feat: add Stat-Check ELO column with daily auto-refresh

- Scraper (statcheck-elo-scraper/refresh_elo.py) downloads the stat-check ELO workbook from OneDrive and builds public/elo-data.json - GitHub Actions workflow (.github/workflows/refresh-elo.yml) runs daily at 06:00 UTC and commits updated ELO data - Frontend fetches elo-data.json and matches players by name, using BCP career event history to disambiguate same-name candidates - ELO score shown in new sortable Stat-Check ELO column, visible on all screen sizes; unmatched players show — Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 00:00:02 -05:00
parent 7dd9ddfefe
commit ac223a6909
10 changed files with 445 additions and 6 deletions
@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+import base64
+import json
+import sys
+from pathlib import Path
+from urllib.parse import quote
+from urllib.request import Request, urlopen
+
+from download_and_parse import download, xlsx_to_csv
+
+
+EMBED_URL = (
+    "https://1drv.ms/x/c/9f33f29504402fa1/"
+    "UQShL0AElfIzIICfIQ4AAAAAAGSZ8S-PJuKWQmM"
+    "?em=2&ActiveCell='Sheet1'!A1&Item='Sheet1'!A1:L40318"
+    "&wdHideGridlines=True&wdHideHeaders=True&wdDownloadButton=True"
+    "&wdInConfigurator=True&wdInConfigurator=True"
+)
+
+BADGER_APP_ID = "00000000-0000-0000-0000-0000481710a4"
+
+
+def request_json(url: str, *, method: str = "GET", data: bytes | None = None, headers: dict[str, str] | None = None) -> dict:
+    req = Request(url, data=data, method=method, headers=headers or {})
+    with urlopen(req, timeout=60) as resp:
+        return json.loads(resp.read().decode("utf-8"))
+
+
+def badger_token() -> str:
+    payload = json.dumps({"appid": BADGER_APP_ID}, separators=(",", ":")).encode()
+    data = request_json(
+        "https://api-badgerp.svc.ms/v1.0/token",
+        method="POST",
+        data=payload,
+        headers={
+            "Content-Type": "application/json",
+            "Origin": "https://onedrive.live.com",
+            "Referer": "https://onedrive.live.com/",
+            "User-Agent": "Mozilla/5.0",
+        },
+    )
+    if data.get("authScheme") != "badger" or not data.get("token"):
+        raise RuntimeError(f"Unexpected Badger token response: {data!r}")
+    return data["token"]
+
+
+def share_id(url: str) -> str:
+    encoded = base64.urlsafe_b64encode(url.encode()).decode().rstrip("=")
+    return "u!" + encoded
+
+
+def download_url_for_embed(embed_url: str) -> str:
+    token = badger_token()
+    select = "id,openWith,officebundle,currentUserRole,eTag,name,size,content.downloadUrl,file,sharepointIds,sensitivityLabel,webUrl,webDavUrl,parentReference,vault"
+    url = (
+        "https://my.microsoftpersonalcontent.com/_api/v2.0/shares/"
+        f"{share_id(embed_url)}/driveItem?action=EmbedView&$select={quote(select, safe=',')}"
+    )
+    data = request_json(
+        url,
+        method="POST",
+        data=b"",
+        headers={
+            "Accept": "application/json",
+            "Authorization": f"Badger {token}",
+            "Origin": "https://onedrive.live.com",
+            "Prefer": "autoredeem",
+            "Referer": "https://onedrive.live.com/",
+            "User-Agent": "Mozilla/5.0",
+        },
+    )
+    if "@content.downloadUrl" not in data:
+        raise RuntimeError(f"No download URL in metadata response: {data!r}")
+    return data["@content.downloadUrl"]
+
+
+def main() -> None:
+    xlsx_path = Path(sys.argv[1] if len(sys.argv) > 1 else "elo-pure.xlsx")
+    csv_path = Path(sys.argv[2] if len(sys.argv) > 2 else "elo-pure.csv")
+    url = download_url_for_embed(EMBED_URL)
+    download(url, xlsx_path)
+    xlsx_to_csv(xlsx_path, csv_path)
+    print(f"downloaded={xlsx_path.stat().st_size} bytes csv={csv_path.stat().st_size} bytes")
+
+
+if __name__ == "__main__":
+    main()