feat: 补 MIT 许可、自动抓取工具与学科覆盖元数据

登记 chinese-poetry / ck12 / phet，并让 source schema、lint 与 INDEX 能按学科和抓取进度消费。

Co-authored-by: Cursor <cursoragent@cursor.com>

sources/china/ceval.yaml

@@ -8,17 +8,10 @@ sources:
     license_note: "⚠️ 仅限非商业研究/教育用途，禁止商用"
     fetch_method: manual-download
     status: planned
+    subjects: [chinese, math, english, physics, chemistry, biology, history, geography, it]
+    stages: [junior]
     items: []
-  - id: phet
-    title: PhET 互动仿真（科学/数学）
-    publisher: University of Colorado Boulder
-    type: website
-    url: https://phet.colorado.edu/
-    license: cc-by
-    license_note: "CC-BY-4.0，署名即可，可商用"
-    fetch_method: manual-download
-    status: planned
-    items: []
+  # phet 已拆分至 sources/china/phet.yaml（科学/物理主力来源，含可自动下载的 items）
   - id: web-papers
     title: 第一试卷网 / 教习网等公开试卷（版权灰）
     publisher: 各第三方站点（非官方）
@@ -28,4 +21,6 @@ sources:
     license_note: "版权状态不明，集中登记、默认按最严格处理；未经核查不得进 structured/derived"
     fetch_method: manual-download
     status: planned
+    subjects: [chinese, math, english, science, morality, physics, chemistry, biology, history, geography, it]
+    stages: [primary, junior]
     items: []

sources/china/chinese-poetry.yaml

@@ -0,0 +1,152 @@
+# 语文 — 公版古诗文开源汇编
+#
+# 说明：小学/初中语文的「课文、阅读理解、作文范文」几乎全部锁在教材与教辅中（restricted，
+# 不可再分发）。语文唯一能合法规模化再分发的路径是「公版文本 + 开源汇编仓库」：
+# 文本本体已过版权保护期（进入公有领域），汇编仓库以 MIT 开源，仅要求保留许可声明。
+# 因此本 source 是语文学科的主力来源，L4 的阅读理解题/作文素材由此衍生（自有 IP，版权干净）。
+
+sources:
+  - id: chinese-poetry
+    title: chinese-poetry 最全中文诗歌古典文集数据库（37 万首）
+    publisher: chinese-poetry（GitHub 开源社区项目）
+    type: dataset
+    url: https://github.com/chinese-poetry/chinese-poetry
+    license: mit
+    license_note: >-
+      仓库 LICENSE 为 MIT（已通过 GitHub API 核实 spdx_id=MIT）。文本本体为历代公版作品，
+      已进入公有领域。再分发/商用均可，但须保留 MIT 许可声明与来源仓库署名。
+    fetch_method: git-clone
+    status: planned
+    subjects: [chinese]
+    stages: [primary, junior]
+    fetched_at: null
+    items:
+      # —— 小学/初中核心（优先下载）——
+      - id: quan-tang-shi
+        title: 全唐诗 + 全宋诗（含作者表）
+        oss_key: edu-raw/k9/chinese/chinese-poetry/quan-tang-shi.tar.gz
+        src_path: "全唐诗"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: >-
+          仓库「全唐诗/」目录，320 个文件：poet.tang.*.json（唐诗约 5.7 万首）、
+          poet.song.*.json（宋诗约 25 万首）、authors.tang.json / authors.song.json 作者表。
+          小学必背古诗与初中古诗文的主力来源。
+      - id: song-ci
+        title: 宋词（含作者表）
+        oss_key: edu-raw/k9/chinese/chinese-poetry/song-ci.tar.gz
+        src_path: "宋词"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「宋词/」目录，ci.song.*.json 约 2.1 万首 + author.song.json。
+      - id: shijing
+        title: 诗经
+        oss_key: edu-raw/k9/chinese/chinese-poetry/shijing.tar.gz
+        src_path: "诗经"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「诗经/」目录。初中文言启蒙与「关雎」「蒹葭」等课内篇目。
+      - id: lunyu
+        title: 论语
+        oss_key: edu-raw/k9/chinese/chinese-poetry/lunyu.tar.gz
+        src_path: "论语"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「论语/」目录。小学「论语十二章」及初中文言文课内篇目。
+      - id: mengxue
+        title: 蒙学（三字经/百家姓/千字文/弟子规/千家诗/古文观止/声律启蒙等）
+        oss_key: edu-raw/k9/chinese/chinese-poetry/mengxue.tar.gz
+        src_path: "蒙学"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: >-
+          仓库「蒙学/」目录，13 部：baijiaxing、dizigui、qianziwen、qianjiashi、
+          guwenguanzhi 等。小学低年级识字与国学启蒙的核心素材。
+      - id: sishu-wujing
+        title: 四书五经（大学/中庸/孟子）
+        oss_key: edu-raw/k9/chinese/chinese-poetry/sishu-wujing.tar.gz
+        src_path: "四书五经"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「四书五经/」目录：daxue.json、zhongyong.json、mengzi.json（论语见 lunyu 条目）。
+      - id: chuci
+        title: 楚辞
+        oss_key: edu-raw/k9/chinese/chinese-poetry/chuci.tar.gz
+        src_path: "楚辞"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「楚辞/」目录。初中「离骚」节选等。
+      # —— 拓展（次优先）——
+      - id: yuanqu
+        title: 元曲
+        oss_key: edu-raw/k9/chinese/chinese-poetry/yuanqu.tar.gz
+        src_path: "元曲"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「元曲/」目录。初中「天净沙·秋思」等散曲。
+      - id: wudai-shici
+        title: 五代诗词
+        oss_key: edu-raw/k9/chinese/chinese-poetry/wudai-shici.tar.gz
+        src_path: "五代诗词"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「五代诗词/」目录，含南唐二主词（李煜「虞美人」等课内篇目）。
+      - id: nalanxingde
+        title: 纳兰性德词集
+        oss_key: edu-raw/k9/chinese/chinese-poetry/nalanxingde.tar.gz
+        src_path: "纳兰性德"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「纳兰性德/」目录。初中「长相思」等。
+      - id: caocao
+        title: 曹操诗集
+        oss_key: edu-raw/k9/chinese/chinese-poetry/caocao.tar.gz
+        src_path: "曹操诗集"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「曹操诗集/」目录。初中「观沧海」「龟虽寿」。
+      - id: youmengying
+        title: 幽梦影
+        oss_key: edu-raw/k9/chinese/chinese-poetry/youmengying.tar.gz
+        src_path: "幽梦影"
+        sha256: null
+        size: null
+        media_type: application/gzip
+        fetch_date: null
+        status: planned
+        note: 仓库「幽梦影/」目录。小品文，作文素材向，非课内。
+      # 未纳入：「御定全唐詩」（繁体，与 quan-tang-shi 内容重复）、「水墨唐诗」（配图素材，
+      # 如需可后续作为 L4 图片素材单列）、rank/ strains/ loader/（项目脚本与排行，非内容数据）。

