feat: initial project structure
- Add FastAPI app with paper browsing UI and REST API - Add crawler service and database models - Add scripts for DB init and manual crawl - Add docs (api-and-ui, data-model, services) - Add requirements and project config
This commit is contained in:
+66
@@ -0,0 +1,66 @@
|
||||
"""CLI 工具 — 手动抓取论文。"""
|
||||
|
||||
import asyncio
|
||||
import sys
|
||||
from datetime import date
|
||||
|
||||
import typer
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# 在导入 app 模块前加载 .env
|
||||
load_dotenv()
|
||||
|
||||
cli_app = typer.Typer(help="HF Daily Papers 管理 CLI")
|
||||
|
||||
|
||||
@cli_app.command()
|
||||
def crawl(
|
||||
date_str: str = typer.Argument(
|
||||
None,
|
||||
help="抓取日期 (YYYY-MM-DD)，默认今天",
|
||||
),
|
||||
top_n: int = typer.Option(None, "--top", "-n", help="取前 N 篇"),
|
||||
):
|
||||
"""手动抓取指定日期的 HuggingFace Daily Papers。"""
|
||||
from app.config import settings
|
||||
from app.database import SessionLocal, engine
|
||||
from app.models import init_db as _init
|
||||
from app.services.crawler import crawl_daily
|
||||
|
||||
target = date_str or date.today().isoformat()
|
||||
|
||||
# 确保数据库和表存在
|
||||
import os
|
||||
os.makedirs(settings.db_path.parent, exist_ok=True)
|
||||
_init(engine)
|
||||
typer.echo(f"📡 开始抓取 {target} ...")
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
result = asyncio.run(crawl_daily(db, target, top_n))
|
||||
if result["status"] == "success":
|
||||
typer.echo(
|
||||
f"✅ 抓取完成：发现 {result['found']} 篇，新增 {result['new']} 篇"
|
||||
)
|
||||
else:
|
||||
typer.echo(f"❌ 抓取失败：{result['error']}", err=True)
|
||||
raise typer.Exit(code=1)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
@cli_app.command()
|
||||
def init_db():
|
||||
"""初始化数据库表。"""
|
||||
from app.config import settings
|
||||
from app.database import engine
|
||||
from app.models import init_db as _init
|
||||
|
||||
import os
|
||||
os.makedirs(settings.db_path.parent, exist_ok=True)
|
||||
_init(engine)
|
||||
typer.echo(f"✅ 数据库已初始化：{settings.db_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
cli_app()
|
||||
@@ -0,0 +1,73 @@
|
||||
"""应用配置 — 从 .env / 环境变量加载。"""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from pydantic_settings import BaseSettings
|
||||
|
||||
BASE_DIR = Path(__file__).resolve().parent.parent
|
||||
|
||||
|
||||
class Settings(BaseSettings):
|
||||
# 应用
|
||||
APP_HOST: str = "127.0.0.1"
|
||||
APP_PORT: int = 8000
|
||||
APP_DEBUG: bool = False
|
||||
BASE_URL: str = "http://127.0.0.1:8000"
|
||||
APP_TIMEZONE: str = "Asia/Shanghai"
|
||||
|
||||
# 安全
|
||||
ADMIN_TOKEN: str = "change-me"
|
||||
|
||||
# HuggingFace / arXiv
|
||||
HF_API_BASE: str = "https://huggingface.co/api"
|
||||
HF_PROXY: str = ""
|
||||
TOP_N: int = 20
|
||||
HTTP_TIMEOUT_SECONDS: int = 30
|
||||
HTTP_MAX_RETRIES: int = 3
|
||||
HTTP_USER_AGENT: str = "hf-daily-papers-local/0.1"
|
||||
|
||||
# AI 总结（Phase 2）
|
||||
PI_BIN: str = ""
|
||||
SUMMARY_SKILL: str = "daily-paper-summary"
|
||||
SUMMARY_CONCURRENCY: int = 3
|
||||
SUMMARY_TIMEOUT_SECONDS: int = 300
|
||||
SUMMARY_MAX_RETRIES: int = 1
|
||||
|
||||
# 调度（Phase 4）
|
||||
SCHEDULER_ENABLED: bool = False
|
||||
SCHEDULE_HOUR: int = 8
|
||||
SCHEDULE_MINUTE: int = 0
|
||||
APP_WORKERS: int = 1
|
||||
|
||||
# 数据库
|
||||
DATABASE_URL: str = "sqlite:///data/db/papers.db"
|
||||
|
||||
# 语义搜索（Phase 5）
|
||||
CHROMA_ENABLED: bool = False
|
||||
CHROMA_DIR: str = "data/chroma"
|
||||
EMBED_API_BASE: str = ""
|
||||
EMBED_API_KEY: str = ""
|
||||
EMBED_MODEL: str = ""
|
||||
EMBED_DIMENSIONS: int = 0
|
||||
|
||||
model_config = {
|
||||
"env_file": str(BASE_DIR / ".env"),
|
||||
"env_file_encoding": "utf-8",
|
||||
"extra": "ignore",
|
||||
}
|
||||
|
||||
@property
|
||||
def db_path(self) -> Path:
|
||||
"""从 DATABASE_URL 解析出 SQLite 文件路径。"""
|
||||
# sqlite:///data/db/papers.db → data/db/papers.db
|
||||
url = self.DATABASE_URL
|
||||
if url.startswith("sqlite:///"):
|
||||
return BASE_DIR / url[len("sqlite:///"):]
|
||||
raise ValueError(f"Unsupported DATABASE_URL: {url}")
|
||||
|
||||
@property
|
||||
def http_proxy(self) -> str | None:
|
||||
return self.HF_PROXY or None
|
||||
|
||||
|
||||
settings = Settings()
|
||||
@@ -0,0 +1,41 @@
|
||||
"""数据库引擎、会话工厂、初始化。"""
|
||||
|
||||
from sqlalchemy import event, create_engine
|
||||
from sqlalchemy.orm import DeclarativeBase, sessionmaker
|
||||
|
||||
from app.config import settings
|
||||
|
||||
|
||||
class Base(DeclarativeBase):
|
||||
pass
|
||||
|
||||
|
||||
def _make_engine():
|
||||
"""创建 SQLite 引擎，启用 foreign_keys。"""
|
||||
engine = create_engine(
|
||||
settings.DATABASE_URL,
|
||||
echo=settings.APP_DEBUG,
|
||||
connect_args={"check_same_thread": False},
|
||||
)
|
||||
|
||||
@event.listens_for(engine, "connect")
|
||||
def _set_sqlite_pragma(dbapi_connection, _connection_record):
|
||||
cursor = dbapi_connection.cursor()
|
||||
cursor.execute("PRAGMA foreign_keys=ON")
|
||||
cursor.execute("PRAGMA journal_mode=WAL")
|
||||
cursor.close()
|
||||
|
||||
return engine
|
||||
|
||||
|
||||
engine = _make_engine()
|
||||
SessionLocal = sessionmaker(bind=engine, autoflush=False, autocommit=False)
|
||||
|
||||
|
||||
def get_db():
|
||||
"""FastAPI 依赖注入：获取数据库会话。"""
|
||||
db = SessionLocal()
|
||||
try:
|
||||
yield db
|
||||
finally:
|
||||
db.close()
|
||||
+59
@@ -0,0 +1,59 @@
