{
  "schemaVersion": "1.2",
  "type": "tutorial-evidence-record",
  "language": "zh-CN",
  "generatedAt": "2026-09-24",
  "publisher": {
    "id": "https://zenleak.cn/#organization",
    "name": "ZenLeak GEO 学院",
    "editorialName": "ZenLeak 编辑部",
    "contact": "geo@allintwo.cloud"
  },
  "policies": {
    "sourceRelationship": "Page sources provide general context. Explicit claim evidence includes a source excerpt, locator, relation, review date and limits; unmapped claims do not imply one-to-one source support.",
    "rankingDisclaimer": "Inclusion in this evidence layer does not guarantee search ranking, indexing, citation, recommendation, or adoption by an AI system."
  },
  "record": {
    "id": "baidu-spider-identity",
    "title": "百度蜘蛛访问了，为什么不等于百度收录？从 User-Agent、IP、状态码到真实核验",
    "url": "https://zenleak.cn/technical/baidu-spider-identity/",
    "path": "/technical/baidu-spider-identity/",
    "evidenceUrl": "https://zenleak.cn/evidence/#baidu-spider-identity",
    "representations": {
      "json": "https://zenleak.cn/evidence/baidu-spider-identity.json",
      "markdown": "https://zenleak.cn/evidence/baidu-spider-identity.md"
    },
    "category": "技术配置",
    "contentType": "guide",
    "status": "reviewed",
    "statusLabel": "已复核",
    "datePublished": "2026-09-24",
    "dateModified": "2026-09-24",
    "reviewedAt": "2026-09-24",
    "evidenceReviewedAt": "2026-09-24",
    "claims": [
      {
        "id": "baidu-spider-identity-claim-1",
        "text": "日志中出现 Baiduspider User-Agent，只能先记为百度来源候选；User-Agent、来源 IP、访问行为和官方身份核验必须分开记录。",
        "url": "https://zenleak.cn/evidence/#baidu-spider-identity-claim-1",
        "articleUrl": "https://zenleak.cn/technical/baidu-spider-identity/#baidu-spider-identity-claim-1",
        "evidence": [
          {
            "tutorialId": "baidu-spider-identity",
            "claimText": "日志中出现 Baiduspider User-Agent，只能先记为百度来源候选；User-Agent、来源 IP、访问行为和官方身份核验必须分开记录。",
            "relation": "context",
            "sourceUrl": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
            "sourceTitle": "Google Search Central · Google crawlers overview",
            "locator": "Verify Googlebot",
            "excerpt": "Googlebot's user agent string can be spoofed by other crawlers, so you should verify that a request actually comes from Google.",
            "checkedAt": "2026-09-24",
            "limits": "官方页面直接说明 User-Agent 可被伪造并介绍 Google 的核验思路；百度的具体身份规则仍应以百度当前官方资料为准。"
          }
        ]
      },
      {
        "id": "baidu-spider-identity-claim-2",
        "text": "ZenLeak 2026 年 9 月 20 日的一组样本连续访问 .env、.git/config、server-status 和 key.pem 等路径，其中 8 条返回 429、1 条返回 404；这说明请求被限流或路径不存在，不证明百度已经抓取网站。",
        "url": "https://zenleak.cn/evidence/#baidu-spider-identity-claim-2",
        "articleUrl": "https://zenleak.cn/technical/baidu-spider-identity/#baidu-spider-identity-claim-2",
        "evidence": [
          {
            "tutorialId": "baidu-spider-identity",
            "claimText": "ZenLeak 2026 年 9 月 20 日的一组样本连续访问 .env、.git/config、server-status 和 key.pem 等路径，其中 8 条返回 429、1 条返回 404；这说明请求被限流或路径不存在，不证明百度已经抓取网站。",
            "relation": "first-party",
            "sourceUrl": "https://zenleak.cn/downloads/research/baidu-crawler-log-audit-2026-09-20.json",
            "sourceTitle": "百度蜘蛛候选请求日志脱敏复核",
            "locator": "records 与 sampleSummary 字段",
            "excerpt": "连续样本包含敏感路径探测；sequentialProbe429 为 8，sequentialProbe404 为 1，identityVerifiedInThisArtifact 为 0。",
            "checkedAt": "2026-09-24",
            "limits": "公开 JSON 是脱敏样本摘录，不代表服务器全部请求；请求身份和搜索收录仍需独立核验。"
          }
        ]
      },
      {
        "id": "baidu-spider-identity-claim-3",
        "text": "HTTP 200 只说明指定请求取得了服务器响应，HTTP 429 只说明这次请求触发了限流或访问控制；二者都不能直接推出搜索收录或 AI 引用。",
        "url": "https://zenleak.cn/evidence/#baidu-spider-identity-claim-3",
        "articleUrl": "https://zenleak.cn/technical/baidu-spider-identity/#baidu-spider-identity-claim-3",
        "evidence": [
          {
            "tutorialId": "baidu-spider-identity",
            "claimText": "HTTP 200 只说明指定请求取得了服务器响应，HTTP 429 只说明这次请求触发了限流或访问控制；二者都不能直接推出搜索收录或 AI 引用。",