sources/china/ck12.yaml

@@ -0,0 +1,27 @@
+# 科学 / 物理 — CK-12 FlexBooks（次选，需人工导出）
+#
+# 定位：内容体系完整（美国 K-12 科学/物理电子课本），但**不可自动下载**——需网页交互
+# 或账号导出 PDF/ePub，且为英文，进 L3 前还要翻译改编。因此优先级低于 phet。
+# 只在 PhET 覆盖不到的知识点（如系统性的教材式讲解、章末习题）才考虑取用。
+
+sources:
+  - id: ck12
+    title: CK-12 FlexBooks — 科学 / 物理开放电子课本
+    publisher: CK-12 Foundation
+    type: book
+    url: https://www.ck12.org/
+    license: cc-nc-education
+    license_note: >-
+      CC BY-NC（署名-非商业）。允许改编与翻译，但**禁止商业使用**，因此 product_safe=false：
+      可用于内部教研与非商业教学，不得进入对外收费产品。取用前须逐本核实当册许可页。
+    fetch_method: manual-download
+    status: planned
+    subjects: [science, physics]
+    stages: [primary, junior]
+    fetched_at: null
+    items: []
+    # items 待人工导出后登记。候选册目（英文）：
+    #   - Middle School Physical Science / Middle School Physics（初中物理）
+    #   - Middle School Life Science / Earth Science（初中科学）
+    #   - Elementary School Science（小学科学）
+    # 导出流程：ck12.org 选册 → Download → PDF/ePub → 上传 OSS edu-raw/k9/{science|physics}/ck12/

