diff --git a/.env b/.env index 39f2243..8f2eecf 100644 --- a/.env +++ b/.env @@ -1,2 +1,3 @@ # Mapbox 地图令牌 -VITE_MAPBOX_ACCESS_TOKEN=pk.eyJ1IjoiZDI5cTAiLCJhIjoiY21oaGRmcTkzMGltZzJscHR1N2FhZnY5dCJ9.7ueF2lS6-C9Mm_xon7NnIA +VITE_MAPBOX_ACCESS_TOKEN=pk.eyJ1IjoiZDI5cTAiLCJhIjoiY21tYWQyOXI3MGFrZzJwcjJmZGltODI4ZCJ9.0jW_aK91VJExw6ffKGqWIA +DASHSCOPE_API_KEY=sk-029a4c4d761d49b99cfe6073234ac443 \ No newline at end of file diff --git a/.env.example b/.env.example index c6f33ba..d32fbeb 100644 --- a/.env.example +++ b/.env.example @@ -1,4 +1,4 @@ -# Mapbox 地图令牌 (波斯湾区域展示) +# Mapbox 地图令牌（仅在此或 .env 中配置，勿写进源码；若曾泄漏请到 Mapbox 控制台轮换） # 免费申请: https://account.mapbox.com/access-tokens/ VITE_MAPBOX_ACCESS_TOKEN=your_mapbox_public_token_here diff --git a/.env的副本 b/.env的副本 new file mode 100644 index 0000000..8f2eecf --- /dev/null +++ b/.env的副本 @@ -0,0 +1,3 @@ +# Mapbox 地图令牌 +VITE_MAPBOX_ACCESS_TOKEN=pk.eyJ1IjoiZDI5cTAiLCJhIjoiY21tYWQyOXI3MGFrZzJwcjJmZGltODI4ZCJ9.0jW_aK91VJExw6ffKGqWIA +DASHSCOPE_API_KEY=sk-029a4c4d761d49b99cfe6073234ac443 \ No newline at end of file diff --git a/.gitignore b/.gitignore index 44a1f0d..bbfec72 100644 --- a/.gitignore +++ b/.gitignore @@ -26,8 +26,8 @@ dist-ssr # API database # server/data.db -# Env -# .env -# .env.local -# .env.*.local +# Env（含 token，勿提交） +.env +.env.local +.env.*.local .pyc diff --git a/crawler/README.md b/crawler/README.md index 4a4991d..c353c6e 100644 --- a/crawler/README.md +++ b/crawler/README.md @@ -54,6 +54,86 @@ pip install -r requirements.txt **事件脉络不更新时**：多半是未启动 `npm run gdelt`。只跑 `npm run api` 时，事件脉络会显示空或仅有缓存。 +## 如何检查爬虫是否工作正常 + +按下面顺序做即可确认整条链路（爬虫 → 数据库 → Node 重载 → API/WebSocket）正常。 + +### 1. 一键验证（推荐） + +先启动 API，再执行验证脚本（可选是否顺带启动爬虫）： + +```bash +# 终端 1：必须 +npm run api + +# 终端 2：执行验证（不启动爬虫，只检查当前状态） +./scripts/verify-pipeline.sh + +# 或：顺带启动爬虫并等首次抓取后再验证 +./scripts/verify-pipeline.sh --start-crawler +``` + +脚本会检查：API 健康、态势数据含 `lastUpdated`、爬虫服务是否可达、`news_content`/situation_update、战损字段、`POST /api/crawler/notify` 是否可用。 + +### 2. 手动快速检查 + +| 步骤 | 命令 / 操作 | 正常表现 | +|-----|-------------|----------| +| API 是否在跑 | `curl -s http://localhost:3001/api/health` | 返回 `{"ok":true}` | +| 态势是否可读 | `curl -s http://localhost:3001/api/situation \| head -c 300` | 含 `lastUpdated`、`usForces`、`recentUpdates` | +| RSS 能否抓到 | `npm run crawler:test` | 输出「RSS 抓取: N 条」，N>0 表示有命中 | +| 爬虫服务（gdelt） | `curl -s http://localhost:8000/crawler/status` | 返回 JSON，含 `db_path`/`db_exists` 等 | +| 库里有无爬虫数据 | `sqlite3 server/data.db "SELECT COUNT(*) FROM situation_update; SELECT COUNT(*) FROM news_content;"` 或访问 `http://localhost:3001/api/db/dashboard` | situation_update、news_content 条数 > 0（跑过流水线后） | +| 通知后是否重载 | 爬虫写库后会 POST `/api/crawler/notify`，Node 会 `reloadFromFile` 再广播 | 前端/`/api/situation` 的 `lastUpdated` 和内容会更新 | + +### 3. 跑一轮流水线（不常驻爬虫时） + +不启动 gdelt 时，可单次跑完整流水线（抓取 → 去重 → 写表 → notify）： + +```bash +npm run api # 保持运行 +cd crawler && python3 -c " +from pipeline import run_full_pipeline +from config import DB_PATH, API_BASE +n_fetched, n_news, n_panel = run_full_pipeline(db_path=DB_PATH, api_base=API_BASE, notify=True) +print('抓取:', n_fetched, '去重新增:', n_news, '面板写入:', n_panel) +" +``` + +有网络且有关键词命中时，应看到非零数字；再查 `curl -s http://localhost:3001/api/situation` 或前端事件脉络是否出现新数据。 + +### 4. 仅测提取逻辑（不写库） + +```bash +npm run crawler:test:extraction # 规则/db_merge 测试 +# 或按 README「快速自测命令」用示例文本调 extract_from_news 看 combat_losses_delta / key_location_updates +``` + +**常见现象**：抓取 0 条 → 网络/RSS 被墙或关键词未命中；situation_update 为空 → 未跑流水线或去重后无新增；前端不刷新 → 未开 `npm run api` 或未开爬虫（gdelt）。 + +### 5. 爬虫与面板是否联通 + +专门检查「爬虫写库」与「面板展示」是否一致： + +```bash +./scripts/check-crawler-panel-connectivity.sh +``` + +会对比：爬虫侧的 `situation_update` 条数 vs 面板 API 返回的 `recentUpdates` 条数，并说明为何战损/基地等不一定随每条新闻变化。 + +## 爬虫与面板数据联动说明 + +| 面板展示 | 数据来源（表/接口） | 是否由爬虫更新 | 说明 | +|----------|---------------------|----------------|------| +| **事件脉络** (recentUpdates) | situation_update → getSituation() | ✅ 是 | 每条去重后的新闻会写入 situation_update，Node 收到 notify 后重载 DB 再广播 | +| **地图冲突点** (conflictEvents) | gdelt_events 或 RSS→gdelt 回填 | ✅ 是 | GDELT 或 GDELT 禁用时由 situation_update 同步到 gdelt_events | +| **战损/装备毁伤** (combatLosses) | combat_losses | ⚠️ 有条件 | 仅当 AI/规则从新闻中提取到数字（如「2 名美军死亡」）时，merge 才写入增量 | +| **基地/地点状态** (keyLocations) | key_location | ⚠️ 有条件 | 仅当提取到 key_location_updates（如某基地遭袭）时更新 | +| **力量摘要/指数/资产** (summary, powerIndex, assets) | force_summary, power_index, force_asset | ❌ 否 | 仅 seed 初始化，爬虫不写 | +| **华尔街/报复情绪** (wallStreet, retaliation) | wall_street_trend, retaliation_* | ⚠️ 有条件 | 仅当提取器输出对应字段时更新 | + +因此：**新闻很多、但战损/基地数字不动**是正常现象——多数标题不含可解析的伤亡/基地数字，只有事件脉络（recentUpdates）和地图冲突点会随每条新闻增加。若**事件脉络也不更新**，请确认 Node 终端在爬虫每轮抓取后是否出现 `[crawler/notify] DB 已重载`；若无，检查爬虫的 `API_BASE` 是否指向当前 API（默认 `http://localhost:3001`）。 + ## 写库流水线（与 server/README 第五节一致） RSS 与主入口均走统一流水线 `pipeline.run_full_pipeline`： @@ -80,6 +160,7 @@ RSS → 抓取 → 清洗 → 去重 → 写 news_content / situation_update / - `DB_PATH`: SQLite 路径，默认 `../server/data.db` - `API_BASE`: Node API 地址，默认 `http://localhost:3001` +- **`DASHSCOPE_API_KEY`**：阿里云通义（DashScope）API Key。**设置后全程使用商业模型，无需本机安装 Ollama**（适合 Mac 版本较低无法跑 Ollama 的情况）。获取： [阿里云百炼 / DashScope](https://dashscope.console.aliyun.com/) → 创建 API-KEY，复制到环境变量或项目根目录 `.env` 中 `DASHSCOPE_API_KEY=sk-xxx`。摘要、分类、战损/基地提取均走通义。 - `GDELT_QUERY`: 搜索关键词，默认 `United States Iran military` - `GDELT_MAX_RECORDS`: 最大条数，默认 30 - `GDELT_TIMESPAN`: 时间范围，`1h` / `1d` / `1week`，默认 `1d`（近日资讯） diff --git a/crawler/__pycache__/cleaner_ai.cpython-39.pyc b/crawler/__pycache__/cleaner_ai.cpython-39.pyc index fe62db8..59c6958 100644 Binary files a/crawler/__pycache__/cleaner_ai.cpython-39.pyc and b/crawler/__pycache__/cleaner_ai.cpython-39.pyc differ diff --git a/crawler/__pycache__/parser_ai.cpython-39.pyc b/crawler/__pycache__/parser_ai.cpython-39.pyc index fc0c9df..cd6053c 100644 Binary files a/crawler/__pycache__/parser_ai.cpython-39.pyc and b/crawler/__pycache__/parser_ai.cpython-39.pyc differ diff --git a/crawler/__pycache__/pipeline.cpython-39.pyc b/crawler/__pycache__/pipeline.cpython-39.pyc index ab5dd1d..b1bab18 100644 Binary files a/crawler/__pycache__/pipeline.cpython-39.pyc and b/crawler/__pycache__/pipeline.cpython-39.pyc differ diff --git a/crawler/__pycache__/realtime_conflict_service.cpython-39.pyc b/crawler/__pycache__/realtime_conflict_service.cpython-39.pyc index f3a0d8c..e7c6f43 100644 Binary files a/crawler/__pycache__/realtime_conflict_service.cpython-39.pyc and b/crawler/__pycache__/realtime_conflict_service.cpython-39.pyc differ diff --git a/crawler/cleaner_ai.py b/crawler/cleaner_ai.py index c5d6f04..fa9b573 100644 --- a/crawler/cleaner_ai.py +++ b/crawler/cleaner_ai.py @@ -2,6 +2,7 @@ """ AI 清洗新闻数据，严格按面板字段约束输出 面板 EventTimelinePanel 所需：summary(≤120字)、category(枚举)、severity(枚举) +优先使用 DASHSCOPE_API_KEY（通义，无需 Ollama），否则 Ollama，最后规则兜底 """ import os import re @@ -9,6 +10,7 @@ from typing import Optional CLEANER_AI_DISABLED = os.environ.get("CLEANER_AI_DISABLED", "0") == "1" OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "llama3.1") +DASHSCOPE_API_KEY = os.environ.get("DASHSCOPE_API_KEY", "").strip() # 面板 schema：必须与 EventTimelinePanel / SituationUpdate 一致 SUMMARY_MAX_LEN = 120 # 面板 line-clamp-2 展示 @@ -30,6 +32,38 @@ def _rule_clean(text: str, max_len: int = SUMMARY_MAX_LEN) -> str: return _sanitize_summary(text, max_len) +def _call_dashscope_summary(text: str, max_len: int, timeout: int = 8) -> Optional[str]: + """调用阿里云通义（DashScope）提炼摘要，无需 Ollama。需设置 DASHSCOPE_API_KEY""" + if not DASHSCOPE_API_KEY or CLEANER_AI_DISABLED or not text or len(str(text).strip()) < 5: + return None + try: + import dashscope + from http import HTTPStatus + dashscope.api_key = DASHSCOPE_API_KEY + prompt = f"""将新闻提炼为1-2句简洁中文事实，直接输出纯文本，不要标号、引号、解释。限{max_len}字内。 + +原文：{str(text)[:350]} + +输出：""" + r = dashscope.Generation.call( + model="qwen-turbo", + messages=[{"role": "user", "content": prompt}], + result_format="message", + max_tokens=150, + ) + if r.status_code != HTTPStatus.OK: + return None + out = (r.output.get("choices", [{}])[0].get("message", {}).get("content", "") or "").strip() + out = re.sub(r"^[\d\.