feat: 军事科技每日资讯推送系统 - Docker部署 + 日志系统 + 数据目录重组

2026-07-12 20:01:02 +08:00
commit 54ca4b1b6a
267 changed files with 47047 additions and 0 deletions
@@ -0,0 +1,198 @@
+"""
+配置模块：系统常量、RSS源、关键词库、评分维度、分类定义、AI配置加载
+"""
+
+import os
+import json
+from pathlib import Path
+
+# =============================================================================
+# 军事科技 RSS 订阅源
+# 优先读取 config/rss_feeds.txt 文件，文件不存在则使用默认12个源
+# =============================================================================
+def load_rss_feeds() -> list:
+    """从配置文件读取RSS源，格式每行：名称|URL，#开头为注释"""
+    default_feeds = [
+        {"name": "Defense One", "url": "https://www.defenseone.com/rss/all/"},
+        {"name": "NEWUAS", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3246130840.rss"},
+        {"name": "Seapower", "url": "https://seapowermagazine.org/feed/"},
+        {"name": "The War Zone", "url": "https://www.twz.com/feed"},
+        {"name": "国防科技要闻", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3921202880.rss"},
+        {"name": "战略前沿技术", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3271903347.rss"},
+        {"name": "无人机邦", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3957361285.rss"},
+        {"name": "浮空飞行器", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3291643707.rss"},
+        {"name": "海鹰资讯", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3091381580.rss"},
+        {"name": "渊亭防务", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3865628826.rss"},
+        {"name": "电波之矛", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3004998095.rss"},
+        {"name": "龙牙的一座山", "url": f"{RSS_PROXY_BASE}/feed/MP_WXS_3517933009.rss"},
+    ]
+    
+    # RSS配置文件路径：项目根目录/config/rss_feeds.txt
+    config_file = Path(__file__).resolve().parent.parent.parent / "config" / "rss_feeds.txt"
+    
+    if not config_file.exists():
+        return default_feeds
+    
+    feeds = []
+    with open(config_file, 'r', encoding='utf-8') as f:
+        for line in f:
+            line = line.strip()
+            # 跳过空行和注释行
+            if not line or line.startswith('#'):
+                continue
+            # 按|分割，确保格式正确
+            parts = line.split('|', 1)
+            if len(parts) == 2:
+                name = parts[0].strip()
+                url = parts[1].strip()
+                if name and url:
+                    feeds.append({"name": name, "url": url})
+    
+    # 如果读取到的源为空，返回默认源
+    return feeds if feeds else default_feeds
+
+# =============================================================================
+# RSS 代理基础 URL（read_env 尚未定义，直接读文件/file和ennv）
+# =============================================================================
+def _load_rss_proxy_base():
+    default = "https://werss.yynnice.top"
+    env_val = os.environ.get("RSS_PROXY_BASE")
+    if env_val:
+        return env_val
+    env_file = Path(__file__).resolve().parent.parent.parent / "config" / ".env"
+    if env_file.exists():
+        with open(env_file, 'r', encoding='utf-8') as f:
+            for line in f:
+                line = line.strip()
+                if line and not line.startswith('#') and line.startswith('RSS_PROXY_BASE='):
+                    _, _, val = line.partition('=')
+                    return val.strip().strip('"').strip("'")
+    return default
+
+RSS_PROXY_BASE = _load_rss_proxy_base()
+
+RSS_FEEDS = load_rss_feeds()
+
+WECHAT_SOURCES = {'NEWUAS', '国防科技要闻', '战略前沿技术', '无人机邦', '浮空飞行器', '海鹰资讯', '渊亭防务', '电波之矛', '龙牙的一座山'}
+
+# =============================================================================
+# 抓取配置
+# =============================================================================
+FETCH_TIMEOUT = 30
+MAX_THREADS = 15  # 抓取并发数，100+源建议15-20
+AI_CONCURRENCY = 8  # AI调用并发数，根据API限流调整
+TIME_WINDOW_HOURS = 24
+
+# =============================================================================
+# 关键词库（44个）
+# =============================================================================
+KEYWORDS = [
+    "首飞", "曝光", "美军", "解放军", "新型", "研发", "部署", "军演", "导弹", "战机",
+    "舰艇", "雷达", "芯片", "突破", "测试", "服役", "列装", "武器", "装备", "军事",
+    "武器系统", "冲突", "封锁", "威慑", "无人机", "AI", "人工智能", "战争", "以色列",
