feat: 内容数据迁移至数据库,合规审查全链路打通

- 文章 HTML 存储从文件系统迁移至 articles 表,删除 releases 目录
- 合规审查从 DB 读取 HTML,审查结果写回 DB,通过后自动推进至待发布
- 新增 todayCount 筛选按钮,与系统概览统计数据一致
- 全屏预览修复:提升 z-index 超过侧边栏,添加退出全屏/关闭按钮
- 统一 '优化' → '审查' 命名,消除前后端术语不一致
- 调度器创作完成后自动触发审查(生成 → 审查 → 待发布)
- 清理旧备份/调试文件、过期大纲和研究笔记
This commit is contained in:
Yuzhiran Dev
2026-05-13 17:33:56 +08:00
parent bc6a302e59
commit 233e23016c
234 changed files with 5670 additions and 10651 deletions
+19 -30
View File
@@ -1,53 +1,42 @@
from fastapi import APIRouter, HTTPException, Query, Depends
from sqlalchemy.orm import Session
from pathlib import Path
import os
from datetime import datetime, date
from ..database import get_db
from ..models import User
from ..models import User, Article
from .auth import get_current_user
router = APIRouter(prefix="/api/articles", tags=["articles"])
PROJECT_ROOT = Path('/root/openclaw-workspace/projects/yu-zhi-ran')
@router.get("/drafts")
def list_drafts(publish_date: str = None, current_user: User = Depends(get_current_user)):
"""列出指定日期的草稿文件(三平台)"""
if not publish_date:
publish_date = date.today().isoformat()
base_dir = PROJECT_ROOT / "automation" / "data" / "releases" / publish_date
if not base_dir.exists():
raise HTTPException(status_code=404, detail="No releases for this date")
platforms = ["zhihu", "wechat", "xiaohongshu"]
def list_drafts(topic_id: str = None, current_user: User = Depends(get_current_user), db: Session = Depends(get_db)):
"""从 articles 表列出草稿"""
query = db.query(Article)
if topic_id:
query = query.filter(Article.topic_id == topic_id)
articles = query.order_by(Article.created_at.desc()).all()
result = {}
for p in platforms:
path = base_dir / p
if path.exists():
files = sorted([f.name for f in path.glob("*.html") if f.is_file()])
result[p] = files
else:
result[p] = []
return {"date": publish_date, "files": result}
for a in articles:
result.setdefault(a.platform, []).append({"id": a.id, "topic_id": a.topic_id, "status": a.status})
return {"articles": result}
@router.get("/{topic_id}/preview")
def preview_article(topic_id: str, platform: str = "zhihu", publish_date: str = None, current_user: User = Depends(get_current_user)):
"""预览某选题的HTML内容"""
if not publish_date:
publish_date = date.today().isoformat()
filename = f"{platform}_{topic_id}_{platform}.html"
file_path = PROJECT_ROOT / "automation" / "data" / "releases" / publish_date / platform / filename
if not file_path.exists():
raise HTTPException(status_code=404, detail=f"Article not found: {file_path}")
content = file_path.read_text(encoding='utf-8')
return {"topic_id": topic_id, "platform": platform, "html": content}
def preview_article(topic_id: str, platform: str = "zhihu", current_user: User = Depends(get_current_user), db: Session = Depends(get_db)):
"""从 articles 表预览某选题的 HTML 内容"""
article_id = f"{platform}_{topic_id}"
article = db.query(Article).filter(Article.id == article_id).first()
if not article or not article.html_content:
raise HTTPException(status_code=404, detail=f"Article not found for {topic_id} on {platform}")
return {"topic_id": topic_id, "platform": platform, "html": article.html_content}
@router.get("/optimization-report")
def get_optimization_report(publish_date: str = None, current_user: User = Depends(get_current_user)):
"""获取合规优化报告"""
if not publish_date:
publish_date = date.today().isoformat()
PROJECT_ROOT = Path('/root/openclaw-workspace/projects/yu-zhi-ran')
report_path = PROJECT_ROOT / "automation" / "data" / "drafts" / publish_date / "optimization_report.json"
if not report_path.exists():
raise HTTPException(status_code=404, detail="No optimization report for this date")
+5 -2
View File
@@ -17,11 +17,14 @@ router = APIRouter(prefix="/api/calendar", tags=["calendar"])
@router.get("", response_model=List[ContentCalendarResponse])