|
||||
"""FastAPI 应用入口。"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
|
||||
from fastapi import FastAPI
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
|
||||
from app.config import settings
|
||||
from app.database import engine
|
||||
from app.models import init_db
|
||||
from app.routes.pages import router as pages_router
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.DEBUG if settings.APP_DEBUG else logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def create_app() -> FastAPI:
|
||||
app = FastAPI(
|
||||
title="HF Daily Papers",
|
||||
description="HuggingFace Daily Papers — 中文论文导览站",
|
||||
version="0.1.0",
|
||||
)
|
||||
|
||||
# 确保数据目录存在
|
||||
os.makedirs(settings.db_path.parent, exist_ok=True)
|
||||
|
||||
# 初始化数据库
|
||||
init_db(engine)
|
||||
logger.info("Database initialized at %s", settings.db_path)
|
||||
|
||||
# 安全警告
|
||||
if settings.ADMIN_TOKEN == "change-me":
|
||||
logger.warning("⚠️ ADMIN_TOKEN is the default value 'change-me'. Please change it in .env!")
|
||||
|
||||
# 静态文件
|
||||
app.mount("/static", StaticFiles(directory="app/static"), name="static")
|
||||
|
||||
# 路由
|
||||
app.include_router(pages_router)
|
||||
|
||||
return app
|
||||
|
||||
|
||||
app = create_app()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(
|
||||
"app.main:app",
|
||||
host=settings.APP_HOST,
|
||||
port=settings.APP_PORT,
|
||||
reload=settings.APP_DEBUG,
|
||||
)
|
||||
+235
@@ -0,0 +1,235 @@
|
||||
"""SQLAlchemy ORM 模型 — papers, authors, tags, summaries, FTS5, logs, locks, user data。"""
|
||||
|
||||
from datetime import date, datetime
|
||||
|
||||
from sqlalchemy import (
|
||||
Boolean,
|
||||
Column,
|
||||
Date,
|
||||
DateTime,
|
||||
ForeignKey,
|
||||
Index,
|
||||
Integer,
|
||||
String,
|
||||
Text,
|
||||
UniqueConstraint,
|
||||
text,
|
||||
)
|
||||
from sqlalchemy.orm import relationship
|
||||
|
||||
from app.database import Base
|
||||
|
||||
|
||||
# ── papers ──────────────────────────────────────────────────────────────
|
||||
class Paper(Base):
|
||||
__tablename__ = "papers"
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
arxiv_id = Column(String, unique=True, nullable=False, index=True)
|
||||
title_en = Column(String, nullable=False)
|
||||
title_zh = Column(String)
|
||||
abstract = Column(Text)
|
||||
published_at = Column(Date)
|
||||
paper_date = Column(Date, nullable=False, index=True)
|
||||
crawled_at = Column(DateTime, nullable=False)
|
||||
upvotes = Column(Integer, default=0)
|
||||
hf_url = Column(String)
|
||||
arxiv_url = Column(String)
|
||||
pdf_url = Column(String)
|
||||
source_url = Column(String)
|
||||
asset_status = Column(String, default="not_downloaded")
|
||||
asset_error = Column(String)
|
||||
meta_path = Column(String)
|
||||
summary_path = Column(String)
|
||||
raw_output_path = Column(String)
|
||||
summary_quality = Column(String)
|
||||
|
||||
authors = relationship("PaperAuthor", back_populates="paper", cascade="all, delete-orphan")
|
||||
tags = relationship("PaperTag", back_populates="paper", cascade="all, delete-orphan")
|
||||
summary = relationship("PaperSummary", back_populates="paper", uselist=False, cascade="all, delete-orphan")
|
||||
summary_status = relationship("SummaryStatus", back_populates="paper", uselist=False, cascade="all, delete-orphan")
|
||||
bookmark = relationship("UserBookmark", back_populates="paper", uselist=False, cascade="all, delete-orphan")
|
||||
reading_status = relationship("UserReadingStatus", back_populates="paper", uselist=False, cascade="all, delete-orphan")
|
||||
note = relationship("UserNote", back_populates="paper", uselist=False, cascade="all, delete-orphan")
|
||||
|
||||
|
||||
# ── paper_authors ───────────────────────────────────────────────────────
|
||||
class PaperAuthor(Base):
|
||||
__tablename__ = "paper_authors"
|
||||
__table_args__ = (UniqueConstraint("paper_id", "name"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
name = Column(String, nullable=False)
|
||||
position = Column(Integer, default=0)
|
||||
|
||||
paper = relationship("Paper", back_populates="authors")
|
||||
|
||||
|
||||
# ── paper_tags ──────────────────────────────────────────────────────────
|
||||
class PaperTag(Base):
|
||||
__tablename__ = "paper_tags"
|
||||
__table_args__ = (UniqueConstraint("paper_id", "tag", "source"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
tag = Column(String, nullable=False)
|
||||
source = Column(String, default="hf")
|
||||
|
||||
paper = relationship("Paper", back_populates="tags")
|
||||
|
||||
|
||||
# ── paper_summaries ─────────────────────────────────────────────────────
|
||||
class PaperSummary(Base):
|
||||
__tablename__ = "paper_summaries"
|
||||
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), primary_key=True)
|
||||
one_line = Column(Text)
|
||||
difficulty = Column(String)
|
||||
prerequisites_json = Column(Text)
|
||||
motivation_problem = Column(Text)
|
||||
motivation_goal = Column(Text)
|
||||
motivation_gap = Column(Text)
|
||||
method_overview = Column(Text)
|
||||
method_key_idea = Column(Text)
|
||||
method_steps_json = Column(Text)
|
||||
method_novelty = Column(Text)
|
||||
results_main_json = Column(Text)
|
||||
results_benchmarks_json = Column(Text)
|
||||
limitations_json = Column(Text)
|
||||
weaknesses_json = Column(Text)
|
||||