sources/china/phet.yaml

@@ -0,0 +1,225 @@
+# 科学 / 物理 — PhET 互动仿真（可自动下载）
+#
+# 为什么是主力来源：CC-BY 4.0（署名即可商用再分发）+ 有官方简体中文版 + 单文件可直接 curl。
+# 这是科学/物理两科里**唯一既高质量又能全自动下载**的开放资源。
+#
+# 下载模板（已实测可用，2026-08-22 全部返回 200）：
+#   https://phet.colorado.edu/sims/html/{item-id}/latest/{item-id}_zh_CN.html
+# 每个仿真是一个自包含的离线 HTML5 单文件（内联全部 JS/资源），大小约 2–5 MB，
+# 下载后可直接本地/内网打开，无需联网。本 source 21 个条目合计约 70 MB。
+#
+# 注意：并非所有仿真都有 zh_CN 版本。已实测 404 的（geometric-optics-basics、
+# sound-waves、my-solar-system）未纳入；新增条目前请先 curl 探测再登记。
+
+sources:
+  - id: phet
+    title: PhET 互动仿真 — 简体中文离线单文件（科学/物理）
+    publisher: University of Colorado Boulder
+    type: tool
+    url: https://phet.colorado.edu/
+    license: cc-by
+    license_note: >-
+      CC-BY 4.0，署名即可，允许商用与再分发。对外发布须保留 "PhET Interactive Simulations,
+      University of Colorado Boulder" 署名与 CC-BY 链接。仿真为交互式工具（非题库），
+      适合嵌入课程页面作探究活动。
+    url_template: https://phet.colorado.edu/sims/html/{item_id}/latest/{item_id}_zh_CN.html
+    fetch_method: curl
+    status: fetched
+    subjects: [science, physics, chemistry]
+    stages: [primary, junior]
+    fetched_at: 2026-08-22
+    items:
+      # ===== 初中物理：力与运动 =====
+      - id: forces-and-motion-basics
+        title: 力和运动基础
+        oss_key: edu-raw/k9/physics/phet/forces-and-motion-basics_zh_CN.html
+        sha256: 2d5bb20f1243f89e0edc807461481904b61a98dee8438854563658515d800a16
+        size: 4851186
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜力的合成、摩擦、牛顿定律入门。实测约 4.8 MB。
+      - id: friction
+        title: 摩擦力
+        oss_key: edu-raw/k9/physics/phet/friction_zh_CN.html
+        sha256: abe2f1ee0de0bb614ab8e00de29f2f6e1668ada97a067e343db306030f1b1320
+        size: 2081436
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜摩擦生热的微观解释。实测约 2.1 MB。
+      - id: balancing-act
+        title: 平衡（杠杆）
+        oss_key: edu-raw/k9/physics/phet/balancing-act_zh_CN.html
+        sha256: f8a725c4242c308ba6a6450fd79a93a98a0954c8a697bee88637f68f82148c86
+        size: 3152716
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜杠杆平衡条件、力矩。实测约 3.2 MB。
+      - id: hookes-law
+        title: 胡克定律
+        oss_key: edu-raw/k9/physics/phet/hookes-law_zh_CN.html
+        sha256: 3ab65654e49500c721f6bdf7995ab48257b8b894042853731adc5d1e64361f26
+        size: 2427596
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜弹力与形变的正比关系。
+      - id: masses-and-springs-basics
+        title: 质量与弹簧（基础）
+        oss_key: edu-raw/k9/physics/phet/masses-and-springs-basics_zh_CN.html
+        sha256: e2802cc4ec2dccde90467fbbda7a47e8dbf37e4a5ce166209501aae38eb8347c
+        size: 1762060
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜弹簧测力计原理、简谐运动直观。
+      - id: projectile-motion
+        title: 抛体运动
+        oss_key: edu-raw/k9/physics/phet/projectile-motion_zh_CN.html
+        sha256: a331570b5d2a6225a26b078e25700a3098b7eb4d99a997b1ccfe04a4f7097943
+        size: 4378652
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理（拓展）｜运动的合成与分解，衔接高中。
+      - id: energy-skate-park-basics
+        title: 能量滑板公园（基础）
+        oss_key: edu-raw/k9/physics/phet/energy-skate-park-basics_zh_CN.html
+        sha256: 33704f185353838f97fde2482d970df456f6ce7c1d34fe487b0303c28c724eb7
+        size: 4912386
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜动能/势能转化与机械能守恒。实测约 4.9 MB。
+      # ===== 初中物理：压强与浮力 =====
+      - id: density
+        title: 密度
+        oss_key: edu-raw/k9/physics/phet/density_zh_CN.html
+        sha256: 1dd91f8c05a0e7839ab5e0a122755ed8808fc46fcd87bc0c08d7ead706f9ebd9
+        size: 4846707
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜密度概念与沉浮判断。实测约 4.8 MB。
+      - id: under-pressure
+        title: 压强（液体内部压强）
+        oss_key: edu-raw/k9/physics/phet/under-pressure_zh_CN.html
+        sha256: df9c145fd82f28157427e452da22f84188366960a258aac19c26fecd91106231
+        size: 1234194
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜液体压强随深度/密度变化。
