Extra db flag

docs/source/command-line-options.rst

@@ -84,6 +84,9 @@ ids. Useful for repeated scanning with found known irrelevant usernames.
 ``--db`` - Load Maigret database from a JSON file or an online, valid,
 JSON file. See :ref:`custom-database` below.
 
+``--extra-db`` - Load an **additional** sites database on top of
+``--db`` (overlay). Repeatable. See :ref:`extra-database` below.
+
 ``--no-autoupdate`` - Disable the automatic database update check that
 runs at startup. The currently cached (or bundled) database is used
 as-is.
@@ -139,6 +142,47 @@ disabled and all sites scanned, looks like::
         --db LLM/maigret_private_db.json \
         --no-autoupdate -a
 
+.. _extra-database:
+
+Overlaying additional databases (``--extra-db``)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+``--extra-db FILE`` loads an additional sites database **on top of**
+``--db``, rather than replacing it. The flag is repeatable, so multiple
+extras can be layered in one invocation::
+
+    python3 -m maigret username \
+        --extra-db private_sites.json \
+        --extra-db team_sites.json -a
+
+Each extra accepts the same three forms as ``--db`` (HTTP(S) URL,
+absolute or cwd-relative local path, or module-relative path).
+
+**Merge semantics.** Sites, engines and tags are merged into the main
+database. On duplicate names, **last wins**: a site or engine defined
+later (either in a subsequent ``--extra-db`` or in an ``--extra-db``
+that re-defines a name from ``--db``) overrides the earlier definition.
+Tag lists are deduplicated while preserving first-seen order.
+
+**Auto-update.** Extras are never auto-updated — they are read exactly
+as provided, regardless of ``--no-autoupdate`` / ``--force-update``.
+
+**Save behaviour.** While any ``--extra-db`` is active, Maigret **skips
+every database save** — including the implicit end-of-run save, the
+``--self-check --auto-disable`` save, and the ``--submit`` save. This
+prevents silently writing merged (main + extras) content back into the
+main ``--db`` file. If you need to persist edits, run Maigret again
+without ``--extra-db``. You will see a warning at startup::
+
+    [!] Database modifications will NOT be persisted while --extra-db is active.
+
+**Missing or unreadable extra.** Maigret exits with a non-zero status —
+extras are opt-in, so a silent skip would hide configuration errors.
+
+**Not supported with** ``--web``. The web UI reloads its own database
+from the main ``--db`` path, so extras would be invisible. Passing both
+exits with an error.
+
 Reports
 -------
 

maigret/maigret.py

@@ -202,6 +202,17 @@ def setup_arguments_parser(settings: Settings):
         default=settings.sites_db_path,
         help="Load Maigret database from a JSON file or HTTP web resource.",
     )
+    parser.add_argument(
+        "--extra-db",
+        metavar="EXTRA_DB_FILE",
+        dest="extra_db_files",
+        action="append",
+        default=[],
+        help="Load an additional sites database on top of --db. Repeatable. "
+             "Accepts a local path (absolute or cwd-relative) or HTTP(S) URL. "
+             "Never auto-updated. Changes from --self-check / --submit are NOT "
+             "persisted when any --extra-db is loaded.",
+    )
     parser.add_argument(
         "--no-autoupdate",
         action="store_true",
@@ -614,6 +625,46 @@ async def main():
             )
         else:
             raise
+
+    for extra_arg in args.extra_db_files:
+        try:
+            extra_path = resolve_db_path(
+                db_file_arg=extra_arg,
+                no_autoupdate=True,
+                meta_url=settings.db_update_meta_url,
+                check_interval_hours=settings.autoupdate_check_interval_hours,
+                color=not args.no_color,
+            )
+        except FileNotFoundError as e:
+            logger.error(f"--extra-db: {e}")
+            sys.exit(2)
+
+        before = len(db.sites)
+        try:
+            db.load_extra_from_path(extra_path)
+        except Exception as e:
+            logger.error(f"Failed to load extra database from {extra_path}: {e}")
+            sys.exit(2)
+        query_notify.success(
+            f'Loaded extra database: {extra_path} '
+            f'(+{len(db.sites) - before} new, {len(db.sites)} total sites)'
+        )
+
+    if args.extra_db_files:
+        query_notify.warning(
+            'Database modifications will NOT be persisted while --extra-db is active.'
+        )
+
+    def save_db_if_safe(reason: str) -> bool:
+        if args.extra_db_files:
+            logger.warning(
+                f"Skipping database save ({reason}): --extra-db is active; "
+                "modifications are in-memory only."
+            )
+            return False
+        db.save_to_file(db_file)
+        return True
+
     get_top_sites_for_id = lambda x: db.ranked_sites_dict(
         top=args.top_sites,
         tags=args.tags,
@@ -629,7 +680,7 @@ async def main():
         submitter = Submitter(db=db, logger=logger, settings=settings, args=args)
         is_submitted = await submitter.dialog(args.new_site_to_submit, args.cookie_file)
         if is_submitted:
-            db.save_to_file(db_file)
+            save_db_if_safe("post-submit")
         await submitter.close()
 
     # Database self-checking
@@ -663,8 +714,8 @@ async def main():
                 'y',
                 '',
             ):
-                db.save_to_file(db_file)
-                print('Database was successfully updated.')
+                if save_db_if_safe("post-self-check"):
+                    print('Database was successfully updated.')
             else:
                 print('Updates will be applied only for current search session.')
 