future_work_json = Column(Text)
|
||||
reproducibility = Column(String)
|
||||
full_json = Column(Text, nullable=False)
|
||||
updated_at = Column(DateTime, nullable=False)
|
||||
|
||||
paper = relationship("Paper", back_populates="summary")
|
||||
|
||||
|
||||
# ── summary_status ──────────────────────────────────────────────────────
|
||||
class SummaryStatus(Base):
|
||||
__tablename__ = "summary_status"
|
||||
__table_args__ = (UniqueConstraint("paper_id"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
status = Column(String, nullable=False, default="pending")
|
||||
quality = Column(String)
|
||||
error_type = Column(String)
|
||||
error = Column(Text)
|
||||
retry_count = Column(Integer, default=0)
|
||||
raw_output_saved = Column(Boolean, default=False)
|
||||
started_at = Column(DateTime)
|
||||
completed_at = Column(DateTime)
|
||||
|
||||
paper = relationship("Paper", back_populates="summary_status")
|
||||
|
||||
|
||||
# ── crawl_logs ──────────────────────────────────────────────────────────
|
||||
class CrawlLog(Base):
|
||||
__tablename__ = "crawl_logs"
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
task = Column(String, nullable=False)
|
||||
status = Column(String, nullable=False)
|
||||
date = Column(Date)
|
||||
papers_found = Column(Integer)
|
||||
papers_new = Column(Integer)
|
||||
error = Column(Text)
|
||||
started_at = Column(DateTime, nullable=False)
|
||||
completed_at = Column(DateTime)
|
||||
|
||||
|
||||
# ── task_locks ──────────────────────────────────────────────────────────
|
||||
class TaskLock(Base):
|
||||
__tablename__ = "task_locks"
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
task = Column(String, nullable=False)
|
||||
lock_key = Column(String, nullable=False)
|
||||
status = Column(String, nullable=False)
|
||||
owner = Column(String)
|
||||
acquired_at = Column(DateTime, nullable=False)
|
||||
released_at = Column(DateTime)
|
||||
|
||||
|
||||
# ── user data ──────────────────────────────────────────────────────────
|
||||
class UserBookmark(Base):
|
||||
__tablename__ = "user_bookmarks"
|
||||
__table_args__ = (UniqueConstraint("paper_id"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
note = Column(Text)
|
||||
created_at = Column(DateTime, nullable=False)
|
||||
|
||||
paper = relationship("Paper", back_populates="bookmark")
|
||||
|
||||
|
||||
class UserReadingStatus(Base):
|
||||
__tablename__ = "user_reading_status"
|
||||
__table_args__ = (UniqueConstraint("paper_id"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
status = Column(String, nullable=False, default="unread")
|
||||
updated_at = Column(DateTime, nullable=False)
|
||||
|
||||
paper = relationship("Paper", back_populates="reading_status")
|
||||
|
||||
|
||||
class UserNote(Base):
|
||||
__tablename__ = "user_notes"
|
||||
__table_args__ = (UniqueConstraint("paper_id"),)
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
paper_id = Column(Integer, ForeignKey("papers.id", ondelete="CASCADE"), nullable=False)
|
||||
content = Column(Text, nullable=False)
|
||||
created_at = Column(DateTime, nullable=False)
|
||||
updated_at = Column(DateTime, nullable=False)
|
||||
|
||||
paper = relationship("Paper", back_populates="note")
|
||||
|
||||
|
||||
# ── data_delete_jobs ───────────────────────────────────────────────────
|
||||
class DataDeleteJob(Base):
|
||||
__tablename__ = "data_delete_jobs"
|
||||
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
date_start = Column(Date, nullable=False)
|
||||
date_end = Column(Date, nullable=False)
|
||||
include_notes = Column(Boolean, default=True)
|
||||
paper_count = Column(Integer, default=0)
|
||||
status = Column(String, nullable=False)
|
||||
error = Column(Text)
|
||||
started_at = Column(DateTime, nullable=False)
|
||||
completed_at = Column(DateTime)
|
||||
|
||||
|
||||
# ── FTS5 索引初始化 SQL（普通虚拟表，由应用层维护）──────────────────────
|
||||
FTS5_CREATE_SQL = """
|
||||
CREATE VIRTUAL TABLE IF NOT EXISTS papers_fts USING fts5(
|
||||
title_en,
|
||||
title_zh,
|
||||
abstract,
|
||||
authors,
|
||||
tags,
|
||||
summary_text,
|
||||
tokenize='unicode61'
|
||||
);
|
||||
"""
|
||||
|
||||
FTS5_TRIGGER_INDEX = """
|
||||
-- partial index for task_locks running
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS uq_task_locks_running
|
||||
ON task_locks(task, lock_key) WHERE status = 'running';
|
||||
"""
|
||||
|
||||
|
||||
def init_db(engine):
|
||||
"""创建所有 ORM 表 + FTS5 虚拟表。"""
|
||||
Base.metadata.create_all(engine)
|
||||
with engine.connect() as conn:
|
||||
conn.execute(text(FTS5_CREATE_SQL))
|
||||
conn.execute(text(FTS5_TRIGGER_INDEX))
|
||||
conn.commit()
|
||||
@@ -0,0 +1,109 @@
|
||||
"""页面路由 — 首页、日期页、论文详情。"""
|
||||
|
||||
from datetime import date, datetime, timedelta
|
||||
from zoneinfo import ZoneInfo
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Request
|
||||
from fastapi.responses import RedirectResponse
|
||||
from fastapi.templating import Jinja2Templates
|
||||
from sqlalchemy.orm import Session, joinedload
|
||||
|
||||
from app.config import settings
|
||||
from app.database import get_db
|
||||
from app.models import Paper
|
||||
|
||||
router = APIRouter()
|
||||
templates = Jinja2Templates(directory="app/templates")
|
||||
|
||||
|
||||
def _today() -> str:
|
||||
tz = ZoneInfo(settings.APP_TIMEZONE)
|
||||
return datetime.now(tz).strftime("%Y-%m-%d")