+      # ===== 初中物理：电与磁 =====
+      - id: circuit-construction-kit-dc
+        title: 直流电路搭建实验
+        oss_key: edu-raw/k9/physics/phet/circuit-construction-kit-dc_zh_CN.html
+        sha256: 94efaabb68fc5a61b69a50b0b63953cb38fe5d4b801473fa3348e2833a640fe7
+        size: 3509296
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜串并联、欧姆定律、电表读数。**电学最重要的一个仿真**。实测约 3.5 MB。
+      - id: balloons-and-static-electricity
+        title: 气球与静电
+        oss_key: edu-raw/k9/physics/phet/balloons-and-static-electricity_zh_CN.html
+        sha256: fde2657d9ba242fd153a5c4b7bd26a8624a38a25249251094d45af5c870bd09c
+        size: 3539205
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜电荷转移与摩擦起电。实测约 3.5 MB。
+      - id: john-travoltage
+        title: 静电放电（John Travoltage）
+        oss_key: edu-raw/k9/physics/phet/john-travoltage_zh_CN.html
+        sha256: ceb1fb773cf93e1e42fab1784f6a72843ff02dda84d3128fac7562fbb767110b
+        size: 1918798
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜电荷积累与放电现象，趣味性强。
+      - id: faradays-law
+        title: 法拉第电磁感应定律
+        oss_key: edu-raw/k9/physics/phet/faradays-law_zh_CN.html
+        sha256: 9c3270c9e0d9485779c92400945be32b03ea6148c77b49790c96f55cabab68e8
+        size: 2227465
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理（拓展）｜磁生电，衔接发电机原理。
+      # ===== 初中物理：光与波 =====
+      - id: bending-light
+        title: 光的折射
+        oss_key: edu-raw/k9/physics/phet/bending-light_zh_CN.html
+        sha256: 7edcfa3f426b9241485e06c3e9ad132a38c9564e4e1eb2637362bf4c08c0116e
+        size: 3406402
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜反射/折射定律、色散。实测约 3.4 MB。
+      - id: wave-on-a-string
+        title: 绳上的波
+        oss_key: edu-raw/k9/physics/phet/wave-on-a-string_zh_CN.html
+        sha256: f7e197797642e04be1d7360681f65bf2df67377d60e53b22a996881801f06b8d
+        size: 2487284
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 初中物理｜波的产生与传播、频率/振幅/波速。实测约 2.5 MB。
+      - id: color-vision
+        title: 视觉与颜色
+        oss_key: edu-raw/k9/physics/phet/color-vision_zh_CN.html
+        sha256: 26466a0acb4515bbd9fda6d70495a9d713e5c6af8064f6a2e94ec6b4c868c9b8
+        size: 5772634
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学 / 初中物理｜三原色与色觉形成。
+      # ===== 小学 / 初中科学 =====
+      - id: states-of-matter-basics
+        title: 物态变化（基础）
+        oss_key: edu-raw/k9/science/phet/states-of-matter-basics_zh_CN.html
+        sha256: e0b511b18f3d19ee3be0df01c694e1eddf10003aae453ed8ff3e07e8fe5a2fe0
+        size: 1918612
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学 / 初中物理｜固液气三态与微观粒子模型。实测约 1.9 MB。
+      - id: gravity-force-lab-basics
+        title: 万有引力实验（基础）
+        oss_key: edu-raw/k9/science/phet/gravity-force-lab-basics_zh_CN.html
+        sha256: 8e302da41a15a1d2d3280082dcf61c495b01b8f606efb4afafdbec328ccab0c5
+        size: 2888393
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学 / 初中物理｜质量与距离如何影响引力。
+      - id: gravity-and-orbits
+        title: 引力与轨道
+        oss_key: edu-raw/k9/science/phet/gravity-and-orbits_zh_CN.html
+        sha256: 9c82f56dd60fe2be49036b9b2eedfa74d7fc36fac37f33148bcd82be361688fa
+        size: 3446870
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学（天文）｜日地月系统、四季与公转。
+      - id: concentration
+        title: 溶液浓度
+        oss_key: edu-raw/k9/science/phet/concentration_zh_CN.html
+        sha256: 8a8f72ee0281f6032492fe42669e5dac7cf1f9855342c0c0f67acd546a488de5
+        size: 2621430
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学 / 初中化学｜溶解、浓度、饱和。
+      - id: ph-scale-basics
+        title: pH 值（基础）
+        oss_key: edu-raw/k9/science/phet/ph-scale-basics_zh_CN.html
+        sha256: 04123b8ae4ba580533f6b784ab8eb26335e244fea71f0051a205b145644137bc
+        size: 2523039
+        media_type: text/html
+        fetch_date: 2026-08-22
+        status: fetched
+        note: 小学科学 / 初中化学｜酸碱性与常见物质 pH。

sources/china/smartedu.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "官方平台，教学使用；具体导出内容须遵守平台服务条款"
     fetch_method: manual-export
     status: planned
+    subjects: [chinese, math, english, science, morality, physics, chemistry, biology, history, geography, it]
+    stages: [primary, junior]
     items: []
   - id: tal-scq5k
     title: TAL-SCQ5K 小学应用题数据集
@@ -18,6 +20,8 @@ sources:
     license_note: "研究/教育用途，非商业（见仓库许可）"
     fetch_method: manual-download
     status: planned
+    subjects: [math]
+    stages: [primary, junior]
     items: []
   - id: ape210k
     title: Ape210K 小学应用题数据集（21万题）
@@ -28,6 +32,8 @@ sources:
     license_note: "研究/教育用途，非商业"
     fetch_method: git-clone
     status: planned
+    subjects: [math]
+    stages: [primary]
     items: []
   - id: math23k
     title: Math23K 初中数学应用题数据集
@@ -38,6 +44,8 @@ sources:
     license_note: "研究/教育用途，非商业"
     fetch_method: git-clone
     status: planned
+    subjects: [math]
+    stages: [junior]
     items: []
   - id: cmath
     title: CMATH 中文小学数学数据集
@@ -48,4 +56,6 @@ sources:
     license_note: "研究/教育用途，非商业"
     fetch_method: manual-download
     status: planned
+    subjects: [math]
+    stages: [primary]
     items: []

sources/exams/amc-past.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "AMC 真题版权归 MAA，公开传播受限；内部教研参考，禁止再分发/商用。待核查后定级"
     fetch_method: manual-download
     status: planned
+    subjects: [amc8, math]
+    stages: [primary, junior]
     items: []
   - id: ccf-csp
     title: CCF CSP-J/S 历年真题
@@ -18,4 +20,6 @@ sources:
     license_note: "CCF 官方公开，允许教学使用"
     fetch_method: manual-download
     status: planned
+    subjects: [cspj, it]
+    stages: [junior]
     items: []