+    "伊朗", "俄罗斯", "乌克兰", "航母", "潜艇", "坦克", "防空", "反导", "激光", "电磁",
+    "卫星", "航天", "蜂群", "拦截", "打击", "攻击", "作战", "战略", "战术", "军工"
+]
+
+# =============================================================================
+# AI评分维度（4维度加权）
+# =============================================================================
+SCORE_DIMENSIONS = [
+    {"name": "技术突破性", "weight": 0.35, "description": "是否有新技术、新武器、新架构曝光，1-10分"},
+    {"name": "战略价值", "weight": 0.30, "description": "对地缘政治、军事格局的影响程度，1-10分"},
+    {"name": "信息可信度", "weight": 0.20, "description": "来源权威性、数据可验证性，1-10分"},
+    {"name": "时效性", "weight": 0.15, "description": "事件的新鲜程度，1-10分"},
+]
+
+# =============================================================================
+# 分类定义
+# =============================================================================
+CATEGORIES = {
+    "today_must_read": {"name": "🔥 今日必看", "desc": "最重磅、最紧急的头条要闻"},
+    "equipment": {"name": "⚙️ 装备动态", "desc": "新型武器、技术突破、军备交付"},
+    "conflict": {"name": "💥 地区冲突", "desc": "热点战事、边境对峙、反恐行动"},
+    "strategy": {"name": "🎯 战略政策", "desc": "国防战略、军演部署、外交安全"},
+}
+
+
+def _read_env_file(file_path):
+    """从.env文件读取配置，返回 {key: value} 字典"""
+    result = {}
+    if file_path.exists():
+        with open(file_path, 'r', encoding='utf-8') as f:
+            for line in f:
+                line = line.strip()
+                if line and not line.startswith('#') and '=' in line:
+                    key, _, value = line.partition('=')
+                    value = value.strip().strip('"').strip("'")
+                    result[key] = value
+    return result
+
+
+def load_ai_config():
+    """加载AI配置（环境变量 > 项目config/.env > 硬编码默认值）"""
+    api_key = None
+    base_url = "https://api.openai.com/v1"
+    model = "gpt-4o-mini"
+    webzine_model = "deepseek-v3.2"
+
+    local_env = Path(__file__).resolve().parent.parent.parent / "config" / ".env"
+    values = _read_env_file(local_env)
+    if values.get('OPENAI_API_KEY'):
+        api_key = values['OPENAI_API_KEY']
+    if values.get('OPENAI_API_BASE'):
+        base_url = values['OPENAI_API_BASE']
+    if values.get('OPENAI_MODEL'):
+        model = values['OPENAI_MODEL']
+    if values.get('WEBZINE_MODEL'):
+        webzine_model = values['WEBZINE_MODEL']
+
+    if os.environ.get('OPENAI_API_KEY'):
+        api_key = os.environ['OPENAI_API_KEY']
+    if os.environ.get('OPENAI_API_BASE'):
+        base_url = os.environ['OPENAI_API_BASE']
+    if os.environ.get('OPENAI_MODEL'):
+        model = os.environ['OPENAI_MODEL']
+    if os.environ.get('WEBZINE_MODEL'):
+        webzine_model = os.environ['WEBZINE_MODEL']
+
+    return api_key, base_url, model, webzine_model
+
+
+def load_push_config():
+    """加载推送配置（环境变量 > config.json > 默认值）"""
+    config = {
+        "enable_wechat_push": False,
+        "enable_feishu_push": False,
+        "wechat_key": "",
+        "wechat_target": "",
+        "feishu_webhook": "",
+    }
+
+    config_file = Path(__file__).resolve().parent.parent.parent / "config" / "config.json"
+    values = _read_env_file(Path(__file__).resolve().parent.parent.parent / "config" / ".env")
+
+    if config_file.exists():
+        try:
+            with open(config_file, 'r', encoding='utf-8') as f:
+                json_config = json.load(f)
+            config["enable_wechat_push"] = json_config.get("enable_wechat_push", False)
+            config["enable_feishu_push"] = json_config.get("enable_feishu_push", False)
+        except Exception:
+            pass
+
+    if values.get("WECHAT_ACCOUNT"):
+        config["wechat_key"] = values["WECHAT_ACCOUNT"]
+    if values.get("WECHAT_TARGET"):
+        config["wechat_target"] = values["WECHAT_TARGET"]
+    if values.get("FEISHU_WEBHOOK"):
+        config["feishu_webhook"] = values["FEISHU_WEBHOOK"]
+
+    if os.environ.get("WECHAT_ACCOUNT"):
+        config["wechat_key"] = os.environ["WECHAT_ACCOUNT"]
+    if os.environ.get("WECHAT_TARGET"):
+        config["wechat_target"] = os.environ["WECHAT_TARGET"]
+    if os.environ.get("FEISHU_WEBHOOK"):
+        config["feishu_webhook"] = os.environ["FEISHU_WEBHOOK"]
+
+    return config