def get_calendar(
year: int = Query(...),
month: int = Query(...),
year: Optional[int] = Query(None),
month: Optional[int] = Query(None),
db: Session = Depends(get_db),
current_user=Depends(get_current_user)
):
today = date.today()
year = year or today.year
month = month or today.month
start = date(year, month, 1)
last_day = monthrange(year, month)[1]
end = date(year, month, last_day)
+2 -2
View File
@@ -35,8 +35,8 @@ async def create_publish_record(
if not topic:
raise HTTPException(status_code=404, detail=f"选题 {req.topic_id} 不存在")
if topic.status != '待发布':
raise HTTPException(status_code=400, detail=f"选题 {req.topic_id} 状态不是待发布")
if topic.status not in ('ready', '待发布'):
raise HTTPException(status_code=400, detail=f"选题 {req.topic_id} 状态不是待发布(当前: {topic.status}")
# 更新选题状态
topic.status = '已发布'
+70 -7
View File
@@ -69,18 +69,37 @@ def trigger_generation(topic_id: str = Body(None, embed=True), db: Session = Dep
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/optimize/run", dependencies=[Depends(get_current_user)])
def trigger_optimization(topic_ids: List[str] = Body(None, embed=True), db: Session = Depends(get_db)):
@router.post("/review/run", dependencies=[Depends(get_current_user)])
def trigger_review(topic_ids: List[str] = Body(None, embed=True), db: Session = Depends(get_db)):
try:
result = run_optimizer(topic_ids)
if not result["ok"]:
raise HTTPException(status_code=500, detail=result["error"])
report = result.get("report")
if report:
sync_all_topics()
return {"message": "Optimization completed", "summary": report["summary"]}
if report and report["summary"]["total_articles"] > 0:
s = report["summary"]
passed = s["passed_auto"]
manual = s["need_manual"]
total = s["total_articles"]
avg = s["average_score"]
msg = f"审查完成: {total} 篇, {passed} 篇通过 ({avg:.0f}分)"
if manual:
msg += f", {manual} 篇需人工处理"
return {"message": msg, "summary": s}
else:
return {"message": "Optimization completed", "stdout": result.get("stdout", "")}
if topic_ids:
updated = 0
for tid in topic_ids:
topic = db.query(Topic).filter(Topic.id == tid).first()
if topic and topic.status in ('review', '待审查'):
topic.status = 'ready'
if not topic.generated_at:
topic.generated_at = datetime.utcnow()
updated += 1
db.commit()
if updated:
logger.info(f"Review: {updated} topics advanced to 'ready' (no release files)")
return {"message": "审查完成(未找到 release 文件,仅推进状态)", "stdout": result.get("stdout", "")}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@@ -152,4 +171,48 @@ def refresh_all():
@router.get("/scheduler/status", dependencies=[Depends(get_current_user)])
def get_scheduler_status():
return {"jobs": scheduler.get_jobs()}
return {"running": scheduler._started, "jobs": scheduler.get_jobs()}
@router.get("/modules/status", dependencies=[Depends(get_current_user)])
def get_modules_status():
today_str = date.today().isoformat()
module_logs = {
"creator": {
"key": "🤖 内容创作引擎",
"log": LOGS_DIR / f"creator_{today_str}.log",
"config_file": PROJECT_ROOT / "automation" / "data" / "outlines" / today_str,
},
"optimizer": {
"key": "🔍 内容优化器",
"log": LOGS_DIR / f"optimizer_{today_str}.log",
"config_file": PROJECT_ROOT / "automation" / "data" / "drafts" / today_str,
},
"collector": {
"key": "📡 内容收集器",
"log": LOGS_DIR / f"collector_{today_str}.log",
"config_file": PROJECT_ROOT / "automation" / "data",
},
}
modules = []
for mod_id, cfg in module_logs.items():
log_file = cfg["log"]
last_run = None
task_count = 0
success_rate = None
if log_file.exists():
mtime = datetime.fromtimestamp(log_file.stat().st_mtime)
last_run = mtime.strftime("%Y-%m-%d %H:%M")
content = log_file.read_text(encoding="utf-8", errors="ignore")
task_count = content.count("完成") + content.count("success") + content.count("SUCCESS")