\-\*\s]+", "", out) + out = re.sub(r"^['\"\s]+|['\"\s]+$", "", out) + out = _sanitize_summary(out, max_len) + if out and len(out) > 3: + return out + return None + except Exception: + return None + + def _call_ollama_summary(text: str, max_len: int, timeout: int = 6) -> Optional[str]: """调用 Ollama 提炼摘要，输出须为纯文本、≤max_len 字""" if CLEANER_AI_DISABLED or not text or len(str(text).strip()) < 5: @@ -71,7 +105,11 @@ def clean_news_for_panel(text: str, max_len: int = SUMMARY_MAX_LEN) -> str: t = str(text).strip() if not t: return "" - res = _call_ollama_summary(t, max_len, timeout=6) + # 优先商业模型（通义），再 Ollama，最后规则 + if DASHSCOPE_API_KEY: + res = _call_dashscope_summary(t, max_len, timeout=8) + else: + res = _call_ollama_summary(t, max_len, timeout=6) if res: return res return _rule_clean(t, max_len) diff --git a/crawler/parser_ai.py b/crawler/parser_ai.py index 774b13c..cf1ca14 100644 --- a/crawler/parser_ai.py +++ b/crawler/parser_ai.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- """ AI 新闻分类与严重度判定 -优先使用 Ollama 本地模型（免费），失败则回退到规则 +优先 DASHSCOPE_API_KEY（通义，无需 Ollama），否则 Ollama，最后规则 设置 PARSER_AI_DISABLED=1 可只用规则（更快） """ import os @@ -11,7 +11,8 @@ Category = Literal["deployment", "alert", "intel", "diplomatic", "other"] Severity = Literal["low", "medium", "high", "critical"] PARSER_AI_DISABLED = os.environ.get("PARSER_AI_DISABLED", "0") == "1" -OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "llama3.1") # 或 qwen2.5:7b +OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "llama3.1") +DASHSCOPE_API_KEY = os.environ.get("DASHSCOPE_API_KEY", "").strip() _CATEGORIES = ("deployment", "alert", "intel", "diplomatic", "other") _SEVERITIES = ("low", "medium", "high", "critical") @@ -32,8 +33,37 @@ def _parse_ai_response(text: str) -> Tuple[Category, Severity]: return cat, sev # type: ignore +def _call_dashscope(text: str, timeout: int = 6) -> Optional[Tuple[Category, Severity]]: + """调用阿里云通义（DashScope）分类，无需 Ollama。需设置 DASHSCOPE_API_KEY""" + if not DASHSCOPE_API_KEY or PARSER_AI_DISABLED: + return None + try: + import dashscope + from http import HTTPStatus + dashscope.api_key = DASHSCOPE_API_KEY + prompt = f"""Classify this news about US-Iran/middle east (one line only): +- category: deployment|alert|intel|diplomatic|other +- severity: low|medium|high|critical + +News: {text[:300]} + +Reply format: category:severity (e.g. alert:high)""" + r = dashscope.Generation.call( + model="qwen-turbo", + messages=[{"role": "user", "content": prompt}], + result_format="message", + max_tokens=32, + ) + if r.status_code != HTTPStatus.OK: + return None + out = r.output.get("choices", [{}])[0].get("message", {}).get("content", "") + return _parse_ai_response(out) + except Exception: + return None + + def _call_ollama(text: str, timeout: int = 5) -> Optional[Tuple[Category, Severity]]: - """调用 Ollama 本地模型。需先运行 ollama run llama3.1 或 qwen2.5:7b""" + """调用 Ollama 本地模型。需先运行 ollama run llama3.1""" if PARSER_AI_DISABLED: return None try: @@ -73,9 +103,16 @@ def _rule_severity(text: str, category: Category) -> Severity: return severity(text, category) +def _call_ai(text: str) -> Optional[Tuple[Category, Severity]]: + """优先通义，再 Ollama""" + if DASHSCOPE_API_KEY: + return _call_dashscope(text) + return _call_ollama(text) + + def classify(text: str) -> Category: """分类。AI 失败时回退规则""" - res = _call_ollama(text) + res = _call_ai(text) if res: return res[0] return _rule_classify(text) @@ -83,7 +120,7 @@ def classify(text: str) -> Category: def severity(text: str, category: Category) -> Severity: """严重度。