abuse: классификатор ловит панели/github/hn и мульти-теги, реальный total из индекса, кап API поднят до 3000

.local/diag8.py

@@ -0,0 +1,79 @@
+import sys, json, re
+sys.path.insert(0, '.')
+from concurrent.futures import ThreadPoolExecutor
+from omni import feeds, net
+from omni.sources import Source
+
+RSS = [
+    ("itsecurityguru", "https://www.itsecurityguru.co.uk/feed/"),
+    ("securityledger", "https://securityledger.com/feed/"),
+    ("zdnet_security", "https://www.zdnet.com/topic/security/rss.xml"),
+    ("grahamcluley", "https://www.grahamcluley.com/feed/"),
+    ("cyberdefensemagazine", "https://www.cyberdefensemagazine.com/feed/"),
+    ("hackersonlineclub", "https://www.hackersonlineclub.com/feed"),
+    ("netspi", "https://www.netspi.com/feed/"),
+    ("hackingarticles", "https://www.hackingarticles.in/feed/"),
+    ("ired_team", "https://www.ired.team/feed.xml"),
+    ("pentestpartners", "https://www.pentestpartners.com/feed/"),
+    ("trustedsec", "https://www.trustedsec.com/feed/"),
+    ("specterops", "https://posts.specterops.io/feed"),
+    ("secjuice", "https://www.secjuice.com/feed/"),
+    ("varonis_blog", "https://www.varonis.com/blog/feed"),
+    ("netenrich", "https://netenrich.com/feed/"),
+    ("opennet_ru", "https://opennet.ru/rss.xml"),
+    ("linuxorg_ru", "https://www.linux.org.ru/feed.jsp"),
+    ("zd3news_security", "https://3dnews.ru/security/rss"),
+    ("securelist_ru", "https://securelist.ru/feed/"),
+    ("hackware_ru", "https://hackware.ru/feed/"),
+    ("cyberint_blog", "https://cyberint.com/blog/feed/"),
+    ("gbhackers_rss", "https://gbhackers.com/rss/"),
+    ("cybersecnews_rss", "https://cybersecuritynews.com/rss/"),
+    ("chaitin_blog", "https://www.chaitin.cn/zh/blog/feed"),
+    ("riskivy_blog", "https://blog.riskivy.com/feed"),
+    ("qianxin_news", "https://www.qianxin.com/news/rss"),
+    ("secwiki_news", "https://www.sec-wiki.com/news/rss"),
+    ("bleeping_ransomware", "https://www.bleepingcomputer.com/tag/ransomware/feed/"),
+    ("hackread_cybercrime", "https://hackread.com/category/cyber-crime/feed/"),
+    ("thecyberwire", "https://thecyberwire.com/feeds/rss.xml"),
+    ("riskybiz", "https://risky.biz/feeds/risky-business-news/"),
+]
+
+TG = ["ITSecForU", "CyberSecurityNews", "securitylab", "xakepnews", "exploitdb", "hacktips",
+      "pentesttools", "sysadmin_ru", "ai_papay", "gonzo_ai", "llm_ru", "malwareunpacked",
+      "databreachnews", "cve2026", "hackersnewsru", "kasperskyclub", "SecNewsRu", "websec",
+      "cyber_ru", "hackernews_ru", "redos", "anti_malware", "Antimalware", "sec_news"]
+
+
+def rss(url):
+    ad = "rss"
+    src = Source(name="p", category="security", kind="rss", url=url, adapter=ad, tags=(), limit=5)
+    r = net.get(url, timeout=25)
+    items = feeds.fetch(src, 5)
+    return {"u": url, "st": r.status, "n": len(items), "first": (items[0].title[:60] if items else "")}
+
+
+def tg(h):
+    url = "https://t.me/s/" + h
+    r = net.get(url, timeout=25)
+    t = r.text or ""
+    if t.count("tgme_widget_message_wrap") < 3:
+        return {"u": url, "n": 0, "why": "no preview"}
+    src = Source(name="p", category="security", kind="html", url=url, adapter="tg_web", tags=("tg",), limit=5)
+    items = feeds.fetch(src, 5)
+    return {"u": url, "n": len(items), "first": (items[0].title[:60] if items else "")}
+
+
+jobs = [("rss", u) for _, u in RSS] + [("tg", h) for h in TG]
+
+
+def run(j):
+    kind, x = j
+    try:
+        return tg(x) if kind == "tg" else rss(x)
+    except Exception as e:
+        return {"u": x, "n": 0, "err": str(e)[:70]}
+
+
+with ThreadPoolExecutor(6) as ex:
+    for r in ex.map(run, jobs):
+        print(json.dumps(r, ensure_ascii=False))