refactor: restructure services and add image/pdf extraction utilities

- Add image_extractor, pdf_downloader, pi_client, trends services
- Add shared utils module
- Refactor summarizer, embedder, routes for cleaner separation
- Update tests to match new service structure

app/utils.py

@@ -0,0 +1,73 @@
+"""公共工具 — 消除各模块间的重复代码。"""
+
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from pathlib import Path
+from zoneinfo import ZoneInfo
+
+import httpx
+from fastapi.templating import Jinja2Templates
+
+from app.config import settings
+
+# ── 路径常量 ──────────────────────────────────────────────────────────
+
+DATA_DIR = Path("data")
+PAPERS_DIR = DATA_DIR / "papers"
+TMP_DIR = DATA_DIR / "tmp"
+
+# ── 模板单例 ──────────────────────────────────────────────────────────
+
+templates = Jinja2Templates(directory="app/templates")
+
+
+# ── 时区工具 ──────────────────────────────────────────────────────────
+
+
+def today_str() -> str:
+    """当前日期字符串（按 APP_TIMEZONE）。"""
+    tz = ZoneInfo(settings.APP_TIMEZONE)
+    return datetime.now(tz).strftime("%Y-%m-%d")
+
+
+# ── 锁释放 ────────────────────────────────────────────────────────────
+
+
+def release_lock(db, lock) -> None:
+    """释放 TaskLock。"""
+    try:
+        lock.status = "finished"
+        lock.released_at = datetime.now(timezone.utc)
+        db.commit()
+    except Exception:
+        db.rollback()
+
+
+# ── HTTP 客户端工厂 ───────────────────────────────────────────────────
+
+
+def make_http_client(*, sync: bool = False, follow_redirects: bool = False, **kwargs) -> httpx.AsyncClient | httpx.Client:
+    """创建带 proxy 和默认配置的 httpx 客户端。
+
+    Args:
+        sync: True 返回同步 Client，False 返回 AsyncClient
+        follow_redirects: 是否跟随重定向
+        **kwargs: 覆盖默认参数
+    """
+    defaults: dict = {
+        "timeout": settings.HTTP_TIMEOUT_SECONDS,
+        "headers": {"User-Agent": settings.HTTP_USER_AGENT},
+        "follow_redirects": follow_redirects,
+    }
+    if settings.http_proxy:
+        defaults["transport"] = (
+            httpx.HTTPTransport(proxy=settings.http_proxy)
+            if sync
+            else httpx.AsyncHTTPTransport(proxy=settings.http_proxy)
+        )
+    defaults.update(kwargs)
+
+    if sync:
+        return httpx.Client(**defaults)
+    return httpx.AsyncClient(**defaults)