AI 失败时回退规则""" - res = _call_ollama(text) + res = _call_ai(text) if res: return res[1] return _rule_severity(text, category) @@ -95,7 +132,7 @@ def classify_and_severity(text: str) -> Tuple[Category, Severity]: from parser import classify, severity c = classify(text) return c, severity(text, c) - res = _call_ollama(text) + res = _call_ai(text) if res: return res return _rule_classify(text), _rule_severity(text, _rule_classify(text)) diff --git a/crawler/pipeline.py b/crawler/pipeline.py index df8494e..45f7fd7 100644 --- a/crawler/pipeline.py +++ b/crawler/pipeline.py @@ -14,10 +14,14 @@ def _notify_api(api_base: str) -> bool: """调用 Node API 触发立即广播""" try: import urllib.request + token = os.environ.get("API_CRAWLER_TOKEN", "").strip() req = urllib.request.Request( f"{api_base.rstrip('/')}/api/crawler/notify", method="POST", - headers={"Content-Type": "application/json"}, + headers={ + "Content-Type": "application/json", + **({"X-Crawler-Token": token} if token else {}), + }, ) with urllib.request.urlopen(req, timeout=5) as resp: return resp.status == 200 diff --git a/crawler/realtime_conflict_service.py b/crawler/realtime_conflict_service.py index ea46f00..5a54a1f 100644 --- a/crawler/realtime_conflict_service.py +++ b/crawler/realtime_conflict_service.py @@ -242,7 +242,16 @@ def _write_to_db(events: List[dict]) -> None: def _notify_node() -> None: try: - r = requests.post(f"{API_BASE}/api/crawler/notify", timeout=5, proxies={"http": None, "https": None}) + headers = {} + token = os.environ.get("API_CRAWLER_TOKEN", "").strip() + if token: + headers["X-Crawler-Token"] = token + r = requests.post( + f"{API_BASE}/api/crawler/notify", + timeout=5, + headers=headers, + proxies={"http": None, "https": None}, + ) if r.status_code != 200: print(" [warn] notify API 失败") except Exception as e: @@ -340,7 +349,10 @@ def crawler_backfill(): return {"ok": False, "error": "db not found"} try: from db_merge import merge - if os.environ.get("CLEANER_AI_DISABLED", "0") == "1": + use_dashscope = bool(os.environ.get("DASHSCOPE_API_KEY", "").strip()) + if use_dashscope: + from extractor_dashscope import extract_from_news + elif os.environ.get("CLEANER_AI_DISABLED", "0") == "1": from extractor_rules import extract_from_news else: from extractor_ai import extract_from_news diff --git a/scripts/check-crawler-panel-connectivity.sh b/scripts/check-crawler-panel-connectivity.sh new file mode 100755 index 0000000..ff96e1b --- /dev/null +++ b/scripts/check-crawler-panel-connectivity.sh @@ -0,0 +1,61 @@ +#!/usr/bin/env bash +# 检查爬虫数据与面板数据是否联通 +# 用法: ./scripts/check-crawler-panel-connectivity.sh +# 需先启动: npm run api；可选: npm run gdelt +set -e + +API_URL="${API_URL:-http://localhost:3001}" +CRAWLER_URL="${CRAWLER_URL:-http://localhost:8000}" + +echo "==========================================" +echo "爬虫 ↔ 面板 联通检查" +echo "API: $API_URL | Crawler: $CRAWLER_URL" +echo "==========================================" + +# 1. 爬虫侧：situation_update 条数 +CRAWLER_SU_COUNT="" +if curl -sf "$CRAWLER_URL/crawler/status" >/dev/null 2>&1; then + if command -v jq &>/dev/null; then + CRAWLER_SU_COUNT=$(curl -sf "$CRAWLER_URL/crawler/status" | jq -r '.situation_update_count // "?"') + else + CRAWLER_SU_COUNT="(需 jq 查看)" + fi + echo "[爬虫] situation_update 条数: $CRAWLER_SU_COUNT" +else + echo "[爬虫] 未启动或不可达 (curl $CRAWLER_URL/crawler/status 失败)" +fi + +# 2. 面板侧：API 返回的 recentUpdates 条数、lastUpdated +if ! curl -sf "$API_URL/api/health" >/dev/null 2>&1; then + echo "[API] 未启动，请先运行: npm run api" + exit 1 +fi + +SIT=$(curl -sf "$API_URL/api/situation" 2>/dev/null || echo "{}") +if command -v jq &>/dev/null; then + RU_LEN=$(echo "$SIT" | jq '.recentUpdates | length') + LAST=$(echo "$SIT" | jq -r '.lastUpdated // "?"') + echo "[面板] recentUpdates 条数: $RU_LEN | lastUpdated: $LAST" +else + echo "[面板] 态势数据已获取 (安装 jq 可显示条数)" +fi + +# 3. 一致性：爬虫写的是 server/data.db，Node 通过 notify 重载后应一致 +echo "" +echo "--- 联动说明 ---" +echo " • 事件脉络 (recentUpdates) ← situation_update 表，由爬虫 write_updates() 写入" +echo " • 爬虫每次抓取后会 POST $API_URL/api/crawler/notify，Node 会 reloadFromFile() 后广播" +echo " • 若爬虫有数据但面板 recentUpdates 很少/为空：检查 Node 终端是否出现 [crawler/notify] DB 已重载" +echo " • 若从未出现：检查 API_BASE 是否指向当前 API（默认 http://localhost:3001）" +echo " • 战损/基地/力量指数：仅当 AI/规则从新闻中提取到数字时才会更新，多数新闻不会触发" +echo "==========================================" + +# 4. 