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/routes/admin.py

@@ -6,7 +6,6 @@ from datetime import date, datetime, timezone
 
 from fastapi import APIRouter, Depends, HTTPException, Query, Request
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
-from fastapi.templating import Jinja2Templates
 from pydantic import BaseModel, field_validator
 from sqlalchemy import select
 from sqlalchemy.orm import Session
@@ -17,10 +16,10 @@ from app.models import CrawlLog, DataDeleteJob, TaskLock
 from app.services.cleaner import cleanup_tmp, delete_papers_by_date_range
 from app.services.crawler import crawl_daily
 from app.services.summarizer import summarize_batch, summarize_single
+from app.utils import release_lock, templates, today_str
 
 router = APIRouter(prefix="/admin", tags=["admin"])
 security = HTTPBearer()
-templates = Jinja2Templates(directory="app/templates")
 
 
 async def verify_admin(
@@ -32,7 +31,7 @@ async def verify_admin(
     return credentials.credentials
 
 
-# ── 请求模型 ──────────────────────────────────────────────────────────────
+# ── 请求模型 ──────────────────────────────────────────────────────────
 
 
 class DeleteRequest(BaseModel):
@@ -49,7 +48,7 @@ class DeleteRequest(BaseModel):
         return v
 
 
-# ── 抓取 ──────────────────────────────────────────────────────────────────
+# ── 抓取 ──────────────────────────────────────────────────────────────
 
 
 @router.post("/crawl")
@@ -59,12 +58,7 @@ async def admin_crawl(
     date: str | None = Query(None, description="YYYY-MM-DD，默认今天"),
 ):
     """手动抓取指定日期，默认今天。"""
-    # 计算 target_date
-    from zoneinfo import ZoneInfo
-
-    tz = ZoneInfo(settings.APP_TIMEZONE)
-    today = datetime.now(tz).strftime("%Y-%m-%d")
-    target_date = date or today
+    target_date = date or today_str()
 
     # TaskLock 防重入
     now = datetime.now(timezone.utc)
@@ -88,10 +82,10 @@ async def admin_crawl(
     except Exception as exc:
         raise HTTPException(status_code=500, detail=str(exc))
     finally:
-        _release_lock(db, lock)
+        release_lock(db, lock)
 
 
-# ── 总结 ──────────────────────────────────────────────────────────────────
+# ── 总结 ──────────────────────────────────────────────────────────────
 
 
 @router.post("/summarize")
@@ -119,7 +113,7 @@ async def admin_summarize_single(
     return result
 
 
-# ── 清理 ──────────────────────────────────────────────────────────────────
+# ── 清理 ──────────────────────────────────────────────────────────────
 
 
 @router.post("/cleanup")
@@ -155,7 +149,7 @@ async def admin_cleanup(
         raise HTTPException(status_code=500, detail=str(exc))
 
 
-# ── 删除 ──────────────────────────────────────────────────────────────────
+# ── 删除 ──────────────────────────────────────────────────────────────
 
 
 @router.post("/delete")
@@ -177,7 +171,7 @@ async def admin_delete(
     return result
 
 
-# ── 日志 ──────────────────────────────────────────────────────────────────
+# ── 日志 ──────────────────────────────────────────────────────────────
 
 
 @router.get("/logs")
@@ -189,7 +183,6 @@ async def admin_logs(
     per_page: int = Query(20, ge=1, le=100),
 ):
     """查看任务日志（CrawlLog + DataDeleteJob）。"""
-    # 查询 crawl_logs
     crawl_logs = (
         db.execute(
             select(CrawlLog)
@@ -201,7 +194,6 @@ async def admin_logs(
         .all()
     )
 
-    # 查询 delete_jobs
     delete_jobs = (
         db.execute(
             select(DataDeleteJob)
@@ -223,16 +215,3 @@ async def admin_logs(
             "per_page": per_page,
         },
     )
-
-
-# ── 工具函数 ──────────────────────────────────────────────────────────────
-
-
-def _release_lock(db: Session, lock: TaskLock) -> None:
-    """释放 TaskLock。"""
-    try:
-        lock.status = "finished"
-        lock.released_at = datetime.now(timezone.utc)
-        db.commit()
-    except Exception:
-        db.rollback()