Filter ransomware.live to LV/EE/LT, dedicated Telegram topic, harden fetcher

- New alert topic (/on_ransomware) separate from RSS malware articles,
  so a busy leak day doesn't bury other malware coverage.
- Filter victims to Latvia/Estonia/Lithuania before they ever touch the
  seen-DB — the global feed is already on ransomware.live's own site.
- Retention bumped to 14 days (bot_config.SEEN_RETENTION_DAYS).
- Add is_first_run(): lets the caller distinguish a genuinely fresh
  seen-DB from a restart of an already-running bot.
- Fix a naive-vs-aware datetime comparison that would TypeError-crash
  a poll cycle if the API ever returned a timestamp without a UTC offset.
- Drop the unused _victim_id/iocs fields from to_article()'s output.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

ransomware_fetcher.py

@@ -14,6 +14,8 @@ from typing import Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 from html import escape
 
+from bot_config import SEEN_RETENTION_DAYS, ALLOWED_RANSOMWARE_COUNTRIES
+
 logger = logging.getLogger(__name__)
 
 API_BASE = "https://api-pro.ransomware.live"
@@ -45,9 +47,15 @@ class RansomwareFetcher:
                 "SELECT 1 FROM seen_victims WHERE victim_id = ?", (victim_id,)
             ).fetchone() is not None
 
+    def is_first_run(self) -> bool:
+        """True if no victims have ever been recorded as seen (fresh DB)."""
+        with sqlite3.connect(self.seen_file) as conn:
+            count = conn.execute("SELECT COUNT(1) FROM seen_victims").fetchone()[0]
+        return count == 0
+
     def mark_seen(self, victim_id: str):
         now = datetime.now(timezone.utc).isoformat()
-        cutoff = (datetime.now(timezone.utc) - timedelta(days=7)).isoformat()
+        cutoff = (datetime.now(timezone.utc) - timedelta(days=SEEN_RETENTION_DAYS)).isoformat()
         with sqlite3.connect(self.seen_file) as conn:
             conn.execute("DELETE FROM seen_victims WHERE seen_at < ?", (cutoff,))
             conn.execute(
@@ -95,6 +103,13 @@ class RansomwareFetcher:
             victims = await self._fetch_month(session, year, month)
             all_victims.extend(victims)
 
+        # Only care about victims in these countries — the general global feed
+        # is available directly on ransomware.live's own site.
+        all_victims = [
+            v for v in all_victims
+            if (v.get("country") or "").strip().upper() in ALLOWED_RANSOMWARE_COUNTRIES
+        ]
+
         new_victims = []
         for v in all_victims:
             discovered_str = v.get("discovered", "")
@@ -104,6 +119,8 @@ class RansomwareFetcher:
                 discovered_dt = datetime.fromisoformat(discovered_str.replace("Z", "+00:00"))
             except ValueError:
                 continue
+            if discovered_dt.tzinfo is None:
+                discovered_dt = discovered_dt.replace(tzinfo=timezone.utc)
             if discovered_dt < cutoff:
                 continue
 
@@ -167,13 +184,11 @@ class RansomwareFetcher:
             "url":              victim.get("permalink", ""),
             "published_human":  published_human,
             "source":           "ransomware.live",
-            "category":         "malware",
-            "feed_type":        "malware",
+            "category":         "ransomware",
+            "feed_type":        "ransomware",
             "thumbnail":        screenshot,
             "cves":             [],
             "threat_actors":    [],
             "malware_families": [group.title()],
             "mitre_techniques": [],
-            "iocs":             {},
-            "_victim_id":       victim.get("id", ""),
         }