|
||||
|
||||
|
||||
@router.get("/")
|
||||
def index(request: Request):
|
||||
"""重定向到 /day/{today}。"""
|
||||
return RedirectResponse(url=f"/day/{_today()}")
|
||||
|
||||
|
||||
@router.get("/day/{date_str}")
|
||||
def day_page(date_str: str, request: Request, db: Session = Depends(get_db)):
|
||||
"""指定日期论文列表。"""
|
||||
try:
|
||||
target = date.fromisoformat(date_str)
|
||||
except ValueError:
|
||||
raise HTTPException(status_code=404, detail="Invalid date format")
|
||||
|
||||
prev_day = (target - timedelta(days=1)).isoformat()
|
||||
next_day = (target + timedelta(days=1)).isoformat()
|
||||
today_str = _today()
|
||||
|
||||
papers = (
|
||||
db.query(Paper)
|
||||
.filter(Paper.paper_date == date_str)
|
||||
.options(
|
||||
joinedload(Paper.authors),
|
||||
joinedload(Paper.tags),
|
||||
joinedload(Paper.summary_status),
|
||||
joinedload(Paper.bookmark),
|
||||
)
|
||||
.order_by(Paper.upvotes.desc())
|
||||
.all()
|
||||
)
|
||||
|
||||
dates_raw = (
|
||||
db.query(Paper.paper_date)
|
||||
.distinct()
|
||||
.order_by(Paper.paper_date.desc())
|
||||
.limit(30)
|
||||
.all()
|
||||
)
|
||||
available_dates = [d[0].isoformat() if isinstance(d[0], date) else str(d[0]) for d in dates_raw]
|
||||
|
||||
return templates.TemplateResponse(
|
||||
request, "index.html",
|
||||
{
|
||||
"papers": papers,
|
||||
"current_date": date_str,
|
||||
"prev_day": prev_day,
|
||||
"next_day": next_day,
|
||||
"today": today_str,
|
||||
"available_dates": available_dates,
|
||||
"page_title": f"{date_str} 论文列表",
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@router.get("/paper/{arxiv_id}")
|
||||
def paper_detail(arxiv_id: str, request: Request, db: Session = Depends(get_db)):
|
||||
"""论文详情页。"""
|
||||
paper = (
|
||||
db.query(Paper)
|
||||
.filter(Paper.arxiv_id == arxiv_id)
|
||||
.options(
|
||||
joinedload(Paper.authors),
|
||||
joinedload(Paper.tags),
|
||||
joinedload(Paper.summary),
|
||||
joinedload(Paper.summary_status),
|
||||
joinedload(Paper.bookmark),
|
||||
joinedload(Paper.reading_status),
|
||||
joinedload(Paper.note),
|
||||
)
|
||||
.first()
|
||||
)
|
||||
if not paper:
|
||||
raise HTTPException(status_code=404, detail="Paper not found")
|
||||
|
||||
summary_state = "none"
|
||||
if paper.summary_status:
|
||||
summary_state = paper.summary_status.status
|
||||
|
||||
return templates.TemplateResponse(
|
||||
request, "detail.html",
|
||||
{
|
||||
"paper": paper,
|
||||
"summary_state": summary_state,
|
||||
"page_title": paper.title_zh or paper.title_en,
|
||||
},
|
||||
)
|
||||
@@ -0,0 +1,182 @@
|
||||
"""爬虫服务 — 从 HuggingFace Daily Papers API 抓取论文元数据。"""
|
||||
|
||||
import logging
|
||||
from datetime import date as date_type
|
||||
from datetime import datetime, timezone
|
||||
|
||||
import httpx
|
||||
from sqlalchemy import select, text
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.config import settings
|
||||
from app.models import (
|
||||
CrawlLog,
|
||||
Paper,
|
||||
PaperAuthor,
|
||||
PaperTag,
|
||||
SummaryStatus,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def fetch_daily(target_date: str, top_n: int | None = None) -> list[dict]:
|
||||
"""从 HF Daily Papers API 获取指定日期的论文列表。
|
||||
|
||||
Args:
|
||||
target_date: YYYY-MM-DD 格式
|
||||
top_n: 取前 N 篇，默认使用 settings.TOP_N
|
||||
|
||||
Returns:
|
||||
论文元数据列表
|
||||
"""
|
||||
top_n = top_n or settings.TOP_N
|
||||
url = f"{settings.HF_API_BASE}/daily_papers"
|
||||
params = {"date": target_date}
|
||||
|
||||
transport = None
|
||||
if settings.http_proxy:
|
||||
transport = httpx.AsyncHTTPTransport(proxy=settings.http_proxy)
|
||||
|
||||
async with httpx.AsyncClient(
|
||||
timeout=settings.HTTP_TIMEOUT_SECONDS,
|
||||
headers={"User-Agent": settings.HTTP_USER_AGENT},
|
||||
transport=transport,
|
||||
) as client:
|
||||
for attempt in range(1, settings.HTTP_MAX_RETRIES + 1):
|
||||
try:
|
||||
logger.info("Fetching HF Daily Papers: date=%s attempt=%d", target_date, attempt)
|
||||
resp = await client.get(url, params=params)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
break
|
||||
except (httpx.HTTPError, httpx.HTTPStatusError) as exc:
|
||||
logger.warning("Fetch failed (attempt %d/%d): %s", attempt, settings.HTTP_MAX_RETRIES, exc)
|
||||
if attempt == settings.HTTP_MAX_RETRIES:
|
||||
raise
|
||||
else:
|
||||
data = []
|
||||
|
||||
papers = data[:top_n]
|
||||
logger.info("Fetched %d papers for %s (raw=%d)", len(papers), target_date, len(data))
|
||||
return papers
|
||||
|
||||
|
||||
def _parse_paper(item: dict) -> dict:
|
||||
"""从 HF API 响应中提取论文元数据。"""
|
||||
paper_info = item.get("paper", item)
|
||||
arxiv_id = paper_info.get("id", "")
|
||||
published_raw = paper_info.get("publishedAt", "")
|
||||
published_at = None
|
||||
if published_raw:
|
||||
try:
|
||||
published_at = date_type.fromisoformat(published_raw[:10])
|
||||
except ValueError:
|
||||
pass
|
||||
return {
|
||||
"arxiv_id": arxiv_id,
|
||||
"title_en": paper_info.get("title", ""),
|
||||
"abstract": paper_info.get("abstract", ""),
|
||||
"published_at": published_at,
|
||||
"upvotes": item.get("paper", {}).get("upvotes", 0) or item.get("upvotes", 0),
|
||||
"hf_url": f"https://huggingface.co/papers/{arxiv_id}" if arxiv_id else "",
|
||||
"arxiv_url": f"https://arxiv.org/abs/{arxiv_id}" if arxiv_id else "",
|
||||