            "relation": "context",
            "sourceUrl": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429",
            "sourceTitle": "MDN Web Docs · HTTP 429 Too Many Requests",
            "locator": "Status code definition",
            "excerpt": "The HTTP 429 Too Many Requests response status code indicates the user agent has sent too many requests in a given amount of time.",
            "checkedAt": "2026-09-24",
            "limits": "HTTP 429 的语义支持限流解释；页面响应和搜索索引、AI 引用属于不同系统状态，不能由状态码单独推出。"
          }
        ]
      },
      {
        "id": "baidu-spider-identity-claim-4",
        "text": "要判断真实搜索蜘蛛，应保存 Host、时间、路径、状态、IP 与 User-Agent，按平台规则做反向和正向 DNS 核验，并把已知人工测试、待核验和已核验请求分开。",
        "url": "https://zenleak.cn/evidence/#baidu-spider-identity-claim-4",
        "articleUrl": "https://zenleak.cn/technical/baidu-spider-identity/#baidu-spider-identity-claim-4",
        "evidence": [
          {
            "tutorialId": "baidu-spider-identity",
            "claimText": "要判断真实搜索蜘蛛，应保存 Host、时间、路径、状态、IP 与 User-Agent，按平台规则做反向和正向 DNS 核验，并把已知人工测试、待核验和已核验请求分开。",
            "relation": "first-party",
            "sourceUrl": "https://zenleak.cn/technical/baidu-spider-identity/",
            "sourceTitle": "百度蜘蛛访问了，为什么不等于百度收录？",
            "locator": "真实百度蜘蛛应该怎样核验、后台应该怎样保存这类数据",
            "excerpt": "文章将原始字段、平台规则、反向 DNS、正向确认、请求行为和核验时间列为可复测步骤。",
            "checkedAt": "2026-09-24",
            "limits": "这是 ZenLeak 的日志审计与编辑记录方法；具体百度身份核验仍需遵循百度当前官方规则，不能用本文字段替代平台认证。"
          }
        ]
      }
    ],
    "sources": [
      {
        "label": "百度搜索资源平台 · 搜索蜘蛛相关说明",
        "url": "https://ziyuan.baidu.com/wiki/",
        "publisher": "百度搜索资源平台"
      },
      {
        "label": "普通收录",
        "url": "https://ziyuan.baidu.com/linksubmit/index",
        "publisher": "百度搜索资源平台"
      },
      {
        "label": "Google crawlers overview",
        "url": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
        "publisher": "Google Search Central"
      },
      {
        "label": "HTTP 429 Too Many Requests",
        "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429",
        "publisher": "MDN Web Docs"
      },
      {
        "label": "百度蜘蛛候选请求日志脱敏复核",
        "url": "https://zenleak.cn/downloads/research/baidu-crawler-log-audit-2026-09-20.json",
        "publisher": "ZenLeak 实验室"
      },
      {
        "label": "机器入口响应检查：4 类 User-Agent × 4 个公开路径",
        "url": "https://zenleak.cn/experiments/records/machine-entry-consistency-2026-09-17/",
        "publisher": "ZenLeak 实验室"
      }
    ],
    "prerequisites": [
      {
        "id": "ai-crawler-governance",
        "title": "AI 爬虫治理：分开管理搜索索引、答案代理与模型训练",
        "url": "https://zenleak.cn/technical/ai-crawler-governance/"
      },
      {
        "id": "crawl-render-index",
        "title": "抓取、渲染、归一与索引：页面不可见问题的完整诊断链",
        "url": "https://zenleak.cn/technical/crawl-render-index/"
      },
      {
        "id": "indexing-vs-ai-citation",
        "title": "百度已经收录，为什么 AI 仍然不引用？从抓取、索引到答案引用的完整链路",
        "url": "https://zenleak.cn/technical/indexing-vs-ai-citation/"
      }
    ],
    "related": [
      {
        "id": "ai-crawler-governance",
        "title": "AI 爬虫治理：分开管理搜索索引、答案代理与模型训练",
        "url": "https://zenleak.cn/technical/ai-crawler-governance/"
      },
      {
        "id": "crawl-render-index",
        "title": "抓取、渲染、归一与索引：页面不可见问题的完整诊断链",
        "url": "https://zenleak.cn/technical/crawl-render-index/"
      },
      {
        "id": "indexing-vs-ai-citation",
        "title": "百度已经收录，为什么 AI 仍然不引用？从抓取、索引到答案引用的完整链路",
        "url": "https://zenleak.cn/technical/indexing-vs-ai-citation/"
      },
      {
        "id": "geo-discovery-vs-citation",
        "title": "GEO 实验如何区分被发现、被收录与被 AI 引用：ZenLeak Day 3 复测记录",
        "url": "https://zenleak.cn/content/geo-discovery-vs-citation/"
      },
      {
        "id": "geo-citation-testing-before-indexed",
        "title": "搜索引擎收录很少时，如何正确做 GEO 引用测试？",
        "url": "https://zenleak.cn/content/geo-citation-testing-before-indexed/"
      }
    ]
  }
}