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
1.2 KiB
Python
35 lines
1.2 KiB
Python
"""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}')>"
|