GoFileEmpty: no retries for content that exists but is empty; add tools/debug_gofile.py for raw content-API inspection

dlp.py

@@ -157,7 +157,7 @@ def run_gofile(
             try:
                 files_spec = client.list_files(f.url)
                 if not files_spec:
-                    raise dlph_gofile.GoFileError("no files found under URL")
+                    raise dlph_gofile.GoFileEmpty("content exists but contains no files")
                 files: list[dict] = []
                 for relpath, name, link in files_spec:
                     dest = Path(args.out_dir) / "downloads" / "gofile" / relpath / name
@@ -182,6 +182,11 @@ def run_gofile(
                 log.error("DEAD LINK %s: %s", f.url, exc)
                 state.mark(f.url, status="failed", error=str(exc), files=[])
                 break
+            except dlph_gofile.GoFileEmpty as exc:
+                # Emptied content is stable - no retry
+                log.error("EMPTY CONTENT %s: %s", f.url, exc)
+                state.mark(f.url, status="failed", error=str(exc), files=[])
+                break
             except dlph_gofile.GoFileAuthError as exc:
                 # Token may have died mid-run (rate limit); re-auth once per attempt
                 log.warning("Auth error for %s: %s - re-authenticating", f.url, exc)

dlphelper/gofile.py

@@ -60,6 +60,13 @@ class GoFileNotFound(GoFileError):
     """
 
 
+class GoFileEmpty(GoFileError):
+    """The content exists but contains no files (e.g. emptied folder).
+
+    Stable state like a dead link: no retry.
+    """
+
+
 class GoFileAuthError(GoFileError):
     """The account token was rejected; the client can re-auth once."""
 

tools/debug_gofile.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""One-off diagnostic: inspect the raw gofile API response for one content id.
+
+Prints everything except the account token. Creates exactly one guest account.
+"""
+
+import hashlib
+import json
+import sys
+import time
+
+import requests
+
+CID = sys.argv[1]
+
+USER_AGENT = "Mozilla/5.0"
+LOCALE = "en-US"
+TOKEN_SECRET = "12af056dacea0b"
+WINDOW_SEC = 14400
+COMMON = {"User-Agent": USER_AGENT, "Accept-Encoding": "gzip", "Accept": "*/*",
+          "Connection": "keep-alive"}
+
+resp = requests.post("https://api.gofile.io/accounts", headers=COMMON, timeout=15)
+data = resp.json()
+assert data.get("status") == "ok", data
+token = data["data"]["token"]
+
+window = int(time.time()) // WINDOW_SEC
+seed = f"{USER_AGENT}::{LOCALE}::{token}::{window}::{TOKEN_SECRET}"
+wtoken = hashlib.sha256(seed.encode()).hexdigest()
+headers = {
+    **COMMON,
+    "Authorization": f"Bearer {token}",
+    "X-Website-Token": wtoken,
+    "X-BL": LOCALE,
+}
+
+r = requests.get(
+    f"https://api.gofile.io/contents/{CID}?cache=true&sortField=createTime&sortDirection=1",
+    headers=headers, timeout=30,
+)
+print("HTTP", r.status_code)
+body = r.json()
+print("api status:", body.get("status"))
+
+
+def scrub(node):
+    """Remove anything token-like from the tree before printing."""
+    if isinstance(node, dict):
+        return {
+            k: ("<redacted>" if k in ("token", "accountToken") else scrub(v))
+            for k, v in node.items()
+        }
+    if isinstance(node, list):
+        return [scrub(x) for x in node]
+    return node
+
+
+d = body.get("data") or {}
+print("data keys:", sorted(d.keys()))
+print("type:", d.get("type"))
+children = d.get("children") or {}
+print("children count:", len(children))
+for cid, child in list(children.items())[:5]:
+    print("  child:", cid, "type:", child.get("type"), "name:", child.get("name"),
+          "has link:", "link" in child)
+print()
+print(json.dumps(scrub(body), indent=2)[:3000])