dfd

Provider/internetarchive.py

@@ -7,6 +7,8 @@ import sys
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
+from urllib.parse import quote, urlparse
+
 from ProviderCore.base import Provider, SearchResult
 from ProviderCore.download import sanitize_filename
 from SYS.logger import log
@@ -71,6 +73,143 @@ def _extract_identifier_from_any(value: str) -> str:
     return raw
 
 
+def extract_identifier(value: str) -> str:
+    """Public wrapper for extracting an IA identifier from URLs/tags/bare ids."""
+    return _extract_identifier_from_any(value)
+
+
+def is_details_url(url: str) -> bool:
+    raw = str(url or "").strip()
+    if not raw:
+        return False
+    if not (raw.startswith("http://") or raw.startswith("https://")):
+        return False
+    try:
+        p = urlparse(raw)
+        host = (p.hostname or "").lower().strip()
+        parts = [x for x in (p.path or "").split("/") if x]
+    except Exception:
+        return False
+    if not host.endswith("archive.org"):
+        return False
+    return len(parts) >= 2 and parts[0].lower() == "details" and bool(parts[1].strip())
+
+
+def is_download_file_url(url: str) -> bool:
+    raw = str(url or "").strip()
+    if not raw:
+        return False
+    if not (raw.startswith("http://") or raw.startswith("https://")):
+        return False
+    try:
+        p = urlparse(raw)
+        host = (p.hostname or "").lower().strip()
+        parts = [x for x in (p.path or "").split("/") if x]
+    except Exception:
+        return False
+    if not host.endswith("archive.org"):
+        return False
+    # /download/<identifier>/<filename>
+    return len(parts) >= 3 and parts[0].lower() == "download" and bool(parts[1].strip()) and bool(parts[2].strip())
+
+
+def list_download_files(identifier: str) -> List[Dict[str, Any]]:
+    """Return a sorted list of downloadable files for an IA identifier.
+
+    Each entry includes: name, size, format, source, direct_url.
+    """
+    ident = str(identifier or "").strip()
+    if not ident:
+        return []
+
+    ia = _ia()
+    get_item = getattr(ia, "get_item", None)
+    if not callable(get_item):
+        raise Exception("internetarchive.get_item is not available")
+
+    try:
+        item: Any = get_item(str(ident))
+    except Exception as exc:
+        raise Exception(f"Internet Archive item lookup failed: {exc}")
+
+    files: List[Dict[str, Any]] = []
+    try:
+        raw_files = getattr(item, "files", None)
+        if isinstance(raw_files, list):
+            for f in raw_files:
+                if isinstance(f, dict):
+                    files.append(f)
+    except Exception:
+        files = []
+
+    if not files:
+        try:
+            for f in item.get_files():
+                name = getattr(f, "name", None)
+                if not name and isinstance(f, dict):
+                    name = f.get("name")
+                if not name:
+                    continue
+                files.append(
+                    {
+                        "name": str(name),
+                        "size": getattr(f, "size", None),
+                        "format": getattr(f, "format", None),
+                        "source": getattr(f, "source", None),
+                    }
+                )
+        except Exception:
+            files = []
+
+    if not files:
+        return []
+
+    def _is_ia_metadata_file(f: Dict[str, Any]) -> bool:
+        try:
+            source = str(f.get("source") or "").strip().lower()
+            fmt = str(f.get("format") or "").strip().lower()
+        except Exception:
+            source = ""
+            fmt = ""
+
+        if source == "metadata":
+            return True
+        if fmt in {"metadata", "archive bittorrent"}:
+            return True
+        if fmt.startswith("thumbnail"):
+            return True
+        return False
+
+    candidates = [f for f in files if isinstance(f, dict) and not _is_ia_metadata_file(f)]
+    if not candidates:
+        candidates = [f for f in files if isinstance(f, dict)]
+
+    out: List[Dict[str, Any]] = []
+    for f in candidates:
+        name = str(f.get("name") or "").strip()
+        if not name:
+            continue
+
+        direct_url = f"https://archive.org/download/{ident}/{quote(name, safe='')}"
+        out.append(
+            {
+                "name": name,
+                "size": f.get("size"),
+                "format": f.get("format"),
+                "source": f.get("source"),
+                "direct_url": direct_url,
+            }
+        )
+
+    def _key(f: Dict[str, Any]) -> tuple[str, str]:
+        fmt = str(f.get("format") or "").strip().lower()
+        name = str(f.get("name") or "").strip().lower()
+        return (fmt, name)
+
+    out.sort(key=_key)
+    return out
+
+
 def _extract_download_filename_from_url(url: str) -> str:
     raw = str(url or "").strip()
     if not raw: