feat(tg): реальные абузы из Telegram без сессии — адаптер tg_web переписан (служебное/пустыши отсекаются, заголовок из тела, порог 12/8 для leak-каналов), 19 живых каналов из 87 проверенных, сигнал абуза в score (+до 1.8), tools/tg_discover.py, tools/fixtg.py, tools/purge_tg_junk.py, tools/rescore.py; реестр 869, база 7295 (ab_ 3135, tg_ 374); тесты 19
Some checks failed
ci / test (3.10) (push) Has been cancelled
ci / test (3.11) (push) Has been cancelled
ci / test (3.12) (push) Has been cancelled

This commit is contained in:
Vlad Gothbreach
2026-10-26 21:06:50 +03:00
parent f9719b9149
commit eaedd37bcd
11 changed files with 414 additions and 22 deletions

View File

@@ -15,6 +15,7 @@ from .sources_ext2 import EXTRA2
from .sources_ext3 import EXTRA3
from .sources_abuse import ABUSE_LIVE
from .abuse_sources import ABUSE as ABUSE_DEEP
from .sources_tg_abuse import TG_ABUSE
from .sources_ext4 import EXTRA5
from .sources_ext5 import EXTRA6
from .sources_x import X_SOURCES
@@ -201,7 +202,7 @@ def _dedup(rows):
return out
SOURCES = _dedup(SOURCES_BASE + [Source(**d) for d in EXTRA] + [Source(**d) for d in EXTRA2] + [Source(**d) for d in EXTRA3] + [Source(**d) for d in ABUSE_LIVE] + [Source(**d) for d in EXTRA4] + [Source(**d) for d in EXTRA5] + [Source(**d) for d in EXTRA6] + [Source(**d) for d in ABUSE_DEEP] + [Source(**d) for d in X_SOURCES])
SOURCES = _dedup(SOURCES_BASE + [Source(**d) for d in EXTRA] + [Source(**d) for d in EXTRA2] + [Source(**d) for d in EXTRA3] + [Source(**d) for d in ABUSE_LIVE] + [Source(**d) for d in EXTRA4] + [Source(**d) for d in EXTRA5] + [Source(**d) for d in EXTRA6] + [Source(**d) for d in ABUSE_DEEP] + [Source(**d) for d in TG_ABUSE] + [Source(**d) for d in X_SOURCES])
BY_NAME = {s.name: s for s in SOURCES}
CATEGORIES = sorted({s.category for s in SOURCES})