fix: 帖子时间解析过滤2053等异常年份，使用crawled_at兜底

feat: 增量脚本去掉LIMIT - 每次跑完所有待处理帖子
fix: 修复增量提取NOT IN子查询bug - 改用NOT EXISTS避免类型转换问题
2026-04-09 23:22:55 +08:00 · 2026-04-07 19:43:16 +08:00 · 2026-04-07 19:33:58 +08:00 · 2026-04-07 15:30:07 +08:00 · 2026-04-07 14:38:25 +08:00 · 2026-04-07 12:24:00 +08:00
9 changed files with 1613 additions and 55 deletions
--- a/crawlers/crawl_today.py
+++ b/crawlers/crawl_today.py
@ -47,6 +47,49 @@ def extract_post_content(html_bytes):
    lines = [l.strip() for l in text.split('\n') if l.strip()]
    text = '\n'.join(lines)
    text = re.sub(r'\n\d{4}[/\-]\d{1,2}[/\-]\d{1,2}\s+\d{1,2}:\d{2}:\d{2}\s*$', '', text)
+
+    # 截取免责声明及之前的内容
+    disclaimer = '免责声明及风险提示：所有交易人员，凡未采用本站中介交易的，被骗后果自负。'
+    discl_pos = text.find(disclaimer)
+    if discl_pos != -1:
+        text = text[:discl_pos + len(disclaimer)]
+    
+    # 清理尾部网站版权和导航信息
+    footer_patterns = [
+        'BoardJumpListSelect',
+        'Powered By Dvbbs',
+        '京ICP备',
+        '页面执行时间',
+        '发短信',
+        '购买论坛点券',
+        '我能做什么',
+        '我发表的主题',
+        '我参与的主题',
+        '基本资料修改',
+        '用户密码修改',
+        '联系资料修改',
+        '用户短信服务',
+        '编辑好友列表',
+        '个人文件管理',
+        '通行证设置',
+        '今日贴数图例',
+        '主题数图例',
+        '总帖数图例',
+        '在线图例',
+        '在线情况',
+        '用户组在线图例',
+        '文件集浏览',
+        '图片集浏览',
+        'Flash浏览',
+        '音乐集浏览',
+        '电影集浏览',
+        '贺卡发送',
+    ]
+    for pat in footer_patterns:
+        pos = text.find(pat)
+        if pos != -1:
+            text = text[:pos]
+    
    return text if text else None


@ -56,8 +99,9 @@ import logging
 logger = logging.getLogger(__name__)

 class YichensTodaySpider(PaginationSpider):
-    def __init__(self):
+    def __init__(self, instance_id=None):
        super().__init__("一尘网今日采集", "pm001")
+        self.instance_id = instance_id or os.environ.get('CRAWLER_INSTANCE_ID', 'unknown')
        self.base_url = "http://www.pm001.net"
        self.board_id = "151"
        self.forum_url = f"{self.base_url}/index.asp?boardid={self.board_id}"
@ -135,7 +179,14 @@ class YichensTodaySpider(PaginationSpider):
        created_at = None
        m = re.search(r"(\d{4}/\d{1,2}/\d{1,2}\s+\d{1,2}:\d{2}:\d{2})", page_text)
        if m:
-            created_at = m.group(1).replace("/", "-")
+            date_str = m.group(1).replace("/", "-")
+            try:
+                from datetime import datetime
+                dt = datetime.strptime(date_str, "%Y-%m-%d %H:%M:%S")
+                if 2020 <= dt.year <= 2030:
+                    created_at = date_str
+            except:
+                pass
        
        phones = re.findall(r'1[3-9]\d{9,10}', page_text)
        contact = ",".join(dict.fromkeys(phones[:5])) if phones else None
@ -158,21 +209,28 @@ class YichensTodaySpider(PaginationSpider):
            if "标百" in title:
                special_types.append("标百")
        
-        post_type = "normal"
+        # post_type 分类逻辑：出售 > 求购 > 其他 > 默认出售
        if title:
-            if any(c in title for c in ["出", "售", "卖", "兑"]):
+            if any(c in title for c in ["出", "售", "卖"]):
                post_type = "deal"
-            elif any(c in title for c in ["求", "收", "购"]):
+            elif any(c in title for c in ["收", "求", "购", "要"]):
                post_type = "want"
+            elif any(c in title for c in ["确认", "朋友", "投诉"]):
+                post_type = "normal"
+            else:
+                post_type = "deal"  # 默认出售
+        else:
+            post_type = "normal"
        
+        # category 分类逻辑（优先级：龙钞 > 马钞 > 蛇钞 > 其他）
        category = "其他"
        if title:
-            if "龙钞" in title or "龙纪念" in title:
+            if any(c in title for c in ["龙", "龙钞", "小龙钞", "钞王"]):
                category = "龙钞"
-            elif "蛇钞" in title:
-                category = "蛇钞"
-            elif "马钞" in title:
+            elif any(c in title for c in ["马", "马钞"]):
                category = "马钞"
+            elif any(c in title for c in ["蛇", "蛇钞"]):
+                category = "蛇钞"
        
        # 从 postuserinfo div 的 <b> 标签提取用户名（跳过电话号码）
        if not author:
@ -295,58 +353,73 @@ class YichensTodaySpider(PaginationSpider):
        if not post or not post.get("post_id"):
            return False
        
-        sql = """
-            INSERT INTO yichens_posts (
-                post_id, title, content, category, post_type,
-                price, price_unit, special_types, number_features,
-                author_username, author_id, contact,
-                has_lifebuoy, reply_count, view_count,
-                post_time, crawled_at, updated_at, url
-            ) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, NOW(), NOW(), %s)
-            ON CONFLICT (post_id) DO UPDATE SET
-                title = EXCLUDED.title,
-                content = EXCLUDED.content,
-                category = EXCLUDED.category,
-                post_type = EXCLUDED.post_type,
-                price = EXCLUDED.price,
-                price_unit = EXCLUDED.price_unit,
-                special_types = EXCLUDED.special_types,
-                author_username = EXCLUDED.author_username,
-                contact = EXCLUDED.contact,
-                has_lifebuoy = EXCLUDED.has_lifebuoy,
-                post_time = EXCLUDED.post_time,
-                updated_at = NOW(),
-                crawled_at = NOW(),
-                url = EXCLUDED.url
-        """
+        import psycopg2.sql as sql
        
        has_lifebuoy = post.get("special_types") and "救生圈" in post.get("special_types", "")
        
+        cols = ['post_id', 'title', 'content', 'category', 'post_type', 'price',
+                'price_unit', 'special_types', 'number_features', 'author_username',
+                'author_id', 'contact', 'has_lifebuoy', 'reply_count', 'view_count',
+                'post_time', 'crawled_at', 'updated_at', 'url', 'instance_id']
+        
+        vals = [
+            sql.Literal(post.get("post_id")),
+            sql.Literal(post.get("title")),
+            sql.Literal(post.get("content")),
+            sql.Literal(post.get("category")),
+            sql.Literal(post.get("post_type")),
+            sql.Literal(post.get("price")),
+            sql.Literal(post.get("price_unit")),
+            sql.Literal(post.get("special_types")),
+            sql.Literal(post.get("number_features")),
+            sql.Literal(post.get("author_username")),
+            sql.Literal(f"user_{post.get('post_id')}"),
+            sql.Literal(post.get("contact")),
+            sql.Literal(has_lifebuoy),
+            sql.Literal(0),
+            sql.Literal(0),
+            sql.Literal(post.get("post_time")),
+            sql.SQL('NOW()'),
+            sql.SQL('NOW()'),
+            sql.Literal(post.get("url")),
+            sql.Literal(self.instance_id),
+        ]
+        
+        update_assigns = [
+            "title = EXCLUDED.title",
+            "content = EXCLUDED.content",
+            "category = EXCLUDED.category",
+            "post_type = EXCLUDED.post_type",
+            "price = EXCLUDED.price",
+            "price_unit = EXCLUDED.price_unit",
+            "special_types = EXCLUDED.special_types",
+            "number_features = EXCLUDED.number_features",
+            "author_username = EXCLUDED.author_username",
+            "author_id = EXCLUDED.author_id",
+            "contact = EXCLUDED.contact",
+            "has_lifebuoy = EXCLUDED.has_lifebuoy",
+            "reply_count = EXCLUDED.reply_count",
+            "view_count = EXCLUDED.view_count",
+            "post_time = EXCLUDED.post_time",
+            "updated_at = NOW()",
+            "crawled_at = NOW()",
+            "url = EXCLUDED.url",
+            
+        ]
+        
+        query = sql.SQL("INSERT INTO yichens_posts ({}) VALUES ({}) ON CONFLICT (post_id) DO UPDATE SET {}").format(
+            sql.SQL(', ').join(sql.Identifier(c) for c in cols),
+            sql.SQL(', ').join(vals),
+            sql.SQL(', ').join(sql.SQL(a) for a in update_assigns),
+        )
+        
        try:
            with get_db() as conn:
                if not conn:
                    print("数据库连接失败")
                    return False
                cur = conn.cursor()
-                cur.execute(sql, (
-                    post.get("post_id"),
-                    post.get("title"),
-                    post.get("content"),
-                    post.get("category"),
-                    post.get("post_type"),
