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

.local/diag7.py

@@ -0,0 +1,43 @@
+import sys, json
+sys.path.insert(0, '.')
+from concurrent.futures import ThreadPoolExecutor
+from omni import feeds, net
+from omni.sources import Source
+
+C = [
+    ("cisa_news", "https://www.cisa.gov/news-events/news/rss.xml", "rss", {}),
+    ("fortinet_blog", "https://www.fortinet.com/blog/rss.xml", "rss", {}),
+    ("mcafee_blogs", "https://www.mcafee.com/blogs/feed/", "rss", {}),
+    ("avast_blog", "https://www.avast.com/en-us/blog/feed", "rss", {}),
+    ("eset_press", "https://www.eset.com/int/about/newsroom/press-releases/feed/", "rss", {}),
+    ("gti_threat_intel", "https://cloud.google.com/blog/topics/threat-intelligence/rss/", "rss", {}),
+    ("checkpoint_blog", "https://www.checkpoint.com/blog/feed/", "rss", {}),
+    ("anquanke_news", "https://www.anquanke.com/news", "html_listing", {"include_prefixes": ["/post/id/"]}),
+    ("secrss_vuln", "https://www.secrss.com/articles", "html_listing", {"include_prefixes": ["/articles/"]}),
+    ("bleeping_dup_check", "https://www.bleepingcomputer.com/feed/", "rss", {}),
+    ("therecord_dup_check", "https://therecord.media/feed", "rss", {}),
+    ("deepwatch_blog", "https://www.deepwatch.com/feed/", "rss", {}),
+    ("huntress_alt", "https://www.huntress.com/blog/feed", "rss", {}),
+    ("dragos_alt", "https://www.dragos.com/feed/", "rss", {}),
+    ("scmedia_alt", "https://www.scmagazine.com/feed", "rss", {}),
+    ("trendmicro_alt", "https://www.trendmicro.com/en_us/research/feed", "rss", {}),
+    ("zscaler_alt", "https://www.zscaler.com/blogs/security-research/rss", "rss", {}),
+    ("gbhackers_alt", "https://gbhackers.com/feed", "rss", {}),
+    ("cybersecnews_alt", "https://cybersecuritynews.com/feed", "rss", {}),
+]
+
+
+def run(t):
+    name, url, ad, extra = t
+    src = Source(name=name, category="security", kind="rss", url=url, adapter=ad, tags=(), limit=5, extra=extra)
+    try:
+        r = net.get(url, timeout=25)
+        items = feeds.fetch(src, 5)
+        return {"name": name, "st": r.status, "n": len(items), "first": (items[0].title[:60] if items else "")}
+    except Exception as e:
+        return {"name": name, "n": 0, "err": str(e)[:70]}
+
+
+with ThreadPoolExecutor(6) as ex:
+    for r in ex.map(run, C):
+        print(json.dumps(r, ensure_ascii=False))