feat(papers): B-3 P2-PR1 oa_url 승격 분기 (arXiv 외 doi.org/KISTI/PMC OA)

arxiv_id 없는 OA 논문(oa_status gold/hybrid/green/diamond + oa_url)도 전문 승격 대상에 포함.
url = arxiv.org/pdf 또는 oa_url(friendly OA host). paywall/비-PDF 는 헤더검증서 skip(실패 격리).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

app/workers/paper_fulltext_promote.py

@@ -18,7 +18,7 @@ import random
 from pathlib import Path
 
 import httpx
-from sqlalchemy import select
+from sqlalchemy import or_, select
 
 from core.config import settings
 from core.crawl_politeness import CRAWL_UA
@@ -35,6 +35,9 @@ _DOWNLOAD_DELAY = (2.0, 5.0)
 _RUN_CAP = 10  # 1회 승격 상한(marker/embed GPU 보호). bulk 시 해제.
 
 _ARXIV_ID_EXPR = Document.extract_meta[("paper", "arxiv_id")].astext
+_OA_URL_EXPR = Document.extract_meta[("paper", "oa_url")].astext
+_OA_STATUS_EXPR = Document.extract_meta[("paper", "oa_status")].astext
+_REAL_OA = ("gold", "hybrid", "green", "diamond")
 
 
 async def _download(url: str, dest: Path) -> int:
@@ -62,7 +65,10 @@ async def run(bulk: bool = False, limit: int = 0) -> None:
             .where(
                 Document.material_type == "paper",
                 Document.file_format == "article",
-                _ARXIV_ID_EXPR.isnot(None),
+                or_(
+                    _ARXIV_ID_EXPR.isnot(None),
+                    Document.extract_meta[("paper", "oa_url")].astext.isnot(None),
+                ),
             )
             .order_by(Document.id.desc())
             .limit(cap)
@@ -75,15 +81,23 @@ async def run(bulk: bool = False, limit: int = 0) -> None:
             doc = await session.get(Document, doc_id)
             if doc is None or doc.file_format != "article":
                 continue
-            arxiv_id = ((doc.extract_meta or {}).get("paper") or {}).get("arxiv_id")
-            if not arxiv_id:
+            paper = (doc.extract_meta or {}).get("paper") or {}
+            arxiv_id = paper.get("arxiv_id")
+            oa_status = (paper.get("oa_status") or "").lower()
+            if arxiv_id:
+                url = _ARXIV_PDF.format(id=arxiv_id)
+                key = arxiv_id.replace("/", "_")
+            elif paper.get("oa_url") and oa_status in _REAL_OA:
+                url = paper["oa_url"]  # doi.org/KISTI/PMC (friendly OA). 비-OA·paywall 은 헤더검증서 skip
+                key = (paper.get("openalex_id") or paper.get("doi") or "oa").replace("/", "_")
+            else:
                 continue
-            rel_path = f"crawl_raw/papers/arxiv/{arxiv_id.replace('/', '_')}.pdf"
+            rel_path = f"crawl_raw/papers/{key}.pdf"
             dest = Path(settings.nas_mount_path) / rel_path
             try:
-                size = await _download(_ARXIV_PDF.format(id=arxiv_id), dest)
+                size = await _download(url, dest)
             except Exception as e:  # noqa: BLE001 — 다운로드 실패 격리
-                logger.error(f"[promote] {arxiv_id} 다운로드 실패: {e}")
+                logger.error(f"[promote] {key} 다운로드 실패: {e}")
                 failed += 1
                 continue
             # in-place 승격: 초록 행 → 전문 PDF 행 (file_hash·extract_meta.paper 보존)
@@ -96,7 +110,7 @@ async def run(bulk: bool = False, limit: int = 0) -> None:
             await enqueue_stage(session, doc.id, "extract")
             await session.commit()
             promoted += 1
-            logger.info(f"[promote] {arxiv_id} → 전문 PDF in-place (doc {doc.id}, {size}b)")
+            logger.info(f"[promote] {key} → 전문 PDF in-place (doc {doc.id}, {size}b)")
 
     logger.info(f"[paper_fulltext_promote] 승격 {promoted} · 실패 {failed} (cap {cap})")