wrongmove/crawler/1_dump_listings.py
2025-06-06 20:09:16 +00:00

69 lines
2.2 KiB
Python

import asyncio
import pathlib
from typing import Any
from rec.query import listing_query, QueryParameters
from rec.districts import get_districts
from data_access import Listing
async def dump_listings(
parameters: QueryParameters,
data_dir: pathlib.Path = pathlib.Path("data/rs/"),
) -> list[Listing]:
if parameters.district_names:
districts = {
district: locid
for district, locid in get_districts().items()
if district in parameters.district_names
}
else:
districts = get_districts()
print("Valid districts to scrape:", districts.keys())
listings = []
semaphore = asyncio.Semaphore(5) # if too high, rightmove drops connections
json_responses = await asyncio.gather(
*[
_dump_listings_with_semaphore(semaphore, i, parameters, locid)
for locid in districts.values()
for i in [1, 2]
]
)
listings = []
for response_json in json_responses:
if response_json["totalAvailableResults"] == 0:
print("No results found")
continue
if response_json["totalAvailableResults"] > 0:
print("totalAvailableResults: ", response_json["totalAvailableResults"])
for property in response_json["properties"]:
identifier = property["identifier"]
listing = Listing(identifier, data_dir=data_dir)
listing.dump_listing(property)
listings.append(listing)
return listings
async def _dump_listings_with_semaphore(
semaphore: asyncio.Semaphore,
page_id: int,
parameters: QueryParameters,
location_id: str,
) -> dict[str, Any]:
async with semaphore:
listing = await listing_query(
page=page_id,
channel=parameters.listing_type,
min_bedrooms=parameters.min_bedrooms,
max_bedrooms=parameters.max_bedrooms,
radius=parameters.radius,
min_price=parameters.min_price,
max_price=parameters.max_price,
location_id=location_id,
page_size=parameters.page_size,
max_days_since_added=parameters.max_days_since_added,
furnish_types=parameters.furnish_types or [],
)
return listing