["description"]["baths_full"],
|
||||
baths_half=result["description"]["baths_half"],
|
||||
est_sf=result["description"]["sqft"],
|
||||
lot_sf=result["description"]["lot_sqft"],
|
||||
list_price=result["list_price"],
|
||||
list_date=result["list_date"].split("T")[0]
|
||||
if result["list_date"]
|
||||
else None,
|
||||
sold_price=result["description"]["sold_price"],
|
||||
prc_sqft=result["price_per_sqft"],
|
||||
last_sold_date=result["last_sold_date"],
|
||||
list_date=result["list_date"].split("T")[0] if result.get("list_date") else None,
|
||||
prc_sqft=result.get("price_per_sqft"),
|
||||
last_sold_date=result.get("last_sold_date"),
|
||||
hoa_fee=result["hoa"]["fee"] if result.get("hoa") and isinstance(result["hoa"], dict) else None,
|
||||
address=Address(
|
||||
street=f"{result['location']['address']['street_number']} {result['location']['address']['street_name']} {result['location']['address']['street_suffix']}",
|
||||
unit=result["location"]["address"]["unit"],
|
||||
city=result["location"]["address"]["city"],
|
||||
state=result["location"]["address"]["state_code"],
|
||||
zip=result["location"]["address"]["postal_code"],
|
||||
),
|
||||
yr_blt=result["description"]["year_built"],
|
||||
latitude=result["location"]["address"]["coordinate"].get("lat") if able_to_get_lat_long else None,
|
||||
longitude=result["location"]["address"]["coordinate"].get("lon") if able_to_get_lat_long else None,
|
||||
prkg_gar=result["description"]["garage"],
|
||||
stories=result["description"]["stories"],
|
||||
neighborhoods=neighborhoods_str,
|
||||
address=self._parse_address(result, search_type="general_search"),
|
||||
neighborhoods=self._parse_neighborhoods(result),
|
||||
description=self._parse_description(result)
|
||||
)
|
||||
properties.append(realty_property)
|
||||
|
||||
return properties
|
||||
|
||||
# print(response_json["data"]["property_search"], variables["offset"])
|
||||
# print(response_json["data"]["home_search"]["total"], variables["offset"])
|
||||
return {
|
||||
"total": response_json["data"][search_key]["total"],
|
||||
"properties": properties,
|
||||
}
|
||||
|
||||
def search(self):
|
||||
location_info = self.handle_location()
|
||||
location_type = location_info["area_type"]
|
||||
is_for_comps = self.radius is not None and location_type == "address"
|
||||
|
||||
offset = 0
|
||||
search_variables = {
|
||||
"offset": offset,
|
||||
"offset": 0,
|
||||
}
|
||||
|
||||
search_type = "comp_address" if is_for_comps \
|
||||
else "address" if location_type == "address" and not is_for_comps \
|
||||
else "area"
|
||||
search_type = "comps" if self.radius and location_type == "address" else "area"
|
||||
print(search_type)
|
||||
if location_type == "address":
|
||||
if not self.radius: #: single address search, non comps
|
||||
property_id = location_info["mpr_id"]
|
||||
search_variables |= {"property_id": property_id}
|
||||
return self.handle_address(property_id)
|
||||
|
||||
if location_type == "address" and not is_for_comps: #: single address search, non comps
|
||||
property_id = location_info["mpr_id"]
|
||||
search_variables = search_variables | {"property_id": property_id}
|
||||
else: #: general search, comps (radius)
|
||||
coordinates = list(location_info["centroid"].values())
|
||||
search_variables |= {
|
||||
"coordinates": coordinates,
|
||||
"radius": "{}mi".format(self.radius),
|
||||
}
|
||||
|
||||
general_search = self.general_search(search_variables, search_type)
|
||||
if general_search:
|
||||
return general_search
|
||||
else:
|
||||
return self.handle_address(property_id) #: TODO: support single address search for query by property address (can go from property -> listing to get better data)
|
||||
|
||||
elif not is_for_comps: #: area search
|
||||
search_variables = search_variables | {
|
||||
else: #: general search, location
|
||||
search_variables |= {
|
||||
"city": location_info.get("city"),
|
||||
"county": location_info.get("county"),
|
||||
"state_code": location_info.get("state_code"),
|
||||
"postal_code": location_info.get("postal_code"),
|
||||
}
|
||||
else: #: comps search
|
||||
coordinates = list(location_info["centroid"].values())
|
||||
search_variables = search_variables | {
|
||||
"coordinates": coordinates,
|
||||
"radius": "{}mi".format(self.radius),
|
||||
}
|
||||
|
||||
total = self.general_search(search_variables, return_total=True, search_type=search_type)
|
||||
result = self.general_search(search_variables, search_type=search_type)
|
||||
total = result["total"]
|
||||
homes = result["properties"]
|
||||
|
||||
homes = []
|
||||
with ThreadPoolExecutor(max_workers=10) as executor:
|
||||
futures = [
|
||||
executor.submit(
|
||||
self.general_search,
|
||||
variables=search_variables | {"offset": i},
|
||||
return_total=False,
|
||||
search_type=search_type,
|
||||
)
|
||||
for i in range(0, total, 200)
|
||||
