426cf4d2cd
- 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>
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
"""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})>"
|