j

Provider/internetarchive.py

@@ -13,6 +13,156 @@ from ProviderCore.base import Provider, SearchResult
 from ProviderCore.download import sanitize_filename
 from SYS.logger import log
 
+# Helper for download-file: render selectable formats for a details URL.
+def maybe_show_formats_table(
+    *,
+    raw_urls: Any,
+    piped_items: Any,
+    parsed: Dict[str, Any],
+    config: Dict[str, Any],
+    quiet_mode: bool,
+    get_field: Any,
+) -> Optional[int]:
+    """If input is a single Internet Archive details URL, render a formats table.
+
+    Returns an exit code when handled; otherwise None.
+    """
+    if quiet_mode:
+        return None
+
+    try:
+        total_inputs = int(len(raw_urls or []) + len(piped_items or []))
+    except Exception:
+        total_inputs = 0
+
+    if total_inputs != 1:
+        return None
+
+    item = piped_items[0] if piped_items else None
+    target = ""
+    if item is not None:
+        try:
+            target = str(get_field(item,
+                                   "path") or get_field(item,
+                                                         "url") or "").strip()
+        except Exception:
+            target = ""
+    if not target and raw_urls:
+        target = str(raw_urls[0]).strip()
+    if not target:
+        return None
+
+    identifier = ""
+    try:
+        md = get_field(item, "full_metadata") if item is not None else None
+        if isinstance(md, dict):
+            identifier = str(md.get("identifier") or "").strip()
+    except Exception:
+        identifier = ""
+    if not identifier:
+        try:
+            identifier = str(extract_identifier(target) or "").strip()
+        except Exception:
+            identifier = ""
+    if not identifier:
+        return None
+
+    # Only show picker for item pages (details); direct download URLs should download immediately.
+    try:
+        if not is_details_url(target):
+            return None
+    except Exception:
+        return None
+
+    try:
+        files = list_download_files(identifier)
+    except Exception as exc:
+        log(f"download-file: Internet Archive lookup failed: {exc}", file=sys.stderr)
+        return 1
+
+    if not files:
+        log("download-file: Internet Archive item has no downloadable files", file=sys.stderr)
+        return 1
+
+    title = ""
+    try:
+        title = str(get_field(item, "title") or "").strip() if item is not None else ""
+    except Exception:
+        title = ""
+    table_title = (
+        f"Internet Archive: {title}".strip().rstrip(":")
+        if title else f"Internet Archive: {identifier}"
+    )
+
+    try:
+        from SYS.result_table import ResultTable
+        from SYS import pipeline as pipeline_context
+    except Exception as exc:
+        log(f"download-file: ResultTable unavailable: {exc}", file=sys.stderr)
+        return 1
+
+    base_args: List[str] = []
+    out_arg = parsed.get("path") or parsed.get("output")
+    if out_arg:
+        base_args.extend(["-path", str(out_arg)])
+
+    table = ResultTable(table_title).set_preserve_order(True)
+    table.set_table("internetarchive.formats")
+    table.set_source_command("download-file", base_args)
+
+    rows: List[Dict[str, Any]] = []
+    for f in files:
+        name = str(f.get("name") or "").strip()
+        if not name:
+            continue
+        fmt = str(f.get("format") or "").strip()
+        src = str(f.get("source") or "").strip()
+        direct_url = str(f.get("direct_url") or "").strip()
+        if not direct_url:
+            continue
+
+        size_val: Any = f.get("size")
+        try:
+            size_val = int(size_val) if size_val not in (None, "") else ""
+        except Exception:
+            pass
+
+        row_item: Dict[str, Any] = {
+            "table": "internetarchive",
+            "title": fmt or name,
+            "path": direct_url,
+            "url": direct_url,
+            "columns": [
+                ("Format", fmt),
+                ("Name", name),
+                ("Size", size_val),
+                ("Source", src),
+            ],
+            "_selection_args": [direct_url],
+            "full_metadata": {
+                "identifier": identifier,
+                "name": name,
+                "format": fmt,
+                "source": src,
+                "size": f.get("size"),
+            },
+        }
+        rows.append(row_item)
+        table.add_result(row_item)
+
+    if not rows:
+        log("download-file: no downloadable files found for this item", file=sys.stderr)
+        return 1
+
+    try:
+        pipeline_context.set_last_result_table(table, rows, subject=item)
+        pipeline_context.set_current_stage_table(table)
+    except Exception:
+        pass
+
+    log("Internet Archive item detected: select a file with @N to download", file=sys.stderr)
+    return 0
+
 
 def _ia() -> Any:
     try:
@@ -322,6 +472,7 @@ class InternetArchive(Provider):
     collection="..."   # optional (upload)
     mediatype="..."    # optional (upload)
     """
+    URL = ("archive.org",)
 
     def __init__(self, config: Optional[Dict[str, Any]] = None):
         super().__init__(config)