"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf" if arxiv_id else "",
|
||||
"authors": [a.get("name", a) if isinstance(a, dict) else a for a in paper_info.get("authors", [])],
|
||||
"tags": [t.get("name", t) if isinstance(t, dict) else t for t in (paper_info.get("tags") or [])],
|
||||
}
|
||||
|
||||
|
||||
def upsert_papers(db: Session, papers_raw: list[dict], paper_date: str) -> list[Paper]:
|
||||
"""将论文元数据写入数据库。已有论文仅更新可变字段（upvotes 等），不重复插入。"""
|
||||
now = datetime.now(timezone.utc)
|
||||
paper_date_obj = date_type.fromisoformat(paper_date)
|
||||
new_papers: list[Paper] = []
|
||||
|
||||
for item in papers_raw:
|
||||
meta = _parse_paper(item)
|
||||
arxiv_id = meta["arxiv_id"]
|
||||
if not arxiv_id:
|
||||
continue
|
||||
|
||||
existing = db.execute(
|
||||
select(Paper).where(Paper.arxiv_id == arxiv_id)
|
||||
).scalar_one_or_none()
|
||||
|
||||
if existing:
|
||||
existing.upvotes = meta["upvotes"]
|
||||
existing.crawled_at = now
|
||||
logger.debug("Updated existing paper: %s", arxiv_id)
|
||||
else:
|
||||
paper = Paper(
|
||||
arxiv_id=arxiv_id,
|
||||
title_en=meta["title_en"],
|
||||
abstract=meta["abstract"],
|
||||
published_at=meta["published_at"],
|
||||
paper_date=paper_date_obj,
|
||||
crawled_at=now,
|
||||
upvotes=meta["upvotes"],
|
||||
hf_url=meta["hf_url"],
|
||||
arxiv_url=meta["arxiv_url"],
|
||||
pdf_url=meta["pdf_url"],
|
||||
)
|
||||
db.add(paper)
|
||||
db.flush()
|
||||
|
||||
for idx, name in enumerate(meta["authors"]):
|
||||
if name:
|
||||
db.add(PaperAuthor(paper_id=paper.id, name=name, position=idx))
|
||||
|
||||
for tag_name in meta["tags"]:
|
||||
if tag_name:
|
||||
db.add(PaperTag(paper_id=paper.id, tag=tag_name, source="hf"))
|
||||
|
||||
db.add(SummaryStatus(paper_id=paper.id, status="pending"))
|
||||
|
||||
authors_text = ", ".join(meta["authors"])
|
||||
tags_text = ", ".join(meta["tags"])
|
||||
db.execute(
|
||||
text(
|
||||
"INSERT INTO papers_fts(rowid, title_en, abstract, authors, tags) "
|
||||
"VALUES (:id, :title, :abstract, :authors, :tags)"
|
||||
),
|
||||
{"id": paper.id, "title": meta["title_en"], "abstract": meta["abstract"] or "",
|
||||
"authors": authors_text, "tags": tags_text},
|
||||
)
|
||||
|
||||
new_papers.append(paper)
|
||||
logger.debug("Inserted new paper: %s", arxiv_id)
|
||||
|
||||
db.commit()
|
||||
logger.info("Upserted %d papers (%d new) for %s", len(papers_raw), len(new_papers), paper_date)
|
||||
return new_papers
|
||||
|
||||
|
||||
async def crawl_daily(db: Session, target_date: str, top_n: int | None = None) -> dict:
|
||||
"""完整的抓取流程：获取 + 入库 + 写日志。"""
|
||||
now = datetime.now(timezone.utc)
|
||||
log_entry = CrawlLog(
|
||||
task="crawl",
|
||||
status="running",
|
||||
date=date_type.fromisoformat(target_date),
|
||||
started_at=now,
|
||||
)
|
||||
db.add(log_entry)
|
||||
db.commit()
|
||||
|
||||
try:
|
||||
raw_papers = await fetch_daily(target_date, top_n)
|
||||
new_papers = upsert_papers(db, raw_papers, target_date)
|
||||
log_entry.status = "success"
|
||||
log_entry.papers_found = len(raw_papers)
|
||||
log_entry.papers_new = len(new_papers)
|
||||
log_entry.completed_at = datetime.now(timezone.utc)
|
||||
db.commit()
|
||||
return {"found": len(raw_papers), "new": len(new_papers), "status": "success", "error": None}
|
||||
except Exception as exc:
|
||||
logger.exception("Crawl failed for %s", target_date)
|
||||
log_entry.status = "failed"
|
||||
log_entry.error = str(exc)
|
||||
log_entry.completed_at = datetime.now(timezone.utc)
|
||||
db.commit()
|
||||
return {"found": 0, "new": 0, "status": "failed", "error": str(exc)}
|
||||
@@ -0,0 +1,338 @@
|
||||
/* ── kami 风格参考：纸张质感、留白、墨蓝强调色 ─────────────────── */
|
||||
:root {
|
||||
--bg: #faf8f5;
|
||||
--surface: #ffffff;
|
||||
--ink: #1a1a2e;
|
||||
--ink-light: #4a4a6a;
|
||||
--accent: #2d5f8a;
|
||||
--accent-hover: #1d4a6f;
|
||||
--border: #e8e4df;
|
||||
--shadow: rgba(0, 0, 0, 0.06);
|
||||
--radius: 8px;
|
||||
--font-body: "Noto Serif SC", "Georgia", serif;
|
||||
--font-sans: "Inter", "Noto Sans SC", system-ui, sans-serif;
|
||||
--max-width: 960px;
|
||||
}
|
||||
|
||||
*, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
|
||||
|
||||
body {
|
||||
font-family: var(--font-sans);
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.7;
|
||||
-webkit-font-smoothing: antialiased;
|
||||
}
|
||||
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { color: var(--accent-hover); text-decoration: underline; }
|
||||
|
||||
/* ── Header ─────────────────────────────────────────────────────── */
|
||||
.site-header {
|
||||
background: var(--surface);
|
||||
border-bottom: 1px solid var(--border);
|
||||
position: sticky;
|
||||
top: 0;
|
||||
z-index: 100;
|
||||
}
|
||||
|
||||
.nav-bar {
|
||||
max-width: var(--max-width);
|
||||
margin: 0 auto;
|
||||
padding: 12px 24px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 24px;
|
||||
}
|
||||
|
||||
.nav-brand {
|
||||
font-family: var(--font-body);
|
||||
font-size: 1.2rem;
|
||||
font-weight: 700;
|
||||
color: var(--ink);
|
||||
}
|
||||
|
||||
.nav-links { display: flex; gap: 16px; margin-left: auto; }
|
||||
.nav-links a { font-size: 0.9rem; color: var(--ink-light); }
|
||||
.nav-links a:hover { color: var(--accent); }
|
||||
|
||||
/* ── Container ──────────────────────────────────────────────────── */
|
||||
.container {
|
