Restore CLI compat and plugin dependency handling

archivebox/cli/__init__.py

@@ -41,6 +41,7 @@ class ArchiveBoxGroup(click.Group):
     archive_commands = {
         # High-level commands
         'add': 'archivebox.cli.archivebox_add.main',
+        'extract': 'archivebox.cli.archivebox_extract.main',
         'list': 'archivebox.cli.archivebox_list.main',
         'remove': 'archivebox.cli.archivebox_remove.main',
         'run': 'archivebox.cli.archivebox_run.main',
@@ -55,6 +56,10 @@ class ArchiveBoxGroup(click.Group):
         # Introspection commands
         'pluginmap': 'archivebox.cli.archivebox_pluginmap.main',
     }
+    legacy_model_commands = {
+        'crawl': 'archivebox.cli.archivebox_crawl_compat.main',
+        'snapshot': 'archivebox.cli.archivebox_snapshot_compat.main',
+    }
     all_subcommands = {
         **meta_commands,
         **setup_commands,
@@ -67,12 +72,35 @@ class ArchiveBoxGroup(click.Group):
         'archive': 'add',
         # Old commands replaced by new model commands
         'orchestrator': 'run',
-        'extract': 'archiveresult',
+    }
+    legacy_model_subcommands = {
+        'crawl': {'create', 'list', 'update', 'delete'},
+        'snapshot': {'create', 'list', 'update', 'delete'},
     }
     
     @classmethod
     def get_canonical_name(cls, cmd_name):
         return cls.renamed_commands.get(cmd_name, cmd_name)
+
+    @classmethod
+    def _should_use_legacy_model_command(cls, cmd_name: str) -> bool:
+        if cmd_name not in cls.legacy_model_commands:
+            return False
+
+        try:
+            arg_idx = sys.argv.index(cmd_name)
+        except ValueError:
+            return False
+
+        remaining_args = sys.argv[arg_idx + 1:]
+        if not remaining_args:
+            return False
+
+        first_arg = remaining_args[0]
+        if first_arg in ('-h', '--help'):
+            return False
+
+        return first_arg not in cls.legacy_model_subcommands[cmd_name]
     
 
     def get_command(self, ctx, cmd_name):
@@ -82,6 +110,9 @@ class ArchiveBoxGroup(click.Group):
             print(f' [violet]Hint:[/violet] `archivebox {cmd_name}` has been renamed to `archivebox {new_name}`')
             cmd_name = new_name
             ctx.invoked_subcommand = cmd_name
+
+        if self._should_use_legacy_model_command(cmd_name):
+            return self._lazy_load(self.legacy_model_commands[cmd_name])
         
         # handle lazy loading of commands
         if cmd_name in self.all_subcommands:
@@ -91,8 +122,8 @@ class ArchiveBoxGroup(click.Group):
         return super().get_command(ctx, cmd_name)
 
     @classmethod
-    def _lazy_load(cls, cmd_name):
-        import_path = cls.all_subcommands[cmd_name]
+    def _lazy_load(cls, cmd_name_or_path):
+        import_path = cls.all_subcommands.get(cmd_name_or_path, cmd_name_or_path)
         modname, funcname = import_path.rsplit('.', 1)
         
         # print(f'LAZY LOADING {import_path}')

archivebox/cli/archivebox_crawl_compat.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+
+__package__ = 'archivebox.cli'
+__command__ = 'archivebox crawl'
+
+import sys
+
+import rich_click as click
+
+from archivebox.cli.archivebox_add import add
+
+
+@click.command(context_settings={'ignore_unknown_options': True})
+@click.option('--depth', '-d', type=int, default=0, help='Max crawl depth (default: 0)')
+@click.option('--tag', '-t', default='', help='Comma-separated tags to add')
+@click.option('--status', '-s', default='queued', help='Initial status (default: queued)')
+@click.option('--wait/--no-wait', 'wait', default=True, help='Accepted for backwards compatibility')
+@click.argument('urls', nargs=-1)
+def main(depth: int, tag: str, status: str, wait: bool, urls: tuple[str, ...]):
+    """Backwards-compatible `archivebox crawl URL...` entrypoint."""
+    del status, wait
+    add(list(urls), depth=depth, tag=tag, index_only=True, bg=True)
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

archivebox/cli/archivebox_extract.py

@@ -226,7 +226,7 @@ def is_archiveresult_id(value: str) -> bool:
 
 
 @click.command()
-@click.option('--plugins', '-p', default='', help='Comma-separated list of plugins to run (e.g., screenshot,singlefile)')
+@click.option('--plugins', '--plugin', '-p', default='', help='Comma-separated list of plugins to run (e.g., screenshot,singlefile)')
 @click.option('--wait/--no-wait', default=True, help='Wait for plugins to complete (default: wait)')
 @click.argument('args', nargs=-1)
 def main(plugins: str, wait: bool, args: tuple):

archivebox/cli/archivebox_remove.py

@@ -12,6 +12,7 @@ import rich_click as click
 from django.db.models import QuerySet
 
 from archivebox.config import DATA_DIR
+from archivebox.config.constants import CONSTANTS
 from archivebox.config.django import setup_django
 from archivebox.misc.util import enforce_types, docstring
 from archivebox.misc.checks import check_data_folder
@@ -65,6 +66,9 @@ def remove(filter_patterns: Iterable[str]=(),
         for snapshot in snapshots:
             if delete:
                 shutil.rmtree(snapshot.output_dir, ignore_errors=True)
+                legacy_path = CONSTANTS.ARCHIVE_DIR / snapshot.timestamp
+                if legacy_path.is_symlink():
+                    legacy_path.unlink(missing_ok=True)
     finally:
         timer.end()
 

archivebox/cli/archivebox_snapshot_compat.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+
+__package__ = 'archivebox.cli'
+__command__ = 'archivebox snapshot'
+
+import sys
+
+import rich_click as click
+
+from archivebox.cli.archivebox_snapshot import create_snapshots
+
+
+@click.command(context_settings={'ignore_unknown_options': True})
+@click.option('--tag', '-t', default='', help='Comma-separated tags to add')
+@click.option('--status', '-s', default='queued', help='Initial status (default: queued)')
+@click.option('--depth', '-d', type=int, default=0, help='Crawl depth (default: 0)')
+@click.argument('urls', nargs=-1)
+def main(tag: str, status: str, depth: int, urls: tuple[str, ...]):
+    """Backwards-compatible `archivebox snapshot URL...` entrypoint."""
+    sys.exit(create_snapshots(urls, tag=tag, status=status, depth=depth))
+
+
+if __name__ == '__main__':
+    main()