Add university scraper system with backend, frontend, and configs

- Add src/university_scraper module with scraper, analyzer, and CLI
- Add backend FastAPI service with API endpoints and database models
- Add frontend React app with university management pages
- Add configs for Harvard, Manchester, and UCL universities
- Add artifacts with various scraper implementations
- Add Docker compose configuration for deployment
- Update .gitignore to exclude generated files

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/schemas/__init__.py

@@ -0,0 +1,33 @@
+"""Pydantic schemas for API"""
+
+from .university import (
+    UniversityCreate,
+    UniversityUpdate,
+    UniversityResponse,
+    UniversityListResponse
+)
+from .script import (
+    ScriptCreate,
+    ScriptResponse,
+    GenerateScriptRequest,
+    GenerateScriptResponse
+)
+from .job import (
+    JobCreate,
+    JobResponse,
+    JobStatusResponse,
+    LogResponse
+)
+from .result import (
+    ResultResponse,
+    SchoolData,
+    ProgramData,
+    FacultyData
+)
+
+__all__ = [
+    "UniversityCreate", "UniversityUpdate", "UniversityResponse", "UniversityListResponse",
+    "ScriptCreate", "ScriptResponse", "GenerateScriptRequest", "GenerateScriptResponse",
+    "JobCreate", "JobResponse", "JobStatusResponse", "LogResponse",
+    "ResultResponse", "SchoolData", "ProgramData", "FacultyData"
+]

backend/app/schemas/job.py

@@ -0,0 +1,52 @@
+"""爬取任务相关的Pydantic模型"""
+
+from datetime import datetime
+from typing import Optional, List
+from pydantic import BaseModel
+
+
+class JobCreate(BaseModel):
+    """创建任务请求"""
+    university_id: int
+    script_id: Optional[int] = None
+
+
+class JobResponse(BaseModel):
+    """任务响应"""
+    id: int
+    university_id: int
+    script_id: Optional[int] = None
+    status: str
+    progress: int
+    current_step: Optional[str] = None
+    started_at: Optional[datetime] = None
+    completed_at: Optional[datetime] = None
+    error_message: Optional[str] = None
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+class JobStatusResponse(BaseModel):
+    """任务状态响应"""
+    id: int
+    status: str
+    progress: int
+    current_step: Optional[str] = None
+    logs: List["LogResponse"] = []
+
+
+class LogResponse(BaseModel):
+    """日志响应"""
+    id: int
+    level: str
+    message: str
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+# 解决循环引用
+JobStatusResponse.model_rebuild()

backend/app/schemas/result.py

@@ -0,0 +1,67 @@
+"""爬取结果相关的Pydantic模型"""
+
+from datetime import datetime
+from typing import Optional, List, Dict, Any
+from pydantic import BaseModel
+
+
+class FacultyData(BaseModel):
+    """导师数据"""
+    name: str
+    url: str
+    title: Optional[str] = None
+    email: Optional[str] = None
+    department: Optional[str] = None
+
+
+class ProgramData(BaseModel):
+    """项目数据"""
+    name: str
+    url: str
+    degree_type: Optional[str] = None
+    description: Optional[str] = None
+    faculty_page_url: Optional[str] = None
+    faculty_count: int = 0
+    faculty: List[FacultyData] = []
+
+
+class SchoolData(BaseModel):
+    """学院数据"""
+    name: str
+    url: str
+    description: Optional[str] = None
+    program_count: int = 0
+    programs: List[ProgramData] = []
+
+
+class ResultResponse(BaseModel):
+    """完整结果响应"""
+    id: int
+    university_id: int
+    job_id: Optional[int] = None
+
+    # 统计
+    schools_count: int
+    programs_count: int
+    faculty_count: int
+
+    # 完整数据
+    result_data: Dict[str, Any]
+
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+class ResultSummary(BaseModel):
+    """结果摘要"""
+    id: int
+    university_id: int
+    schools_count: int
+    programs_count: int
+    faculty_count: int
+    created_at: datetime
+
+    class Config:
+        from_attributes = True

backend/app/schemas/script.py

@@ -0,0 +1,46 @@
+"""爬虫脚本相关的Pydantic模型"""
+
+from datetime import datetime
+from typing import Optional, Dict, Any
+from pydantic import BaseModel
+
+
+class ScriptBase(BaseModel):
+    """脚本基础字段"""
+    script_name: str
+    script_content: str
+    config_content: Optional[Dict[str, Any]] = None
+
+
+class ScriptCreate(ScriptBase):
+    """创建脚本请求"""
+    university_id: int
+
+
+class ScriptResponse(ScriptBase):
+    """脚本响应"""
+    id: int
+    university_id: int
+    version: int
+    status: str
+    error_message: Optional[str] = None
+    created_at: datetime
+    updated_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+class GenerateScriptRequest(BaseModel):
+    """生成脚本请求"""
+    university_url: str
+    university_name: Optional[str] = None
+
+
+class GenerateScriptResponse(BaseModel):
+    """生成脚本响应"""
+    success: bool
+    university_id: int
+    script_id: Optional[int] = None
+    message: str
+    status: str  # analyzing, completed, failed

backend/app/schemas/university.py

@@ -0,0 +1,48 @@
+"""大学相关的Pydantic模型"""
+
+from datetime import datetime
+from typing import Optional, List
+from pydantic import BaseModel, HttpUrl
+
+
+class UniversityBase(BaseModel):
+    """大学基础字段"""
+    name: str
+    url: str
+    country: Optional[str] = None
+    description: Optional[str] = None
+
+
+class UniversityCreate(UniversityBase):
+    """创建大学请求"""
+    pass
+
+
+class UniversityUpdate(BaseModel):
+    """更新大学请求"""
+    name: Optional[str] = None
+    url: Optional[str] = None
+    country: Optional[str] = None
+    description: Optional[str] = None
+
+
+class UniversityResponse(UniversityBase):
+    """大学响应"""
+    id: int
+    status: str
+    created_at: datetime
+    updated_at: datetime
+
+    # 统计信息
+    scripts_count: int = 0
+    jobs_count: int = 0
+    latest_result: Optional[dict] = None
+
+    class Config:
+        from_attributes = True
+
+
+class UniversityListResponse(BaseModel):
+    """大学列表响应"""
+    total: int
+    items: List[UniversityResponse]