feat: drive gdl-sync from a file of profile URLs

Adds --urls-file so a run can reference a hand-maintained list rather
than repeating --profile, which is how this actually gets used: the
ARTMS accounts now live in artms_account_links.txt at the archive root.

The parser takes what a person would paste. Full URLs, scheme-less URLs
and bare usernames all work; blank lines and # comments are ignored and
duplicates dropped, so the list can be appended to carelessly. Lines that
are not profiles are rejected loudly rather than silently syncing
nothing: an Instagram post URL yields the segment "p", which would
otherwise be treated as a username and create a directory called "p".

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

scripts/gdl-sync.py

@@ -6,9 +6,8 @@ The CLI replacement for the JDownloader2 workflow. See docs/gallery-dl.md for
 the measurements behind every choice here — especially the safety model, which
 is the reason this script exists in this shape rather than a simpler one.
 
-STATUS: exercised end-to-end against `withaseul` (posts, reels, stories,
-highlights) publishing to a scratch directory. It has never written to the live
-archive.
+STATUS: in use. `withaseul` was fetched and published to the live archive
+(322 files added, nothing overwritten or deleted).
 
 The fetch host needs no copy of the archive. It stages locally and rsyncs
 afterwards; what it already holds is learned from a *file listing* alone
@@ -17,9 +16,13 @@ afterwards; what it already holds is learned from a *file listing* alone
 Usage:
     ./scripts/gdl-sync.py --index https://instaarchive.ergosteur.com \\
         --staging /var/tmp/gdl --publish user@host:/path/to/archives \\
-        --profile 0ct0ber19 --dry-run
+        --urls-file artms_account_links.txt --dry-run
 
-    # ...then swap --dry-run for --execute. --index also accepts a local path.
+    # ...then swap --dry-run for --execute. --index also accepts a local path,
+    # and --profile / --all work instead of --urls-file.
+
+Always --dry-run first: it prints the plan, and the publish step it reports is
+the one that would touch the archive.
 
 Run it from the host whose public IP matches the browser the cookie came from;
 using the cookie from elsewhere is what session-hijack detection looks for.
@@ -114,6 +117,54 @@ def scan_archives(root: Path) -> dict[str, Profile]:
     return profiles
 
 
+RE_PROFILE_URL = re.compile(
+    r"^(?:https?://)?(?:www\.)?instagram\.com/(?P<user>[^/?#\s]+)/?", re.I)
+
+# Path segments that are Instagram features, not profiles. A line like
+# ".../p/ABC123/" names a post, and treating "p" as a username would silently
+# sync nothing under a nonsense directory.
+RESERVED_SEGMENTS = {
+    "p", "reel", "reels", "stories", "explore", "accounts", "direct",
+    "tv", "s", "invites", "challenge", "about", "developer",
+}
+
+
+def read_urls_file(path: Path) -> list[str]:
+    """
+    Read profile URLs (or bare usernames) from a file, one per line.
+
+    Written for hand-maintained lists: blank lines are skipped, `#` starts a
+    comment, and either a full URL or a bare username works. Order is kept and
+    duplicates dropped, so a list can be appended to without care.
+    """
+    users: list[str] = []
+    seen: set[str] = set()
+
+    for lineno, raw in enumerate(path.read_text().splitlines(), 1):
+        line = raw.split("#", 1)[0].strip()
+        if not line:
+            continue
+
+        m = RE_PROFILE_URL.match(line)
+        user = m.group("user") if m else line.strip("/")
+
+        if not user or "/" in user or " " in user:
+            print(f"{path}:{lineno}: cannot read a username from {raw.strip()!r}",
+                  file=sys.stderr)
+            continue
+        if user.lower() in RESERVED_SEGMENTS:
+            print(f"{path}:{lineno}: {user!r} is an Instagram path, not a "
+                  f"profile — skipping", file=sys.stderr)
+            continue
+        if user in seen:
+            continue
+
+        seen.add(user)
+        users.append(user)
+
+    return users
+
+
 class ArchiveIndex:
     """
     What the archive already holds, as filenames only.
@@ -451,6 +502,9 @@ def main() -> int:
     g.add_argument("--profile", action="append", default=[],
                    help="profile to sync; repeatable")
     g.add_argument("--all", action="store_true", help="every profile on disk")
+    g.add_argument("--urls-file", type=Path,
+                   help="file of Instagram profile URLs or usernames, one per "
+                        "line; # comments and blank lines allowed")
     ap.add_argument("--cookies", default="chrome:/home/matt/.config/google-chrome-devtools",
                     help="gallery-dl --cookies-from-browser value")
     ap.add_argument("--archive-db", type=Path, default=None,
@@ -478,7 +532,17 @@ def main() -> int:
 
     index = ArchiveIndex(args.index)
     names = index.profiles()
-    if args.profile:
+    if args.urls_file:
+        if not args.urls_file.is_file():
+            print(f"urls file not found: {args.urls_file}", file=sys.stderr)
+            return 2
+        wanted = read_urls_file(args.urls_file)
+        if not wanted:
+            print(f"no usable profiles in {args.urls_file}", file=sys.stderr)
+            return 2
+        print(f"read {len(wanted)} profile(s) from {args.urls_file}")
+        selected = [Profile(p) for p in wanted]
+    elif args.profile:
         for p in args.profile:
             if p not in names:
                 print(f"note: {p} is not in the index yet; it will be created")