-                    post.get("price"),
-                    post.get("price_unit"),
-                    post.get("special_types"),
-                    post.get("number_features"),
-                    post.get("author_username"),
-                    f"user_{post.get('post_id')}",
-                    post.get("contact"),
-                    has_lifebuoy,
-                    0,
-                    0,
-                    post.get("post_time"),
-                    post.get("url"),
-                ))
+                cur.execute(query)
                conn.commit()
                cur.close()
                return True
@ -370,8 +443,8 @@ class YichensTodaySpider(PaginationSpider):
            with get_db() as conn:
                cur = conn.cursor()
                cur.execute(
-                    "INSERT INTO crawl_logs (spider_name, status, started_at) VALUES (%s, %s, NOW()) RETURNING id",
-                    (self.source, "running")
+                    "INSERT INTO crawl_logs (spider_name, status, started_at, instance_id) VALUES (%s, %s, NOW(), %s) RETURNING id",
+                    (self.source, "running", self.instance_id)
                )
                log_id = cur.fetchone()[0]
                conn.commit()
--- a/docs/服务器运维手册.md
+++ b/docs/服务器运维手册.md
@ -0,0 +1,250 @@
+# 一尘数据系统 - 服务器运维手册
+
+> 适用服务器：2号 (101.37.160.219)、3号 (42.121.116.25)
+> 统一密码：`Coolbot123`（2号也用此密码登录）
+
+---
+
+## 一、服务器概览
+
+| 服务器 | IP | 用途 | 爬虫 cron |
+|--------|-----|------|-----------|
+| 2号 | 101.37.160.219 | 爬虫 + API | 每 15 分钟 |
+| 3号 | 42.121.116.25 | 爬虫 + API | 每 25 分钟 |
+
+---
+
+## 二、下载更新版本
+
+### 方式 A：通过 Git 拉取（推荐）
+
+```bash
+cd /root/coolbot-data
+git pull origin main
+```
+
+> 注意：可能需要先设置 Git 凭据
+> ```bash
+> git config --global credential.helper store
+> # 首次需要输入一次用户名密码
+> # 用户名: caibotmi
+> # 密码: Caibotmi123
+> ```
+
+### 方式 B：手动上传
+
+如果 Git 有问题，可以让机器人（我）从 1 号服务器打包文件，通过中间服务器转发。
+
+---
+
+## 三、部署启动服务
+
+### 3.1 安装 Python 依赖
+
+```bash
+cd /root/coolbot-data
+source venv/bin/activate
+pip install -r requirements.txt -q
+```
+
+### 3.2 重启爬虫服务
+
+```bash
+# 重启 cron（让新代码生效）
+crontab /root/coolbot-data/scripts/root.cron
+
+# 或手动重启 crond
+systemctl restart crond
+```
+
+### 3.3 重启 API 服务
+
+```bash
+# 查看 API 是否在运行
+ps aux | grep uvicorn | grep -v grep
+
+# 如果在运行，kill 掉
+pkill -f uvicorn
+
+# 重新启动（后台运行）
+cd /root/coolbot-data
+source venv/bin/activate
+nohup python3 -m uvicorn api.main:app --host 0.0.0.0 --port 8080 > /root/coolbot-data/logs/api.log 2>&1 &
+echo "API 已重启，PID: $!"
+```
+
+---
+
+## 四、验证服务
+
+### 4.1 验证爬虫日志
+
+```bash
+# 查看最近爬虫执行记录
+tail -20 /root/coolbot-data/logs/cron_s2.log   # 2号
+tail -20 /root/coolbot-data/logs/cron_s3.log   # 3号
+```
+
+**正常的日志格式：**
+```
+开始全量采集第1-2页 (今天: 2026/4/7)
+扫描第 1 页...
+  该页共 391 条帖子
+  [保存] 36193766 - ，，，13100元求购... (今日2026/4/7中已存2条)
+===== 采集完成 =====
+总计检查: 781 条
+成功保存: 23 条
+```
+
+**出现以下情况请处理：**
+- `保存失败: not all arguments converted` → 代码未更新，需重新拉取
+- `保存失败: connection` → 数据库连接问题
+- 一直是 0 条 → 检查网络或目标网站
+
+### 4.2 验证 API 服务
+
+```bash
+# 测试 API 是否响应
+curl -s http://localhost:8080/health | python3 -m json.tool
+```
+
+**正常响应：**
+```json
+{"status": "ok", "message": "CoolBotDataSys API is running", "version": "1.0.0"}
+```
+
+### 4.3 验证数据库新帖
+
+```bash
+python3 -c "
+import psycopg2
+conn = psycopg2.connect(host='pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com', port=5432, database='coolbot_data', user='coolbot', password='Coolbot123')
+cur = conn.cursor()
+cur.execute('SELECT COUNT(*), MAX(crawled_at) FROM yichens_posts WHERE DATE(crawled_at) = CURRENT_DATE')
+r = cur.fetchone()
+print(f'今日帖子: {r[0]}条 | 最后采集: {r[1]}')
+conn.close()
+"
+```
+
+---
+
+## 五、定期检查
+
+### 5.1 每日检查（建议）
+
+```bash
+# 1. 检查爬虫是否在运行
+ps aux | grep crawl_today | grep -v grep
+
+# 2. 检查 cron 是否生效
+crontab -l | grep crawl
+
+# 3. 检查今日数据量（应该 > 0）
+python3 -c "import psycopg2; conn = psycopg2.connect(host='pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com', port=5432, database='coolbot_data', user='coolbot', password='Coolbot123'); cur = conn.cursor(); cur.execute('SELECT COUNT(*) FROM yichens_posts WHERE DATE(crawled_at) = CURRENT_DATE'); print(cur.fetchone()[0], '条'); conn.close()"
+```
+
+### 5.2 每周检查
+
+- 检查磁盘空间：`df -h`
+- 检查日志文件大小：`ls -lh /root/coolbot-data/logs/`
+- 清理旧日志：`find /root/coolbot-data/logs -name "*.log" -mtime +7 -delete`
+
+---
+
+## 六、问题处理
+
+### 问题 1：爬虫一直报 "保存失败: not all arguments converted"
+
+**原因：** 代码未更新到最新版本
+
+**解决：**
+```bash
+cd /root/coolbot-data
+git pull origin main
+```
+
+### 问题 2：爬虫返回 0 条新帖
+
+**排查步骤：**
+1. 检查网络：`curl -s -o /dev/null -w "%{http_code}" http://www4.pm001.net`
+2. 查看详细日志：`tail -50 /root/coolbot-data/logs/cron_s*.log`
+3. 手动跑一次爬虫看输出
+
+### 问题 3：API 服务无响应
+
+**解决：**
+```bash
+# 检查端口是否监听
+netstat -tlnp | grep 8080
+
+# 重启 API
+cd /root/coolbot-data
+pkill -f uvicorn
+source venv/bin/activate
+nohup python3 -m uvicorn api.main:app --host 0.0.0.0 --port 8080 > logs/api.log 2>&1 &
+```
+
+### 问题 4：数据库连接失败
+
+**原因：** 阿里云 RDS 网络不通 或 密码错误
+
+**排查：**
+```bash
+# 测试数据库连接
+psql "postgresql://coolbot:Coolbot123@pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com:5432/coolbot_data" -c "SELECT 1"
+```
+
+### 问题 5：SSH 连接被拒
+
+**原因：** 服务器 SSH 策略或网络问题
+
+**解决：** 等待几分钟后重试，或联系网络管理员
+
+---
+
+## 七、快速命令汇总
+
+```bash
+# === 查看状态 ===
+git -C /root/coolbot-data log --oneline -1        # 最新版本
+ps aux | grep crawl_today | grep -v grep          # 爬虫进程
+ps aux | grep uvicorn | grep -v grep              # API 进程
+tail -5 /root/coolbot-data/logs/cron_s*.log       # 最新日志
+
+# === 更新代码 ===
+cd /root/coolbot-data && git pull origin main
+
+# === 重启爬虫 ===
+pkill -f crawl_today
+# 等待 cron 自动触发，或手动运行：
+# cd /root/coolbot-data && source venv/bin/activate && python3 scripts/crawl_cron_s2.sh
+
+# === 重启 API ===
+cd /root/coolbot-data && pkill -f uvicorn && source venv/bin/activate && nohup python3 -m uvicorn api.main:app --host 0.0.0.0 --port 8080 > logs/api.log 2>&1 &
+
+# === 验证服务 ===
+curl -s http://localhost:8080/health              # API 健康检查
+python3 -c "import psycopg2; c=psycopg2.connect(host='pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com',port=5432,database='coolbot_data',user='coolbot',password='Coolbot123'); print(c.cursor().execute('SELECT 1'),'OK')"  # DB 连接
+```
+
+---
+
+## 八、重要文件路径
+
+| 路径 | 说明 |
+|------|------|
+| `/root/coolbot-data/crawlers/crawl_today.py` | 爬虫主程序 |
+| `/root/coolbot-data/scripts/crawl_cron_s2.sh` | 2号 cron 脚本 |
+| `/root/coolbot-data/scripts/crawl_cron_s3.sh` | 3号 cron 脚本 |
+| `/root/coolbot-data/logs/cron_s2.log` | 2号爬虫日志 |
+| `/root/coolbot-data/logs/cron_s3.log` | 3号爬虫日志 |
+| `/root/coolbot-data/api/main.py` | API 主程序 |
+| `/root/coolbot-data/logs/api.log` | API 日志 |
+| `/root/coolbot-data/.env` | 环境变量（包含数据库密码） |
+
+---
+
+## 九、联系方式
+
+如遇到无法解决的问题，请联系：**菜鸟Mi（caibotmini）**
--- a/frontend/index.html
+++ b/frontend/index.html
@ -0,0 +1,684 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
+<title>一尘数据</title>
+<style>
+*{margin:0;padding:0;box-sizing:border-box;-webkit-tap-highlight-color:transparent}
+body{font-family:-apple-system,BlinkMacSystemFont,PingFang SC,Helvetica,Arial,sans-serif;background:#f2f2f2;font-size:14px;color:#333;min-height:100vh;padding-bottom:60px}
+a{color:inherit;text-decoration:none}
+
+/* 顶部 */
+.header{background:linear-gradient(135deg,#1a1a2e,#16213e);color:#fff;padding:12px 16px;position:sticky;top:0;z-index:50;display:flex;align-items:center;justify-content:space-between}
+.header h1{font-size:17px;font-weight:600}
+.hdr-btn{font-size:20px;background:none;border:none;cursor:pointer}
+
+/* 统计 */
+.stats{padding:12px;display:grid;grid-template-columns:1fr 1fr;gap:10px}
+.stat{background:#fff;border-radius:10px;padding:14px;text-align:center;cursor:pointer}
+.stat:active{background:#f0f0f0}
+.s-num{font-size:26px;font-weight:700;margin-bottom:4px}
+.s-num.blue{color:#1976d2}.s-num.green{color:#2e7d32}.s-num.orange{color:#e65100}.s-num.red{color:#c62828}
+.s-label{font-size:12px;color:#999}
+.stat.full{grid-column:1/-1;display:flex;justify-content:space-around}
+
+/* 筛选 */
+.f-bar{background:#fff;padding:10px 12px;border-bottom:1px solid #eee;overflow-x:auto;white-space:nowrap}
+.f-row{display:flex;gap:8px}
+.f-btn{flex-shrink:0;padding:5px 14px;border:1px solid #ddd;border-radius:16px;font-size:13px;background:#fff;color:#666;cursor:pointer}
+.f-btn:active,.f-btn.on{background:#1a1a2e;color:#fff;border-color:#1a1a2e}
+
+/* 列表 */
+.list{padding:10px 12px;padding-bottom:65px}