sources/exams/cambridge-official.yaml

@@ -8,38 +8,90 @@ sources:
     license_note: "官方免费发布，允许教学使用（样卷/词表/听力音频）"
     fetch_method: manual-download
     status: fetched
-    fetched_at: "2026-08-21"
+    subjects: [ket, pet, fce, english]
+    stages: [primary, junior]
+    fetched_at: 2026-08-22
     items:
       - id: a2-key-vocab
         title: A2 Key 2020 词汇表 PDF
         oss_key: edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocabulary-list.pdf
-        sha256: null
-        size: null
+        sha256: 2abe174d067cd17ffa061cfc4bbbc0e5a55185ac696a5ef8ba49372c753a3ad6
+        size: 544296
         media_type: application/pdf
-        fetch_date: "2026-08-21"
-        status: planned
+        fetch_date: 2026-08-22
+        status: fetched
         note: "vocab JSONL (structured/exams/ket/vocab/) 由此清洗；待 oss_sync 上传"
       - id: b1-preliminary-vocab
-        title: B1 Preliminary 词汇表 PDF
-        oss_key: edu-raw/exams/pet/vocab/cambridge-official/b1-preliminary-vocabulary-list.pdf
-        sha256: null
-        size: null
+        title: B1 Preliminary 2020 词汇表 PDF
+        oss_key: edu-raw/exams/pet/vocab/cambridge-official/b1-preliminary-2020-vocabulary-list.pdf
+        sha256: 85b094be8c214e4da6cb710f0b5450a455ae010ccb4064c5578f68ef6aa139ad
+        size: 628829
         media_type: application/pdf
-        fetch_date: "2026-08-21"
-        status: planned
+        fetch_date: 2026-08-22
+        status: fetched
+        note: "B1 词表清洗源；直链域名用 cambridgeenglish.cn（.org 已 404）"
+      - id: b1-preliminary-vocab-booklet
+        title: B1 Preliminary 词汇手册 PDF（含释义/例句，较厚）
+        oss_key: edu-raw/exams/pet/vocab/cambridge-official/b1-preliminary-vocabulary-booklet.pdf
+        sha256: c4fae109ab5416c7bc68e6686fd9a69abf2428f73e5768ce248d810e612eef20
+        size: 8202984
+        media_type: application/pdf
+        fetch_date: 2026-08-22
+        status: fetched
       - id: a2-key-listening
         title: A2 Key 听力音频
         oss_key: edu-raw/exams/ket/audio/cambridge-official/a2-key-listening.mp3
-        sha256: null
-        size: null
+        sha256: f50df0695c23148f0caac3cf059fb9028db6ee467e75b993ebb0e60af2f70654
+        size: 11974884
         media_type: audio/mpeg
-        fetch_date: "2026-08-21"
-        status: planned
-      - id: sample-papers
-        title: 官方样卷包（PDF/MP3/ZIP）
-        oss_key: edu-raw/exams/ket/sample_papers/cambridge-official/
-        sha256: null
-        size: null
+        fetch_date: 2026-08-22
+        status: fetched
+      - id: b1-preliminary-listening
+        title: B1 Preliminary 听力音频
+        oss_key: edu-raw/exams/pet/audio/cambridge-official/b1-preliminary-listening.mp3
+        sha256: 8d2cd238fc9b3fe6342467a0f288a98dfb4481c5239d7bd8539f6d9b4bc76090
+        size: 26401678
+        media_type: audio/mpeg
+        fetch_date: 2026-08-22
+        status: fetched
+      # 样卷：oss_key 必须是具体文件（目录形式无法单文件上传/校验）
+      - id: a2-key-sample-tests-zip
+        title: A2 Key for Schools 官方样卷包 ZIP
+        oss_key: edu-raw/exams/ket/sample_papers/cambridge-official/a2-key-for-schools-sample-tests.zip
+        sha256: 349d83c36718e597322588895a5dfce59e319f773263b3a60d96e0650f784e07
+        size: 24264467
         media_type: application/zip
-        fetch_date: "2026-08-21"
-        status: planned
+        fetch_date: 2026-08-22
+        status: fetched
+      - id: b1-preliminary-sample-tests-zip
+        title: B1 Preliminary for Schools 官方样卷包 ZIP
+        oss_key: edu-raw/exams/pet/sample_papers/cambridge-official/b1-preliminary-for-schools-sample-tests.zip
+        sha256: 3e11b30226c492d4dab168b60d8607d19131751e4e465e2e5b20e98c217cc077
+        size: 23143382
+        media_type: application/zip
+        fetch_date: 2026-08-22
+        status: fetched
+      - id: a2-key-handbook
+        title: A2 Key for Schools 考官手册 PDF
+        oss_key: edu-raw/exams/ket/sample_papers/cambridge-official/a2-key-handbook.pdf
+        sha256: ebd74b6103c0a06276c6459f5eb947531b49f365bc4df2d52fc7bec85bbd9f0c
+        size: 7860476
+        media_type: application/pdf
+        fetch_date: 2026-08-22
+        status: fetched
+      - id: b1-preliminary-handbook
+        title: B1 Preliminary for Schools 考官手册 PDF
+        oss_key: edu-raw/exams/pet/sample_papers/cambridge-official/b1-preliminary-handbook.pdf
+        sha256: fd47cbd4bf647a9188b4e913eafe8a63eb904e4babd7f89fc8abc1ebd47e5d49
+        size: 9073455
+        media_type: application/pdf
+        fetch_date: 2026-08-22
+        status: fetched
+      - id: score-conversion
+        title: 分数换算表 PDF（原始分 → Cambridge Scale）
+        oss_key: edu-raw/exams/ket/sample_papers/cambridge-official/score-conversion.pdf
+        sha256: 63e371b4f1dc6d51069a443461af3f3811dac5599ce0f879f867e7521f5d9330
+        size: 695401
+        media_type: application/pdf
+        fetch_date: 2026-08-22
+        status: fetched

