feat: configure collector endpoints and health plan

backend/app/services/collectors/top500.py

@@ -10,6 +10,7 @@ from typing import Dict, Any, List
 from bs4 import BeautifulSoup
 import httpx
 
+from app.core.data_sources import get_data_sources_config
 from app.services.collectors.base import BaseCollector
 
 
@@ -22,7 +23,7 @@ class TOP500Collector(BaseCollector):
 
     async def fetch(self) -> List[Dict[str, Any]]:
         """Fetch TOP500 list data and enrich each row with detail-page metadata."""
-        url = "https://top500.org/lists/top500/list/2025/11/"
+        url = self._resolved_url or ""
 
         async with httpx.AsyncClient(timeout=60.0, follow_redirects=True) as client:
             response = await client.get(url)
@@ -48,11 +49,13 @@ class TOP500Collector(BaseCollector):
             return await asyncio.gather(*(enrich(entry) for entry in entries))
 
     def _extract_system_fields(self, system_cell) -> Dict[str, str]:
+        config = get_data_sources_config()
+        top500_base_url = config.get_yaml_value("top500.base_url") or "https://top500.org"
         link = system_cell.find("a")
         system_name = link.get_text(" ", strip=True) if link else system_cell.get_text(" ", strip=True)
         detail_url = ""
         if link and link.get("href"):
-            detail_url = f"https://top500.org{link.get('href')}"
+            detail_url = f"{str(top500_base_url).rstrip('/')}{link.get('href')}"
 
         manufacturer = ""
         if link and link.next_sibling: