stocks-query/scripts/yahoo-broker-trading-browserless.py

#!/usr/bin/env python3
"""
用 Browserless 抓 Yahoo 主力券商進出頁，輸出精簡摘要

用法：
  python3 skills/stocks-query/scripts/yahoo-broker-trading-browserless.py 2330
  python3 skills/stocks-query/scripts/yahoo-broker-trading-browserless.py 3481

環境變數（可覆蓋）：
  BROWSERLESS_ENDPOINT=http://192.168.42.124:13000
  BROWSERLESS_TOKEN=6R0W53R135510
"""

import json
import os
import re
import sys
import urllib.error
import urllib.request
from pathlib import Path


def load_dotenv() -> None:
    """載入 .env（優先目前目錄，其次 workspace 根目錄）。"""
    candidates = [
        Path.cwd() / ".env",
        Path(__file__).resolve().parents[3] / ".env",
    ]
    for env_path in candidates:
        if not env_path.exists():
            continue
        for raw in env_path.read_text(encoding="utf-8").splitlines():
            line = raw.strip()
            if not line or line.startswith("#") or "=" not in line:
                continue
            k, v = line.split("=", 1)
            k = k.strip()
            v = v.strip().strip('"').strip("'")
            if k and k not in os.environ:
                os.environ[k] = v
        break


load_dotenv()

ENDPOINT = os.getenv("BROWSERLESS_ENDPOINT")
TOKEN = os.getenv("BROWSERLESS_TOKEN")
if not ENDPOINT or not TOKEN:
    raise RuntimeError("缺少必要環境變數：BROWSERLESS_ENDPOINT / BROWSERLESS_TOKEN")
STOCK_NO = sys.argv[1] if len(sys.argv) > 1 else "2330"


def fetch_html(stock_no: str) -> str:
    url = f"https://tw.stock.yahoo.com/quote/{stock_no}.TW/broker-trading"
    api = f"{ENDPOINT}/content?token={TOKEN}"
    payload = {
        "url": url,
        "gotoOptions": {"waitUntil": "domcontentloaded", "timeout": 60000},
    }

    req = urllib.request.Request(
        api,
        data=json.dumps(payload).encode("utf-8"),
        headers={"Content-Type": "application/json"},
        method="POST",
    )

    try:
        with urllib.request.urlopen(req, timeout=90) as resp:
            text = resp.read().decode("utf-8", errors="replace")
            status = resp.getcode()
    except urllib.error.HTTPError as e:
        body = e.read().decode("utf-8", errors="replace") if hasattr(e, "read") else str(e)
        raise RuntimeError(f"Browserless HTTP {e.code}: {body[:200]}") from e

    if status != 200:
        raise RuntimeError(f"Browserless HTTP {status}: {text[:200]}")
    if "TimeoutError" in text:
        raise RuntimeError("Browserless 導航逾時（TimeoutError）")
    return text


def pick(html: str, pattern: str, default: str = "-") -> str:
    m = re.search(pattern, html, flags=re.S)
    return m.group(1) if m else default


def parse_brokers(html: str, stock_no: str) -> dict:
    name = pick(html, r'property="og:title" content="([^"(]+)\([0-9]+\.TW\)', "").strip()
    if not name:
        name = pick(html, r"<title>([^<(]+)\([0-9]+\.TW\)", "-").strip()

    # 嘗試從嵌入 JSON 中抓券商進出資料
    buy_brokers = []
    sell_brokers = []

    # 方法1：從 brokerBuySellData / topBrokers JSON 結構抓取
    json_match = re.search(r'"brokerBuySellData"\s*:\s*(\{[\s\S]*?\})\s*[,}]', html)
    if json_match:
        try:
            raw = json.loads(json_match.group(1))
            for item in raw.get("buy", raw.get("buyBrokers", []))[:10]:
                buy_brokers.append({
                    "name": item.get("brokerName", item.get("name", "-")),
                    "buy": str(item.get("buy", item.get("buyVolume", 0))),
                    "sell": str(item.get("sell", item.get("sellVolume", 0))),
                    "diff": str(item.get("diff", item.get("net", 0))),
                })
            for item in raw.get("sell", raw.get("sellBrokers", []))[:10]:
                sell_brokers.append({
                    "name": item.get("brokerName", item.get("name", "-")),
                    "buy": str(item.get("buy", item.get("buyVolume", 0))),
                    "sell": str(item.get("sell", item.get("sellVolume", 0))),
                    "diff": str(item.get("diff", item.get("net", 0))),
                })
        except (json.JSONDecodeError, KeyError):
            pass