for i in range(200, min(total, 10000), 200)
|
||||
]
|
||||
|
||||
for future in as_completed(futures):
|
||||
homes.extend(future.result())
|
||||
homes.extend(future.result()["properties"])
|
||||
|
||||
return homes
|
||||
|
||||
@staticmethod
|
||||
def _parse_neighborhoods(result: dict) -> Optional[str]:
|
||||
neighborhoods_list = []
|
||||
neighborhoods = result["location"].get("neighborhoods", [])
|
||||
|
||||
if neighborhoods:
|
||||
for neighborhood in neighborhoods:
|
||||
name = neighborhood.get("name")
|
||||
if name:
|
||||
neighborhoods_list.append(name)
|
||||
|
||||
return ", ".join(neighborhoods_list) if neighborhoods_list else None
|
||||
|
||||
@staticmethod
|
||||
def _parse_address(result: dict, search_type):
|
||||
if search_type == "general_search":
|
||||
return Address(
|
||||
street=f"{result['location']['address']['street_number']} {result['location']['address']['street_name']} {result['location']['address']['street_suffix']}",
|
||||
unit=result["location"]["address"]["unit"],
|
||||
city=result["location"]["address"]["city"],
|
||||
state=result["location"]["address"]["state_code"],
|
||||
zip=result["location"]["address"]["postal_code"],
|
||||
)
|
||||
return Address(
|
||||
street=f"{result['address']['street_number']} {result['address']['street_name']} {result['address']['street_suffix']}",
|
||||
unit=result['address']['unit'],
|
||||
city=result['address']['city'],
|
||||
state=result['address']['state_code'],
|
||||
zip=result['address']['postal_code'],
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _parse_description(result: dict) -> Description:
|
||||
description_data = result.get("description", {})
|
||||
return Description(
|
||||
style=description_data.get("type", "").upper(),
|
||||
beds=description_data.get("beds"),
|
||||
baths_full=description_data.get("baths_full"),
|
||||
baths_half=description_data.get("baths_half"),
|
||||
sqft=description_data.get("sqft"),
|
||||
lot_sqft=description_data.get("lot_sqft"),
|
||||
sold_price=description_data.get("sold_price"),
|
||||
year_built=description_data.get("year_built"),
|
||||
garage=description_data.get("garage"),
|
||||
stories=description_data.get("stories"),
|
||||
)
|
||||
|
|
@ -1,18 +1,6 @@
|
|||
class InvalidSite(Exception):
|
||||
"""Raised when a provided site is does not exist."""
|
||||
|
||||
|
||||
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 GeoCoordsNotFound(Exception):
|
||||
"""Raised when no property is found for the given address"""
|
||||
|
||||
|
||||
class SearchTooBroad(Exception):
|
||||
"""Raised when the search is too broad"""
|
||||
|
|
|
|||
|
|
@ -39,7 +39,6 @@ def process_result(result: Property) -> pd.DataFrame:
|
|||
prop_data["MLS"] = prop_data["mls"]
|
||||
prop_data["MLS #"] = prop_data["mls_id"]
|
||||
prop_data["Status"] = prop_data["status"]
|
||||
prop_data["Style"] = prop_data["style"]
|
||||
|
||||
if "address" in prop_data:
|
||||
address_data = prop_data["address"]
|
||||
|
|
@ -49,26 +48,27 @@ def process_result(result: Property) -> pd.DataFrame:
|
|||
prop_data["State"] = address_data.state
|
||||
prop_data["Zip"] = address_data.zip
|
||||
|
||||
prop_data["Community"] = prop_data["neighborhoods"]
|
||||
prop_data["Beds"] = prop_data["beds"]
|
||||
prop_data["FB"] = prop_data["baths_full"]
|
||||
prop_data["NumHB"] = prop_data["baths_half"]
|
||||
prop_data["EstSF"] = prop_data["est_sf"]
|
||||
prop_data["ListPrice"] = prop_data["list_price"]
|
||||
prop_data["Lst Date"] = prop_data["list_date"]
|
||||
prop_data["Sold Price"] = prop_data["sold_price"]
|
||||
prop_data["COEDate"] = prop_data["last_sold_date"]
|
||||
prop_data["LotSFApx"] = prop_data["lot_sf"]
|
||||
prop_data["PrcSqft"] = prop_data["prc_sqft"]
|
||||
prop_data["HOAFee"] = prop_data["hoa_fee"]
|
||||
|
||||
if prop_data.get("prc_sqft") is not None:
|
||||
prop_data["PrcSqft"] = round(prop_data["prc_sqft"], 2)
|
||||
description = result.description
|
||||
prop_data["Style"] = description.style
|
||||
prop_data["Beds"] = description.beds
|
||||
prop_data["FB"] = description.baths_full
|
||||
prop_data["NumHB"] = description.baths_half
|
||||
prop_data["EstSF"] = description.sqft
|
||||
prop_data["LotSFApx"] = description.lot_sqft
|
||||
prop_data["Sold Price"] = description.sold_price
|
||||
prop_data["YrBlt"] = description.year_built
|
||||
prop_data["PrkgGar"] = description.garage
|
||||
prop_data["Stories"] = description.stories
|
||||
|
||||
prop_data["YrBlt"] = prop_data["yr_blt"]
|
||||
prop_data["LATITUDE"] = prop_data["latitude"]
|
||||
prop_data["LONGITUDE"] = prop_data["longitude"]
|
||||
prop_data["Stories"] = prop_data["stories"]
|
||||
prop_data["PrkgGar"] = prop_data["prkg_gar"]
|
||||
prop_data["Community"] = prop_data["neighborhoods"]
|
||||
|
||||
properties_df = pd.DataFrame([prop_data])
|
||||
properties_df = properties_df.reindex(columns=ordered_properties)
|
||||
|
|
|
|||
Loading…
Reference in New Issue