scripts/dl.py

#!/usr/bin/env python3
"""Resumable download (Range) with retries. Survives under setsid (python does;
curl/wget under setsid died with the bash tool). Usage: dl.py URL DEST [RETRIES]

Fix 2026-08-05: if the server answers 416 (Range past EOF), the file is already
complete → exit OK after comparing against the real Content-Length (HEAD).
"""

from __future__ import annotations

import os
import sys
import time
import urllib.error
import urllib.request

URL, DEST = sys.argv[1], sys.argv[2]
RETRIES = int(sys.argv[3]) if len(sys.argv) > 3 else 30


def content_length() -> int | None:
    """Total length of the remote file (HEAD, following redirects)."""
    try:
        req = urllib.request.Request(URL, method="HEAD")
        with urllib.request.urlopen(req, timeout=30) as r:
            return int(r.headers.get("Content-Length", 0)) or None
    except Exception:  # noqa: BLE001
        return None


def download() -> bool:
    pos = os.path.getsize(DEST) if os.path.exists(DEST) else 0
    total = content_length()
    if total is not None and pos >= total:
        return True  # already complete
    req = urllib.request.Request(URL, headers={"Range": f"bytes={pos}-"})
    with urllib.request.urlopen(req) as r, open(DEST, "ab") as f:
        while True:
            chunk = r.read(1 << 20)
            if not chunk:
                return True
            f.write(chunk)


for attempt in range(1, RETRIES + 1):
    try:
        if download():
            print(f"OK {os.path.getsize(DEST)}", flush=True)
            sys.exit(0)
    except urllib.error.HTTPError as e:
        if e.code == 416:  # range from EOF → the file is already complete
            print(f"OK 416-complete {os.path.getsize(DEST)}", flush=True)
            sys.exit(0)
        print(
            f"attempt {attempt} failed: HTTP {e.code} (partial {os.path.getsize(DEST)})",
            flush=True,
        )
    except Exception as e:  # noqa: BLE001
        print(f"attempt {attempt} failed: {e!r} (partial {os.path.getsize(DEST)})", flush=True)
    time.sleep(5)
print(f"EXHAUSTED after {RETRIES} attempts", flush=True)
sys.exit(1)