+.post{background:#fff;border-radius:10px;padding:12px;margin-bottom:10px;cursor:pointer}
+.post:active{background:#fafafa}
+.post-title{font-size:14px;font-weight:500;line-height:1.5;margin-bottom:8px;display:-webkit-box;-webkit-line-clamp:2;-webkit-box-orient:vertical;overflow:hidden}
+.post-meta{display:flex;flex-wrap:wrap;gap:5px;align-items:center;font-size:12px}
+.badge{padding:2px 7px;border-radius:4px;font-weight:500}
+.b-deal{background:#e8f5e9;color:#2e7d32}.b-want{background:#fff3e0;color:#e65100}.b-normal{background:#e3f2fd;color:#1565c0}.b-lifebuoy{background:#ffebee;color:#c62828}
+.price{color:#e53935;font-weight:600}
+.author{color:#1976d2}.tm{color:#999}
+
+/* 分页 */
+.pager{display:flex;justify-content:center;align-items:center;gap:12px;padding:14px;background:#fff;border-radius:10px;margin-top:10px}
+.pg-btn{padding:8px 18px;background:#f5f5f5;border:1px solid #ddd;border-radius:6px;font-size:14px;cursor:pointer}
+.pg-btn:disabled{opacity:.4;cursor:not-allowed}
+.pg-info{font-size:13px;color:#999}
+/* 统计页 */
+.stats-grid{display:grid;grid-template-columns:1fr 1fr;gap:10px}
+.st-card{background:#fff;border-radius:10px;padding:16px;text-align:center;cursor:pointer}
+.st-card:active{background:#f0f0f0}
+.st-num{font-size:32px;font-weight:700;color:#e65100;line-height:1.2}
+.st-card.st-deal .st-num{color:#2e7d32}
+.st-label{font-size:14px;color:#333;margin:6px 0 4px;font-weight:500}
+.st-price{font-size:12px;color:#999}
+
+/* 空/加载 */
+.empty,.loading{text-align:center;padding:50px;color:#999}
+.empty::before{content:'📭';font-size:40px;display:block;margin-bottom:10px}
+
+/* 底部导航 */
+.tab{position:fixed;bottom:0;left:0;right:0;background:#fff;border-top:1px solid #eee;display:flex;z-index:50;padding-bottom:env(safe-area-inset-bottom,0)}
+.tab-i{flex:1;text-align:center;padding:10px 0;font-size:11px;color:#999;cursor:pointer}
+.tab-i.on{color:#1a1a2e}
+.tab-i span{display:block;font-size:22px;margin-bottom:2px}
+
+/* 详情页 */
+.detail{position:fixed;inset:0;background:#fff;z-index:100;overflow-y:auto}
+.detail-hdr{position:sticky;top:0;background:#fff;padding:12px 16px;border-bottom:1px solid #eee;display:flex;align-items:center;justify-content:space-between;z-index:5}
+.back{background:none;border:none;font-size:16px;color:#1976d2;cursor:pointer}
+.detail-link{font-size:13px;color:#1976d2}
+.detail-body{padding:16px}
+.detail-title{font-size:16px;font-weight:600;line-height:1.5;margin-bottom:14px}
+.sec{margin-bottom:20px}
+.sec-title{font-size:13px;font-weight:600;margin-bottom:10px;padding-bottom:6px;border-bottom:2px solid #1a1a2e}
+.info-g{	display:grid;grid-template-columns:1fr 1fr;gap:10px}
+.info-i{display:flex;flex-direction:column;gap:2px}
+.info-l{font-size:11px;color:#999}
+.info-v{font-size:14px;color:#333}
+.info-v.prime{font-size:22px;color:#e53935;font-weight:700}
+.content{background:#f8f9fa;padding:12px;border-radius:8px;white-space:pre-wrap;font-size:14px;line-height:1.7;word-break:break-all;max-height:300px;overflow-y:auto}
+.tag-l{display:flex;flex-wrap:wrap;gap:6px}
+.tag{padding:3px 10px;background:#e3f2fd;color:#1565c0;border-radius:12px;font-size:12px}
+
+/* 品类 */
+.cat-list{background:#fff;border-radius:10px;padding:12px;margin:0 12px 80px}
+.cat-row{display:flex;justify-content:space-between;padding:8px 0;border-bottom:1px solid #f0f0f0;font-size:13px}
+.cat-row:last-child{border:none}
+</style>
+</head>
+<body>
+
+<div id="app"></div>
+
+<script>
+const API = '/api/v1'
+let S = {
+  v: 'home',       // home | list | detail
+  stats: {},
+  posts: [],
+  cur: null,
+  loading: false,
+  pg: 1,
+  ps: 300,
+  total: 0,
+  ft: { type: '', cat: '', lifebuoy: '' }
+}
+
+function render() {
+  const app = document.getElementById('app')
+  if (S.v === 'home') {
+    const s = S.stats
+    app.innerHTML = `
+      <div class="header">
+        <h1>📊 一尘数据分析</h1>
+        <button class="hdr-btn" onclick="loadStats()">🔄</button>
+      </div>
+      <div class="stats">
+        <div class="stat" onclick="goList('deal')">
+          <div class="s-num green">${s.deal_count||0}</div>
+          <div class="s-label">今日出售</div>
+        </div>
+        <div class="stat" onclick="goList('want')">
+          <div class="s-num orange">${s.want_count||0}</div>
+          <div class="s-label">今日求购</div>
+        </div>
+        <div class="stat" onclick="goList('')">
+          <div class="s-num blue">${s.today_count||0}</div>
+          <div class="s-label">今日新增</div>
+        </div>
+        <div class="stat" onclick="goList('lifebuoy')">
+          <div class="s-num red">${s.lifebuoy_count||0}</div>
+          <div class="s-label">大救生圈</div>
+        </div>
+        <div class="stat full">
+          <div>
+            <div class="s-num blue" style="font-size:20px">${s.total_posts||0}</div>
+            <div class="s-label">总帖子</div>
+          </div>
+          <div>
+            <div style="font-size:22px">🟢</div>
+            <div class="s-label">在线</div>
+          </div>
+        </div>
+      </div>
+      <div style="padding:0 12px 20px">
+        <div class="sec-title">📋 品类分布</div>
+        <div class="cat-list">
+          <div style="margin-bottom:12px">
+            <div style="font-size:12px;color:#1976d2;margin-bottom:8px">📅 当日新增</div>
+            ${((S.catReport&&S.catReport.today&&S.catReport.today.categories)||[]).map(c=>`
+              <div class="cat-row" onclick="goList('','today','${c.category}')">
+                <span>${c.category}</span>
+                <span style="color:#1976d2;font-weight:600">${c.count}条</span>
+              </div>
+            `).join('')}
+          </div>
+          <div>
+            <div style="font-size:12px;color:#e65100;margin-bottom:8px">⏰ 近1小时新增</div>
+            ${((S.catReport&&S.catReport.last_1h&&S.catReport.last_1h.categories)||[]).map(c=>`
+              <div class="cat-row" onclick="goList('','1h','${c.category}')">
+                <span>${c.category}</span>
+                <span style="color:#e65100;font-weight:600">${c.count}条</span>
+              </div>
+            `).join('')}
+          </div>
+        </div>
+      </div>
+      <div class="tab">
+        <div class="tab-i on" onclick="S.v='home';render()"><span>📊</span>首页</div>
+        <div class="tab-i" onclick="goList('')"><span>📋</span>帖子</div>
+        <div class="tab-i" onclick="goCollections()"><span>💎</span>藏品</div>
+        <div class="tab-i" onclick="goUsers()"><span>👤</span>用户</div>
+        <div class="tab-i" onclick="S.v='stats';loadStats()"><span>📈</span>统计</div>
+      </div>
+    `
+  }
+
+
+  if (S.v === 'collections') {
+    const cols = S.collections || []
+    app.innerHTML = `
+      <div class="header"><h1>💎 藏品列表</h1><button class="hdr-btn" onclick="loadCollections()">🔄</button></div>
+      <div class="filter-bar">
+        <select id="col-cat" onchange="S.colCat=this.value;render()">
+          <option value="">全部品类</option>
+          <option value="龙钞">🐉 龙钞</option>
+          <option value="马钞">🐴 马钞</option>
+          <option value="蛇钞">🐍 蛇钞</option>
+          <option value="其他">📦 其他</option>
+        </select>
+        <input type="text" id="col-search" placeholder="搜索名称/冠号" onkeyup="S.colSearch=this.value;render()" style="flex:1;padding:8px;border:1px solid #ddd;border-radius:6px">
+      </div>
+      <div class="list">
+        ${cols.filter(c => (!S.colCat || c.category === S.colCat) && (!S.colSearch || (c.name&&c.name.includes(S.colSearch)) || (c.crown_code&&c.crown_code.includes(S.colSearch)))).map(c => `
+          <div class="post-item" onclick="goCollectionDetail('${c.id}')">
+            <div class="post-title">${c.name || c.crown_code || '无名'}</div>
+            <div class="post-meta">
+              <span class="${c.category==='龙钞'?'green':c.category==='马钞'?'orange':c.category==='蛇钞'?'purple':'gray'}">${c.category||'其他'}</span>
+              <span>🏷️ ${c.series||'-'}</span>
+              <span>📅 ${c.issue_year||'-'}</span>
+              <span>🖥️ ${c.instance_id?c.instance_id.replace('server_','S'):'-'}</span>
+            </div>
+          </div>
+        `).join('')}
+        ${cols.length===0?'<div style="padding:40px;text-align:center;color:#999">暂无藏品，点击刷新</div>':''}
+      </div>
+      <div class="tab">
+        <div class="tab-i" onclick="S.v='home';render()"><span>📊</span>首页</div>
+        <div class="tab-i" onclick="goList('')"><span>📋</span>帖子</div>
+        <div class="tab-i on" onclick="goCollections()"><span>💎</span>藏品</div>
+        <div class="tab-i" onclick="goUsers()"><span>👤</span>用户</div>