||||
max-width: var(--max-width);
|
||||
margin: 0 auto;
|
||||
padding: 24px;
|
||||
}
|
||||
|
||||
/* ── Date Navigation ────────────────────────────────────────────── */
|
||||
.date-nav {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 16px;
|
||||
margin-bottom: 24px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.date-title {
|
||||
font-family: var(--font-body);
|
||||
font-size: 1.5rem;
|
||||
font-weight: 700;
|
||||
}
|
||||
|
||||
.date-nav-btn {
|
||||
display: inline-block;
|
||||
padding: 6px 14px;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
font-size: 0.85rem;
|
||||
color: var(--ink-light);
|
||||
transition: all 0.2s;
|
||||
}
|
||||
.date-nav-btn:hover { border-color: var(--accent); color: var(--accent); text-decoration: none; }
|
||||
|
||||
/* ── Date Chips ─────────────────────────────────────────────────── */
|
||||
.date-quick-nav {
|
||||
margin-top: 32px;
|
||||
padding-top: 16px;
|
||||
border-top: 1px solid var(--border);
|
||||
font-size: 0.85rem;
|
||||
color: var(--ink-light);
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.date-chip {
|
||||
padding: 4px 10px;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 4px;
|
||||
font-size: 0.8rem;
|
||||
color: var(--ink-light);
|
||||
}
|
||||
.date-chip:hover { border-color: var(--accent); color: var(--accent); text-decoration: none; }
|
||||
.date-chip.active { background: var(--accent); color: #fff; border-color: var(--accent); }
|
||||
|
||||
/* ── Paper Card ─────────────────────────────────────────────────── */
|
||||
.paper-list { display: flex; flex-direction: column; gap: 16px; }
|
||||
|
||||
.paper-card {
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
padding: 20px 24px;
|
||||
transition: box-shadow 0.2s;
|
||||
}
|
||||
.paper-card:hover { box-shadow: 0 2px 12px var(--shadow); }
|
||||
|
||||
.paper-card-header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: flex-start;
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.paper-title {
|
||||
font-family: var(--font-body);
|
||||
font-size: 1.1rem;
|
||||
font-weight: 600;
|
||||
line-height: 1.5;
|
||||
flex: 1;
|
||||
}
|
||||
.paper-title a { color: var(--ink); }
|
||||
.paper-title a:hover { color: var(--accent); }
|
||||
|
||||
.paper-upvotes {
|
||||
font-size: 0.85rem;
|
||||
color: var(--ink-light);
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.paper-one-line, .paper-abstract-preview {
|
||||
margin-top: 8px;
|
||||
color: var(--ink-light);
|
||||
font-size: 0.92rem;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.paper-meta {
|
||||
margin-top: 8px;
|
||||
font-size: 0.82rem;
|
||||
color: var(--ink-light);
|
||||
}
|
||||
|
||||
.paper-tags {
|
||||
margin-top: 8px;
|
||||
display: flex;
|
||||
gap: 6px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.tag {
|
||||
display: inline-block;
|
||||
padding: 2px 8px;
|
||||
background: #eef3f8;
|
||||
color: var(--accent);
|
||||
border-radius: 3px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
.paper-footer {
|
||||
margin-top: 12px;
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.summary-badge {
|
||||
font-size: 0.8rem;
|
||||
padding: 2px 8px;
|
||||
border-radius: 3px;
|
||||
}
|
||||
.summary-none { background: #f0f0f0; color: #888; }
|
||||
.summary-pending { background: #fff3e0; color: #e67e22; }
|
||||
.summary-processing { background: #e3f2fd; color: #1976d2; }
|
||||
.summary-done { background: #e8f5e9; color: #388e3c; }
|
||||
.summary-failed, .summary-permanent_failure { background: #fce4ec; color: #c62828; }
|
||||
|
||||
.btn-detail {
|
||||
font-size: 0.85rem;
|
||||
color: var(--accent);
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
/* ── Empty State ────────────────────────────────────────────────── */
|
||||
.empty-state {
|
||||
text-align: center;
|
||||
padding: 60px 20px;
|
||||
color: var(--ink-light);
|
||||
}
|
||||
.empty-state p:first-child { font-size: 1.2rem; }
|
||||
.hint { font-size: 0.85rem; margin-top: 8px; }
|
||||
|
||||
/* ── Paper Detail ───────────────────────────────────────────────── */
|
||||
.paper-detail { max-width: 780px; margin: 0 auto; }
|
||||
|
||||
.back-link {
|
||||
display: inline-block;
|
||||
margin-bottom: 16px;
|
||||
font-size: 0.85rem;
|
||||
color: var(--ink-light);
|
||||
}
|
||||
|
||||
.detail-title {
|
||||
font-family: var(--font-body);
|
||||
font-size: 1.6rem;
|
||||
font-weight: 700;
|
||||
line-height: 1.4;
|
||||
margin-bottom: 12px;
|
||||
}
|
||||
.detail-title .title-en {
|
||||
display: block;
|
||||
font-size: 1rem;
|
||||
font-weight: 400;
|
||||
color: var(--ink-light);
|
||||
margin-top: 4px;
|
||||
}
|
||||
|
||||
.detail-meta {
|
||||
display: flex;
|
||||
gap: 16px;
|
||||
flex-wrap: wrap;
|
||||
font-size: 0.88rem;
|
||||
color: var(--ink-light);
|
||||
margin-bottom: 12px;
|
||||
}
|
||||
|
||||
.detail-tags { margin-bottom: 12px; display: flex; gap: 6px; flex-wrap: wrap; }
|
||||
|
||||
.detail-links {
|
||||
display: flex;
|
||||
gap: 12px;
|
||||
margin-bottom: 24px;
|
||||
}
|
||||
.ext-link {
|
||||
padding: 6px 14px;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
font-size: 0.85rem;
|
||||
color: var(--ink-light);
|
||||
}
|
||||
.ext-link:hover { border-color: var(--accent); color: var(--accent); text-decoration: none; }
|
||||
|
||||
/* ── Summary Sections ───────────────────────────────────────────── */
