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/api/scripts.py

@@ -0,0 +1,167 @@
+"""爬虫脚本API"""
+
+from typing import List
+from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
+from sqlalchemy.orm import Session
+
+from ..database import get_db
+from ..models import University, ScraperScript
+from ..schemas.script import (
+    ScriptCreate,
+    ScriptResponse,
+    GenerateScriptRequest,
+    GenerateScriptResponse
+)
+from ..services.script_generator import generate_scraper_script
+
+router = APIRouter()
+
+
+@router.post("/generate", response_model=GenerateScriptResponse)
+async def generate_script(
+    data: GenerateScriptRequest,
+    background_tasks: BackgroundTasks,
+    db: Session = Depends(get_db)
+):
+    """
+    一键生成爬虫脚本
+
+    分析大学网站结构，自动生成爬虫脚本
+    """
+    # 检查或创建大学记录
+    university = db.query(University).filter(University.url == data.university_url).first()
+
+    if not university:
+        # 从URL提取大学名称
+        name = data.university_name
+        if not name:
+            from urllib.parse import urlparse
+            parsed = urlparse(data.university_url)
+            name = parsed.netloc.replace("www.", "").split(".")[0].title()
+
+        university = University(
+            name=name,
+            url=data.university_url,
+            status="analyzing"
+        )
+        db.add(university)
+        db.commit()
+        db.refresh(university)
+    else:
+        # 更新状态
+        university.status = "analyzing"
+        db.commit()
+
+    # 在后台执行脚本生成
+    background_tasks.add_task(
+        generate_scraper_script,
+        university_id=university.id,
+        university_url=data.university_url
+    )
+
+    return GenerateScriptResponse(
+        success=True,
+        university_id=university.id,
+        script_id=None,
+        message="正在分析网站结构并生成爬虫脚本...",
+        status="analyzing"
+    )
+
+
+@router.get("/university/{university_id}", response_model=List[ScriptResponse])
+def get_university_scripts(
+    university_id: int,
+    db: Session = Depends(get_db)
+):
+    """获取大学的所有爬虫脚本"""
+    scripts = db.query(ScraperScript).filter(
+        ScraperScript.university_id == university_id
+    ).order_by(ScraperScript.version.desc()).all()
+
+    return scripts
+
+
+@router.get("/{script_id}", response_model=ScriptResponse)
+def get_script(
+    script_id: int,
+    db: Session = Depends(get_db)
+):
+    """获取脚本详情"""
+    script = db.query(ScraperScript).filter(ScraperScript.id == script_id).first()
+    if not script:
+        raise HTTPException(status_code=404, detail="脚本不存在")
+
+    return script
+
+
+@router.post("", response_model=ScriptResponse)
+def create_script(
+    data: ScriptCreate,
+    db: Session = Depends(get_db)
+):
+    """手动创建脚本"""
+    # 检查大学是否存在
+    university = db.query(University).filter(University.id == data.university_id).first()
+    if not university:
+        raise HTTPException(status_code=404, detail="大学不存在")
+
+    # 获取当前最高版本
+    max_version = db.query(ScraperScript).filter(
+        ScraperScript.university_id == data.university_id
+    ).count()
+
+    script = ScraperScript(
+        university_id=data.university_id,
+        script_name=data.script_name,
+        script_content=data.script_content,
+        config_content=data.config_content,
+        version=max_version + 1,
+        status="active"
+    )
+
+    db.add(script)
+    db.commit()
+    db.refresh(script)
+
+    # 更新大学状态
+    university.status = "ready"
+    db.commit()
+
+    return script
+
+
+@router.put("/{script_id}", response_model=ScriptResponse)
+def update_script(
+    script_id: int,
+    data: ScriptCreate,
+    db: Session = Depends(get_db)
+):
+    """更新脚本"""
+    script = db.query(ScraperScript).filter(ScraperScript.id == script_id).first()
+    if not script:
+        raise HTTPException(status_code=404, detail="脚本不存在")
+
+    script.script_content = data.script_content
+    if data.config_content:
+        script.config_content = data.config_content
+
+    db.commit()
+    db.refresh(script)
+
+    return script
+
+
+@router.delete("/{script_id}")
+def delete_script(
+    script_id: int,
+    db: Session = Depends(get_db)
+):
+    """删除脚本"""
+    script = db.query(ScraperScript).filter(ScraperScript.id == script_id).first()
+    if not script:
+        raise HTTPException(status_code=404, detail="脚本不存在")
+
+    db.delete(script)
+    db.commit()
+
+    return {"message": "删除成功"}