fix:优化数据来源

crawler/config.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+"""爬虫配置"""
+import os
+from pathlib import Path
+
+# 数据库路径（与 server 共用 SQLite）
+PROJECT_ROOT = Path(__file__).resolve().parent.parent
+DB_PATH = os.environ.get("DB_PATH", str(PROJECT_ROOT / "server" / "data.db"))
+
+# Node API 地址（用于通知推送）
+API_BASE = os.environ.get("API_BASE", "http://localhost:3001")
+
+# 抓取间隔（秒）
+CRAWL_INTERVAL = int(os.environ.get("CRAWL_INTERVAL", "300"))
+
+# RSS 源（美伊/中东相关，多源保证实时事件脉络）
+RSS_FEEDS = [
+    "https://feeds.reuters.com/reuters/topNews",
+    "https://feeds.bbci.co.uk/news/world/rss.xml",
+    "https://feeds.bbci.co.uk/news/world/middle_east/rss.xml",
+    "https://www.aljazeera.com/xml/rss/all.xml",
+    "https://www.aljazeera.com/xml/rss/middleeast.xml",
+    "https://rss.nytimes.com/services/xml/rss/nyt/World.xml",
+]
+
+# 关键词过滤：至少匹配一个才会入库
+KEYWORDS = [
+    "iran", "iranian", "tehran", "以色列", "israel",
+    "usa", "us ", "american", "美军", "美国",
+    "middle east", "中东", "persian gulf", "波斯湾",
+    "strike", "attack", "military", "missile", "核", "nuclear",
+    "carrier", "航母", "houthi", "胡塞", "hamas",
+]