可选：触发一次 notify 看 Node 是否重载（不启动爬虫时可用于测试） +# 非交互时跳过；交互时可用: echo y | ./scripts/check-crawler-panel-connectivity.sh +if [[ -t 0 ]]; then + echo "" + read -r -p "是否发送一次 POST /api/crawler/notify 测试 Node 重载? [y/N] " ans + if [[ "${ans,,}" = "y" ]]; then + curl -sf -X POST "$API_URL/api/crawler/notify" && echo " 已发送 notify，请看 Node 终端是否打印 [crawler/notify] DB 已重载" + fi +fi diff --git a/server/data.db b/server/data.db index e458902..e85286d 100644 Binary files a/server/data.db and b/server/data.db differ diff --git a/server/db.js b/server/db.js index 92bb9d8..0991791 100644 --- a/server/db.js +++ b/server/db.js @@ -7,6 +7,8 @@ const fs = require('fs') const dbPath = process.env.DB_PATH || path.join(__dirname, 'data.db') let _db = null +/** sql.js 构造函数，initDb 时注入，供 reloadFromFile 使用 */ +let _sqlJs = null function getDb() { if (!_db) throw new Error('DB not initialized. Call initDb() first.') @@ -239,6 +241,7 @@ function runMigrations(db) { async function initDb() { const initSqlJs = require('sql.js') const SQL = await initSqlJs() + _sqlJs = SQL let data = new Uint8Array(0) if (fs.existsSync(dbPath)) { data = new Uint8Array(fs.readFileSync(dbPath)) @@ -261,6 +264,30 @@ async function initDb() { return _db } +/** + * 从磁盘重新加载 DB（爬虫写入同一文件后调用，使 Node 内存中的库与文件一致） + */ +function reloadFromFile() { + if (!_sqlJs || !_db) throw new Error('DB not initialized. Call initDb() first.') + let data = new Uint8Array(0) + if (fs.existsSync(dbPath)) { + data = new Uint8Array(fs.readFileSync(dbPath)) + } + const nativeDb = new _sqlJs.Database(data) + function persist() { + try { + const buf = nativeDb.export() + fs.writeFileSync(dbPath, Buffer.from(buf)) + } catch (e) { + console.error('[db] persist error:', e.message) + } + } + nativeDb.run('PRAGMA journal_mode = WAL') + const wrapped = wrapDatabase(nativeDb, persist) + runMigrations(wrapped) + _db = wrapped +} + const proxy = { prepare(sql) { return getDb().prepare(sql) @@ -276,3 +303,4 @@ const proxy = { module.exports = proxy module.exports.initDb = initDb module.exports.getDb = getDb +module.exports.reloadFromFile = reloadFromFile diff --git a/server/index.js b/server/index.js index b1132e9..38d6277 100644 --- a/server/index.js +++ b/server/index.js @@ -14,6 +14,9 @@ const openApiSpec = require('./openapi') const app = express() const PORT = process.env.API_PORT || 3001 +// 爬虫通知用的共享密钥：API_CRAWLER_TOKEN（仅在服务端与爬虫进程间传递） +const CRAWLER_TOKEN = process.env.API_CRAWLER_TOKEN || '' + app.set('trust proxy', 1) app.use(cors()) app.use(express.json()) @@ -23,7 +26,14 @@ app.use('/api-docs', swaggerUi.serve, swaggerUi.setup(openApiSpec)) app.use('/api', routes) app.get('/api/health', (_, res) => res.json({ ok: true })) -app.post('/api/crawler/notify', (_, res) => { +app.post('/api/crawler/notify', (req, res) => { + // 若配置了 API_CRAWLER_TOKEN，则要求爬虫携带 X-Crawler-Token 头 + if (CRAWLER_TOKEN) { + const token = req.headers['x-crawler-token'] + if (typeof token !== 'string' || token !== CRAWLER_TOKEN) { + return res.status(401).json({ error: 'unauthorized' }) + } + } notifyCrawlerUpdate() res.json({ ok: true }) }) @@ -59,13 +69,18 @@ function broadcastSituation() { app.set('broadcastSituation', broadcastSituation) setInterval(broadcastSituation, 3000) -// 供爬虫调用：更新 situation.updated_at 并立即广播 +// 供爬虫调用：先从磁盘重载 DB（纳入爬虫写入），再更新 updated_at 并立即广播 function notifyCrawlerUpdate() { try { const db = require('./db') + db.reloadFromFile() db.prepare("INSERT OR REPLACE INTO situation (id, data, updated_at) VALUES (1, '{}', ?)").run(new Date().toISOString()) broadcastSituation() - } catch (_) {} + const n = db.prepare('SELECT COUNT(*) as c FROM situation_update').get().c + console.log('[crawler/notify] DB 已重载并广播，situation_update 条数:', n) + } catch (e) { + console.error('[crawler/notify]', e?.message || e) + } } db.initDb().then(() => { diff --git a/server/routes.js b/server/routes.js index 5d621be..c9fd475 100644 --- a/server/routes.js +++ b/server/routes.js @@ -5,8 +5,22 @@ const db = require('./db') const router = express.Router() -// 数据库 Dashboard：返回各表原始数据 -router.get('/db/dashboard', (req, res) => { +// 简单鉴权：通过环境变量配置的 API_ADMIN_KEY 保护敏感接口（不返回真实密钥） +const ADMIN_API_KEY = process.env.API_ADMIN_KEY || '' + +function requireAdmin(req, res, next) { + if (!ADMIN_API_KEY) { + return res.status(500).json({ error: 'admin key not configured' }) + } + const token = req.headers['x-api-key'] + if (typeof token !