total = task_count + content.count("失败") + content.count("failed") + content.count("ERROR")
success_rate = round(task_count / total * 100) if total > 0 else None
modules.append({
"id": mod_id,
"title": cfg["key"],
"status": "running" if log_file.exists() else "stopped",
"last_run": last_run or "从未运行",
"task_count": task_count,
"success_rate": success_rate,
})
return {"modules": modules, "scheduler": {"running": scheduler._started, "jobs": scheduler.get_jobs()}}
+19 -16
View File
@@ -88,9 +88,9 @@ def start_task(
if not task:
raise HTTPException(status_code=404, detail="任务不存在")
from datetime import datetime
from datetime import datetime, timezone
task.status = "running"
task.started_at = datetime.now()
task.started_at = datetime.now(timezone.utc)
task.message = "任务已启动"
task.progress = 0
db.commit()
@@ -130,16 +130,17 @@ def complete_task(
if not task:
raise HTTPException(status_code=404, detail="任务不存在")
from datetime import datetime
from datetime import datetime, timezone
finished = datetime.now(timezone.utc)
task.status = "completed"
task.finished_at = datetime.now()
task.finished_at = finished
task.progress = 100
if message:
task.message = message
if result_data:
task.result_data = result_data
if task.started_at:
task.duration = int((task.finished_at - task.started_at).total_seconds())
task.duration = int((finished - task.started_at).total_seconds())
db.commit()
db.refresh(task)
return task
@@ -156,12 +157,13 @@ def fail_task(
if not task:
raise HTTPException(status_code=404, detail="任务不存在")
from datetime import datetime
from datetime import datetime, timezone
finished = datetime.now(timezone.utc)
task.status = "failed"
task.finished_at = datetime.now()
task.finished_at = finished
task.error_msg = error_msg
if task.started_at:
task.duration = int((task.finished_at - task.started_at).total_seconds())
task.duration = int((finished - task.started_at).total_seconds())
db.commit()
db.refresh(task)
return task
@@ -189,8 +191,9 @@ def run_creator_task(
current_user=Depends(get_current_user)
):
import threading
from datetime import datetime
from datetime import datetime, timezone
now = datetime.now(timezone.utc)
task_id = f"task_{uuid.uuid4().hex[:16]}"
task = ContentTask(
@@ -198,7 +201,7 @@ def run_creator_task(
topic_id=topic_id,
stage="creator",
status="running",
started_at=datetime.now(),
started_at=now,
created_by=current_user.username
)
db.add(task)
@@ -210,22 +213,22 @@ def run_creator_task(
def _run():
try:
result = run_creator(topic_id)
from datetime import datetime
finished = datetime.now(timezone.utc)
task.status = "completed"
task.finished_at = datetime.now()
task.finished_at = finished
task.progress = 100
task.message = "创作完成"
task.result_data = result or {}
if task.started_at:
task.duration = int((task.finished_at - task.started_at).total_seconds())
task.duration = int((finished - task.started_at).total_seconds())
db.commit()
except Exception as e:
from datetime import datetime
finished = datetime.now(timezone.utc)
task.status = "failed"
task.finished_at = datetime.now()
task.finished_at = finished
task.error_msg = str(e)
if task.started_at:
task.duration = int((task.finished_at - task.started_at).total_seconds())
task.duration = int((finished - task.started_at).total_seconds())
db.commit()
thread = threading.Thread(target=_run)
+7 -3
View File
@@ -167,9 +167,13 @@ def delete_topic(
topic = db.query(Topic).filter(Topic.id == topic_id).first()
if not topic:
raise HTTPException(status_code=404, detail="Topic not found")
db.delete(topic)
db.commit()
return {"ok": True}
try:
db.delete(topic)
db.commit()
return {"ok": True}
except Exception as e:
db.rollback()
raise HTTPException(status_code=400, detail=f"删除失败:该选题有关联数据(文章/发布记录等),请先删除关联数据。{str(e)}")
@router.post("/{topic_id}/score")