reform/omni-parse
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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
Details
ci / test (3.11) (push) Has been cancelled
Details
ci / test (3.12) (push) Has been cancelled
Details

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

49
omni/sources_tg_abuse.py Normal file
View File

@@ -0,0 +1,49 @@
"""Telegram-каналы с абузами/сливами/утечками: публичное веб-превью t.me/s, без сессии и ключей.
Отобраны живыми: парсер даёт 1+ содержательный пост.
Выкинуты (превью пустое: только Channel created + инвайт-ссылки):
leakbase, abuse_ch, cracked_io, ai_zona, gpt_bot_news, codeby.
"""
TG_ABUSE = [
{"name": "tg_vxunderground", "category": "abuse", "kind": "html", "url": "https://t.me/s/vxunderground",
"adapter": "tg_web", "tags": ["malware", "abuse"], "limit": 25},
{"name": "tg_infosec_ru", "category": "abuse", "kind": "html", "url": "https://t.me/s/infosec_ru",
"adapter": "tg_web", "tags": ["security", "abuse"], "limit": 25},
{"name": "tg_true_secator", "category": "abuse", "kind": "html", "url": "https://t.me/s/true_secator",
"adapter": "tg_web", "tags": ["security", "abuse"], "limit": 25},
{"name": "tg_ai_newz", "category": "abuse", "kind": "html", "url": "https://t.me/s/ai_newz",
"adapter": "tg_web", "tags": ["ai", "news"], "limit": 25},
{"name": "tg_neurohive", "category": "abuse", "kind": "html", "url": "https://t.me/s/neurohive",
"adapter": "tg_web", "tags": ["abuse"], "limit": 25},
{"name": "tg_ai_free_ru", "category": "abuse", "kind": "html", "url": "https://t.me/s/ai_free_ru",
"adapter": "tg_web", "tags": ["abuse"], "limit": 25},
{"name": "tg_alstack", "category": "abuse", "kind": "html", "url": "https://t.me/s/alstack",
"adapter": "tg_web", "tags": ["own", "ai", "deals"], "limit": 25},
{"name": "tg_abuz_ai_soft", "category": "abuse", "kind": "html", "url": "https://t.me/s/Abuz_ai_soft",
"adapter": "tg_web", "tags": ["own", "abuse", "soft"], "limit": 25},
{"name": "tg_openai_news", "category": "abuse", "kind": "html", "url": "https://t.me/s/openai_news",
"adapter": "tg_web", "tags": ["ai", "news"], "limit": 25},
{"name": "tg_xakep_ru", "category": "abuse", "kind": "html", "url": "https://t.me/s/xakep_ru",
"adapter": "tg_web", "tags": ["security", "abuse"], "limit": 25},
{"name": "tg_ai_products", "category": "abuse", "kind": "html", "url": "https://t.me/s/ai_products",
"adapter": "tg_web", "tags": ["ai", "promo"], "limit": 25},
{"name": "tg_breachradar", "category": "abuse", "kind": "html", "url": "https://t.me/s/breachradar",
"adapter": "tg_web", "tags": ["leak", "abuse"], "limit": 25},
{"name": "tg_thehackernews", "category": "abuse", "kind": "html", "url": "https://t.me/s/thehackernews",
"adapter": "tg_web", "tags": ["security", "abuse"], "limit": 25},
{"name": "tg_ransomware_news", "category": "abuse", "kind": "html", "url": "https://t.me/s/ransomware_news",
"adapter": "tg_web", "tags": ["malware", "abuse"], "limit": 25},
{"name": "tg_vulnwatch", "category": "abuse", "kind": "html", "url": "https://t.me/s/vulnwatch",
"adapter": "tg_web", "tags": ["cve", "abuse"], "limit": 25},
{"name": "tg_poc_in_github", "category": "abuse", "kind": "html", "url": "https://t.me/s/poc_in_github",
"adapter": "tg_web", "tags": ["exploit", "abuse"], "limit": 25},
{"name": "tg_prompt_injection", "category": "abuse", "kind": "html", "url": "https://t.me/s/prompt_injection",
"adapter": "tg_web", "tags": ["ai", "abuse"], "limit": 25},
{"name": "tg_bleepingcomputer", "category": "abuse", "kind": "html", "url": "https://t.me/s/bleepingcomputer",
"adapter": "tg_web", "tags": ["security", "abuse"], "limit": 25},
{"name": "tg_cvefeed", "category": "abuse", "kind": "html", "url": "https://t.me/s/cvefeed",
"adapter": "tg_web", "tags": ["cve", "abuse"], "limit": 25},
{"name": "tg_hunt_news", "category": "abuse", "kind": "html", "url": "https://t.me/s/hunt_news",
"adapter": "tg_web", "tags": ["security", "news"], "limit": 25},
]