sources/exams/cepoc.yaml

@@ -8,23 +8,27 @@ sources:
     license_note: "研究/教育用途，非商业（见仓库 licence.txt）"
     fetch_method: git-clone
     status: fetched
+    subjects: [ket, pet, fce, english]
+    stages: [primary, junior]
     fetched_at: "2026-08-21"
     items:
       - id: cepoc-ket-json
-        title: KET.json（6套68空）
+        title: KET.json（6套完形）
         oss_key: edu-raw/exams/ket/questions/cepoc/KET.json
+        src_path: KET.json
         sha256: null
         size: null
         media_type: application/json
         fetch_date: "2026-08-21"
         status: planned
-        note: "latin1 编码；清洗为 qb-1.1 落 structured/exams/ket/questions/cepoc-a2-key.jsonl"
+        note: "latin1 编码 JSONL；清洗为 qb-1.1 落 structured/exams/ket/questions/cepoc-a2-key.jsonl"
       - id: cepoc-b1-json
-        title: B1 Preliminary.json（含 FCE 36套360空）
-        oss_key: edu-raw/exams/pet/questions/cepoc/B1-Preliminary.json
+        title: PET.json（21套完形，即 B1 Preliminary）
+        oss_key: edu-raw/exams/pet/questions/cepoc/PET.json
+        src_path: PET.json
         sha256: null
         size: null
         media_type: application/json
         fetch_date: "2026-08-21"
         status: planned
-        note: "清洗为 qb-1.1 落 structured/exams/pet/questions/cepoc-b1-preliminary.jsonl"
+        note: "repo 实际文件名为 PET.json（此前误登记为 B1-Preliminary.json）；清洗落 structured/exams/pet/questions/cepoc-b1-preliminary.jsonl"

sources/internal/qihang-v1.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "自制课件，仅内部参考，禁止再分发/商用"
     fetch_method: manual-export
     status: archived
+    subjects: [it]
+    stages: [primary, junior]
     items:
       - id: qihang-v1-all
         title: 启航班V1 整包归档

sources/internal/qihang-v2.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "自制课件，仅内部参考，禁止再分发/商用"
     fetch_method: manual-export
     status: archived
+    subjects: [it]
+    stages: [primary, junior]
     items:
       - id: qihang-v2-all
         title: 启航班V2 整包归档

sources/internal/qihang-v3.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "自制工程，仅内部参考；若持续演进可未来拆独立 repo"
     fetch_method: manual-export
     status: archived
+    subjects: [it]
+    stages: [primary, junior]
     items:
       - id: qihang-v3-all
         title: 启航班V3 整包归档

sources/internal/zhizaoying-v1.yaml

@@ -8,6 +8,8 @@ sources:
     license_note: "自制课件，仅内部参考，禁止再分发/商用"
     fetch_method: manual-export
     status: archived
+    subjects: [it]
+    stages: [primary, junior]
     items:
       - id: zhizaoying-v1-all
         title: 智造营V1 整包归档