+        <div class="tab-i" onclick="S.v='stats';loadStats()"><span>📈</span>统计</div>
+      </div>
+    `
+  }
+
+  if (S.v === 'users') {
+    const users = S.users || []
+    app.innerHTML = `
+      <div class="header"><h1>👤 用户列表</h1><button class="hdr-btn" onclick="loadUsers()">🔄</button></div>
+      <div class="filter-bar">
+        <input type="text" id="user-search" placeholder="搜索用户名" onkeyup="S.userSearch=this.value;render()" style="flex:1;padding:8px;border:1px solid #ddd;border-radius:6px">
+      </div>
+      <div class="list">
+        ${users.filter(u => !S.userSearch || u.username.includes(S.userSearch)).map(u => `
+          <div class="post-item">
+            <div class="post-title">${u.username}</div>
+            <div class="post-meta">
+              <span>${u.is_seller?'🏪 商家':'👤 个人'}</span>
+              <span>📝 ${u.post_count||0}帖</span>
+              <span>⭐ ${u.credit_score||0}分</span>
+              <span>📅 ${u.registration_date?u.registration_date.substring(0,10):'-'}</span>
+            </div>
+          </div>
+        `).join('')}
+        ${users.length===0?'<div style="padding:40px;text-align:center;color:#999">暂无用户，点击刷新</div>':''}
+      </div>
+      <div class="tab">
+        <div class="tab-i" onclick="S.v='home';render()"><span>📊</span>首页</div>
+        <div class="tab-i" onclick="goList('')"><span>📋</span>帖子</div>
+        <div class="tab-i" onclick="goCollections()"><span>💎</span>藏品</div>
+        <div class="tab-i on" onclick="goUsers()"><span>👤</span>用户</div>
+        <div class="tab-i" onclick="S.v='stats';loadStats()"><span>📈</span>统计</div>
+      </div>
+    `
+  }
+
+  if (S.v === 'stats') {
+    const st = S.statsData || {}
+    const want = st.want || {}
+    const deal = st.deal || {}
+    app.innerHTML = `
+      <div class="header"><h1>📈 统计分析</h1><button class="hdr-btn" onclick="loadStats()">🔄</button></div>
+      <div style="padding:12px">
+        <div style="font-size:13px;font-weight:600;color:#e65100;margin-bottom:10px">🔍 求购龙钞类</div>
+        <div class="stats-grid">
+          <div class="st-card" onclick="goStatPosts('want_dai4_biao10')">
+            <div class="st-num">${want.dai4_biao10?.count||0}</div>
+            <div class="st-label">带4标十</div>
+            <div class="st-price">均 ${want.dai4_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card" onclick="goStatPosts('want_wu47_biao10')">
+            <div class="st-num">${want.wu47_biao10?.count||0}</div>
+            <div class="st-label">无47标十</div>
+            <div class="st-price">均 ${want.wu47_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card" onclick="goStatPosts('want_wu247_biao10')">
+            <div class="st-num">${want.wu247_biao10?.count||0}</div>
+            <div class="st-label">无247/天马标十</div>
+            <div class="st-price">均 ${want.wu247_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card" onclick="goStatPosts('want_wu247_biaobai')">
+            <div class="st-num">${want.wu247_biaobai?.count||0}</div>
+            <div class="st-label">无247/天马标百/刀</div>
+            <div class="st-price">均 ${want.wu247_biaobai?.avg||0}元</div>
+          </div>
+          <div class="st-card" onclick="goStatPosts('want_wu47_biaobai')">
+            <div class="st-num">${want.wu47_biaobai?.count||0}</div>
+            <div class="st-label">无47标百/刀</div>
+            <div class="st-price">均 ${want.wu47_biaobai?.avg||0}元</div>
+          </div>
+        </div>
+        <div style="font-size:13px;font-weight:600;color:#2e7d32;margin:16px 0 10px">🔍 出售龙钞类</div>
+        <div class="stats-grid">
+          <div class="st-card st-deal" onclick="goStatPosts('deal_dai4_biao10')">
+            <div class="st-num">${deal.dai4_biao10?.count||0}</div>
+            <div class="st-label">带4标十</div>
+            <div class="st-price">均 ${deal.dai4_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card st-deal" onclick="goStatPosts('deal_wu47_biao10')">
+            <div class="st-num">${deal.wu47_biao10?.count||0}</div>
+            <div class="st-label">无47标十</div>
+            <div class="st-price">均 ${deal.wu47_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card st-deal" onclick="goStatPosts('deal_wu247_biao10')">
+            <div class="st-num">${deal.wu247_biao10?.count||0}</div>
+            <div class="st-label">无247/天马标十</div>
+            <div class="st-price">均 ${deal.wu247_biao10?.avg||0}元</div>
+          </div>
+          <div class="st-card st-deal" onclick="goStatPosts('deal_wu247_biaobai')">
+            <div class="st-num">${deal.wu247_biaobai?.count||0}</div>
+            <div class="st-label">无247/天马标百/刀</div>
+            <div class="st-price">均 ${deal.wu247_biaobai?.avg||0}元</div>
+          </div>
+          <div class="st-card st-deal" onclick="goStatPosts('deal_wu47_biaobai')">
+            <div class="st-num">${deal.wu47_biaobai?.count||0}</div>
+            <div class="st-label">无47标百/刀</div>
+            <div class="st-price">均 ${deal.wu47_biaobai?.avg||0}元</div>
+          </div>
+        </div>
+      </div>
+      <div class="tab">
+        <div class="tab-i" onclick="S.v='home';render()"><span>📊</span>首页</div>
+        <div class="tab-i" onclick="goList('')"><span>📋</span>帖子</div>
+        <div class="tab-i" onclick="goCollections()"><span>💎</span>藏品</div>
+        <div class="tab-i" onclick="goUsers()"><span>👤</span>用户</div>
+        <div class="tab-i on" onclick="S.v='stats';loadStats()"><span>📈</span>统计</div>
+      </div>
+    `
+  }
+
+  if (S.v === 'list') {
+    const ft = S.ft
+    app.innerHTML = `
+      <div class="header"><h1>📋 帖子列表</h1></div>
+      <div class="f-bar">
+        <div class="f-row">
+          <button class="f-btn${ft.type===''?' on':''}" onclick="setF('type','')">全部</button>
+          <button class="f-btn${ft.type==='deal'?' on':''}" onclick="setF('type','deal')">出售</button>
+          <button class="f-btn${ft.type==='want'?' on':''}" onclick="setF('type','want')">求购</button>
+          <button class="f-btn${ft.type==='other'?' on':''}" onclick="setF('type','other')">其他</button>
+        </div>
+        <div class="f-row" style="margin-top:8px">
+          <button class="f-btn${ft.cat===''?' on':''}" onclick="setF('cat','')">全品类</button>
+          <button class="f-btn${ft.cat==='龙钞'?' on':''}" onclick="setF('cat','龙钞')">龙钞</button>
+          <button class="f-btn${ft.cat==='蛇钞'?' on':''}" onclick="setF('cat','蛇钞')">蛇钞</button>
+          <button class="f-btn${ft.cat==='马钞'?' on':''}" onclick="setF('cat','马钞')">马钞</button>
+          <button class="f-btn${ft.cat==='其他'?' on':''}" onclick="setF('cat','其他')">其他</button>
+        </div>
+      </div>
+      <div class="list">
+        ${S.loading?'<div class="loading">加载中...</div>':''}
+        ${!S.loading&&S.posts.length===0?'<div class="empty">暂无数据</div>':''}
+        ${!S.loading&&S.posts.length>0?S.posts.map(p=>`
+          <div class="post" onclick="showDetail(${p.id})">
+            <div class="post-title">${p.title||'无标题'}</div>
+            <div class="post-meta">
+              <span class="badge b-${p.post_type||'normal'}">${p.post_type==='deal'?'出售':p.post_type==='want'?'求购':'普通'}</span>
+              ${p.has_lifebuoy?'<span class="badge b-lifebuoy">🔥大救生圈</span>':''}
+              ${p.price?'<span class="price">'+p.price+'元</span>':''}
+              ${p.category?'<span class="tm">'+p.category+'</span>':''}
+              ${p.author_username?'<span class="author">'+p.author_username+'</span>':''}
+              <span class="tm">${fmtTime(p.post_time)}</span>
+              ${p.instance_id?'<span class="tm">🖥️'+p.instance_id.replace('server_','S')+'</span>':''}
+            </div>
+          </div>
+        `).join(''):''}
+        ${!S.loading&&S.posts.length>0?`
+          <div class="pager">
+            <button class="pg-btn"${S.pg<=1?' disabled':''} onclick="prevP()">上一页</button>
+            <span class="pg-info">${S.pg} / ${Math.max(1,Math.ceil(S.total/S.ps))} (共${S.total}条)</span>
+            <button class="pg-btn"${S.pg>=Math.ceil(S.total/S.ps)?' disabled':''} onclick="nextP()">下一页</button>
+          </div>
+        `:''}
+      </div>
+      <div class="tab">
+        <div class="tab-i" onclick="S.v='home';render()"><span>📊</span>首页</div>
+        <div class="tab-i on" onclick="goList('')"><span>📋</span>帖子</div>
+        <div class="tab-i" onclick="goCollections()"><span>💎</span>藏品</div>
+        <div class="tab-i" onclick="goUsers()"><span>👤</span>用户</div>
