"""site_import 抓取编排（spec §3.1/§3.3 的 crawl 段）。

BFS 选页 ≤10（深度 ≤2）→ safe_fetch 逐页 → extract 清洗抽取 →
CSS/logo 追抓（15s 超时）→ 组装 crawl_result dict 供生成器。

入口页双重门（spec §3.1/§6）：非 text/html → 零页内容不足；清洗后
<200 字符 → SPA 空壳（子页过薄只跳过不失败——JS 渲染的产品子页常见，
整站不该陪葬）。单页 >500KB 截断解析（clean_html 未闭合块二遍清洗兜底）。
discover_links 会回吐入口自身（href="#"/"/"）——visited 预置 start URL
去重，防浪费 ≤10 页名额（Task 3 备忘）。
"""
from __future__ import annotations

import base64
import re
from collections import deque
from urllib.parse import urljoin, urlsplit, urlunsplit

from app.platform.site_import import safe_fetch
from app.platform.site_import.extract import (
    clean_html, discover_links, extract_color, extract_contacts,
    extract_logo_url, is_thin,
)
from app.platform.site_import.safe_fetch import FetchError

MAX_PAGES = 10
MAX_DEPTH = 2
DEFAULT_COLOR = "#066fc0"  # extract_color None 的函数层不兜底原则（Task 3 备忘）
PAGE_TIMEOUT = 10.0
ASSET_TIMEOUT = 15.0
MAX_PAGE_CHARS = 500 * 1024  # 单页 500KB 上限（截断解析）
LOGO_MAX_BYTES = 2 * 1024 * 1024
LOGO_OK_MIME = {"image/png", "image/jpeg", "image/webp"}
INSUFFICIENT_TOTAL_CHARS = 1000

SPA_MESSAGE = "该网站需要浏览器渲染才能看到内容，暂不支持自动导入——请在配置中心手动配置"
INSUFFICIENT_MESSAGE = "网站内容不足以生成配置，请在配置中心手动配置"

# 首个外链样式表发现（link 标签内 rel 含 stylesheet → 提取 href）
_RE_LINK_TAG = re.compile(r"<link\b[^>]*>", re.IGNORECASE)
_RE_REL_STYLESHEET = re.compile(r"""rel\s*=\s*["']?\s*stylesheet\b""",
                                re.IGNORECASE)
_RE_HREF_IN_TAG = re.compile(r"""href\s*=\s*["']([^"']+)["']""",
                             re.IGNORECASE)


class CrawlError(Exception):
    """抓取阶段不可恢复失败（SPA 空壳/内容不足）——phase=crawl，不可 retry。"""


def _sniff_image(data: bytes) -> str | None:
    """魔数指纹（与 Content-Type 双验——防伪造头）。"""
    if data.startswith(b"\x89PNG\r\n\x1a\n"):
        return "image/png"
    if data.startswith(b"\xff\xd8\xff"):
        return "image/jpeg"
    if len(data) >= 12 and data[:4] == b"RIFF" and data[8:12] == b"WEBP":
        return "image/webp"
    return None


def _normalize(url: str) -> str:
    """同源同径去重键（与 discover_links 的清洗口径对齐：去查询去锚点）。"""
    parts = urlsplit(url)
    return urlunsplit((parts.scheme.lower(), parts.netloc.lower(),
                       parts.path, "", ""))


def _html_text(resp) -> str | None:
    """Content-Type 非 text/html → None（调用方跳页/判零页）；500KB 截断。"""
    ct = resp.headers.get("content-type", "").lower()
    if "text/html" not in ct:
        return None
    return resp.text[:MAX_PAGE_CHARS]


def _first_css_url(base_url: str, html_text: str) -> str | None:
    for m in _RE_LINK_TAG.finditer(html_text):
        tag = m.group(0)
        if _RE_REL_STYLESHEET.search(tag):
            hm = _RE_HREF_IN_TAG.search(tag)
            if hm:
                return urljoin(base_url, hm.group(1).strip())
    return None


