wrongmove/crawler/csv_exporter.py

from pathlib import Path
import pandas as pd
from models.listing import QueryParameters
from repositories.listing_repository import ListingRepository


async def export_to_csv(
    repository: ListingRepository,
    output_file: Path,
    query_parameters: QueryParameters | None = None,
) -> None:
    listings = await repository.get_listings(query_parameters=query_parameters)
    ds = [listing.__dict__ for listing in listings]
    df = pd.DataFrame(ds)

    # read decisions on file
    decisions_path = "data/decisions.json"
    decisions = pd.read_json(decisions_path)
    df.loc[:, "decision"] = df.id.apply(lambda x: decisions.get(x))

    # remove _sa_instance_state column
    drop_columns = ["_sa_instance_state", "additional_info"]
    df = df.drop(columns=drop_columns)

    # fill in gap values for service charge and lease left for Excel filters
    if "service_charge" not in df.columns:
        df.loc[:, "service_charge"] = -1
    df.loc[:, "service_charge"] = df.service_charge.fillna(-1)
    if "lease_left" not in df.columns:
        df.loc[:, "lease_left"] = -1
    df.loc[:, "lease_left"] = df.lease_left.fillna(-1)
    if "square_meters" not in df.columns:
        df.loc[:, "square_meters"] = -1
    df.loc[:, "square_meters"] = df.square_meters.fillna(-1)

    # Add price per sqm column
    df.loc[:, "price_per_sqm"] = df.price / df.square_meters

    df = df.sort_values(by=["price_per_sqm"], ascending=True)
    df.to_csv(str(output_file), index=False)