export_bing_serp_csv.py

"""Flatten a Bing Dataset JSON export into a CSV file."""

from __future__ import annotations

import argparse
import csv
import json
from pathlib import Path
from typing import Any


FIELDS = [
    "type",
    "query",
    "country",
    "market",
    "page",
    "position",
    "title",
    "url",
    "sourceDomain",
    "description",
    "date",
    "paginationStoppedReason",
]


def export_csv(input_path: Path, output_path: Path) -> None:
    rows: list[dict[str, Any]] = json.loads(input_path.read_text(encoding="utf-8"))
    with output_path.open("w", encoding="utf-8", newline="") as handle:
        writer = csv.DictWriter(handle, fieldnames=FIELDS, extrasaction="ignore")
        writer.writeheader()
        writer.writerows(rows)


def main() -> None:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("input", type=Path, nargs="?", default=Path("data/sample-output.json"))
    parser.add_argument("output", type=Path, nargs="?", default=Path("data/exported-bing-results.csv"))
    args = parser.parse_args()
    export_csv(args.input, args.output)
    print(f"Wrote {args.output}")


if __name__ == "__main__":
    main()