Foresttrip Vacancy

#!/usr/bin/env python3
"""Read-only foresttrip.go.kr vacancy lookup helper.

The script logs in with Playwright to obtain a CSRF token and session cookies,
extracts forest IDs from the official monthly reservation status page, then
queries the read-only monthly availability JSON endpoint.

It intentionally does not click booking buttons, submit reservation forms,
handle payment, solve captcha, or bypass queues.
"""
from __future__ import annotations

import argparse
import concurrent.futures
import json
import os
import sys
import time
import urllib.error
import urllib.request
from dataclasses import asdict, dataclass
from datetime import datetime, timedelta
from pathlib import Path
from typing import Any

LOGIN_URL = "https://www.foresttrip.go.kr/com/login.do"
RSRVT_PAGE = "https://www.foresttrip.go.kr/rep/or/sssn/monthRsrvtSmplStatus.do"
POST_URL = "https://www.foresttrip.go.kr/rep/or/selectRsrvtAvailInfoListForMonthRsrvtSmpl.do"
DEFAULT_CONCURRENCY = 4
MAX_CONCURRENCY = 5
DEFAULT_WEEK_RANGE = 1
CATEGORY_CODES = {"01", "02"}
RESERVE_ROOM_MARKER = "예비"


@dataclass
class Session:
    cookies: dict[str, str]
    csrf: str
    user_agent: str
    forests: dict[str, str]
    expires_at: float


def parse_csv(value: str) -> list[str]:
    return [part.strip() for part in value.split(",") if part.strip()]


def parse_categories(value: str) -> tuple[str, ...]:
    categories = parse_csv(value)
    if not categories:
        raise argparse.ArgumentTypeError("must include at least one category code")
    invalid = [category for category in categories if category not in CATEGORY_CODES]
    if invalid:
        raise argparse.ArgumentTypeError(
            "unknown category code(s): "
            + ", ".join(invalid)
            + " (allowed: 01=lodging, 02=camping)"
        )
    return tuple(dict.fromkeys(categories))


def parse_dates(value: str) -> tuple[str, ...]:
    dates = parse_csv(value)
    if not dates:
        raise argparse.ArgumentTypeError("must include at least one YYYYMMDD date")

    today = datetime.now().date()
    normalized: list[str] = []
    for raw_date in dates:
        try:
            parsed = datetime.strptime(raw_date, "%Y%m%d").date()
        except ValueError as exc:
            raise argparse.ArgumentTypeError(f"invalid YYYYMMDD date: {raw_date}") from exc
        if parsed.strftime("%Y%m%d") != raw_date:
            raise argparse.ArgumentTypeError(f"invalid YYYYMMDD date: {raw_date}")
        if parsed < today:
            raise argparse.ArgumentTypeError(f"date is in the past: {raw_date}")
        normalized.append(raw_date)
    return tuple(sorted(dict.fromkeys(normalized)))


def parse_concurrency(value: str) -> int:
    try:
        concurrency = int(value)
    except ValueError as exc:
        raise argparse.ArgumentTypeError("must be an integer") from exc
    if not 1 <= concurrency <= MAX_CONCURRENCY:
        raise argparse.ArgumentTypeError(f"must be between 1 and {MAX_CONCURRENCY}")
    return concurrency


def parse_week_range(value: str) -> int:
    try:
        week_range = int(value)
    except ValueError as exc:
        raise argparse.ArgumentTypeError("must be an integer") from exc
    if week_range < 1:
        raise argparse.ArgumentTypeError("must be at least 1")
    return week_range


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Read-only foresttrip.go.kr vacancy lookup.",
    )
    target = parser.add_argument_group("target selection")
    target.add_argument("--all", action="store_true", help="Scan all extracted forest IDs.")
    target.add_argument(
        "--forest-id",
        action="append",
        help="ForestTrip insttId. Can be passed multiple times or comma-separated.",
    )
    target.add_argument(
        "--forest-name",
        action="append",
        help="Substring to match against official forest names.",
    )

    output = parser.add_mutually_exclusive_group()
    output.add_argument("--json", action="sto