sources/source.schema.json

@@ -3,47 +3,230 @@
   "title": "edu-content source registry",
   "description": "机器可读的 L1 资源清单。一个 YAML 文件 = 一个域，内含多条 source。source 是四层血缘链的根 id。",
   "type": "object",
-  "required": ["sources"],
+  "required": [
+    "sources"
+  ],
   "additionalProperties": false,
   "properties": {
     "sources": {
       "type": "array",
-      "items": { "$ref": "#/definitions/source" }
+      "items": {
+        "$ref": "#/definitions/source"
+      }
     }
   },
   "definitions": {
     "source": {
       "type": "object",
-      "required": ["id", "title", "publisher", "type", "license", "status"],
+      "required": [
+        "id",
+        "title",
+        "publisher",
+        "type",
+        "license",
+        "status",
+        "subjects"
+      ],
       "additionalProperties": false,
       "properties": {
-        "id": { "type": "string", "pattern": "^[a-z0-9][a-z0-9-]*$", "description": "全局唯一 kebab-case，血缘链根 id" },
-        "title": { "type": "string" },
-        "publisher": { "type": "string" },
-        "type": { "type": "string", "enum": ["dataset", "website", "book", "internal", "tool"] },
-        "url": { "type": ["string", "null"], "description": "internal 可为 null" },
-        "license": { "type": "string", "enum": ["official-free", "cc-by", "cc-by-sa", "cc-nc-education", "restricted", "internal-only", "llm-generated", "unknown"] },
-        "license_note": { "type": "string" },
-        "fetch_method": { "type": "string", "enum": ["curl", "git-clone", "manual-download", "manual-export", "generated"], "description": "unknown 允许暂存" },
-        "status": { "type": "string", "enum": ["planned", "fetching", "fetched", "failed", "archived"] },
-        "fetched_at": { "type": ["string", "null"], "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$" },
-        "items": { "type": "array", "items": { "$ref": "#/definitions/item" } }
+        "id": {
+          "type": "string",
+          "pattern": "^[a-z0-9][a-z0-9-]*$",
+          "description": "全局唯一 kebab-case，血缘链根 id"
+        },
+        "title": {
+          "type": "string"
+        },
+        "publisher": {
+          "type": "string"
+        },
+        "type": {
+          "type": "string",
+          "enum": [
+            "dataset",
+            "website",
+            "book",
+            "internal",
+            "tool"
+          ]
+        },
+        "url": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "internal 可为 null"
+        },
+        "license": {
+          "type": "string",
+          "enum": [
+            "official-free",
+            "mit",
+            "cc-by",
+            "cc-by-sa",
+            "cc-nc-education",
+            "restricted",
+            "internal-only",
+            "llm-generated",
+            "unknown"
+          ]
+        },
+        "license_note": {
+          "type": "string"
+        },
+        "fetch_method": {
+          "type": "string",
+          "enum": [
+            "curl",
+            "git-clone",
+            "manual-download",
+            "manual-export",
+            "generated"
+          ],
+          "description": "unknown 允许暂存"
+        },
+        "status": {
+          "type": "string",
+          "enum": [
+            "planned",
+            "fetching",
+            "fetched",
+            "failed",
+            "archived"
+          ]
+        },
+        "fetched_at": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$"
+        },
+        "items": {
+          "type": "array",
+          "items": {
+            "$ref": "#/definitions/item"
+          }
+        },
+        "subjects": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": [
+              "chinese",
+              "math",
+              "english",
+              "science",
+              "morality",
+              "physics",
+              "chemistry",
+              "biology",
+              "history",
+              "geography",
+              "it",
+              "ket",
+              "pet",
+              "fce",
+              "amc8",
+              "cspj"
+            ]
+          },
+          "description": "该来源覆盖的学科/考试域，取值与 structured/ 目录名一致；用于回答『某学科有哪些来源』"
+        },
+        "stages": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": [
+              "primary",
+              "junior"
+            ]
+          },
+          "description": "覆盖学段：primary=小学，junior=初中"
+        },
+        "url_template": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetch_method=curl 时的下载模板，{item_id} 占位；item.url 优先级更高。例：https://host/sims/{item_id}/{item_id}_zh_CN.html"
+        }
       }
     },
     "item": {
       "type": "object",
-      "required": ["id", "title"],
+      "required": [
+        "id",
+        "title"
+      ],
       "additionalProperties": false,
       "properties": {
-        "id": { "type": "string", "pattern": "^[a-z0-9][a-z0-9-]*$", "description": "source 内唯一" },
-        "title": { "type": "string" },
-        "oss_key": { "type": ["string", "null"], "description": "fetched 后必填，形如 edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocab.pdf" },
-        "sha256": { "type": ["string", "null"], "pattern": "^[a-f0-9]{64}$|^$" },
-        "size": { "type": ["integer", "null"], "minimum": 0 },
-        "media_type": { "type": "string" },
-        "fetch_date": { "type": ["string", "null"], "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$" },
-        "status": { "type": "string", "enum": ["planned", "fetching", "fetched", "failed", "archived"] },
-        "note": { "type": "string" }
+        "id": {
+          "type": "string",
+          "pattern": "^[a-z0-9][a-z0-9-]*$",
+          "description": "source 内唯一"
+        },
+        "title": {
+          "type": "string"
+        },
+        "oss_key": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetched 后必填，形如 edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocab.pdf"
+        },
+        "sha256": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^[a-f0-9]{64}$|^$"
+        },
+        "size": {
+          "type": [
+            "integer",
+            "null"
+          ],
+          "minimum": 0
+        },
+        "media_type": {
+          "type": "string"
+        },
+        "fetch_date": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$"
+        },
+        "status": {
+          "type": "string",
+          "enum": [
+            "planned",
+            "fetching",
+            "fetched",
+            "failed",
+            "archived"
+          ]
+        },
+        "note": {
+          "type": "string"
+        },
+        "url": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "该条目的直接下载地址；缺省时由 source.url_template 渲染"
+        },
+        "src_path": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetch_method=git-clone 时，条目在仓库内的相对路径（打包为 oss_key 指向的归档）"
+        }
       }
     }
   }