Rain-Bus
21f16e6756
- Split summarizer into summary_generator and summary_persister modules - Refactor pdf_image_extractor to two-phase pipeline with PicoDet layout detection - Add layout_detector service for PicoDet-S_layout_3cls integration - Add exceptions module with ConflictError and NotFoundError - Improve admin dashboard with better statistics and task management - Add design review document with system optimization suggestions - Add new tests for crawler, pdf_downloader, pipeline, and summary_utils - Update dependencies and configuration - Clean up dead code and improve error handling
102 lines
3.3 KiB
Python
102 lines
3.3 KiB
Python
"""PDF 下载 — 从 arXiv 下载论文 PDF。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
import requests
|
|
|
|
from app.config import settings
|
|
from app.utils import PAPERS_DIR, TMP_DIR
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
# ── 自定义异常 ──────────────────────────────────────────────────────────
|
|
|
|
|
|
class PdfDownloadError(Exception):
|
|
pass
|
|
|
|
|
|
# ── 路径工具 ────────────────────────────────────────────────────────────
|
|
|
|
|
|
def paper_dir(arxiv_id: str) -> Path:
|
|
return PAPERS_DIR / arxiv_id
|
|
|
|
|
|
def tmp_dir(arxiv_id: str) -> Path:
|
|
return TMP_DIR / arxiv_id
|
|
|
|
|
|
# ── PDF 下载 ────────────────────────────────────────────────────────────
|
|
|
|
# 复用 TCP 连接的 session
|
|
_http_session: requests.Session | None = None
|
|
|
|
|
|
def _get_session() -> requests.Session:
|
|
global _http_session
|
|
if _http_session is None:
|
|
_http_session = requests.Session()
|
|
_http_session.headers.update({"User-Agent": "hf-daily-papers/1.0"})
|
|
# 代理：优先 $PROXY_SERVER，其次 settings.http_proxy
|
|
proxy = os.environ.get("PROXY_SERVER")
|
|
if proxy:
|
|
_http_session.proxies = {"http": proxy, "https": proxy}
|
|
logger.info("PDF download using proxy from $PROXY_SERVER: %s", proxy)
|
|
return _http_session
|
|
|
|
|
|
def close_http_session() -> None:
|
|
"""关闭全局 HTTP Session，供应用 shutdown 时调用。"""
|
|
global _http_session
|
|
if _http_session is not None:
|
|
_http_session.close()
|
|
_http_session = None
|
|
|
|
|
|
async def download_pdf(arxiv_id: str, pdf_url: str) -> Path:
|
|
"""下载 PDF 到 data/tmp/{arxiv_id}/paper.pdf。"""
|
|
if not pdf_url:
|
|
raise PdfDownloadError(f"no pdf_url for {arxiv_id}")
|
|
|
|
dest_dir = tmp_dir(arxiv_id)
|
|
dest_dir.mkdir(parents=True, exist_ok=True)
|
|
dest = dest_dir / "paper.pdf"
|
|
|
|
try:
|
|
session = _get_session()
|
|
resp = session.get(pdf_url, timeout=settings.PDF_DOWNLOAD_TIMEOUT, allow_redirects=True)
|
|
resp.raise_for_status()
|
|
dest.write_bytes(resp.content)
|
|
except Exception as exc:
|
|
# 清理残留的部分文件
|
|
if dest.exists():
|
|
try:
|
|
dest.unlink()
|
|
except OSError:
|
|
pass
|
|
raise PdfDownloadError(f"failed to download PDF for {arxiv_id}: {exc}") from exc
|
|
|
|
logger.info("Downloaded PDF: %s (%d bytes)", arxiv_id, dest.stat().st_size)
|
|
return dest
|
|
|
|
|
|
# ── 临时文件清理 ────────────────────────────────────────────────────────
|
|
|
|
|
|
def cleanup_tmp(arxiv_id: str) -> None:
|
|
"""清理 data/tmp/{arxiv_id}/ 目录。"""
|
|
td = tmp_dir(arxiv_id)
|
|
if td.exists():
|
|
try:
|
|
shutil.rmtree(td)
|
|
logger.debug("Cleaned tmp: %s", arxiv_id)
|
|
except Exception:
|
|
logger.warning("Failed to clean tmp for %s", arxiv_id, exc_info=True)
|