Phase 1 MVP: crawl 10 high-quality oshwhub projects into LFS

Why:
- Charles 指定：先爬 10 个高质量项目存 Gitea LFS，一个项目一个文件夹，
  保留原文件和 URL。先以小批量验证 schema + LFS 流水线，放量前再拍板
  存储规模。

What:
- crawlers/oshwhub: 列表 API (`/api/project?sort=hot`) + SSR HTML 解析，
  一次性产出 metadata / description / cover / files / _urls
- schemas/project.schema.json: 跨源统一 schema
- docs/sources/oshwhub.md: API 入口 / 字段映射 / 陷阱调研
- pyproject.toml: httpx[http2] 单依赖
- .gitattributes: data/raw/**/files/** 一律走 LFS（规则写窄，避免误伤 schemas/*.json 等）
- .gitignore: 移除 data/raw/* 排除（改走 LFS 入库）

10 个项目覆盖：调试器 / 加热台 / 盖革计数器 / 数控电源 / 焊台 /
智能手表 / USB 测电流 / ZVS 感应加热 / AI 开发板 / 红外热成像。
共 52 附件 ≈ 524 MB 入 LFS，筛选判据 grade=4 & likes>=100 & 多样性。

Known gaps（见 plan.md § Phase 1.4）：
- EasyEDA 源 JSON 需登录 (u.lceda.cn)，v0.1 跳过
- fs-web-stream.jlc.com 的工程源下载未测
- scripts/validate.py 自动 schema 校验未实现

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

schemas/project.schema.json

@@ -0,0 +1,95 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://git.deepknow.site/Facere/FacereDataset/schemas/project.schema.json",
+  "title": "FacereDataset Project",
+  "description": "统一项目记录。跨源（oshwhub / hackaday / github / ...）通用。",
+  "type": "object",
+  "required": [
+    "source",
+    "source_url",
+    "project_id",
+    "title",
+    "author",
+    "license",
+    "crawled_at",
+    "files"
+  ],
+  "properties": {
+    "source": {
+      "type": "string",
+      "description": "数据源标识，如 'oshwhub'、'hackaday'、'github'",
+      "enum": ["oshwhub", "hackaday", "github", "cern_ohr", "wikifactory", "other"]
+    },
+    "source_url": { "type": "string", "format": "uri" },
+    "project_id": {
+      "type": "string",
+      "description": "源站点内部 ID（oshwhub 用 uuid）"
+    },
+    "title": { "type": "string" },
+    "description_short": {
+      "type": "string",
+      "description": "简介（< 200 chars）"
+    },
+    "description_path": {
+      "type": "string",
+      "description": "长描述 markdown 相对本项目目录的路径，如 'description.md'"
+    },
+    "author": {
+      "type": "object",
+      "required": ["username"],
+      "properties": {
+        "username": { "type": "string" },
+        "display_name": { "type": "string" },
+        "user_id": { "type": "string" }
+      }
+    },
+    "license": {
+      "type": "string",
+      "description": "原始许可证字符串；下游做规范化映射。未知标 'unknown'"
+    },
+    "tags": {
+      "type": "array",
+      "items": { "type": "string" }
+    },
+    "created_at": { "type": "string", "format": "date-time" },
+    "updated_at": { "type": "string", "format": "date-time" },
+    "published_at": { "type": "string", "format": "date-time" },
+    "crawled_at": { "type": "string", "format": "date-time" },
+    "metrics": {
+      "type": "object",
+      "additionalProperties": true,
+      "description": "任意源站点统计：likes/stars/views/forks 等"
+    },
+    "cover": {
+      "type": "object",
+      "properties": {
+        "url": { "type": "string", "format": "uri" },
+        "path": { "type": "string", "description": "本地相对路径，如 'cover.png'" }
+      }
+    },
+    "files": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["name", "url"],
+        "properties": {
+          "name": { "type": "string" },
+          "url": { "type": "string", "format": "uri" },
+          "path": { "type": "string", "description": "本地相对路径，如 'files/xxx.pdf'。缺省表示只保留 URL" },
+          "size": { "type": "integer" },
+          "md5": { "type": "string" },
+          "sha256": { "type": "string" },
+          "ext": { "type": "string" },
+          "mime": { "type": "string" },
+          "original_id": { "type": "string", "description": "源站点内部文件 ID" }
+        }
+      }
+    },
+    "raw_fields": {
+      "type": "object",
+      "description": "不易规范化但想保留的源站原始字段（grade、download_count 等）",
+      "additionalProperties": true
+    }
+  },
+  "additionalProperties": false
+}