wegli-filter.py

wegli-filter.py

import argparse
import csv
import sys

PLZ_DEFAULT_MIN = 80331
PLZ_DEFAULT_MAX = 81929

parser = argparse.ArgumentParser(description="Filter wegli CSV by PLZ range (default: München)")
parser.add_argument("input", help="Input CSV file")
parser.add_argument("-o", "--output", default=None, help="Output CSV file (default: notices-muenchen.csv)")
parser.add_argument("--plz-min", type=int, default=PLZ_DEFAULT_MIN, help=f"Min PLZ (default: {PLZ_DEFAULT_MIN})")
parser.add_argument("--plz-max", type=int, default=PLZ_DEFAULT_MAX, help=f"Max PLZ (default: {PLZ_DEFAULT_MAX})")
parser.add_argument("--year", type=int, default=None, help="Filter by year of start_date (e.g. 2024)")
args = parser.parse_args()

OUTPUT = args.output or "notices-muenchen.csv"

with open(args.input, newline="", encoding="utf-8") as infile, open(OUTPUT, "w", newline="", encoding="utf-8") as outfile:
    reader = csv.reader(infile)
    writer = csv.writer(outfile)

    header = next(reader)
    writer.writerow(header)

    plz_idx = None
    start_idx = None
    for i, col in enumerate(header):
        c = col.strip().lower()
        if c in ("plz", "zip", "postal_code", "postleitzahl"):
            plz_idx = i
        if c in ("start_date", "start"):
            start_idx = i
    if plz_idx is None:
        print("Fehler: Keine PLZ-Spalte im Header gefunden.")
        sys.exit(1)

    count = 0
    for row in reader:
        try:
            plz = int(row[plz_idx])
            if args.plz_min <= plz <= args.plz_max:
                if args.year is not None and start_idx is not None:
                    if not row[start_idx].startswith(str(args.year)):
                        continue
                writer.writerow(row)
                count += 1
        except (ValueError, IndexError):
            pass

    label = f"PLZ {args.plz_min}–{args.plz_max}"
    if args.year:
        label += f", Jahr {args.year}"
    print(f"{count} Einträge für {label} nach {OUTPUT} geschrieben.")