== 'string' || token !== ADMIN_API_KEY) { + return res.status(401).json({ error: 'unauthorized' }) + } + return next() +} + +// 数据库 Dashboard：返回各表原始数据（需 admin 鉴权） +router.get('/db/dashboard', requireAdmin, (req, res) => { try { const tables = [ 'feedback', @@ -58,8 +72,14 @@ router.get('/db/dashboard', (req, res) => { } }) -// 资讯内容（独立表，供后续消费） +// 资讯内容（独立表，供后续消费，可选 admin key；若配置了 ADMIN_API_KEY 则也要求鉴权） router.get('/news', (req, res) => { + if (ADMIN_API_KEY) { + const token = req.headers['x-api-key'] + if (typeof token !== 'string' || token !== ADMIN_API_KEY) { + return res.status(401).json({ error: 'unauthorized' }) + } + } try { const limit = Math.min(parseInt(req.query.limit, 10) || 50, 200) const rows = db.prepare('SELECT id, title, summary, url, source, published_at, category, severity, created_at FROM news_content ORDER BY published_at DESC LIMIT ?').all(limit) diff --git a/src/components/WarMap.tsx b/src/components/WarMap.tsx index a1cd150..93ff240 100644 --- a/src/components/WarMap.tsx +++ b/src/components/WarMap.tsx @@ -15,6 +15,7 @@ import { ISRAEL_STRIKE_SOURCE, ISRAEL_STRIKE_TARGETS, } from '@/data/mapLocations' +import { EXTENDED_WAR_ZONES } from '@/data/extendedWarData' const MAPBOX_TOKEN = config.mapboxAccessToken || '' @@ -64,6 +65,9 @@ const ALLIES_ADMIN = [ // 伊朗攻击源 德黑兰 [lng, lat] const TEHRAN_SOURCE: [number, number] = [51.389, 35.6892] +// 真主党打击源（黎巴嫩南部大致位置），用于绘制向以色列北部的攻击矢量 +const HEZBOLLAH_SOURCE: [number, number] = [35.3, 33.2] + /** 二次贝塞尔曲线路径，更平滑的弧线 height 控制弧高 */ function parabolaPath( start: [number, number], @@ -150,6 +154,7 @@ export function WarMap() { const lincolnPathsRef = useRef<[number, number][][]>([]) const fordPathsRef = useRef<[number, number][][]>([]) const israelPathsRef = useRef<[number, number][][]>([]) + const hezbollahPathsRef = useRef<[number, number][][]>([]) const situation = useReplaySituation() const { usForces, iranForces, conflictEvents = [] } = situation @@ -210,9 +215,15 @@ export function WarMap() { () => ISRAEL_STRIKE_TARGETS.map((t) => parabolaPath(ISRAEL_STRIKE_SOURCE, t)), [] ) + // 真主党 → 以色列北部三处目标（低平弧线） + const hezbollahPaths = useMemo( + () => EXTENDED_WAR_ZONES.activeAttacks.map((t) => parabolaPath(HEZBOLLAH_SOURCE, t.coords, 1.5)), + [] + ) lincolnPathsRef.current = lincolnPaths fordPathsRef.current = fordPaths israelPathsRef.current = israelPaths + hezbollahPathsRef.current = hezbollahPaths const lincolnLinesGeoJson = useMemo( () => ({ @@ -247,6 +258,17 @@ export function WarMap() { }), [israelPaths] ) + const hezbollahLinesGeoJson = useMemo( + () => ({ + type: 'FeatureCollection' as const, + features: hezbollahPaths.map((coords) => ({ + type: 'Feature' as const, + properties: {}, + geometry: { type: 'LineString' as const, coordinates: coords }, + })), + }), + [hezbollahPaths] + ) const attackLinesGeoJson = useMemo( () => ({ @@ -260,6 +282,23 @@ export function WarMap() { [attackPaths] ) + // 真主党当前攻击目标点 + const hezbollahTargetsGeoJson = useMemo( + () => ({ + type: 'FeatureCollection' as const, + features: EXTENDED_WAR_ZONES.activeAttacks.map((t) => ({ + type: 'Feature' as const, + properties: { name: t.name, type: t.type, damage: t.damage }, + geometry: { type: 'Point' as const, coordinates: t.coords }, + })), + }), + [] + ) + + // 霍尔木兹海峡交战区 & 真主党势力范围（静态面） + const hormuzZone = EXTENDED_WAR_ZONES.hormuzCombatZone + const hezbollahZone = EXTENDED_WAR_ZONES.hezbollahZone + // GDELT 冲突事件：1–3 绿, 4–6 橙闪, 7–10 红脉 const { conflictEventsGreen, conflictEventsOrange, conflictEventsRed } = useMemo(() => { const green: GeoJSON.Feature[] = [] @@ -404,6 +443,24 @@ export function WarMap() { ) israelSrc.setData({ type: 'FeatureCollection', features }) } + // 