feat: configure collector endpoints and health plan

backend/app/core/data_sources.yaml

@@ -2,53 +2,87 @@
 # All external data source URLs should be configured here
 
 arcgis:
+  # ArcGIS 海缆 GeoJSON 查询接口
   cable_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/2/query"
+  # ArcGIS 登陆点 GeoJSON 查询接口
   landing_point_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/1/query"
+  # ArcGIS 海缆与登陆点关联关系查询接口
   cable_landing_relation_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/3/query"
 
 fao:
+  # FAO 登陆点 CSV 下载地址
   landing_point_url: "https://data.apps.fao.org/catalog/dataset/1b75ff21-92f2-4b96-9b7b-98e8aa65ad5d/resource/b6071077-d1d4-4e97-aa00-42e902847c87/download/landing-point-geo.csv"
 
 telegeography:
+  # TeleGeography 海缆/系统主数据源，当前使用 GitHub 镜像 JSON
   cable_url: "https://raw.githubusercontent.com/lintaojlu/submarine_cable_information/main/cable.json"
+  # TeleGeography 登陆点主数据源，当前使用 GitHub 镜像 JSON
   landing_point_url: "https://raw.githubusercontent.com/lintaojlu/submarine_cable_information/main/landing_point.json"
+  # TeleGeography 历史 API 存档，用于 cable collector 的 fallback
+  archived_cable_url: "https://web.archive.org/web/2024/https://www.submarinecablemap.com/api/v3/cable"
+  # TeleGeography 官网页面，用于 cable collector 的最终 HTML 抓取 fallback
+  live_map_url: "https://www.submarinecablemap.com"
 
 huggingface:
+  # Hugging Face 模型目录 API
   models_url: "https://huggingface.co/api/models"
+  # Hugging Face 数据集目录 API
   datasets_url: "https://huggingface.co/api/datasets"
+  # Hugging Face Spaces 目录 API
   spaces_url: "https://huggingface.co/api/spaces"
 
 cloudflare:
+  # Cloudflare Radar 设备类型摘要接口
   radar_device_url: "https://api.cloudflare.com/client/v4/radar/http/summary/device_type"
+  # Cloudflare Radar 请求量时间序列接口
   radar_traffic_url: "https://api.cloudflare.com/client/v4/radar/http/timeseries/requests"
+  # Cloudflare Radar 热点地理位置接口
   radar_top_locations_url: "https://api.cloudflare.com/client/v4/radar/http/top/locations"
 
 peeringdb:
+  # PeeringDB IXP API
   ixp_url: "https://www.peeringdb.com/api/ix"
+  # PeeringDB Network API
   network_url: "https://www.peeringdb.com/api/net"
+  # PeeringDB Facility API
   facility_url: "https://www.peeringdb.com/api/fac"
 
 top500:
+  # TOP500 榜单页面，用于主表抓取
   url: "https://top500.org/lists/top500/list/2025/11/"
+  # TOP500 站点根地址，用于拼详情页链接
+  base_url: "https://top500.org"
 
 epoch_ai:
+  # Epoch AI GPU Cluster 页面
   gpu_clusters_url: "https://epoch.ai/data/gpu-clusters"
 
 spacetrack:
+  # Space-Track 站点根地址，用于首页访问和登录地址推导
   base_url: "https://www.space-track.org"
+  # Space-Track TLE 主查询接口
   tle_query_url: "https://www.space-track.org/basicspacedata/query/class/gp/orderby/EPOCH%20desc/limit/1000/format/json"
 
+celestrak:
+  # CelesTrak TLE 基础接口，collector 会在其后拼接 GROUP / FORMAT 参数
+  base_url: "https://celestrak.org/NORAD/elements/gp.php"
+
 ris_live:
+  # RIPE RIS Live 流式订阅地址
   url: "https://ris-live.ripe.net/v1/stream/?format=json&client=planet-ris-live"
 
 bgpstream:
+  # CAIDA BGPStream Broker API
   url: "https://broker.bgpstream.caida.org/v2"
 
 iptoasn:
+  # IPtoASN prefix geography 合并数据下载地址
   combined_url: "https://iptoasn.com/data/ip2asn-combined.tsv.gz"
 
 opengeofeed:
+  # OpenGeoFeed 公共 geofeed CSV
   public_csv_url: "https://opengeofeed.org/feed/public.csv"
 
 nro:
+  # NRO delegated stats 下载地址
   delegated_stats_url: "https://ftp.ripe.net/pub/stats/ripencc/nro-stats/latest/nro-delegated-stats"