"""抓取全市场 ETF 列表（规模 + 成交额），用于挑选各热门板块的代表性标的。

数据源：东方财富行情接口（公开 JSON，无需登录）。
字段：f12=代码 f13=市场(0深/1沪) f14=名称 f2=最新价 f3=涨跌幅 f6=成交额 f20=总市值 f21=流通市值

用法： py -3.14 -B labs/analysis/etf/screen_etf.py [关键词...]
      不带关键词时按板块关键词分组输出候选。
"""

import json
import sys
import time
import urllib.parse
import urllib.request

try:
    sys.stdout.reconfigure(encoding="utf-8", errors="replace")
except Exception:
    pass

BASE_HOSTS = ("82.push2.eastmoney.com", "push2delay.eastmoney.com", "push2.eastmoney.com")
FS = "b:MK0021,b:MK0022,b:MK0023,b:MK0024"   # 沪深 ETF/LOF 集合
FIELDS = "f12,f13,f14,f2,f3,f6,f20,f21"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Referer": "https://fund.eastmoney.com/",
}

# 每个板块的候选关键词（用于在名称里匹配）；越靠前优先级越高
SECTORS = {
    "AI": ["人工智能", "AIETF", "AIETF", "科创AI", "智能"],
    "CPO": ["光通信", "通信ETF", "通信设备", "5G通信", "通信"],
    "PCB": ["PCB", "电子ETF", "消费电子", "电子50", "电子"],
    "人形机器人": ["机器人", "智能制造", "工业母机"],
    "光": ["光伏", "新能源", "电池"],
    "创新药": ["创新药", "医药", "生物医药", "医疗"],
    "半导体": ["半导体", "芯片", "集成电路", "科创芯片"],
    "存储": ["存储", "集成电路", "科创芯片"],
    "半导体材料": ["半导体材料", "材料ETF", "新材料"],
    "玻璃基板": ["玻璃", "建材", "新材料"],
    "电力": ["电力", "公用事业", "电网", "绿电"],
    "航空航天": ["航空", "航天", "军工", "国防"],
    "金属": ["有色", "金属", "黄金", "稀土"],
    "金融": ["证券", "银行", "保险", "金融"],
    "能源": ["能源", "煤炭", "石油", "油气"],
}


def fetch_page(page: int, size: int = 100, retries: int = 4) -> tuple[list[dict], int]:
    query = urllib.parse.urlencode({
        "pn": page, "pz": size, "po": 1, "np": 1, "fltt": 2, "invt": 2,
        "fid": "f3", "fs": FS, "fields": FIELDS,
        "ut": "bd1d9ddb04089700cf9c27f6f7426281",
    })
    last_error = None
    for attempt in range(retries):
        # 主站 push2 容易被限流返回 502，轮换到镜像域名
        host = BASE_HOSTS[attempt % len(BASE_HOSTS)]
        request = urllib.request.Request(f"http://{host}/api/qt/clist/get?{query}", headers=HEADERS)
        try:
            with urllib.request.urlopen(request, timeout=30) as response:
                payload = json.load(response)
            data = payload.get("data") or {}
            return data.get("diff") or [], int(data.get("total") or 0)
        except Exception as exc:                 # 502/超时都换域名重试
            last_error = exc
            time.sleep(1.0 * (attempt + 1))
    raise RuntimeError(f"第 {page} 页抓取失败：{last_error}")


def fetch_all() -> list[dict]:
    rows, total = fetch_page(1)
    page = 2
    while len(rows) < total:
        try:
            more, _ = fetch_page(page)
        except RuntimeError as exc:
            print(f"警告：{exc}，已抓 {len(rows)}/{total}", file=sys.stderr)
            break
        if not more:
            break
        rows.extend(more)
        page += 1
        time.sleep(0.6)          # 轻量限速，避免被限流
    return rows


def code_of(row: dict) -> str:
    suffix = "SH" if str(row.get("f13")) == "1" else "SZ"
    return f"{row['f12']}.{suffix}"


def size_yi(row: dict) -> float:
    """规模（亿元）：接口给的是元。"""
    value = row.get("f20") or row.get("f21") or 0
    return float(value) / 1e8


def turnover_yi(row: dict) -> float:
    """成交额（亿元）。"""
    return float(row.get("f6") or 0) / 1e8


def main() -> int:
    keywords = sys.argv[1:]
    rows = fetch_all()
    print(f"抓取到 {len(rows)} 只 ETF/LOF")
    if keywords:
        for row in rows:
            name = str(row.get("f14") or "")
            if any(k in name for k in keywords):
                print(f"{code_of(row):12} {name:24} 规模={size_yi(row):8.2f}亿 "
                      f"成交额={turnover_yi(row):7.3f}亿 涨跌={row.get('f3')}%")
        return 0

    for sector, words in SECTORS.items():
        hits = [r for r in rows if any(w in str(r.get("f14") or "") for w in words)]
        hits.sort(key=lambda r: -size_yi(r))
        print(f"\n== {sector} 候选 {len(hits)} 只（按规模降序，取前 6）==")
        for row in hits[:6]:
            print(f"  {code_of(row):12} {str(row.get('f14')):26} "
                  f"规模={size_yi(row):8.2f}亿 成交额={turnover_yi(row):7.3f}亿")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())