ykxmz/_build/check_lightsail.py

# -*- coding: utf-8 -*-
r'''看一眼 Lightsail 上中转服务器的完整状态。

⚠ 写这个文件的原因：用 `python -c @"..."@` 传带 `$(...)` 的远端命令，
PowerShell 会**先在本机求值** `$(systemctl ...)`（报"无法将 systemctl
项识别为 cmdlet"），还会吃掉引号导致 Python 语法错。
这个毛病我这一轮犯了四五次 —— **凡是超过两行的远端命令，一律写文件。**

用法：
    python _build/check_lightsail.py
    python _build/check_lightsail.py --fix      # 顺便修文件属主
'''
from __future__ import annotations

import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(ROOT / "_build"))
from lssh import run      # noqa: E402

PORT = "13245"
DOMAIN = "yk.xxmxxs.top"
RELAY_DIR = "/opt/ykxmz-relay"

# 三层地址各查一遍：
#   域名      —— 用户实际走的路（Cloudflare -> nginx -> 中转）
#   IP:80     —— 绕过 Cloudflare，直连 nginx（域名没配好时靠它）
#   :13245    —— **应该不通**（中转已只绑 127.0.0.1，不再对公网）
DOMAIN_URL = "http://%s" % DOMAIN
NGINX_URL = "http://<源站IP>:80"
DIRECT_URL = "http://<源站IP>:%s" % PORT

REMOTE = r'''
R=__DIR__
P=__PORT__

echo "════ 服务 ════"
for s in ykxmz-relay nginx ykxmz-monitor.timer; do
    printf '  %-22s %s\n' "$s" "$(systemctl is-active $s 2>&1)"
done

echo
echo "════ 三层地址（用户路径 / 绕 CF / 直连中转）════"
# ⚠ 一律加 -L 跟跳转：nginx 那边 http 会 301 到 https，
#   不跟跳转拿到的是 301 而不是 200，会看着像"挂了"。
printf '  %-26s %s\n' "域名 __DOMAIN__" "$(curl -sL -o /dev/null -w '%{http_code}' --max-time 12 __DOMAIN_URL__/v1/health)"
printf '  %-26s %s\n' "IP:80（nginx）" "$(curl -sL -o /dev/null -w '%{http_code}' --max-time 12 __NGINX_URL__/v1/health)"
printf '  %-26s %s\n' ":__PORT__（应 000）" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 __DIRECT_URL__/v1/health)"
printf '  %-26s %s\n' "本机 :__PORT__" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 http://127.0.0.1:$P/v1/health)"
printf '  %-26s %s\n' "域名延迟" "$(curl -sL -o /dev/null -w '%{time_total}s' --max-time 12 __DOMAIN_URL__/v1/health)"

echo
echo "════ 首页角标 ════"
echo "  域名   -> $(curl -sL --max-time 12 __DOMAIN_URL__/ | grep -o '最新版 [0-9.]*' | head -1)"
echo "  IP:80  -> $(curl -sL --max-time 12 __NGINX_URL__/ | grep -o '最新版 [0-9.]*' | head -1)"

echo
echo "════ 缓存头（决定 Cloudflare 缓不缓存）════"
printf '  %-20s %s 条\n' "下载" "$(curl -sL -I --max-time 12 __DOMAIN_URL__/download/ykxmz-setup-2.1.3.exe | grep -ci cache-control)"
curl -sL -I --max-time 12 __DOMAIN_URL__/download/ykxmz-setup-2.1.3.exe \
    | grep -i '^cache-control' | sed 's/^/    /'
printf '  %-20s %s\n' "长轮询" "$(curl -sL -I --max-time 12 __DOMAIN_URL__/v1/health | grep -i '^cache-control' | tr -d '\r')"

echo
echo "════ 监听 / 进程 ════"
ss -tlnp 2>/dev/null | grep -E ":(80|$P) " | sed 's/^/  /'
ps -eo pid,rss,etime,cmd --sort=-rss 2>/dev/null | grep 'relay\.py' | grep -v grep | head -1 | sed 's/^/  /'

echo
echo "════ 监测单元 ════"
cat $R/monitor_state.txt 2>/dev/null | sed 's/^/  /'
echo "  --- 探测的是什么地址 ---"
grep -E '^(PUBLIC_URL|FALLBACK_URL)=' $R/monitor.sh | sed 's/^/  /'
echo "  --- monitor.log 尾部（只挑非 Permission 的）---"
grep -v 'Permission denied' $R/monitor.log 2>/dev/null | tail -4 | sed 's/^/  /'

echo
echo "════ 抢救报告 / 知识库 ════"
echo "  报告 $(ls $R/rescue_reports 2>/dev/null | wc -l) 份"
echo "  知识库 $(wc -l < $R/rescue_knowledge.md 2>/dev/null || echo 0) 行"

echo
echo "════ 资源 ════"
free -m 2>/dev/null | sed -n 2p | awk '{printf "  内存 %s/%s MB\n", $3, $2}'
df -h / | tail -1 | awk '{printf "  磁盘 %s 用 %s\n", $2, $5}'
uptime | sed 's/^/  /'

echo
echo "════ 文件属主（admin 必须能写日志）════"
ls -la $R/*.log $R/monitor_state.txt 2>/dev/null | awk '{print "  " $3":"$4"  "$9}'
'''


def main() -> int:
    if "--fix" in sys.argv:
        print("  ── 修属主 ──")
        out = run("sudo chown -R admin:admin %s && sudo chmod 755 %s && echo OK"
                  % (RELAY_DIR, RELAY_DIR), timeout=120, quiet=True)
        print("  " + out[1].strip())

    cmd = (REMOTE
           .replace("__DIR__", RELAY_DIR)
           .replace("__PORT__", PORT)
           .replace("__DOMAIN__", DOMAIN)
           .replace("__DOMAIN_URL__", DOMAIN_URL)
           .replace("__NGINX_URL__", NGINX_URL)
           .replace("__DIRECT_URL__", DIRECT_URL))
    out = run(cmd, timeout=300, quiet=True)
    print(out[1] if isinstance(out, tuple) else out)
    return 0


if __name__ == "__main__":
    sys.exit(main())