verify-invoice-default/scripts/service/rpa/browser_session.py

"""浏览器会话管理：基于 skill-template 的 simulator_browser_rpa 示例。"""

from __future__ import annotations

import logging
import os
import random
from typing import Any, List, Optional, Tuple

from jiangchang_skill_core import config
from jiangchang_skill_core.activity import interruptible_sleep

logger = logging.getLogger(__name__)

DEFAULT_PAGE_TIMEOUT_MS = 15_000

CHROME_LAUNCH_ARGS: List[str] = [
    "--start-maximized",
    "--disable-blink-features=AutomationControlled",
]

STEALTH_INIT_SCRIPT = """
(() => {
  try { Object.defineProperty(navigator, 'webdriver', { get: () => undefined }); } catch (e) {}
})();
"""


def chrome_launch_args() -> List[str]:
    return list(CHROME_LAUNCH_ARGS)


def _headless_from_env() -> bool:
    v = (os.getenv("OPENCLAW_BROWSER_HEADLESS") or "0").strip().lower()
    return v in ("1", "true", "yes", "on")


def find_browser_executable() -> Optional[str]:
    """查找系统 Chrome 或 Edge 浏览器。"""
    try:
        from jiangchang_skill_core.runtime_env import find_chrome_executable as _find
        chrome = _find()
        if chrome and os.path.isfile(chrome):
            return chrome
    except ImportError:
        pass

    candidates = [
        os.path.expandvars(r"%ProgramFiles%\Google\Chrome\Application\chrome.exe"),
        os.path.expandvars(r"%ProgramFiles(x86)%\Google\Chrome\Application\chrome.exe"),
        os.path.expandvars(r"%ProgramFiles%\Microsoft\Edge\Application\msedge.exe"),
        os.path.expandvars(r"%ProgramFiles(x86)%\Microsoft\Edge\Application\msedge.exe"),
    ]
    for path in candidates:
        if path and os.path.isfile(path):
            return path
    return None


# 向后兼容别名
find_edge_executable = find_browser_executable


def _clear_node_options() -> None:
    os.environ.pop("NODE_OPTIONS", None)


async def start_browser_session(
    profile_dir: str,
    headless: bool = False,
) -> Tuple[Any, Any, Any]:
    """启动持久化 Chrome/Edge 浏览器会话。

    URL 不在此文件打开；由 invoice_rpa.py 负责 page.goto。

    Args:
        profile_dir: 浏览器配置目录
        headless: 是否无头模式（生产必须为 False）

    Returns:
        (playwright, context, page) 三元组

    Raises:
        RuntimeError: 浏览器启动失败
    """
    if not profile_dir:
        raise RuntimeError("ERROR:MISSING_BROWSER 缺少浏览器配置目录")

    # 确保有头模式（生产要求）
    if headless:
        logger.warning("生产环境强制使用有头模式")
        headless = False

    # 确保 profile 目录存在
    os.makedirs(profile_dir, exist_ok=True)

    _clear_node_options()
    hl = headless if headless is not None else _headless_from_env()
    chrome = find_browser_executable()
    if not chrome:
        raise RuntimeError(
            "ERROR:MISSING_BROWSER 未检测到 Chrome 或 Edge 浏览器，请先安装系统浏览器后重试。"
        )

    args = chrome_launch_args()
    logger.info(
        "browser_launch chrome=%s profile_dir=%s args=%s headless=%s",
        chrome,
        profile_dir,
        args,
        hl,
    )

    try:
        from playwright.async_api import async_playwright

        pw = await async_playwright().start()
        context = None
        try:
            context = await pw.chromium.launch_persistent_context(
                user_data_dir=profile_dir,
                headless=hl,
                executable_path=chrome,
                locale="zh-CN",
                no_viewport=True,
                args=args,
                ignore_default_args=["--enable-automation"],
            )
            await context.add_init_script(STEALTH_INIT_SCRIPT)

            page = context.pages[0] if context.pages else await context.new_page()
            page.set_default_timeout(DEFAULT_PAGE_TIMEOUT_MS)
            logger.info("browser_started profile_dir=%s", profile_dir)
            return pw, context, page
        except Exception:
            if context is not None:
                try:
                    await context.close()
                except Exception:
                    pass
            await pw.stop()
            raise
    except RuntimeError:
        raise
    except Exception as e:
        logger.error("browser_start_failed error=%s", str(e))
        raise RuntimeError(f"ERROR:MISSING_BROWSER 浏览器启动失败: {str(e)}")


async def close_browser_context(pw: Any, context: Any) -> None:
    """安全关闭浏览器上下文。"""
    try:
        if context is not None:
            await context.close()
    except Exception:
        pass
    try:
        if pw is not None:
            await pw.stop()
    except Exception:
        pass


async def wait_for_page_ready(page: Any, timeout_sec: float = 30.0) -> bool:
    """等待页面加载完成。"""
    async def _check_ready():
        try:
            ready_state = await page.evaluate("document.readyState")
            if ready_state == "complete":
                return True
            loading_selectors = [".loading", ".spinner", "[data-loading]"]
            for sel in loading_selectors:
                if await page.locator(sel).count() > 0:
                    return False
            return True
        except Exception:
            return False

    try:
        from jiangchang_skill_core.rpa import poll_until
        result = await poll_until(_check_ready, timeout_sec=timeout_sec, interval_sec=0.5)
        return result.ok
    except ImportError:
        # fallback: 简单等待
        import asyncio
        await asyncio.sleep(min(timeout_sec, 3.0))
        return True


async def random_delay(min_sec: float = 1.0, max_sec: float = 3.0) -> None:
    """随机延迟，模拟人类操作节奏。"""
    delay = random.uniform(min_sec, max_sec)
    await interruptible_sleep(delay)