初始化

crawler/utils.py

@@ -0,0 +1,51 @@
+"""爬虫工具函数"""
+
+import logging
+from datetime import datetime, timedelta
+from pathlib import Path
+
+import yaml
+
+logger = logging.getLogger(__name__)
+
+# 默认日切分小时（凌晨）
+DEFAULT_CUTOFF_HOUR = 6
+
+
+def _load_cutoff_hour() -> int:
+    """从 system.yaml 读取日切分小时"""
+    config_path = Path("configs/system.yaml")
+    if config_path.exists():
+        try:
+            with open(config_path, encoding="utf-8") as f:
+                raw = yaml.safe_load(f)
+            return int(raw.get("schedule", {}).get("day_cutoff_hour", DEFAULT_CUTOFF_HOUR))
+        except Exception:
+            pass
+    return DEFAULT_CUTOFF_HOUR
+
+
+def get_news_day(now: datetime | None = None) -> str:
+    """获取当前新闻日（YYYYMMDD）
+
+    规则：当天 06:00 到次日 05:59 属于同一个新闻日。
+    例如 2026-06-19 04:00 → "20260618"，07:00 → "20260619"
+
+    Args:
+        now: 参考时间，默认当前时间
+
+    Returns:
+        新闻日字符串 YYYYMMDD
+    """
+    if now is None:
+        now = datetime.now()
+
+    cutoff = _load_cutoff_hour()
+
+    if now.hour < cutoff:
+        # 凌晨 0:00 - 5:59，属于前一天
+        news_date = now - timedelta(days=1)
+    else:
+        news_date = now
+
+    return news_date.strftime("%Y%m%d")