+        <div class="tab-i" onclick="S.v='stats';loadStats()"><span>📈</span>统计</div>
+      </div>
+    `
+  }
+
+  if (S.v === 'collection-detail' && S.curCollection) {
+    const c = S.curCollection
+    app.innerHTML = `
+      <div class="detail">
+        <div class="detail-hdr">
+          <button class="back" onclick="S.v='collections';render()">← 返回藏品</button>
+          <a class="detail-link" href="${c.post_url||'#'}" target="_blank">原文链接</a>
+        </div>
+        <div class="detail-body">
+          <div class="detail-title">${c.name || c.crown_code || '无名称'}</div>
+
+          <div class="sec">
+            <div class="sec-title">🏷️ 藏品信息</div>
+            <div class="info-g">
+              <div class="info-i"><span class="info-l">品类</span><span class="${c.category==='龙钞'?'green':c.category==='马钞'?'orange':c.category==='蛇钞'?'purple':'gray'}">${c.category||'其他'}</span></div>
+              <div class="info-i"><span class="info-l">系列</span><span class="info-v">${c.series||'-'}</span></div>
+              <div class="info-i"><span class="info-l">发行年份</span><span class="info-v">${c.issue_year||'-'}</span></div>
+              <div class="info-i"><span class="info-l">冠号</span><span class="info-v" style="font-size:16px;font-weight:600;color:#1976d2">${c.crown_code||'-'}</span></div>
+            </div>
+          </div>
+
+          <div class="sec">
+            <div class="sec-title">📝 描述</div>
+            <div class="content">${c.description||'暂无描述'}</div>
+          </div>
+
+          <div class="sec">
+            <div class="sec-title">🔗 关联信息</div>
+            <div class="info-g">
+              <div class="info-i"><span class="info-l">帖子ID</span><span class="info-v">${c.post_id||'-'}</span></div>
+              <div class="info-i"><span class="info-l">藏品ID</span><span class="info-v">${c.id||'-'}</span></div>
+              <div class="info-i"><span class="info-l">创建时间</span><span class="info-v">${c.created_at?new Date(c.created_at).toLocaleString('zh-CN'):'-'}</span></div>
+              <div class="info-i"><span class="info-l">更新时间</span><span class="info-v">${c.updated_at?new Date(c.updated_at).toLocaleString('zh-CN'):'-'}</span></div>
+              <div class="info-i"><span class="info-l">采集服务器</span><span class="info-v">${c.instance_id||'-'}</span></div>
+            </div>
+          </div>
+
+          <div style="margin-top:20px">
+            <button onclick="goCollectionPost('${c.post_id}')" style="width:100%;padding:12px;background:#1976d2;color:#fff;border:none;border-radius:8px;font-size:15px;cursor:pointer">查看关联帖子 →</button>
+          </div>
+        </div>
+      </div>
+    `
+  }
+
+  if (S.v === 'detail' && S.cur) {
+    const p = S.cur
+    app.innerHTML = `
+      <div class="detail">
+        <div class="detail-hdr">
+          <button class="back" onclick="S.v='list';render()">← 返回</button>
+          <a class="detail-link" href="${p.url||'#'}" target="_blank">原文链接</a>
+        </div>
+        <div class="detail-body">
+          <div class="detail-title">${p.title||'无标题'}</div>
+
+          <div class="sec">
+            <div class="sec-title">💰 价格信息</div>
+            <div class="info-g">
+              <div class="info-i">
+                <span class="info-l">价格</span>
+                <span class="info-v prime">${p.price?p.price+'元':'-'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">品类</span>
+                <span class="info-v">${p.category||'-'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">包装</span>
+                <span class="info-v">${p.special_types||'-'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">号码</span>
+                <span class="info-v">${p.number_features||'-'}</span>
+              </div>
+            </div>
+          </div>
+
+
+          ${p.special_types?`
+          <div class="sec">
+            <div class="sec-title">📦 包装分类</div>
+            <div class="tag-l">
+              ${p.special_types.split(/[,\/|]/).map(s=>`<span class="tag">${s.trim()}</span>`).join('')}
+            </div>
+          </div>
+          `:''}
+
+          ${p.number_features?`
+          <div class="sec">
+            <div class="sec-title">🔢 号码分类</div>
+            <div class="tag-l">
+              ${p.number_features.split(/[,\/|]/).map(s=>`<span class="tag">${s.trim()}</span>`).join('')}
+            </div>
+          </div>
+          `:''}
+
+          ${p.special_tags?`
+          <div class="sec">
+            <div class="sec-title">🏷️ 特殊标识</div>
+            <div class="tag-l">
+              ${p.special_tags.split(/[,\/|]/).map(s=>`<span class="tag">${s.trim()}</span>`).join('')}
+            </div>
+          </div>
+          `:''}
+
+          <div class="sec">
+            <div class="sec-title">👤 作者信息</div>
+            <div class="info-g">
+              <div class="info-i">
+                <span class="info-l">用户名</span>
+                <span class="info-v" style="color:#1976d2">${p.author_username||'-'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">联系方式</span>
+                <span class="info-v">${p.contact||'-'}</span>
+              </div>
+            </div>
+          </div>
+
+          <div class="sec">
+            <div class="sec-title">📊 帖子状态</div>
+            <div class="info-g">
+              <div class="info-i">
+                <span class="info-l">类型</span>
+                <span class="badge b-${p.post_type||'normal'}">${p.post_type==='deal'?'出售':p.post_type==='want'?'求购':'普通'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">大救生圈</span>
+                <span class="info-v">${p.has_lifebuoy?'🔥 是':'否'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">发帖时间</span>
+                <span class="info-v">${p.post_time?new Date(p.post_time).toLocaleString('zh-CN'):'-'}</span>
+              </div>
+              <div class="info-i">
+                <span class="info-l">回复数</span>
+                <span class="info-v">${p.reply_count||0}</span>
+              </div>
+              ${p.instance_id?'<div class="info-i"><span class="info-l">来源</span><span class="info-v">🖥️ '+p.instance_id.replace('server_','服务器')+'</span></div>':''}
+            </div>
+          </div>
+
+          <div class="sec">
+            <div class="sec-title">📝 帖子内容</div>
+            <div class="content">${p.content||'暂无内容'}</div>
+          </div>
+        </div>
+      </div>
+    `
+  }
+}
+
+function goCollections() {
+  console.log('goCollections clicked')
+  S.v = 'collections'
+  loadCollections()
+}
+function goUsers() {
+  console.log('goUsers clicked')
+  S.v = 'users'
+  loadUsers()
+}
+async function loadCollections() {
+  console.log('loadCollections called, current S.v=', S.v)
+  try {
+    const res = await fetch('/api/v1/collections?page=1&page_size=100')
+    const json = await res.json()
+    console.log('collections API response code:', json.code, 'items:', (json.data&&json.data.items||[]).length)
+    if (json.code === 0) {
+      S.collections = json.data.items || []
+      render()
+    }
+  } catch(e) { console.error('loadCollections error:', e.message) }
+}
+async function loadUsers() {
+  console.log('loadUsers called, current S.v=', S.v)
+  try {
+    const res = await fetch('/api/v1/users?page=1&page_size=100')
+    const json = await res.json()
+    console.log('users API response code:', json.code, 'items:', (json.data&&json.data.items||[]).length)
+    if (json.code === 0) {
+      S.users = json.data.items || []
+      render()
+    }
+  } catch(e) { console.error('loadUsers error:', e.message) }
+}
+function showCollectionDetail(c) {
+  alert(['名称: '+(c.name||'-'), '品类: '+(c.category||'-'), '系列: '+(c.series||'-'),
+    '年份: '+(c.issue_year||'-'), '冠号: '+(c.crown_code||'-'), '描述: '+(c.description||'-')].join('\n'))
+}
+
+async function goCollectionDetail(collectionId) {
+  try {
+    const res = await fetch('/api/v1/collections/'+collectionId)
+    const json = await res.json()
+    if (json.code === 0) {
+      S.curCollection = json.data
+      S.v = 'collection-detail'
+      render()
+    } else {
+      alert('藏品不存在')
+    }
+  } catch(e) { alert('加载失败: '+e.message) }
+}
+
+async function goCollectionPost(postId) {
+  try {
+    const res = await fetch('/api/v1/yichens/posts/'+encodeURIComponent(postId))
+    const json = await res.json()
+    if (json.code === 0) {
+      S.cur = json.data
+      S.v = 'detail'
+      render()
+    } else {
+      alert('帖子不存在或已删除')
+    }
+  } catch(e) { alert('加载失败: '+e.message) }
