release: archivebox 0.9.33rc23

archivebox/cli/archivebox_extract.py

@@ -293,11 +293,13 @@ def run_plugins(
         rprint("[red]No snapshots to process[/red]", file=sys.stderr)
         return 1
 
-    rprint(f"[blue]Queued {processed_count} snapshots for extraction[/blue]", file=sys.stderr)
+    if show_progress:
+        rprint(f"[blue]Queued {processed_count} snapshots for extraction[/blue]", file=sys.stderr)
 
     # Run orchestrator if --wait (default)
     if wait:
-        rprint("[blue]Running plugins...[/blue]", file=sys.stderr)
+        if show_progress:
+            rprint("[blue]Running plugins...[/blue]", file=sys.stderr)
         snapshot_ids_by_crawl: dict[str, set[str]] = defaultdict(set)
         for snapshot_id, crawl_id in existing_snapshots:
             snapshot_ids_by_crawl[str(crawl_id)].add(str(snapshot_id))

archivebox/cli/archivebox_update.py

@@ -180,7 +180,7 @@ def update(
     before: float | None = None,
     after: float | None = None,
     resume: str | None = None,
-    batch_size: int = 100,
+    batch_size: int = 500,
     continuous: bool = False,
     index_only: bool = False,
     migrate_only: bool = False,
@@ -403,7 +403,7 @@ def update(
             resume_cmd.append("--migrate-only")
         if index_only:
             resume_cmd.append("--index-only")
-        if batch_size != 100:
+        if batch_size != 500:
             resume_cmd.extend(["--batch-size", str(batch_size)])
         if exact_resume or resume:
             resume_cmd.extend(["--resume", str(exact_resume or resume)])
@@ -446,7 +446,7 @@ def update(
             stop_own_supervisord_process()
 
 
-def drain_old_archive_dirs(resume_from: str | None = None, batch_size: int = 100) -> dict[str, int]:
+def drain_old_archive_dirs(resume_from: str | None = None, batch_size: int = 500) -> dict[str, int]:
     """
     Drain old archive/ directories (0.8.x → 0.9.x migration).
 
@@ -605,7 +605,7 @@ def drain_old_archive_dirs(resume_from: str | None = None, batch_size: int = 100
     return stats
 
 
-def process_all_db_snapshots(batch_size: int = 100, resume: str | None = None, wait_for_turn=None) -> dict[str, int]:
+def process_all_db_snapshots(batch_size: int = 500, resume: str | None = None, wait_for_turn=None) -> dict[str, int]:
     """
     O(n) scan over entire DB from most recent to least recent.
 
@@ -880,7 +880,7 @@ def print_index_stats(stats: dict[str, Any]) -> None:
 @click.option("--before", type=float, help="Only snapshots before timestamp")
 @click.option("--after", type=float, help="Only snapshots after timestamp")
 @click.option("--filter-type", type=click.Choice(["exact", "substring", "regex", "domain", "tag", "timestamp"]), default="exact")
-@click.option("--batch-size", type=int, default=100, help="Commit every N snapshots")
+@click.option("--batch-size", type=int, default=500, help="Commit every N records")
 @click.option("--continuous", is_flag=True, help="Run continuously as background worker")
 @click.option("--index-only", is_flag=True, help="Backfill available search indexes from existing archived content")
 @click.option("--migrate-only", is_flag=True, help="Only migrate filesystem and update database/index state")

archivebox/core/shutdown_util.py

@@ -100,8 +100,9 @@ def foreground_shutdown_signals(
     previous_handlers = {sig: signal.getsignal(sig) for sig in handled_signals}
 
     def raise_keyboard_interrupt(signum, _frame):
-        state.signal_name = signal.Signals(signum).name
-        os.write(sys.stdout.fileno(), f"\n[🛑] Got {state.signal_name}, stopping gracefully...\n".encode())
+        if state.signal_name is None:
+            state.signal_name = signal.Signals(signum).name
+            os.write(sys.stdout.fileno(), f"\n[🛑] Got {state.signal_name}, stopping gracefully...\n".encode())
         raise KeyboardInterrupt
 
     try:

etc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "archivebox",
-  "version": "0.9.33rc22",
+  "version": "0.9.33rc23",
   "repository": "github:ArchiveBox/ArchiveBox",
   "license": "MIT",
   "dependencies": {

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "archivebox"
-version = "0.9.33rc22"
+version = "0.9.33rc23"
 requires-python = ">=3.13"
 description = "Self-hosted internet archiving solution."
 authors = [{name = "Nick Sweeting", email = "pyproject.toml@archivebox.io"}]
@@ -79,9 +79,9 @@ dependencies = [
     ### Extractor dependencies (optional binaries detected at runtime via shutil.which)
     ### Binary/Package Management
     "abxbus==2.5.7",          # EventBus API
-    "abxpkg>=1.11.48",        # for: detecting, versioning, and installing binaries via apt/brew/pip/npm
-    "abx-plugins>=1.11.54",  # shared ArchiveBox plugin package with Chrome/Puppeteer dependency wiring
-    "abx-dl>=1.11.54",       # shared ArchiveBox downloader package with blocking install preflight
+    "abxpkg>=1.11.49",        # for: detecting, versioning, and installing binaries via apt/brew/pip/npm
+    "abx-plugins>=1.11.55",  # shared ArchiveBox plugin package with Chrome/Puppeteer dependency wiring
+    "abx-dl>=1.11.55",       # shared ArchiveBox downloader package with blocking install preflight
     ### UUID7 backport for Python <3.14
     "uuid7>=0.1.0; python_version < '3.14'",  # provides the uuid_extensions module on Python 3.13
 ]