@@ -687,6 +738,14 @@ async def main():
 
     # Web interface
     if args.web is not None:
+        if args.extra_db_files:
+            logger.error(
+                '--web is not compatible with --extra-db: the web UI reloads '
+                'the database from --db only, so extras would be silently '
+                'ignored. Remove --extra-db or use the CLI mode.'
+            )
+            sys.exit(2)
+
         from maigret.web.app import app
 
         app.config["MAIGRET_DB_FILE"] = db_file
@@ -873,7 +932,7 @@ async def main():
             print(text_report)
 
     # update database
-    db.save_to_file(db_file)
+    save_db_if_safe("end-of-run")
 
 
 def run():

maigret/resources/db_meta.json

@@ -1,6 +1,6 @@
 {
     "version": 1,
-    "updated_at": "2026-04-22T16:15:02Z",
+    "updated_at": "2026-04-23T15:02:48Z",
     "sites_count": 3142,
     "min_maigret_version": "0.6.0",
     "data_sha256": "1e1ed6da2aa9db0f34171f61a044c20bbd1ed53a0430dec4a9ce8f8543655d1a",

maigret/sites.py

@@ -516,6 +516,15 @@ class MaigretDatabase:
         else:
             return self.load_from_file(path)
 
+    def load_extra_from_path(self, path: str) -> "MaigretDatabase":
+        """Merge an additional DB on top of self. Last-wins on duplicate
+        site/engine names; tags deduped preserving first-seen order."""
+        self.load_from_path(path)
+        self._sites = list({s.name: s for s in self._sites}.values())
+        self._engines = list({e.name: e for e in self._engines}.values())
+        self._tags = list(dict.fromkeys(self._tags))
+        return self
+
     def load_from_http(self, url: str) -> "MaigretDatabase":
         is_url_valid = url.startswith("http://") or url.startswith("https://")
 

sites.md

@@ -3146,7 +3146,7 @@ Rank data fetched from Majestic Million by domains.
 1. ![](https://www.google.com/s2/favicons?domain=https://flarum.es) [flarum.es (https://flarum.es)](https://flarum.es)*: top 100M, es, forum*
 1. ![](https://www.google.com/s2/favicons?domain=https://forum.fibra.click) [forum.fibra.click (https://forum.fibra.click)](https://forum.fibra.click)*: top 100M, forum, it*
 
-The list was updated at (2026-04-22)
+The list was updated at (2026-04-23)
 ## Statistics
 
 Enabled/total sites: 2529/3142 = 80.49%

tests/test_cli.py

@@ -51,6 +51,7 @@ DEFAULT_ARGS: Dict[str, Any] = {
     'md': False,
     'no_autoupdate': False,
     'force_update': False,
+    'extra_db_files': [],
 }
 
 
@@ -126,6 +127,38 @@ def test_args_exclude_tags(argparser):
         assert getattr(args, arg) == want_args[arg]
 
 
+def test_args_single_extra_db(argparser):
+    args = argparser.parse_args('--extra-db extras.json username'.split())
+
+    want_args = dict(DEFAULT_ARGS)
+    want_args.update(
+        {
+            'extra_db_files': ['extras.json'],
+            'username': ['username'],
+        }
+    )
+
+    for arg in vars(args):
+        assert getattr(args, arg) == want_args[arg]
+
+
+def test_args_multiple_extra_dbs(argparser):
+    args = argparser.parse_args(
+        '--extra-db a.json --extra-db https://example.com/b.json username'.split()
+    )
+
+    want_args = dict(DEFAULT_ARGS)
+    want_args.update(
+        {
+            'extra_db_files': ['a.json', 'https://example.com/b.json'],
+            'username': ['username'],
+        }
+    )
+
+    for arg in vars(args):
+        assert getattr(args, arg) == want_args[arg]
+
+
 def test_args_tags_with_exclude_tags(argparser):
     args = argparser.parse_args('--tags coding --exclude-tags porn username'.split())
 

tests/test_sites.py

@@ -1,5 +1,6 @@
 """Maigret Database test functions"""
 
+import json
 from typing import Any, Dict
 
 from maigret.sites import MaigretDatabase, MaigretSite
@@ -96,6 +97,163 @@ def test_site_strip_engine_data_with_site_prior_updates():
     assert amperka_stripped.json == UPDATED_EXAMPLE_DB['sites']['Amperka']
 
