j

Provider/openlibrary.py

@@ -229,6 +229,30 @@ def _archive_id_from_url(url: str) -> str:
                                            "advancedsearch.php"}:
             return first
 
+
+        def edition_id_from_url(u: str) -> str:
+            """Extract an OpenLibrary edition id (OL...M) from a book URL."""
+            try:
+                p = urlparse(str(u))
+                parts = [x for x in (p.path or "").split("/") if x]
+            except Exception:
+                parts = []
+            if len(parts) >= 2 and str(parts[0]).lower() == "books":
+                return str(parts[1]).strip()
+            return ""
+
+
+        def title_hint_from_url_slug(u: str) -> str:
+            """Derive a human-friendly title hint from the URL slug."""
+            try:
+                p = urlparse(str(u))
+                parts = [x for x in (p.path or "").split("/") if x]
+                slug = parts[-1] if parts else ""
+            except Exception:
+                slug = ""
+            slug = (slug or "").strip().replace("_", " ")
+            return slug or "OpenLibrary"
+
     return ""
 
 
@@ -415,6 +439,7 @@ class OpenLibrary(Provider):
         "openlibrary.org",
         "archive.org",
     )
+    URL = URL_DOMAINS
     """Search provider for OpenLibrary books + Archive.org direct/borrow download."""
 
     def __init__(self, config: Optional[Dict[str, Any]] = None):
@@ -1419,6 +1444,64 @@ class OpenLibrary(Provider):
             log("[openlibrary] Direct download failed", file=sys.stderr)
             return None
 
+        # --- Convenience helpers for URL-driven downloads (used by download-file) ---
+
+        def search_result_from_url(self, url: str) -> Optional[SearchResult]:
+            """Build a minimal SearchResult from a bare OpenLibrary URL."""
+            edition_id = edition_id_from_url(url)
+            title_hint = title_hint_from_url_slug(url)
+            return SearchResult(
+                table="openlibrary",
+                title=title_hint,
+                path=str(url),
+                media_kind="book",
+                full_metadata={"openlibrary_id": edition_id} if edition_id else {},
+            )
+
+        def download_url(
+            self,
+            url: str,
+            output_dir: Path,
+            progress_callback: Optional[Callable[[str, int, Optional[int], str], None]] = None,
+        ) -> Optional[Dict[str, Any]]:
+            """Download a book directly from an OpenLibrary URL.
+
+            Returns a dict with the downloaded path and SearchResult when successful.
+            """
+            sr = self.search_result_from_url(url)
+            if sr is None:
+                return None
+
+            downloaded = self.download(sr, output_dir, progress_callback)
+            if not downloaded:
+                return None
+
+            return {
+                "path": Path(downloaded),
+                "search_result": sr,
+            }
+            try:
+                if progress_callback is not None:
+                    progress_callback("step", 0, None, "direct download")
+            except Exception:
+                pass
+            out_path = unique_path(output_dir / f"{safe_title}.pdf")
+            ok = download_file(
+                pdf_url,
+                out_path,
+                session=self._session,
+                progress_callback=(
+                    (
+                        lambda downloaded, total, label:
+                        progress_callback("bytes", downloaded, total, label)
+                    ) if progress_callback is not None else None
+                ),
+            )
+            if ok:
+                return out_path
+            log("[openlibrary] Direct download failed", file=sys.stderr)
+            return None
+
         # 2) Borrow flow (credentials required).
         try:
             email, password = self._credential_archive(self.config or {})