Init

app/core/config.py

@@ -0,0 +1,118 @@
+"""应用配置：通过环境变量和 .env 文件加载所有配置项
+
+配置项统一使用 RAKUTEN_ 前缀，例如 RAKUTEN_APP_PORT=31107。
+支持 .env 文件自动加载。
+"""
+from functools import lru_cache
+from pathlib import Path
+from typing import Literal
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+from app.core import site
+
+BASE_DIR = Path(__file__).resolve().parent.parent.parent
+
+
+class Settings(BaseSettings):
+    """应用全局配置
+
+    所有配置项均可通过环境变量覆盖，前缀为 RAKUTEN_。
+    例如：RAKUTEN_APP_PORT=31107 对应 app_port 配置项。
+    """
+
+    model_config = SettingsConfigDict(
+        env_file=str(BASE_DIR / ".env"),
+        env_file_encoding="utf-8",
+        env_prefix="RAKUTEN_",
+        extra="ignore",
+    )
+
+    # ---- 服务基本配置 ----
+    app_name: str = "Rakuten Scraper Service"
+    app_env: Literal["dev", "prod", "test"] = "dev"
+    app_host: str = "0.0.0.0"
+    app_port: int = 31107
+
+    # ---- 日志配置 ----
+    log_level: str = "INFO"
+    log_to_file: bool | None = None  # None 表示根据环境自动决定
+    log_dir: str = "logs"
+    log_rotation: str = "100 MB"
+    log_retention: str = "14 days"
+    log_compression: str = "zip"
+    log_format: str = "{time:YYYY-MM-DD HH:mm:ss} {level} {message}"
+    log_enqueue: bool = True
+
+    # ---- 鉴权配置 ----
+    bearer_token: str = "REPLACE_WITH_TOKEN_32CHARS"
+
+    # ---- HTTP 抓取配置 ----
+    request_timeout_seconds: float = 30.0
+    max_site_concurrency: int = 8  # 对站点的最大并发请求数
+    http_max_attempts: int = 3  # 单次抓取的最大尝试次数（含首次）
+    session_ttl_seconds: float = 1800.0  # Akamai cookie 会话最长复用时长，超时后重新预热
+
+    # ---- 浏览器兜底配置 ----
+    # 纯 HTTP 被 Akamai 拦截时，用 Playwright 打开页面取回 cookie 再回灌给
+    # HTTP 客户端重试。日常流量不会触发；未安装 playwright 时自动降级为不兜底。
+    browser_fallback_enabled: bool = True
+    browser_headless: bool | None = None  # None 表示根据环境自动决定
+    browser_channel: str | None = None  # 例如 chrome；留空使用 bundled chromium
+    browser_launch_timeout_seconds: float = 60.0
+    browser_nav_timeout_seconds: float = 60.0
+
+    # ---- 代理配置（可选，用于日本 IP）----
+    proxy_server: str | None = None
+    proxy_username: str | None = None
+    proxy_password: str | None = None
+
+    # ---- 目标站点 ----
+    home_url: str = site.HOME_URL
+
+    @property
+    def browser_headless_effective(self) -> bool:
+        """浏览器无头模式：显式配置优先，否则开发环境使用有头模式方便调试"""
+        if self.browser_headless is not None:
+            return self.browser_headless
+        return self.app_env != "dev"
+
+    @property
+    def log_to_file_effective(self) -> bool:
+        """是否写日志文件：显式配置优先，否则生产环境默认写文件"""
+        if self.log_to_file is not None:
+            return self.log_to_file
+        return self.app_env == "prod"
+
+    @property
+    def playwright_proxy(self) -> dict[str, str] | None:
+        """构建 Playwright 代理配置字典"""
+        if not self.proxy_server:
+            return None
+
+        proxy: dict[str, str] = {"server": self.proxy_server}
+        if self.proxy_username:
+            proxy["username"] = self.proxy_username
+        if self.proxy_password:
+            proxy["password"] = self.proxy_password
+        return proxy
+
+    @property
+    def httpx_proxy(self) -> str | None:
+        """构建 httpx 代理 URL（含认证信息）"""
+        if not self.proxy_server:
+            return None
+        if not self.proxy_username:
+            return self.proxy_server
+
+        scheme, _, rest = self.proxy_server.partition("://")
+        if not rest:
+            return self.proxy_server
+        credentials = f"{self.proxy_username}:{self.proxy_password or ''}"
+        return f"{scheme}://{credentials}@{rest}"
+
+
+@lru_cache(maxsize=1)
+def get_settings() -> Settings:
+    """获取全局配置单例"""
+    return Settings()