+}
+
+async function loadStats() {
+  try {
+    const r = await fetch(API+'/yichens/statistics')
+    const d = await r.json()
+    if (d.code === 0) { S.stats = d.data }
+    const r2 = await fetch(API+'/yichens/report/categories')
+    const d2 = await r2.json()
+    if (d2.code === 0) { S.catReport = d2.data }
+    const r3 = await fetch(API+'/yichens/report/stats')
+    const d3 = await r3.json()
+    if (d3.code === 0) { S.statsData = d3.data }
+    render()
+  } catch(e) { console.error(e) }
+}
+
+async function loadPosts() {
+  S.loading = true; render()
+  try {
+    let url = API+'/yichens/posts?page='+S.pg+'&page_size='+S.ps
+    if (S.ft.type) url += '&post_type='+S.ft.type
+    if (S.ft.cat) url += '&category='+S.ft.cat
+    if (S.ft.lifebuoy === 'yes') url += '&has_lifebuoy=true'
+    if (S.ft.timeRange) url += '&time_range='+S.ft.timeRange
+    if (S.ft.statType) { S.loading = false; loadStatPosts(); return }
+    const r = await fetch(url)
+    const d = await r.json()
+    if (d.code === 0) { S.posts = d.data.items||[]; S.total = d.data.total||0 }
+  } catch(e) { console.error(e) }
+  S.loading = false; render()
+}
+
+function goList(type, timeRange, cat) {
+  S.ft = { type: '', cat: '', lifebuoy: '', timeRange: '' }
+  if (type === 'lifebuoy') S.ft.lifebuoy = 'yes'
+  else if (type) S.ft.type = type
+  if (timeRange) S.ft.timeRange = timeRange
+  if (cat) S.ft.cat = cat
+  S.pg = 1; S.v = 'list'; loadPosts()
+  S.collections = []; S.users = []; S.colCat = ''; S.colSearch = ''; S.userSearch = ''
+}
+
+function goStatPosts(statType) {
+  S.ft = { type: '', cat: '', lifebuoy: '', timeRange: '', statType: statType }
+  S.pg = 1; S.v = 'list'; loadStatPosts()
+}
+
+async function loadStatPosts() {
+  if (!S.ft.statType) return
+  S.loading = true; render()
+  try {
+    let url = API+'/yichens/report/posts?stat_type='+S.ft.statType+'&page='+S.pg+'&page_size='+S.ps
+    const r = await fetch(url)
+    const d = await r.json()
+    if (d.code === 0) { S.posts = d.data.items||[]; S.total = d.data.total||0 }
+  } catch(e) { console.error(e) }
+  S.loading = false; render()
+}
+
+function setF(key, val) {
+  if (key === 'type') { S.ft.type = val; S.ft.timeRange = '' }
+  if (key === 'cat') { S.ft.cat = val; S.ft.timeRange = '' }
+  S.pg = 1; loadPosts()
+}
+
+function showDetail(id) {
+  S.cur = S.posts.find(p => p.id === id)
+  S.v = 'detail'; render()
+}
+
+function prevP() { if (S.pg > 1) { S.pg--; loadPosts(); window.scrollTo(0,0) } }
+function nextP() { S.pg++; loadPosts(); window.scrollTo(0,0) }
+
+function fmtTime(ts) {
+  if (!ts) return '-'
+  const d = new Date(ts), n = new Date()
+  const diff = n - d
+  if (diff < 60000) return '刚刚'
+  if (diff < 3600000) return Math.floor(diff/60000)+'分钟前'
+  if (diff < 86400000) return Math.floor(diff/3600000)+'小时前'
+  if (diff < 604800000) return Math.floor(diff/86400000)+'天前'
+  return d.toLocaleDateString('zh-CN')
+}
+
+// init
+loadStats()
+</script>
+</body>
+</html>
--- a/scripts/crawl_cron_s1.sh
+++ b/scripts/crawl_cron_s1.sh
@ -0,0 +1,27 @@
+#!/bin/bash
+cd /root/coolbot-data
+source venv/bin/activate
+export CRAWLER_INSTANCE_ID=server_1
+python3 -u -c "
+import sys, os
+sys.path.insert(0, '/root/coolbot-data')
+os.environ['DB_HOST'] = 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com'
+os.environ['DB_PORT'] = '5432'
+os.environ['DB_USER'] = 'coolbot'
+os.environ['DB_PASSWORD'] = 'Coolbot123'
+os.environ['DB_NAME'] = 'coolbot_data'
+os.environ['CRAWLER_INSTANCE_ID'] = 'server_1'
+from crawlers.crawl_today import YichensTodaySpider
+spider = YichensTodaySpider()
+spider.max_pages = 2
+spider.min_delay = 0.2
+spider.max_delay = 0.5
+log_id = spider._log_start()
+try:
+    result = spider.crawl_today()
+    spider._log_finish(log_id, 'success', result)
+    print('[server_1] 采集完成: ' + str(result) + ' 条', flush=True)
+except Exception as e:
+    spider._log_finish(log_id, 'failed', 0, str(e))
+    raise
+"
--- a/scripts/crawl_cron_s2.sh
+++ b/scripts/crawl_cron_s2.sh
@ -0,0 +1,21 @@
+#!/bin/bash
+cd /root/coolbot-data
+source venv/bin/activate
+export CRAWLER_INSTANCE_ID=server_2
+python3 -u -c "
+import sys, os
+sys.path.insert(0, '/root/coolbot-data')
+os.environ['DB_HOST'] = 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com'
+os.environ['DB_PORT'] = '5432'
+os.environ['DB_USER'] = 'coolbot'
+os.environ['DB_PASSWORD'] = 'Coolbot123'
+os.environ['DB_NAME'] = 'coolbot_data'
+os.environ['CRAWLER_INSTANCE_ID'] = 'server_2'
+from crawlers.crawl_today import YichensTodaySpider
+spider = YichensTodaySpider()
+spider.max_pages = 2
+spider.min_delay = 0.2
+spider.max_delay = 0.5
+result = spider.crawl_today()
+print('[server_2] 采集完成: ' + str(result) + ' 条', flush=True)
+"
--- a/scripts/crawl_cron_s3.sh
+++ b/scripts/crawl_cron_s3.sh
@ -0,0 +1,29 @@
+#!/bin/bash
+cd /root/coolbot-data
+export PYTHONPATH=/usr/lib64/python3.6/site-packages:$PYTHONPATH
+export CRAWLER_INSTANCE_ID=server_3
+python3 -u -c "
+import sys
+sys.path.insert(0, '/usr/lib64/python3.6/site-packages')
+sys.path.insert(0, '/root/coolbot-data')
+import os
+os.environ['DB_HOST'] = 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com'
+os.environ['DB_PORT'] = '5432'
+os.environ['DB_USER'] = 'coolbot'
+os.environ['DB_PASSWORD'] = 'Coolbot123'
+os.environ['DB_NAME'] = 'coolbot_data'
+os.environ['CRAWLER_INSTANCE_ID'] = 'server_3'
+from crawlers.crawl_today import YichensTodaySpider
+spider = YichensTodaySpider()
+spider.max_pages = 2
+spider.min_delay = 0.2
+spider.max_delay = 0.5
+log_id = spider._log_start()
+try:
+    result = spider.crawl_today()
+    spider._log_finish(log_id, 'success', result)
+    print('[server_3] 采集完成: ' + str(result) + '条', flush=True)
+except Exception as e:
+    spider._log_finish(log_id, 'failed', 0, str(e))
+    raise
+"
--- a/scripts/crawler_monitor.py
+++ b/scripts/crawler_monitor.py
@ -0,0 +1,140 @@
+#!/usr/bin/env python3
+"""
+Crawler 健康监控 - 检查所有服务器爬虫是否正常运行
+每10分钟运行一次，检查最近30分钟内各实例是否有记录
+"""
+import sys
+import os
+sys.path.insert(0, '/root/coolbot-data')
+
+import psycopg2
+import requests
+from datetime import datetime, timedelta
+
+# ========== 配置 ==========
+# 各服务器实例ID（对应crawl_logs.instance_id）
+INSTANCES = {
+    'server_1': '1号服务器-每00/30分',
+    'server_2': '2号服务器-每10/40分',
+    'server_3': '3号服务器-每20/50分',
+}
+
+DB_CONFIG = {
+    'host': os.environ.get('DB_HOST', 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com'),
+    'port': int(os.environ.get('DB_PORT', 5432)),
+    'database': os.environ.get('DB_NAME', 'coolbot_data'),
+    'user': os.environ.get('DB_USER', 'coolbot'),
+    'password': os.environ.get('DB_PASSWORD', 'Coolbot123'),
+}
+
+# 飞书 Webhook
+FEISHU_WEBHOOK = os.environ.get('FEISHU_WEBHOOK_URL', '')
+FEISHU_SECRET = os.environ.get('FEISHU_APP_SECRET', '')
+
+# 检查时间窗口（分钟）
+WINDOW_MINUTES = 35  # 宽松5分钟容错
+
+# ==========================
+
+def get_db():
+    return psycopg2.connect(**DB_CONFIG)
+
+def check_instance_status(conn, instance_id):
+    """检查某实例最近是否在窗口内运行过"""
+    cur = conn.cursor()
+    cur.execute("""
+        SELECT COUNT(*), MAX(finished_at) 
+        FROM crawl_logs 
+        WHERE instance_id = %s 
+          AND finished_at >= NOW() - INTERVAL '%s minutes'
+          AND status = 'success'
+    """, (instance_id, WINDOW_MINUTES))
+    r = cur.fetchone()
+    cur.close()
+    return {'count': r[0], 'last_run': r[1]}
+
+def send_feishu_alert(message):
+    """发送飞书告警"""
+    if not FEISHU_WEBHOOK:
+        print("⚠️ 未配置飞书Webhook，跳过告警")
+        return
+    
+    now = datetime.now().strftime('%H:%M')
+    card = {
+        "msg_type": "interactive",
+        "card": {
+            "header": {
+                "title": {"tag": "plain_text", "content": f"⚠️ 爬虫监控告警 {now}"},
+                "template": "red"
+            },
+            "elements": [
+                {"tag": "div", "text": {"tag": "lark_md", "content": message}}
+            ]
+        }
+    }
+    try:
+        r = requests.post(FEISHU_WEBHOOK, json=card, timeout=10)
+        print(f"飞书告警响应: {r.status_code}")
+    except Exception as e:
+        print(f"飞书发送失败: {e}")
+
+def send_feishu_healthy():
+    """发送健康状态（仅关键时段发送，避免骚扰）"""
+    hour = datetime.now().hour
+    if hour not in [8, 9, 17, 18, 19]:  # 只在工作时段发送
+        return
+    
+    if not FEISHU_WEBHOOK:
+        return
+    
+    card = {
+        "msg_type": "interactive",
+        "card": {
+            "header": {
+                "title": {"tag": "plain_text", "content": f"✅ 爬虫监控正常 {datetime.now().strftime('%H:%M')}"},
