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/models/__init__.py

@@ -0,0 +1,8 @@
+"""数据库模型"""
+
+from .university import University
+from .script import ScraperScript
+from .job import ScrapeJob, ScrapeLog
+from .result import ScrapeResult
+
+__all__ = ["University", "ScraperScript", "ScrapeJob", "ScrapeLog", "ScrapeResult"]

backend/app/models/job.py

@@ -0,0 +1,56 @@
+"""爬取任务模型"""
+
+from datetime import datetime
+from sqlalchemy import Column, Integer, String, DateTime, Text, ForeignKey
+from sqlalchemy.orm import relationship
+
+from ..database import Base
+
+
+class ScrapeJob(Base):
+    """爬取任务表"""
+
+    __tablename__ = "scrape_jobs"
+
+    id = Column(Integer, primary_key=True, index=True)
+    university_id = Column(Integer, ForeignKey("universities.id"), nullable=False)
+    script_id = Column(Integer, ForeignKey("scraper_scripts.id"))
+
+    status = Column(String(50), default="pending")  # pending, running, completed, failed, cancelled
+    progress = Column(Integer, default=0)  # 0-100 进度百分比
+    current_step = Column(String(255))  # 当前步骤描述
+
+    started_at = Column(DateTime)
+    completed_at = Column(DateTime)
+    error_message = Column(Text)
+
+    created_at = Column(DateTime, default=datetime.utcnow)
+
+    # 关联
+    university = relationship("University", back_populates="jobs")
+    script = relationship("ScraperScript", back_populates="jobs")
+    logs = relationship("ScrapeLog", back_populates="job", cascade="all, delete-orphan")
+    results = relationship("ScrapeResult", back_populates="job", cascade="all, delete-orphan")
+
+    def __repr__(self):
+        return f"<ScrapeJob(id={self.id}, status='{self.status}')>"
+
+
+class ScrapeLog(Base):
+    """爬取日志表"""
+
+    __tablename__ = "scrape_logs"
+
+    id = Column(Integer, primary_key=True, index=True)
+    job_id = Column(Integer, ForeignKey("scrape_jobs.id"), nullable=False)
+
+    level = Column(String(20), default="info")  # debug, info, warning, error
+    message = Column(Text, nullable=False)
+
+    created_at = Column(DateTime, default=datetime.utcnow)
+
+    # 关联
+    job = relationship("ScrapeJob", back_populates="logs")
+
+    def __repr__(self):
+        return f"<ScrapeLog(id={self.id}, level='{self.level}')>"

backend/app/models/result.py

@@ -0,0 +1,34 @@
+"""爬取结果模型"""
+
+from datetime import datetime
+from sqlalchemy import Column, Integer, DateTime, ForeignKey, JSON
+from sqlalchemy.orm import relationship
+
+from ..database import Base
+
+
+class ScrapeResult(Base):
+    """爬取结果表"""
+
+    __tablename__ = "scrape_results"
+
+    id = Column(Integer, primary_key=True, index=True)
+    job_id = Column(Integer, ForeignKey("scrape_jobs.id"))
+    university_id = Column(Integer, ForeignKey("universities.id"), nullable=False)
+
+    # JSON数据: 学院 → 项目 → 导师 层级结构
+    result_data = Column(JSON, nullable=False)
+
+    # 统计信息
+    schools_count = Column(Integer, default=0)
+    programs_count = Column(Integer, default=0)
+    faculty_count = Column(Integer, default=0)
+
+    created_at = Column(DateTime, default=datetime.utcnow)
+
+    # 关联
+    job = relationship("ScrapeJob", back_populates="results")
+    university = relationship("University", back_populates="results")
+
+    def __repr__(self):
+        return f"<ScrapeResult(id={self.id}, programs={self.programs_count}, faculty={self.faculty_count})>"

backend/app/models/script.py

@@ -0,0 +1,34 @@
+"""爬虫脚本模型"""
+
+from datetime import datetime
+from sqlalchemy import Column, Integer, String, DateTime, Text, ForeignKey, JSON
+from sqlalchemy.orm import relationship
+
+from ..database import Base
+
+
+class ScraperScript(Base):
+    """爬虫脚本表"""
+
+    __tablename__ = "scraper_scripts"
+
+    id = Column(Integer, primary_key=True, index=True)
+    university_id = Column(Integer, ForeignKey("universities.id"), nullable=False)
+
+    script_name = Column(String(255), nullable=False)
+    script_content = Column(Text, nullable=False)  # Python脚本代码
+    config_content = Column(JSON)  # YAML配置转为JSON存储
+
+    version = Column(Integer, default=1)
+    status = Column(String(50), default="draft")  # draft, active, deprecated, error
+    error_message = Column(Text)
+
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+    # 关联
+    university = relationship("University", back_populates="scripts")
+    jobs = relationship("ScrapeJob", back_populates="script")
+
+    def __repr__(self):
+        return f"<ScraperScript(id={self.id}, name='{self.script_name}')>"

backend/app/models/university.py

@@ -0,0 +1,31 @@
+"""大学模型"""
+
+from datetime import datetime
+from sqlalchemy import Column, Integer, String, DateTime, Text
+from sqlalchemy.orm import relationship
+
+from ..database import Base
+
+
+class University(Base):
+    """大学表"""
+
+    __tablename__ = "universities"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String(255), nullable=False, index=True)
+    url = Column(String(500), nullable=False)
+    country = Column(String(100))
+    description = Column(Text)
+    status = Column(String(50), default="pending")  # pending, analyzing, ready, error
+
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+    # 关联
+    scripts = relationship("ScraperScript", back_populates="university", cascade="all, delete-orphan")
+    jobs = relationship("ScrapeJob", back_populates="university", cascade="all, delete-orphan")
+    results = relationship("ScrapeResult", back_populates="university", cascade="all, delete-orphan")
+
+    def __repr__(self):
+        return f"<University(id={self.id}, name='{self.name}')>"