async def _fetch_logo(url: str, warnings: list[str]) -> str | None:
    """logo 下载校验（spec §3.1）：MIME 白名单 + 魔数双验 + ≤2MB →
    base64 data URL；不合格 → None + warning 注记（审核页无头像预览，
    保存链路头像项空置——零新后端端点）。"""
    try:
        resp = await safe_fetch.fetch(url, ASSET_TIMEOUT)
    except FetchError:
        warnings.append("logo 下载失败，已跳过头像")
        return None
    data = resp.content
    if len(data) > LOGO_MAX_BYTES:
        warnings.append("logo 超过 2MB 上限，已跳过头像")
        return None
    mime = resp.headers.get("content-type", "").split(";", 1)[0].strip().lower()
    sniffed = _sniff_image(data)
    if mime not in LOGO_OK_MIME or sniffed is None or sniffed != mime:
        warnings.append("logo 为不支持的格式，已跳过头像")
        return None
    return f"data:{sniffed};base64," + base64.b64encode(data).decode("ascii")


async def crawl(start_url: str) -> dict:
    """整站抓取编排，返回 crawl_result dict。

    FetchError 不在此包装——交任务层 fail（白话化 + phase 归档）。
    """
    warnings: list[str] = []

    # 1) 入口页：非 text/html → 零页（内容不足三触发之一）
    entry = await safe_fetch.fetch(start_url, PAGE_TIMEOUT)
    entry_html = _html_text(entry)
    if entry_html is None:
        raise CrawlError(INSUFFICIENT_MESSAGE)
    entry_clean = clean_html(entry_html)
    if is_thin(entry_clean):
        raise CrawlError(SPA_MESSAGE)

    # 2) BFS：入口 depth 0 → 子页 ≤MAX_DEPTH；关键词优先序即抓取优先级
    pages_text = entry_clean
    htmls = [entry_html]
    fetched = 1
    visited = {_normalize(start_url)}  # discover_links 含入口自身——预置去重
    queue: deque[tuple[str, int]] = deque(
        (u, 1) for u in discover_links(start_url, entry_html))

    while queue and fetched < MAX_PAGES:
        url, depth = queue.popleft()
        norm = _normalize(url)
        if norm in visited:
            continue
        visited.add(norm)
        try:
            resp = await safe_fetch.fetch(url, PAGE_TIMEOUT)
        except FetchError:
            warnings.append(f"子页抓取失败已跳过：{url}")
            continue
        html = _html_text(resp)
        if html is None:
            warnings.append(f"子页非 HTML 已跳过：{url}")
            continue
        clean = clean_html(html)
        if is_thin(clean):
            warnings.append(f"子页内容过薄已跳过：{url}")
            continue
        pages_text += "\n" + clean
        htmls.append(html)
        fetched += 1
        if depth < MAX_DEPTH:
            queue.extend((u, depth + 1) for u in discover_links(url, html))

    # 3) 总文本 <1K（内容不足三触发之一）
    if len(pages_text) < INSUFFICIENT_TOTAL_CHARS:
        raise CrawlError(INSUFFICIENT_MESSAGE)

    # 4) 主色：内联 style（全页 html 集）+ 首个外链 CSS（15s 追抓，失败
    #    静默回退内联/默认色——样式表属增益项不陪葬）
    css_text: str | None = None
    css_url = _first_css_url(start_url, entry_html)
    if css_url:
        try:
            css_resp = await safe_fetch.fetch(css_url, ASSET_TIMEOUT)
            css_text = css_resp.text[:MAX_PAGE_CHARS]
        except FetchError:
            pass
    combined_html = "\n".join(htmls)
    color = extract_color(combined_html, css_text) or DEFAULT_COLOR

    contacts = extract_contacts(combined_html)

    logo_data_url = None
    logo_url = extract_logo_url(combined_html)
    if logo_url:
        # src 可能是相对路径（WordPress uploads 常见）——对入口页绝对化
        logo_data_url = await _fetch_logo(urljoin(start_url, logo_url),
                                          warnings)

    return {
        "pages_text": pages_text,
        "color": color,
        "whatsapp": contacts["whatsapp"],
        "email": contacts["email"],
        "logo_data_url": logo_data_url,
        "warnings": warnings,
        "pages_fetched": fetched,
    }