真主党打击以色列北部：橙红色光点，低平飞行 + const hezSrc = map.getSource('hezbollah-strike-dots') as + | { setData: (d: GeoJSON.FeatureCollection) => void } + | undefined + const hezPaths = hezbollahPathsRef.current + if (hezSrc && hezPaths.length > 0) { + const features: GeoJSON.Feature[] = hezPaths.map((path, i) => { + const progress = + (elapsed / FLIGHT_DURATION_MS + 0.2 + i / Math.max(hezPaths.length, 1)) % 1 + const coord = interpolateOnPath(path, progress) + return { + type: 'Feature' as const, + properties: {}, + geometry: { type: 'Point' as const, coordinates: coord }, + } + }) + hezSrc.setData({ type: 'FeatureCollection', features }) + } // 伊朗被打击目标：蓝色脉冲 (2s 周期), 半径随 zoom 缩放；phase/r/opacity 钳位 if (map.getLayer('allied-strike-targets-pulse')) { const cycle = 2000 @@ -427,6 +484,15 @@ export function WarMap() { map.setPaintProperty('gdelt-events-red-pulse', 'circle-radius', r) map.setPaintProperty('gdelt-events-red-pulse', 'circle-opacity', opacity) } + // 真主党攻击目标：橙红脉冲，效果与 allied-strike-targets 保持一致 + if (map.getLayer('hezbollah-attack-targets-pulse')) { + const cycle = 2000 + const phase = Math.max(0, Math.min(1, (elapsed % cycle) / cycle)) + const r = Math.max(0, 30 * phase * zoomScale) + const opacity = Math.min(1, Math.max(0, 1 - phase * 1.15)) + map.setPaintProperty('hezbollah-attack-targets-pulse', 'circle-radius', r) + map.setPaintProperty('hezbollah-attack-targets-pulse', 'circle-opacity', opacity) + } } catch (_) {} } animRef.current = requestAnimationFrame(tick) @@ -532,6 +598,12 @@ export function WarMap() { 高烈度 + + 霍尔木兹交战区 + + + 真主党势力 + + {/* 真主党对以色列北部的攻击矢量线（低平红线） */} + + + + {/* 真主党打击光点（沿矢量路径移动） */} + ({ + type: 'Feature' as const, + properties: {}, + geometry: { type: 'Point' as const, coordinates: path[0] }, + })), + }} + > + + + + + + + + {/* 美以联军打击伊朗：路径线 */} + + {/* 霍尔木兹海峡交战区 - 金黄色 mesh 区域 */} + + + + + + {/* 真主党势力范围 - 绿色半透明区域 */} + + + + + + {/* 霍尔木兹海峡区域标注 */} + + + + + {/* 真主党势力范围标注 */} + + + ) diff --git a/src/config.ts b/src/config.ts index 3221625..da6411d 100644 --- a/src/config.ts +++ b/src/config.ts @@ -1,11 +1,11 @@ /** - * 应用配置（不依赖 .env） + * 应用配置：敏感项仅从环境变量读取，勿在源码中写 token + * 构建时 Vite 会将 VITE_* 内联到前端；token 只应放在 .env（且 .env 不提交） */ export const config = { - /** Mapbox 地图令牌 */ - mapboxAccessToken: - 'pk.eyJ1IjoiZDI5cTAiLCJhIjoiY21oaGRmcTkzMGltZzJscHR1N2FhZnY5dCJ9.7ueF2lS6-C9Mm_xon7NnIA', + /** Mapbox 地图令牌（仅从 VITE_MAPBOX_ACCESS_TOKEN 读取，勿硬编码） */ + mapboxAccessToken: import.meta.env.VITE_MAPBOX_ACCESS_TOKEN ?? '', /** 是否显示滚动情报 */ - showNewsTicker: false, + showNewsTicker: import.meta.env.VITE_SHOW_NEWS_TICKER === 'true', } diff --git a/src/data/extendedWarData.ts b/src/data/extendedWarData.ts new file mode 100644 index 0000000..fdbf74c --- /dev/null +++ b/src/data/extendedWarData.ts @@ -0,0 +1,245 @@ +// 扩展战区与打击数据（2026-03-03 态势） +// 仅用于前端展示，不参与任何真实评估 + +export const EXTENDED_WAR_ZONES = { + // 1. 霍尔木兹海峡交战区 (Strait of Hormuz) — 多边形，包络海峡水道及两侧水域 [lng, lat] + hormuzCombatZone: { + type: 'Feature' as const, + properties: { + name: '霍尔木兹海峡交战区', + status: 'BLOCKED / ENGAGED', + style: { + fillColor: '#FFD700', + fillOpacity: 0.4, + meshPattern: 'diagonal-line', + }, + }, + geometry: { + type: 'Polygon' as const, + coordinates: [ + [ + [55.0, 25.0], + [55.5, 25.4], + [56.2, 26.0], + [56.8, 26.6], + [57.2, 27.0], + [57.0, 27.4], + [56.4, 27.2], + [55.8, 26.6], + [55.2, 25.9], + [54.8, 25.4], + [55.0, 25.0], + ], + ], + }, + }, + + // 霍尔木兹区域标注点（多边形中心附近，用于显示文字） + hormuzLabelCenter: [56.0, 26.2] as [number, number], + + // 2. 真主党势力范围 (Hezbollah) — 黎巴嫩南部 + 贝卡谷地，多边形 [lng, lat] + hezbollahZone: { + type: 'Feature' as const, + properties: { + name: '真主党势力范围', + status: 'OFFENSIVE ACTIVE', + color: '#32CD32', + }, + geometry: { + type: 'MultiPolygon' as const, + coordinates: [ + // 黎巴嫩南部（利塔尼河以南） + [ + [ + [35.05, 33.05], + [35.45, 33.15], + [35.85, 33.35], + [35.95, 33.65], + [35.75, 33.95], + [35.35, 33.85], + [35.05, 33.55], + [35.05, 33.05], + ], + ], + // 贝卡谷地 + [ + [ + [35.85, 33.75], + [36.15, 33.85], + [36.45, 34.05], + [36.55, 34.35], + [36.35, 34.55], + [35.95, 34.45], + [35.75, 34.15], + [35.85, 33.75], + ], + ], + ], + }, + }, + + // 真主党区域标注点（用于显示文字） + hezbollahLabelCenter: [35.7, 33.7] as [number, number], + + // 3. 