 
+def _write_db(tmp_path, name, data):
+    p = tmp_path / name
+    p.write_text(json.dumps(data), encoding='utf-8')
+    return str(p)
+
+
+def test_extra_db_new_site(tmp_path):
+    db = MaigretDatabase()
+    db.load_from_json(EXAMPLE_DB)
+    assert len(db.sites) == 1
+
+    extra = {
+        'engines': {},
+        'sites': {
+            'ExampleExtra': {
+                'tags': ['us'],
+                'checkType': 'status_code',
+                'url': 'https://example.com/{username}',
+                'urlMain': 'https://example.com/',
+                'usernameClaimed': 'test',
+                'usernameUnclaimed': 'noonewouldeverusethis7',
+            }
+        },
+        'tags': ['us'],
+    }
+    db.load_extra_from_path(_write_db(tmp_path, 'extra.json', extra))
+
+    assert len(db.sites) == 2
+    assert set(db.sites_dict.keys()) == {'Amperka', 'ExampleExtra'}
+    assert len(db._sites) == len(db.sites_dict)
+
+
+def test_extra_db_site_override_last_wins(tmp_path):
+    db = MaigretDatabase()
+    db.load_from_json(EXAMPLE_DB)
+    assert db.sites_dict['Amperka'].url_main == 'http://forum.amperka.ru'
+
+    extra = {
+        'engines': {},
+        'sites': {
+            'Amperka': {
+                'engine': 'XenForo',
+                'rank': 1,
+                'tags': ['overridden'],
+                'urlMain': 'https://overridden.example',
+                'usernameClaimed': 'adam',
+                'usernameUnclaimed': 'noonewouldeverusethis7',
+            }
+        },
+        'tags': [],
+    }
+    db.load_extra_from_path(_write_db(tmp_path, 'extra.json', extra))
+
+    assert len(db.sites) == 1
+    amperka = db.sites_dict['Amperka']
+    assert amperka.url_main == 'https://overridden.example'
+    assert 'overridden' in amperka.tags
+
+
+def test_extra_db_engine_override(tmp_path):
+    main = {
+        'engines': {
+            'Proto': {
+                'presenseStrs': ['orig'],
+                'site': {
+                    'absenceStrs': ['original absence'],
+                    'checkType': 'message',
+                    'url': '{urlMain}/orig/{username}',
+                },
+            }
+        },
+        'sites': {
+            'MainSite': {
+                'engine': 'Proto',
+                'rank': 1,
+                'tags': [],
+                'urlMain': 'https://main.example',
+                'usernameClaimed': 'a',
+                'usernameUnclaimed': 'noonewouldeverusethis7',
+            }
+        },
+        'tags': [],
+    }
+    db = MaigretDatabase()
+    db.load_from_json(main)
+
+    extra = {
+        'engines': {
+            'Proto': {
+                'presenseStrs': ['overridden'],
+                'site': {
+                    'absenceStrs': ['overridden absence'],
+                    'checkType': 'message',
+                    'url': '{urlMain}/overridden/{username}',
+                },
+            }
+        },
+        'sites': {
+            'ExtraSite': {
+                'engine': 'Proto',
+                'rank': 10,
+                'tags': [],
+                'urlMain': 'https://extra.example',
+                'usernameClaimed': 'a',
+                'usernameUnclaimed': 'noonewouldeverusethis7',
+            }
+        },
+        'tags': [],
+    }
+    db.load_extra_from_path(_write_db(tmp_path, 'extra.json', extra))
+
+    assert len(db._engines) == 1
+    assert db.engines_dict['Proto'].presenseStrs == ['overridden']
+    extra_site = db.sites_dict['ExtraSite']
+    assert extra_site.absence_strs == ['overridden absence']
+    main_site = db.sites_dict['MainSite']
+    assert main_site.absence_strs == ['original absence']
+
+
+def test_extra_db_tag_dedup(tmp_path):
+    db = MaigretDatabase()
+    db.load_from_json({'engines': {}, 'sites': {}, 'tags': ['forum', 'ru']})
+
+    extra = {'engines': {}, 'sites': {}, 'tags': ['forum', 'us']}
+    db.load_extra_from_path(_write_db(tmp_path, 'extra.json', extra))
+
+    assert db._tags.count('forum') == 1
+    assert sorted(db._tags) == ['forum', 'ru', 'us']
+
+
+def test_extra_db_chain_last_wins(tmp_path):
+    db = MaigretDatabase()
+    db.load_from_json(EXAMPLE_DB)
+
+    def site_with_url(url):
+        return {
+            'engines': {},
+            'sites': {
+                'Amperka': {
+                    'engine': 'XenForo',
+                    'rank': 1,
+                    'tags': ['ru'],
+                    'urlMain': url,
+                    'usernameClaimed': 'adam',
+                    'usernameUnclaimed': 'noonewouldeverusethis7',
+                }
+            },
+            'tags': [],
+        }
+
+    db.load_extra_from_path(_write_db(tmp_path, 'a.json', site_with_url('https://a')))
+    db.load_extra_from_path(_write_db(tmp_path, 'b.json', site_with_url('https://b')))
+
+    assert len(db.sites) == 1
+    assert db.sites_dict['Amperka'].url_main == 'https://b'
+
+
 def test_saving_site_error():
     db = MaigretDatabase()