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/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