真主党当前攻击目标 (North Israel Targets) + activeAttacks: [ + { + name: 'Meron Intelligence Base', + coords: [35.41, 32.99] as [number, number], + type: 'Rocket Strike', + damage: 'High', + }, + { + name: 'Ramat David Airbase', + coords: [35.18, 32.66] as [number, number], + type: 'Drone Swarm', + damage: 'Moderate', + }, + { + name: 'Mishmar HaCarmel (Haifa)', + coords: [35.01, 32.76] as [number, number], + type: 'Precision Missile', + damage: 'Intercepted', + }, + ], +} as const + +// 战损评估点位（以色列打击黎巴嫩 & 联军打击伊朗本土） +export const STRIKE_DAMAGE_ASSESSMENT = { + lebanonFront: [ + { + id: 'L1', + name: 'Dahieh Command', + coords: [35.5, 33.86] as [number, number], + type: 'Leadership', + color: '#ff4d4d', + }, + { + id: 'L2', + name: 'Litani Ammo Depot', + coords: [35.32, 33.34] as [number, number], + type: 'Logistics', + color: '#ff4d4d', + }, + { + id: 'L3', + name: 'Baalbek Logistics Hub', + coords: [36.2, 34.01] as [number, number], + type: 'Logistics', + color: '#ffb84d', + }, + { + id: 'L4', + name: 'Tyre Coastal Battery', + coords: [35.19, 33.27] as [number, number], + type: 'Naval', + color: '#ffb84d', + }, + { + id: 'L5', + name: 'Hermel UAV Site', + coords: [36.38, 34.39] as [number, number], + type: 'UAV', + color: '#ffd84d', + }, + ], + iranMainland: [ + { + id: 'I1', + name: 'Parchin Military Complex', + coords: [51.76, 35.53] as [number, number], + type: 'Strategic', + severity: 'Critical', + marker: 'Explosion', + }, + { + id: 'I2', + name: 'Mehrabad Airbase', + coords: [51.31, 35.68] as [number, number], + type: 'Airbase', + severity: 'High', + marker: 'Runway', + }, + { + id: 'I3', + name: 'Hesa Aircraft Factory', + coords: [51.59, 32.92] as [number, number], + type: 'Industrial', + severity: 'Moderate', + marker: 'Factory', + }, + { + id: 'I4', + name: 'Natanz Enrichment Entrance', + coords: [51.91, 33.72] as [number, number], + type: 'Nuclear', + severity: 'Critical', + marker: 'Radiation', + }, + { + id: 'I5', + name: 'Bushehr Air Defense Net', + coords: [50.88, 28.82] as [number, number], + type: 'AirDefense', + severity: 'High', + marker: 'Radar', + }, + { + id: 'I6', + name: 'Shahid Rajaee Port', + coords: [56.12, 27.14] as [number, number], + type: 'Naval', + severity: 'Critical', + marker: 'Blocked', + }, + { + id: 'I7', + name: 'Kermanshah Silo Cluster', + coords: [47.16, 34.35] as [number, number], + type: 'Missile', + severity: 'Critical', + marker: 'Silo', + }, + { + id: 'I8', + name: 'Tabriz Tactical Airbase 2', + coords: [46.24, 38.12] as [number, number], + type: 'Airbase', + severity: 'High', + marker: 'Runway', + }, + { + id: 'I9', + name: 'Arak Heavy Water Support', + coords: [49.23, 34.11] as [number, number], + type: 'Nuclear', + severity: 'High', + marker: 'Power', + }, + { + id: 'I10', + name: 'Fordow Entrance', + coords: [50.99, 34.88] as [number, number], + type: 'Nuclear', + severity: 'Critical', + marker: 'Tunnel', + }, + { + id: 'I11', + name: 'Nojeh Airbase', + coords: [48.8, 35.21] as [number, number], + type: 'Airbase', + severity: 'High', + marker: 'Runway', + }, + { + id: 'I12', + name: 'Kish SIGINT Site', + coords: [53.98, 26.54] as [number, number], + type: 'Radar', + severity: 'Moderate', + marker: 'Sensor', + }, + ], +} as const + diff --git a/start.sh b/start.sh index 7ed6c5b..a0b5eac 100755 --- a/start.sh +++ b/start.sh @@ -3,9 +3,13 @@ set -e cd "$(dirname "$0")" -# 无 Ollama 时禁用 AI；GDELT 国内常超时，仅用 RSS 更新 -export CLEANER_AI_DISABLED=1 -export PARSER_AI_DISABLED=1 +# 若存在 .env 则加载（可在此设置 DASHSCOPE_API_KEY=sk-xxx，勿提交 .env） +[ -f .env ] && set -a && . ./.env && set +a + +# AI 模式：有 DASHSCOPE_API_KEY 时用通义（商业模型，无需 Ollama）；否则用 Ollama 或规则 +export CLEANER_AI_DISABLED=0 +export PARSER_AI_DISABLED=0 +# GDELT 国内常超时，仅用 RSS 更新（如需 GDELT 可改为 0） export GDELT_DISABLED=1 export RSS_INTERVAL_SEC=60