mirror of
https://github.com/Bunsly/HomeHarvest.git
synced 2026-03-05 20:14:30 -08:00
[chore]: clean up
This commit is contained in:
Cullen Watson
@@ -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"),
|
||||
)
|
||||
Reference in New Issue
Block a user