fix: bug

crawler/pipeline.py

@@ -109,6 +109,33 @@ def run_full_pipeline(
     if not items:
         return 0, 0, 0
 
+    # 可选：仅保留指定起始时间之后的条目（如 CRAWL_START_DATE=2026-02-28T00:00:00）
+    start_date_env = os.environ.get("CRAWL_START_DATE", "").strip()
+    if start_date_env:
+        try:
+            raw = start_date_env.replace("Z", "+00:00").strip()
+            start_dt = datetime.fromisoformat(raw)
+            if start_dt.tzinfo is None:
+                start_dt = start_dt.replace(tzinfo=timezone.utc)
+            else:
+                start_dt = start_dt.astimezone(timezone.utc)
+            before = len(items)
+            items = [it for it in items if (it.get("published") or datetime.min.replace(tzinfo=timezone.utc)) >= start_dt]
+            if before > len(items):
+                print(f"  [pipeline] 按 CRAWL_START_DATE={start_date_env} 过滤后保留 {len(items)} 条（原 {before} 条）")
+        except Exception as e:
+            print(f"  [warn] CRAWL_START_DATE 解析失败，忽略: {e}")
+
+    if not items:
+        return 0, 0, 0
+    n_total = len(items)
+    print(f"  [pipeline] 抓取 {n_total} 条")
+    for i, it in enumerate(items[:5]):
+        title = (it.get("title") or it.get("summary") or "").strip()[:60]
+        print(f"    [{i + 1}] {title}" + ("…" if len((it.get("title") or it.get("summary") or "")[:60]) >= 60 else ""))
+    if n_total > 5:
+        print(f"    ... 共 {n_total} 条")
+
     # 2. 清洗（标题/摘要/分类，符合面板 schema）
     if translate:
         from translate_utils import translate_to_chinese
@@ -128,6 +155,11 @@ def run_full_pipeline(
 
     # 3. 去重：落库 news_content，仅新项返回
     new_items, n_news = save_and_dedup(items, db_path=path)
+    if new_items:
+        print(f"  [pipeline] 去重后新增 {n_news} 条，写入事件脉络 {len(new_items)} 条")
+        for i, it in enumerate(new_items[:3]):
+            title = (it.get("title") or it.get("summary") or "").strip()[:55]
+            print(f"    新增 [{i + 1}] {title}" + ("…" if len((it.get("title") or it.get("summary") or "").strip()) > 55 else ""))
 
     # 3.5 数据增强：为参与 AI 提取的条目抓取正文，便于从全文提取精确数据（伤亡、基地等）
     if new_items: