import re
import httpx
from http import HTTPMethod
from urllib.parse import urlparse
from common.utils import http_request

NAVER_BASE = "https://openapi.naver.com/v1/search"


class NaverClient:
    def __init__(self, client_id: str, client_secret: str):
        self.client_id = client_id
        self.client_secret = client_secret

    def _headers(self) -> dict:
        return {
            "X-Naver-Client-Id": self.client_id,
            "X-Naver-Client-Secret": self.client_secret,
        }

    async def fetch_blog_search(self, query: str, display: int = 5) -> list[dict]:
        resp = await http_request(
            HTTPMethod.GET,
            url=f"{NAVER_BASE}/blog.json",
            headers=self._headers(),
            params={"query": query, "display": display, "sort": "sim"},
            label="naver-blog",
        )
        if not resp or not resp.is_success:
            return []
        return resp.json().get("items", [])

    async def fetch_web_search(self, query: str, display: int = 10) -> list[dict]:
        resp = await http_request(
            HTTPMethod.GET,
            url=f"{NAVER_BASE}/webkr.json",
            headers=self._headers(),
            params={"query": query, "display": display},
            label="naver-web",
        )
        if not resp or not resp.is_success:
            return []
        return resp.json().get("items", [])

    async def fetch_local_search(self, query: str, display: int = 5) -> list[dict]:
        resp = await http_request(
            HTTPMethod.GET,
            url=f"{NAVER_BASE}/local.json",
            headers=self._headers(),
            params={"query": query, "display": display, "sort": "comment"},
            label="naver-local",
        )
        if not resp or not resp.is_success:
            return []
        return resp.json().get("items", [])

    async def fetch_blog_rss(self, handle: str) -> str | None:
        resp = await http_request(
            HTTPMethod.GET,
            url=f"https://rss.blog.naver.com/{handle}.xml",
            timeout=15,
            label="naver-rss",
        )
        if not resp or not resp.is_success:
            return None
        return resp.text

    async def fetch_blog_total_count(self, handle: str) -> int | None:
        """블로그 전체 글 수는 RSS에 없어서 PostList HTML에서 '554개의 글' 패턴 추출.
        <h4 class="category_title pcol2">... 554개의 글</h4> 구조."""
        resp = await http_request(
            HTTPMethod.GET,
            url=f"https://blog.naver.com/PostList.naver?blogId={handle}&from=postList&directAccess=true",
            timeout=15,
            label="naver-blog-postlist",
        )
        if not resp or not resp.is_success:
            return None
        m = re.search(r"(\d+)개의 글", resp.text)
        return int(m.group(1)) if m else None

    async def get_blog_rss(self, url: str) -> dict | None:
        blog_handle = urlparse(url).path.strip("/").split("/")[0] if "://" in url else url
        xml = await self.fetch_blog_rss(blog_handle)
        if not xml:
            return None
        posts = []
        for m in re.finditer(r"<item>([\s\S]*?)</item>", xml):
            block = m.group(1)
            title = re.search(r"<title><!\[CDATA\[(.*?)\]\]></title>", block) or re.search(r"<title>(.*?)</title>", block)
            link = re.search(r"<link>(.*?)</link>", block)
            date = re.search(r"<pubDate>(.*?)</pubDate>", block)
            desc = re.search(r"<description><!\[CDATA\[(.*?)\]\]></description>", block) or re.search(r"<description>(.*?)</description>", block)
            posts.append({
                "title": title.group(1) if title else "",
                "link": link.group(1) if link else "",
                "postDate": date.group(1) if date else "",
                "description": re.sub(r"<[^>]*>", "", desc.group(1) if desc else "").strip()[:150],
            })
        # RSS의 totalCount 우선, 없으면 블로그 PostList 페이지에서 "N개의 글" 파싱, 그것도 없으면 RSS 글수
        total_match = re.search(r"<totalCount>(\d+)</totalCount>", xml)
        if total_match:
            total = int(total_match.group(1))
        else:
            total = await self.fetch_blog_total_count(blog_handle) or len(posts)
        return {
            "officialBlogUrl": f"https://blog.naver.com/{blog_handle}",
            "officialBlogHandle": blog_handle,
            "totalResults": total,
            "posts": posts[:10],
        }

    async def get_cafe_info(self, cafe_url: str, *_args, **_kwargs) -> dict | None:
        """네이버 카페 운영 신호 수집. 2단계 fetch:
        1) https://cafe.naver.com/{handle} → cafeId 추출
        2) ArticleList.nhn?search.clubid={cafeId} → memberCount + cafeName 추출
        본문/게시글은 로그인 필요라 못 가져옴. 회원수·카페명만 잡히면 충분.
        common.http_request는 redirect 안 따라가서 카페 페이지에 안 맞아 httpx 직접 사용."""
        handle = urlparse(cafe_url).path.strip("/").split("/")[0] if "://" in cafe_url else cafe_url.split("/")[-1]
        if not handle:
            return None

        async with httpx.AsyncClient(
            timeout=10, follow_redirects=True,
            headers={"User-Agent": "Mozilla/5.0"},
        ) as c:
            # 1. cafeId 추출
            try:
                main = await c.get(f"https://cafe.naver.com/{handle}")
            except Exception:
                return {"url": f"https://cafe.naver.com/{handle}", "cafeHandle": handle, "accessible": False}
            if main.status_code != 200:
                return {"url": f"https://cafe.naver.com/{handle}", "cafeHandle": handle, "accessible": False}
            cid_match = re.search(r'cafeId["\']?\s*[:=]\s*["\']?(\d+)', main.text)
            cafe_id = cid_match.group(1) if cid_match else None

            result: dict = {
                "url": f"https://cafe.naver.com/{handle}",
                "cafeHandle": handle,
                "cafeId": cafe_id,
                "accessible": True,
                "cafeName": None,
                "memberCount": None,
            }
            if not cafe_id:
                return result

            # 2. ArticleList 페이지에서 회원수 + 카페명 추출 (로그인 없이 접근 가능한 유일한 endpoint)
            try:
                listing = await c.get(
                    f"https://cafe.naver.com/ArticleList.nhn?search.clubid={cafe_id}&search.menuid=&search.boardtype=L",
                    headers={"Referer": f"https://cafe.naver.com/{handle}"},
                )
            except Exception:
                return result
            if listing.status_code != 200:
                return result
            mc = re.search(r'memberCount[^0-9]+(\d[\d,]*)', listing.text)
            if mc:
                result["memberCount"] = int(mc.group(1).replace(",", ""))
            tm = re.search(r"<title>(.+?)\s*:\s*네이버 카페</title>", listing.text)
            if tm:
                name = re.sub(r"&amp;", "&", tm.group(1)).strip()
                if "," in name:
                    name = name.split(",", 1)[1].strip()
                result["cafeName"] = name
            return result