+                "template": "green"
+            },
+            "elements": [
+                {"tag": "div", "text": {"tag": "lark_md", "content": "所有服务器爬虫运行正常"}}
+            ]
+        }
+    }
+    try:
+        requests.post(FEISHU_WEBHOOK, json=card, timeout=10)
+    except:
+        pass
+
+def main():
+    print(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] 爬虫健康检查...")
+    
+    conn = get_db()
+    
+    all_ok = True
+    details = []
+    
+    for instance_id, name in INSTANCES.items():
+        status = check_instance_status(conn, instance_id)
+        last_run_str = status['last_run'].strftime('%H:%M') if status['last_run'] else '从未运行'
+        
+        if status['count'] > 0:
+            details.append(f"✅ {name}: 最近 {last_run_str} (共{status['count']}次)")
+        else:
+            details.append(f"❌ {name}: ⚠️ 超过{WINDOW_MINUTES}分钟无记录！")
+            all_ok = False
+    
+    conn.close()
+    
+    print('\n'.join(details))
+    
+    if all_ok:
+        print("✅ 所有服务器正常")
+        send_feishu_healthy()
+    else:
+        msg = "**爬虫告警：部分服务器超过30分钟无爬取记录**\n\n" + '\n'.join(details)
+        print(f"\n❌ 告警: {msg}")
+        send_feishu_alert(msg)
+    
+    return 0 if all_ok else 1
+
+if __name__ == '__main__':
+    sys.exit(main())
--- a/scripts/crown_extract.py
+++ b/scripts/crown_extract.py
@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+"""
+冠字号提取脚本 - 最终版
+规则：只提取J0开头的冠字号（J0+8位或J0+9位）
+"""
+import sys
+sys.path.insert(0, '/root/coolbot-data')
+
+import re
+import psycopg2
+from datetime import datetime
+
+DB_CONFIG = {
+    'host': 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com',
+    'port': 5432,
+    'database': 'coolbot_data',
+    'user': 'coolbot',
+    'password': 'Coolbot123'
+}
+
+FEATURE_KEYWORDS = [
+    '无47', '无34', '无347', '无4', '无3', '无2',
+    '标十', '标百', '标九', '标准十', '标准百',
+    '首日', '生日', '金马', '银马',
+    '金钩', '倒置', '满号', '圆圆',
+    '豹子', '顺子', '恐龙', '天龙',
+    'PMG', '爱藏', '尾号',
+    '大象', '麒麟', '老虎', '狮子',
+    '金马王', '天马', '龙马精神',
+    '连号', '散号', '一刀', '龙凤', '熊猫',
+]
+
+def extract_codes(text):
+    """只提取J0开头的冠字号：J0+8位或J0+9位"""
+    if not text:
+        return set()
+    codes = set()
+    for p in [r'J0\d{8}', r'J0\d{9}']:
+        for c in re.findall(p, text):
+            # J0+8位: 总长10, J0+9位: 总长11
+            if len(c) in (10, 11):
+                codes.add(c)
+    return codes
+
+def extract_features(text):
+    if not text:
+        return None
+    feat = [kw for kw in FEATURE_KEYWORDS if kw in text]
+    return '|'.join(feat) if feat else None
+
+def extract_price(text):
+    if not text:
+        return None, '元'
+    prices = []
+    for p in [r'(\d+(?:\.\d+)?)\s*元', r'(\d+(?:\.\d+)?)\s*/\s*[张件组百]']:
+        for x in re.findall(p, text):
+            try:
+                v = float(x)
+                if 1 <= v < 100000:
+                    prices.append(v)
+            except:
+                pass
+    return (min(prices), '元') if prices else (None, '元')
+
+def get_category(title):
+    if not title:
+        return '其他'
+    for kw in ['龙', '龙钞', '小龙钞', '钞王']:
+        if kw in title:
+            return '龙钞'
+    for kw in ['马', '马钞']:
+        if kw in title:
+            return '马钞'
+    for kw in ['蛇', '蛇钞']:
+        if kw in title:
+            return '蛇钞'
+    return '其他'
+
+def main():
+    print(f'[{datetime.now()}] 冠字号提取开始（仅J0冠字号）...')
+
+    conn = psycopg2.connect(**DB_CONFIG)
+    cur = conn.cursor()
+
+    # 清空旧数据
+    cur.execute('DELETE FROM collections WHERE crown_code IS NOT NULL')
+    conn.commit()
+    print(f'清空旧数据完成')
+
+    BATCH = 100
+    offset = 0
+    total_new = 0
+
+    while True:
+        cur.execute(f'''
+            SELECT id, post_id, title, content, post_type,
+                   author_username, price, price_unit, url, crawled_at
+            FROM yichens_posts
+            ORDER BY id
+            LIMIT {BATCH} OFFSET {offset}
+        ''')
+        posts = cur.fetchall()
+        if not posts:
+            break
+
+        for (pid, post_id, title, content, post_type,
+             author, price, price_unit, url, crawled_at) in posts:
+
+            text = f'{title or ""} {content or ""}'
+            codes = extract_codes(text)
+            if not codes:
+                offset += 1
+                continue
+
+            features = extract_features(text)
+            price_val, _ = extract_price(text)
+            price_val = price_val if price_val else price
+            category = get_category(title)
+
+            for code in codes:
+                try:
+                    cur.execute('''
+                        INSERT INTO collections (
+                            name, crown_code, category, post_id, post_url,
+                            author, price, price_unit,
+                            number_feature, post_title, post_type,
+                            post_crawled_at, created_at, updated_at
+                        ) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,NOW(),NOW())
+                    ''', (
+                        code, code, category, str(post_id), url,
+                        author, price_val, price_unit or '元',
+                        features, title, post_type,
+                        crawled_at
+                    ))
+                    total_new += 1
+                except Exception as e:
+                    pass
+
+        conn.commit()
+        offset += len(posts)
+        print(f'  已处理 {offset} 条，新增 {total_new} 条')
+
+    print(f'\n完成！总计新增: {total_new} 条')
+    conn.close()
+
+if __name__ == '__main__':
+    main()
--- a/scripts/crown_extract_incremental.py
+++ b/scripts/crown_extract_incremental.py
@ -0,0 +1,187 @@
+#!/usr/bin/env python3
+"""
+冠字号全量提取脚本 - 跑完所有待处理帖子
+"""
+import sys
+sys.path.insert(0, '/root/coolbot-data')
+
+import re, psycopg2
+from datetime import datetime
+
+DB_CONFIG = {
+    'host': 'pgm-bp1t1008h019ez6c.pg.rds.aliyuncs.com',
+    'port': 5432,
+    'database': 'coolbot_data',
+    'user': 'coolbot',
+    'password': 'Coolbot123'
+}
+
+FEATURE_KEYWORDS = [
+    '无47', '无34', '无347', '无4', '无3', '无2',
+    '标十', '标百', '标九', '标准十', '标准百',
+    '首日', '生日', '金马', '银马',
+    '金钩', '倒置', '满号', '圆圆',
+    '豹子', '顺子', '恐龙', '天龙',
+    'PMG', '爱藏', '尾号',
+    '大象', '麒麟', '老虎', '狮子',
+    '金马王', '天马', '龙马精神',
+    '连号', '散号', '一刀', '龙凤', '熊猫',
+]
+
+def is_date_code(code):
+    if len(code) != 8:
+        return False
+    try:
+        year = int(code[:4])
+        month = int(code[4:6])
+        day = int(code[6:8])
+        if 2000 <= year <= 2030 and 1 <= month <= 12 and 1 <= day <= 31:
+            return True
+    except:
+        pass
+    return False
+
+def is_phone(code):
+    return len(code) == 11 and code.startswith('1')
+
+def is_valid_crown(code):
+    if not code:
+        return False
+    if code.startswith('J0'):
+        return len(code) in (10, 11)
+    if len(code) not in (8, 9):
+        return False
+    if is_phone(code):
+        return False
+    if len(code) == 8 and is_date_code(code):
+        return False
+    return True
+
+def extract_codes(text):
+    if not text:
+        return set()
+    codes = set()
+    for p in [r'J0\d{8}', r'J0\d{9}']:
+        codes.update(re.findall(p, text))
+    for c in re.findall(r'\b\d{8}\b', text):
+        if is_valid_crown(c):
+            codes.add(c)
+    for c in re.findall(r'\b\d{9}\b', text):
+        if is_valid_crown(c):
+            codes.add(c)
+    return codes
+
+def extract_features(text):
+    if not text:
+        return None
+    feat = [kw for kw in FEATURE_KEYWORDS if kw in text]
+    return '|'.join(feat) if feat else None
+
+def extract_price(text):
+    if not text:
+        return None, '元'
+    prices = []
+    for p in [r'(\d+(?:\.\d+)?)\s*元', r'(\d+(?:\.\d+)?)\s*/\s*[张件组百]']:
+        for x in re.findall(p, text):
+            try:
+                v = float(x)
+                if 1 <= v < 100000:
+                    prices.append(v)
+            except:
+                pass
+    return (min(prices), '元') if prices else (None, '元')
+
+def get_category(title):
+    if not title:
+        return '其他'
+    for kw in ['龙', '龙钞', '小龙钞', '钞王']:
+        if kw in title:
+            return '龙钞'
+    for kw in ['马', '马钞']:
+        if kw in title:
+            return '马钞'
+    for kw in ['蛇', '蛇钞']:
+        if kw in title:
+            return '蛇钞'
+    return '其他'
+
+def main():
+    print(f'[{datetime.now()}] 冠字号全量提取开始...')