|
||||
.summary-section {
|
||||
margin-bottom: 24px;
|
||||
padding: 20px;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
}
|
||||
|
||||
.summary-section h2 {
|
||||
font-family: var(--font-body);
|
||||
font-size: 1.05rem;
|
||||
font-weight: 600;
|
||||
margin-bottom: 8px;
|
||||
color: var(--accent);
|
||||
}
|
||||
|
||||
.summary-section p {
|
||||
font-size: 0.92rem;
|
||||
line-height: 1.8;
|
||||
}
|
||||
|
||||
.one-line {
|
||||
font-size: 1rem;
|
||||
font-weight: 500;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.abstract-section { background: #faf8f5; }
|
||||
.abstract-en { font-size: 0.9rem; color: var(--ink-light); font-style: italic; }
|
||||
|
||||
/* ── Summary Placeholders ───────────────────────────────────────── */
|
||||
.summary-placeholder {
|
||||
padding: 24px;
|
||||
text-align: center;
|
||||
border-radius: var(--radius);
|
||||
margin-bottom: 24px;
|
||||
}
|
||||
.summary-placeholder.processing { background: #e3f2fd; }
|
||||
.summary-placeholder.failed { background: #fce4ec; }
|
||||
.summary-placeholder.none { background: #f5f5f5; }
|
||||
.error-detail { font-size: 0.85rem; color: #c62828; margin-top: 8px; }
|
||||
|
||||
.quality-warning {
|
||||
padding: 10px 16px;
|
||||
background: #fff8e1;
|
||||
border: 1px solid #ffe082;
|
||||
border-radius: var(--radius);
|
||||
font-size: 0.85rem;
|
||||
color: #f57f17;
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
/* ── Footer ─────────────────────────────────────────────────────── */
|
||||
.site-footer {
|
||||
margin-top: 48px;
|
||||
padding: 20px;
|
||||
text-align: center;
|
||||
font-size: 0.8rem;
|
||||
color: var(--ink-light);
|
||||
border-top: 1px solid var(--border);
|
||||
}
|
||||
|
||||
/* ── Responsive ─────────────────────────────────────────────────── */
|
||||
@media (max-width: 640px) {
|
||||
.container { padding: 16px; }
|
||||
.nav-bar { padding: 10px 16px; }
|
||||
.date-nav { gap: 8px; }
|
||||
.date-title { font-size: 1.2rem; }
|
||||
.paper-card { padding: 14px 16px; }
|
||||
.detail-title { font-size: 1.3rem; }
|
||||
.detail-meta { flex-direction: column; gap: 4px; }
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
/* app.js — 基础前端交互（HTMX 后续增强） */
|
||||
@@ -0,0 +1,32 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>{% block title %}HF Daily Papers{% endblock %}</title>
|
||||
<link rel="stylesheet" href="/static/css/style.css">
|
||||
</head>
|
||||
<body>
|
||||
<header class="site-header">
|
||||
<nav class="nav-bar">
|
||||
<a href="/" class="nav-brand">📚 HF Daily Papers</a>
|
||||
<div class="nav-links">
|
||||
<a href="/day/{{ today }}">今日</a>
|
||||
<a href="/search">搜索</a>
|
||||
<a href="/reading-list">阅读列表</a>
|
||||
</div>
|
||||
</nav>
|
||||
</header>
|
||||
|
||||
<main class="container">
|
||||
{% block content %}{% endblock %}
|
||||
</main>
|
||||
|
||||
<footer class="site-footer">
|
||||
<p>HF Daily Papers — 中文论文导览站 · 数据来源于 <a href="https://huggingface.co/papers" target="_blank">HuggingFace</a></p>
|
||||
</footer>
|
||||
|
||||
<script src="/static/js/app.js"></script>
|
||||
{% block scripts %}{% endblock %}
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,121 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}{{ page_title }} — HF Daily Papers{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<article class="paper-detail">
|
||||
<a href="/day/{{ paper.paper_date.isoformat() }}" class="back-link">← 返回 {{ paper.paper_date.isoformat() }}</a>
|
||||
|
||||
{# 标题 #}
|
||||
<h1 class="detail-title">
|
||||
{{ paper.title_zh or paper.title_en }}
|
||||
{% if paper.title_zh and paper.title_en != paper.title_zh %}
|
||||
<small class="title-en">{{ paper.title_en }}</small>
|
||||
{% endif %}
|
||||
</h1>
|
||||
|
||||
{# 元信息 #}
|
||||
<div class="detail-meta">
|
||||
<span class="detail-authors">{{ paper.authors|map(attribute='name')|join(', ') }}</span>
|
||||
<span class="detail-date">📅 {{ paper.published_at or paper.paper_date }}</span>
|
||||
<span class="detail-upvotes">👍 {{ paper.upvotes }}</span>
|
||||
</div>
|
||||
|
||||
{# 标签 #}
|
||||
{% if paper.tags %}
|
||||
<div class="detail-tags">
|
||||
{% for tag in paper.tags %}
|
||||
<span class="tag">{{ tag.tag }}</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{# 链接 #}
|
||||
<div class="detail-links">
|
||||
{% if paper.arxiv_url %}<a href="{{ paper.arxiv_url }}" target="_blank" class="ext-link">arXiv</a>{% endif %}
|
||||
{% if paper.hf_url %}<a href="{{ paper.hf_url }}" target="_blank" class="ext-link">HuggingFace</a>{% endif %}
|
||||
{% if paper.pdf_url %}<a href="{{ paper.pdf_url }}" target="_blank" class="ext-link">PDF</a>{% endif %}
|
||||
</div>
|
||||
|
||||
{# 总结内容 — 按状态降级 #}
|
||||
{% if summary_state == 'done' and paper.summary %}
|
||||
{% if paper.summary_status and paper.summary_status.quality == 'low' %}
|
||||
<div class="quality-warning">⚠️ AI 总结质量较低，仅供参考</div>
|
||||
{% elif paper.summary_status and paper.summary_status.quality == 'degraded' %}
|
||||
<div class="quality-warning">📝 总结部分字段不完整</div>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.one_line %}
|
||||
<section class="summary-section">
|
||||
<h2>一句话摘要</h2>
|
||||
<p class="one-line">{{ paper.summary.one_line }}</p>
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.difficulty %}
|
||||
<section class="summary-section">