    # 方法2：從 HTML table 結構抓取
    if not buy_brokers and not sell_brokers:
        # 買超券商區塊
        buy_section = ""
        sell_section = ""
        buy_start = html.find("買超券商")
        sell_start = html.find("賣超券商")

        if buy_start != -1 and sell_start != -1:
            buy_section = html[buy_start:sell_start]
            sell_section = html[sell_start:sell_start + 50000]
        elif buy_start != -1:
            buy_section = html[buy_start:buy_start + 50000]

        broker_row_pat = re.compile(
            r'<li[^>]*>.*?'
            r'(?:券商|broker)[^<]*</[^>]+>.*?'
            r'([^<]{2,20})</(?:span|div|td)>'
            r'.*?([\d,]+).*?([\d,]+).*?([+-]?[\d,]+)',
            re.S,
        )

        # 更通用的抓法：連續出現的券商名+數字 pattern
        simple_pat = re.compile(
            r'>([^\d<>]{2,12}(?:證券|期貨|投顧|銀行|金控)?[^<>]{0,6})</(?:span|div|td|a)>'
            r'[^<]*<[^>]+>([\d,]+)</[^>]+>'
            r'[^<]*<[^>]+>([\d,]+)</[^>]+>'
            r'[^<]*<[^>]+>([+-]?[\d,]+)</[^>]+>',
            re.S,
        )

        for section, target_list in [(buy_section, buy_brokers), (sell_section, sell_brokers)]:
            for m in simple_pat.finditer(section):
                broker_name = m.group(1).strip()
                if len(broker_name) < 2 or broker_name.isdigit():
                    continue
                target_list.append({
                    "name": broker_name,
                    "buy": m.group(2).replace(",", ""),
                    "sell": m.group(3).replace(",", ""),
                    "diff": m.group(4).replace(",", ""),
                })
                if len(target_list) >= 10:
                    break

    # 日期
    date = pick(html, r"資料日期[：:]\s*([0-9/\-]+)")
    if date == "-":
        date = pick(html, r'"formattedDate"\s*:\s*"([^"]+)"')

    return {
        "name": name,
        "stock_no": stock_no,
        "date": date,
        "buy_brokers": buy_brokers[:10],
        "sell_brokers": sell_brokers[:10],
    }


def sign(v: str) -> str:
    if not v or v == "-":
        return "-"
    try:
        n = int(v.replace(",", ""))
        return f"+{n:,}" if n >= 0 else f"{n:,}"
    except ValueError:
        return v


def print_summary(d: dict) -> None:
    print(f"{d['name']}（{d['stock_no']}）｜主力券商進出")
    if d["date"] != "-":
        print(f"• 日期：{d['date']}")

    if d["buy_brokers"]:
        print("• 買超前幾大券商：")
        for b in d["buy_brokers"][:5]:
            print(f"  - {b['name']}：買 {b['buy']}／賣 {b['sell']}／差 {sign(b['diff'])} 張")
    else:
        print("• 買超券商：無資料")

    if d["sell_brokers"]:
        print("• 賣超前幾大券商：")
        for b in d["sell_brokers"][:5]:
            print(f"  - {b['name']}：買 {b['buy']}／賣 {b['sell']}／差 {sign(b['diff'])} 張")
    else:
        print("• 賣超券商：無資料")


if __name__ == "__main__":
    try:
        html = fetch_html(STOCK_NO)
        data = parse_brokers(html, STOCK_NO)
        print_summary(data)
    except Exception as e:
        print(f"取得失敗：{e}", file=sys.stderr)
        sys.exit(1)