make the csv exporter use the filtering params to allow exporting customizable reports

crawler/csv_exporter.py

@@ -2,13 +2,17 @@ import asyncio
 from pathlib import Path
 from data_access import Listing
 import pandas as pd
+from rec.query import QueryParameters, filter_listings
 
 
 async def export_to_csv(
     listings: list[Listing],
     output_file: Path,
     columns: list[str],
+    query_parameters: QueryParameters | None = None,
 ) -> None:
+    if query_parameters is not None:
+        listings = await filter_listings(listings, query_parameters)
     ds = await asyncio.gather(*[listing.dict_nicely() for listing in listings])
     df = pd.DataFrame(ds)
     # read decisions on file

crawler/main.py

@@ -258,14 +258,48 @@ def routing(
     ),
 )
 @click.pass_context
-def export_csv(ctx: click.core.Context, output_file: str, columns: tuple[str]):
+@listing_filter_options
+def export_csv(
+    ctx: click.core.Context,
+    output_file: str,
+    columns: tuple[str],
+    district: list[str],
+    min_bedrooms: int,
+    max_bedrooms: int,
+    min_price: int,
+    max_price: int,
+    type: str,
+    furnish_types: list[str],
+    available_from: datetime | None,
+    last_seen_days: int,
+    min_sqm: int | None = None,
+):
     data_dir = ctx.obj["data_dir"]
-    click.echo(f"Exporting data to {output_file} using {data_dir=}")
+    query_parameters = QueryParameters(
+        listing_type=ListingType[type],
+        district_names=set(district),
+        min_bedrooms=min_bedrooms,
+        max_bedrooms=max_bedrooms,
+        min_price=min_price,
+        max_price=max_price,
+        furnish_types=[FurnishType[furnish_type] for furnish_type in furnish_types],
+        let_date_available_from=available_from,
+        last_seen_days=last_seen_days,
+        min_sqm=min_sqm,
+    )
+    click.echo(
+        f"Exporting data to {output_file} using {data_dir=} and query parameters: {query_parameters}"
+    )
     output_file_path = pathlib.Path(output_file)
     listing_paths = sorted(list(pathlib.Path(data_dir).glob("*/listing.json")))
     listings = Listing.get_all_listings([str(path) for path in listing_paths])
     asyncio.run(
-        csv_exporter.export_to_csv(listings, output_file_path, list(columns)),
+        csv_exporter.export_to_csv(
+            listings,
+            output_file_path,
+            list(columns),
+            query_parameters=query_parameters,
+        ),
     )