+
+    conn = psycopg2.connect(**DB_CONFIG)
+    cur = conn.cursor()
+
+    # 无 LIMIT，全量跑完所有待处理帖子
+    cur.execute("""
+        SELECT p.id, p.post_id, p.title, p.content, p.post_type,
+               p.author_username, p.price, p.price_unit, p.url, p.crawled_at
+        FROM yichens_posts p
+        WHERE p.category IN ('龙钞', '马钞', '蛇钞', '其他')
+          AND NOT EXISTS (
+              SELECT 1 FROM collections c
+              WHERE c.post_id = CAST(p.id AS TEXT)
+          )
+        ORDER BY p.id
+    """)
+    posts = cur.fetchall()
+    total = len(posts)
+    print(f'待处理新帖子: {total} 条')
+
+    new_count = 0
+    skip_count = 0
+    total_codes = 0
+    processed = 0
+
+    for (pid, post_id, title, content, post_type,
+         author, price, price_unit, url, crawled_at) in posts:
+
+        text = f'{title or ""} {content or ""}'
+        codes = extract_codes(text)
+        total_codes += len(codes)
+        processed += 1
+
+        if not codes:
+            skip_count += 1
+            if processed % 500 == 0:
+                print(f'  已处理 {processed}/{total} 条，当前新增 {new_count} 条...')
+            continue
+
+        features = extract_features(text)
+        price_val, _ = extract_price(text)
+        price_val = price_val if price_val else price
+        category = get_category(title)
+
+        for code in codes:
+            try:
+                cur.execute("""
+                    INSERT INTO collections (
+                        name, crown_code, category, post_id, post_url,
+                        author, price, price_unit,
+                        number_feature, post_title, post_type,
+                        post_crawled_at, created_at, updated_at
+                    ) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,NOW(),NOW())
+                    ON CONFLICT (post_id, crown_code) DO NOTHING
+                """, (
+                    code, code, category, str(post_id), url,
+                    author, price_val, price_unit or '元',
+                    features, title, post_type,
+                    crawled_at
+                ))
+                if cur.rowcount > 0:
+                    new_count += 1
+            except Exception as e:
+                print(f'  插入失败 post_id={post_id}, code={code}: {e}')
+
+        if processed % 500 == 0:
+            print(f'  已处理 {processed}/{total} 条，当前新增 {new_count} 条...')
+            conn.commit()
+
+    conn.commit()
+    print(f'完成！新增: {new_count} 条, 总冠号: {total_codes}, 无冠号跳过: {skip_count} 条, 总处理: {total} 条')
+
+    cur.execute('SELECT COUNT(*) FROM collections')
+    print(f'collections表当前总量: {cur.fetchone()[0]} 条')
+    conn.close()
+
+if __name__ == '__main__':
+    main()
Author	SHA1	Message	Date
caibotmini	be0bc603b7	fix: 帖子时间解析过滤2053等异常年份，使用crawled_at兜底	2026-04-09 23:22:55 +08:00
caibotmini	c20a2f50ce	feat: 增量脚本去掉LIMIT - 每次跑完所有待处理帖子	2026-04-07 19:43:16 +08:00
caibotmini	25129bfc07	fix: 修复增量提取NOT IN子查询bug - 改用NOT EXISTS避免类型转换问题	2026-04-07 19:33:58 +08:00
caibotmini	b9554562de	feat: 新增冠字号增量提取脚本 - 每天3点/11点/16点增量同步藏品数据 - 只提取新帖子的冠字号，INSERT ... ON CONFLICT DO NOTHING - 删掉原来的 DELETE + 全量 INSERT 逻辑 - 加唯一索引 idx_collections_post_crown (post_id, crown_code)	2026-04-07 15:30:07 +08:00
caibotmini	8a100a9a95	fix: 修复帖子内容解析 - 清理网站免责声明和底部导航 - 修复免责声明空格匹配问题 - 增加 BoardJumpListSelect/Powered By Dvbbs/京ICP备等底部清理 - 清理历史污染数据10条	2026-04-07 14:38:25 +08:00
caibotmini	35d238555f	feat: 新增藏品和用户Tab - 新增 💎藏品和 👤用户两个Tab - 藏品列表：按品类筛选+名称/冠号搜索，点击进入详情 - 藏品详情：品类/系列/年份/冠号/描述/关联信息 - 藏品详情可跳转关联帖子 - 用户列表：用户名搜索，展示商家/个人/发帖数/信用分 - 修复 page_size 上限500导致422错误 - 帖子列表增加服务器来源标识 - 修复 ON CONFLICT 时 instance_id 被覆盖问题	2026-04-07 12:24:00 +08:00
caibotmini	52ece4f412	docs: 添加2号3号服务器运维手册	2026-04-07 09:19:42 +08:00
caibotmini	b0bb3372fa	fix: 修复 save_full_post SQL 参数不匹配问题 - save_full_post 使用 psycopg2.sql 模块构建动态 SQL - 修正 INSERT/ON CONFLICT UPDATE 缺失字段(number_features/reply_count/view_count/author_id) - 修正 VALUES 占位符数量不匹配(%s vs 实际参数) - 添加 instance_id 字段追踪爬虫来源 - 更新分类逻辑: 出/售/卖>deal, 收/求/购/要>want, 确认/朋友/投诉>normal	2026-04-07 09:15:04 +08:00
caibotmini	e112b4c1e6	feat: v0.0.4 - 冠字号提取功能新增脚本：scripts/crown_extract.py - 从一尘帖子标题/内容中提取J0开头的冠字号（J0+8位/J0+9位） - 提取号码特征（标十、无47、PMG等） - 提取价格信息 - 按龙钞/马钞/蛇钞/其他自动分类 - 存入 collections 表 - 每天凌晨3点定时全量扫描提取	2026-04-07 00:05:53 +08:00
caibotmini	65162298c5	feat: v0.0.3 - 分类逻辑优化【post_type 分类优化】 - 有"出"、"售"、"卖" → 出售(deal) - 有"收"、"求"、"购"、"要" → 求购(want) - 有"确认"、"朋友"、"投诉" → 其他(normal) - else → 出售(deal) # 默认改为出售【category 分类优化】 - 优先级：龙钞 > 马钞 > 蛇钞 > 其他 - 龙钞：含"龙"、"龙钞"、"小龙钞"、"钞王" - 马钞：含"马"、"马钞" - 蛇钞：含"蛇"、"蛇钞" - 其他：以上都不是【历史数据清洗】 - 重新分类 1813 条 post_type - 重新分类全量 category 数据	2026-04-06 23:29:51 +08:00
caibotmini	1c0f74ccb6	feat: v0.0.2 - 帖子正文爬取优化 - extract_post_content 新增免责声明截断逻辑：只保留到"免责声明及风险提示：所有交易人员，凡未采用本站中介交易的，被骗后果自负。"为止 - 爬虫脚本 crawl_cron_s1/s2/s3 支持 instance_id 日志记录 - crawler_monitor.py 监控脚本：检查三台服务器爬虫运行状态 - 修复 crawl_today 日志写入 crawl_logs 表的问题	2026-04-06 16:42:43 +08:00