|
||||
<h2>难度</h2>
|
||||
<p>{{ paper.summary.difficulty }}</p>
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.motivation_problem %}
|
||||
<section class="summary-section">
|
||||
<h2>研究动机</h2>
|
||||
{% if paper.summary.motivation_problem %}<p><strong>问题：</strong>{{ paper.summary.motivation_problem }}</p>{% endif %}
|
||||
{% if paper.summary.motivation_goal %}<p><strong>目标：</strong>{{ paper.summary.motivation_goal }}</p>{% endif %}
|
||||
{% if paper.summary.motivation_gap %}<p><strong>差距：</strong>{{ paper.summary.motivation_gap }}</p>{% endif %}
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.method_key_idea %}
|
||||
<section class="summary-section">
|
||||
<h2>核心方法</h2>
|
||||
{% if paper.summary.method_overview %}<p>{{ paper.summary.method_overview }}</p>{% endif %}
|
||||
<p><strong>关键思路：</strong>{{ paper.summary.method_key_idea }}</p>
|
||||
{% if paper.summary.method_novelty %}<p><strong>新颖性：</strong>{{ paper.summary.method_novelty }}</p>{% endif %}
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.results_main_json %}
|
||||
<section class="summary-section">
|
||||
<h2>实验结果</h2>
|
||||
<p>{{ paper.summary.results_main_json }}</p>
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% if paper.summary.limitations_json %}
|
||||
<section class="summary-section">
|
||||
<h2>局限与改进</h2>
|
||||
<p>{{ paper.summary.limitations_json }}</p>
|
||||
</section>
|
||||
{% endif %}
|
||||
|
||||
{% elif summary_state == 'processing' %}
|
||||
<div class="summary-placeholder processing">
|
||||
<p>🔄 正在生成 AI 总结，请稍后刷新页面</p>
|
||||
</div>
|
||||
|
||||
{% elif summary_state in ('failed', 'permanent_failure') %}
|
||||
<div class="summary-placeholder failed">
|
||||
<p>❌ 总结生成失败{% if paper.summary_status and paper.summary_status.error_type %}（{{ paper.summary_status.error_type }}）{% endif %}</p>
|
||||
{% if paper.summary_status and paper.summary_status.error %}
|
||||
<p class="error-detail">{{ paper.summary_status.error }}</p>
|
||||
{% endif %}
|
||||
</div>
|
||||
|
||||
{% else %}
|
||||
<div class="summary-placeholder none">
|
||||
<p>📝 AI 总结尚未生成</p>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{# 英文摘要 — 始终显示 #}
|
||||
{% if paper.abstract %}
|
||||
<section class="summary-section abstract-section">
|
||||
<h2>Abstract</h2>
|
||||
<p class="abstract-en">{{ paper.abstract }}</p>
|
||||
</section>
|
||||
{% endif %}
|
||||
</article>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,36 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}{{ page_title }} — HF Daily Papers{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<div class="date-nav">
|
||||
{% if prev_day %}
|
||||
<a href="/day/{{ prev_day }}" class="date-nav-btn">← 前一天</a>
|
||||
{% endif %}
|
||||
<h1 class="date-title">{{ current_date }}</h1>
|
||||
{% if next_day <= today %}
|
||||
<a href="/day/{{ next_day }}" class="date-nav-btn">后一天 →</a>
|
||||
{% endif %}
|
||||
<a href="/day/{{ today }}" class="date-nav-btn">今日</a>
|
||||
</div>
|
||||
|
||||
{% if papers %}
|
||||
<div class="paper-list">
|
||||
{% for paper in papers %}
|
||||
{% include "partials/paper_card.html" %}
|
||||
{% endfor %}
|
||||
</div>
|
||||
{% else %}
|
||||
<div class="empty-state">
|
||||
<p>📭 当天暂无论文数据</p>
|
||||
<p class="hint">试试浏览其他日期，或使用管理接口抓取数据</p>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
<div class="date-quick-nav">
|
||||
<span>有数据的日期：</span>
|
||||
{% for d in available_dates[:10] %}
|
||||
<a href="/day/{{ d }}" class="date-chip {% if d == current_date %}active{% endif %}">{{ d }}</a>
|
||||
{% endfor %}
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,44 @@
|
||||
{# 论文卡片组件 — paper 变量必须在上下文中 #}
|
||||
<article class="paper-card" data-arxiv="{{ paper.arxiv_id }}">
|
||||
<div class="paper-card-header">
|
||||
<h2 class="paper-title">
|
||||
<a href="/paper/{{ paper.arxiv_id }}">
|
||||
{{ paper.title_zh or paper.title_en }}
|
||||
</a>
|
||||
</h2>
|
||||
<span class="paper-upvotes">👍 {{ paper.upvotes }}</span>
|
||||
</div>
|
||||
|
||||
{% if paper.summary and paper.summary.one_line %}
|
||||
<p class="paper-one-line">{{ paper.summary.one_line }}</p>
|
||||
{% elif paper.abstract %}
|
||||
<p class="paper-abstract-preview">{{ paper.abstract[:200] }}{% if paper.abstract|length > 200 %}…{% endif %}</p>
|
||||
{% endif %}
|
||||
|
||||
<div class="paper-meta">
|
||||
<span class="paper-authors">
|
||||
{{ paper.authors|map(attribute='name')|join(', ')|truncate(80) }}
|
||||
</span>
|
||||
</div>
|
||||
|
||||
<div class="paper-tags">
|
||||
{% for tag in paper.tags[:5] %}
|
||||
<span class="tag">{{ tag.tag }}</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
|
||||
<div class="paper-footer">
|
||||
<span class="summary-badge summary-{{ paper.summary_status.status if paper.summary_status else 'none' }}">
|
||||
{% if not paper.summary_status or paper.summary_status.status == 'pending' %}
|
||||
未总结
|
||||
{% elif paper.summary_status.status == 'processing' %}
|
||||
🔄 总结中
|
||||
{% elif paper.summary_status.status == 'failed' or paper.summary_status.status == 'permanent_failure' %}
|
||||
❌ 总结失败
|
||||
{% elif paper.summary_status.status == 'done' %}
|
||||
✅ 已总结
|
||||
{% endif %}
|
||||
</span>
|
||||
<a href="/paper/{{ paper.arxiv_id }}" class="btn-detail">详情 →</a>
|
||||
</div>
|
||||
</article>
|
||||
Reference in New Issue
Block a user