{
  "schemaVersion": 1,
  "id": "baidu-crawler-log-audit-2026-09-20",
  "title": "百度蜘蛛候选请求日志脱敏复核",
  "observedAt": "2026-09-20T23:45:00+08:00",
  "timezone": "Asia/Shanghai",
  "site": "https://zenleak.cn",
  "source": "ZenLeak 服务器访问日志与管理员流量记录",
  "scope": "2026-09-20 23:40:33 至 23:40:43 的连续请求样本，并附带历史对照请求",
  "records": [
    {
      "observedAt": "2026-09-20T23:40:38+08:00",
      "method": "GET",
      "path": "/.env",
      "status": 429,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "104.199.152.xxx",
      "identityStatus": "pending",
      "interpretation": "带有百度 User-Agent 的敏感文件探测请求；未通过官方身份核验。"
    },
    {
      "observedAt": "2026-09-20T23:40:38+08:00",
      "method": "GET",
      "path": "/.git/config",
      "status": 429,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "104.199.152.xxx",
      "identityStatus": "pending",
      "interpretation": "带有百度 User-Agent 的敏感文件探测请求；未通过官方身份核验。"
    },
    {
      "observedAt": "2026-09-20T23:40:39+08:00",
      "method": "GET",
      "path": "/.env.old",
      "status": 429,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "104.199.152.xxx",
      "identityStatus": "pending",
      "interpretation": "连续敏感路径探测的一部分；未通过官方身份核验。"
    },
    {
      "observedAt": "2026-09-20T23:40:41+08:00",
      "method": "GET",
      "path": "/server-status",
      "status": 429,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "104.199.152.xxx",
      "identityStatus": "pending",
      "interpretation": "连续敏感路径探测的一部分；未通过官方身份核验。"
    },
    {
      "observedAt": "2026-09-20T23:40:33+08:00",
      "method": "GET",
      "path": "/key.pem",
      "status": 404,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "104.199.152.xxx",
      "identityStatus": "pending",
      "interpretation": "敏感文件名探测；服务器未找到该路径。"
    },
    {
      "observedAt": "2026-09-19T14:08:00+08:00",
      "method": "GET",
      "path": "/content/china-ai-search-geo/",
      "status": 200,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "120.235.226.xxx",
      "identityStatus": "known-test",
      "interpretation": "与已知测试 IP 和时间吻合；属于测试记录，不作为百度真实抓取证据。"
    },
    {
      "observedAt": "2026-09-16T19:46:35+08:00",
      "method": "HEAD",
      "path": "/",
      "status": 200,
      "selfReportedSource": "百度",
      "userAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
      "ip": "61.146.178.xx",
      "identityStatus": "pending",
      "interpretation": "自报百度来源的首页 HEAD 请求；没有足够的官方核验信息。"
    }
  ],
  "sampleSummary": {
    "sequentialProbeRequests": 9,
    "sequentialProbe429": 8,
    "sequentialProbe404": 1,
    "knownTestRequests": 1,
    "identityVerifiedInThisArtifact": 0
  },
  "interpretation": [
    "User-Agent 只能作为来源分类候选，不能单独证明百度身份。",
    "HTTP 429 说明这次请求触发了限流或访问控制；它不能证明请求来自百度，也不能说明正常公开页面一定被百度拦截。",
    "敏感路径连续探测与正常内容抓取的路径形态不同，但仅凭路径也不能确定请求者身份或恶意意图。",
    "页面访问、爬虫身份、搜索收录和 AI 引用是不同事实层级。"
  ],
  "limits": [
    "IP 已脱敏，公开文件不能替代管理员后台中的完整审计记录。",
    "本文件是样本摘录，不代表服务器所有请求。",
    "历史日志部分没有 Host 字段，不能把整台服务器的全部请求无条件归属到 ZenLeak。",
    "未核验不等于恶意，已核验也不等于页面已经收录或被 AI 引用。"
  ],
  "redaction": {
    "ip": "仅保留部分地址，隐藏最后一段或最后两段",
    "fullAnswer": "完整日志仅供管理员审计，不在公开 JSON 中保存"
  }
}
