Danawa Price Search

#!/usr/bin/env python3
"""Read-only Danawa search/price comparison helper for Hermes.

Usage:
  python scripts/danawa_search.py search "에어팟 프로 2세대" --limit 8
  python scripts/danawa_search.py offers 28208783 --limit 10
  python scripts/danawa_search.py compare "에어팟 프로 2세대" --limit 5 --offers 5
"""
from __future__ import annotations

import argparse
import json
import re
import sys
import time
import urllib.parse
import urllib.request
from html import unescape
from typing import Any, Dict, List, Optional

try:
    from bs4 import BeautifulSoup
except ImportError as exc:  # pragma: no cover - environment guard
    raise SystemExit("beautifulsoup4 is required: python -m pip install beautifulsoup4") from exc

UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 Chrome/121 Safari/537.36"


def fetch(url: str, *, method: str = "GET", data: Optional[dict] = None, referer: Optional[str] = None) -> str:
    headers = {
        "User-Agent": UA,
        "Accept-Language": "ko-KR,ko;q=0.9,en;q=0.8",
    }
    body = None
    if data is not None:
        body = urllib.parse.urlencode(data).encode("utf-8")
        headers["Content-Type"] = "application/x-www-form-urlencoded; charset=UTF-8"
        headers["X-Requested-With"] = "XMLHttpRequest"
    if referer:
        headers["Referer"] = referer
    req = urllib.request.Request(url, data=body, headers=headers, method=method)
    with urllib.request.urlopen(req, timeout=25) as resp:
        return resp.read().decode("utf-8", "replace")


def soup_for(html: str) -> BeautifulSoup:
    return BeautifulSoup(html, "html.parser")


def clean_text(s: Optional[str]) -> Optional[str]:
    if s is None:
        return None
    return " ".join(unescape(s).split())


def parse_int(s: Optional[str]) -> Optional[int]:
    if not s:
        return None
    digits = re.sub(r"\D", "", s)
    return int(digits) if digits else None


def abs_url(url: Optional[str]) -> Optional[str]:
    if not url:
        return None
    if url.startswith("//"):
        return "https:" + url
    if url.startswith("/"):
        return "https://prod.danawa.com" + url
    return url


def search(query: str, limit: int = 10) -> Dict[str, Any]:
    url = "https://search.danawa.com/dsearch.php?query=" + urllib.parse.quote(query)
    html = fetch(url)
    soup = soup_for(html)
    items: List[Dict[str, Any]] = []
    for li in soup.select("li.prod_item"):
        pid = (li.get("id") or "").replace("productItem", "") or None
        name_el = li.select_one(".prod_name a") or li.select_one("p.prod_name a") or li.select_one('a[name="productName"]')
        if not name_el:
            continue
        name = clean_text(name_el.get_text(" ", strip=True))
        link = abs_url(name_el.get("href"))
        min_input = li.select_one(f"#min_price_{pid}") if pid else None
        price = parse_int(min_input.get("value") if min_input else None)
        if price is None:
            price_el = li.select_one(".price_sect strong") or li.select_one(".prod_pricelist strong")
            price = parse_int(price_el.get_text() if price_el else None)
        img = li.select_one(".thumb_image img")
        image = abs_url((img.get("data-original") or img.get("src")) if img else None)
        mall_el = li.select_one(".prod_pricelist .memory_sect") or li.select_one(".meta_item")
        spec = " / ".join(clean_text(e.get_text(" ", strip=True)) or "" for e in li.select(".spec_list a, .spec_list span")[:10])
        items.append(
            {
                "pcode": pid,
                "title": name,
                "price": price,
                "price_text": f"{price:,}원" if price else None,
                "mall_text": clean_text(mall_el.get_text(" ", strip=True)) if mall_el else None,
                "url": link,
                "image_url": image,
                "spec": spec[:300] if spec else None,
            }
        )
        if len(items) >= limit:
            break
    return {"query": query, "source_url": url, "count"