University-Playwright-Codegen-Agent/backend/app/api/results.py

"""爬取结果API"""

from typing import Optional
from fastapi import APIRouter, Depends, HTTPException, Query
from fastapi.responses import JSONResponse
from sqlalchemy.orm import Session

from ..database import get_db
from ..models import ScrapeResult
from ..schemas.result import ResultResponse

router = APIRouter()


@router.get("/university/{university_id}", response_model=ResultResponse)
def get_university_result(
    university_id: int,
    db: Session = Depends(get_db)
):
    """获取大学最新的爬取结果"""
    result = db.query(ScrapeResult).filter(
        ScrapeResult.university_id == university_id
    ).order_by(ScrapeResult.created_at.desc()).first()

    if not result:
        raise HTTPException(status_code=404, detail="没有爬取结果")

    return result


@router.get("/university/{university_id}/schools")
def get_schools(
    university_id: int,
    db: Session = Depends(get_db)
):
    """获取学院列表"""
    result = db.query(ScrapeResult).filter(
        ScrapeResult.university_id == university_id
    ).order_by(ScrapeResult.created_at.desc()).first()

    if not result:
        raise HTTPException(status_code=404, detail="没有爬取结果")

    schools = result.result_data.get("schools", [])

    # 返回简化的学院列表
    return {
        "total": len(schools),
        "schools": [
            {
                "name": s.get("name"),
                "url": s.get("url"),
                "program_count": len(s.get("programs", []))
            }
            for s in schools
        ]
    }


@router.get("/university/{university_id}/programs")
def get_programs(
    university_id: int,
    school_name: Optional[str] = Query(None, description="按学院筛选"),
    search: Optional[str] = Query(None, description="搜索项目名称"),
    db: Session = Depends(get_db)
):
    """获取项目列表"""
    result = db.query(ScrapeResult).filter(
        ScrapeResult.university_id == university_id
    ).order_by(ScrapeResult.created_at.desc()).first()

    if not result:
        raise HTTPException(status_code=404, detail="没有爬取结果")

    schools = result.result_data.get("schools", [])
    programs = []

    for school in schools:
        if school_name and school.get("name") != school_name:
            continue

        for prog in school.get("programs", []):
            if search and search.lower() not in prog.get("name", "").lower():
                continue

            programs.append({
                "name": prog.get("name"),
                "url": prog.get("url"),
                "degree_type": prog.get("degree_type"),
                "school": school.get("name"),
                "faculty_count": len(prog.get("faculty", []))
            })

    return {
        "total": len(programs),
        "programs": programs
    }


@router.get("/university/{university_id}/faculty")
def get_faculty(
    university_id: int,
    school_name: Optional[str] = Query(None, description="按学院筛选"),
    program_name: Optional[str] = Query(None, description="按项目筛选"),
    search: Optional[str] = Query(None, description="搜索导师姓名"),
    skip: int = Query(0, ge=0),
    limit: int = Query(50, ge=1, le=200),
    db: Session = Depends(get_db)
):
    """获取导师列表"""
    result = db.query(ScrapeResult).filter(
        ScrapeResult.university_id == university_id
    ).order_by(ScrapeResult.created_at.desc()).first()

    if not result:
        raise HTTPException(status_code=404, detail="没有爬取结果")

    schools = result.result_data.get("schools", [])
    faculty_list = []

    for school in schools:
        if school_name and school.get("name") != school_name:
            continue

        for prog in school.get("programs", []):
            if program_name and prog.get("name") != program_name:
                continue

            for fac in prog.get("faculty", []):
                if search and search.lower() not in fac.get("name", "").lower():
                    continue

                faculty_list.append({
                    "name": fac.get("name"),
                    "url": fac.get("url"),
                    "title": fac.get("title"),
                    "email": fac.get("email"),
                    "program": prog.get("name"),
                    "school": school.get("name")
                })

    total = len(faculty_list)
    faculty_list = faculty_list[skip:skip + limit]

    return {
        "total": total,
        "skip": skip,
        "limit": limit,
        "faculty": faculty_list
    }


@router.get("/university/{university_id}/export")
def export_result(
    university_id: int,
    format: str = Query("json", enum=["json"]),
    db: Session = Depends(get_db)
):
    """导出爬取结果"""
    result = db.query(ScrapeResult).filter(
        ScrapeResult.university_id == university_id
    ).order_by(ScrapeResult.created_at.desc()).first()

    if not result:
        raise HTTPException(status_code=404, detail="没有爬取结果")

    if format == "json":
        return JSONResponse(
            content=result.result_data,
            headers={
                "Content-Disposition": f"attachment; filename=university_{university_id}_result.json"
            }
        )

    raise HTTPException(status_code=400, detail="不支持的格式")