fix: add sec-fetch headers and fallback to notification listing on 403

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

check_zipair.py

@@ -22,6 +22,7 @@ NTFY_TOKEN  = os.environ.get("NTFY_TOKEN", "")   # optional, if your ntfy requir
 STATE_FILE  = os.environ.get("STATE_FILE", "last_seen.txt")
 
 ZIPAIR_SITEMAP   = "https://www.zipair.net/sitemap.xml"
+ZIPAIR_NOTIF_LIST = "https://www.zipair.net/en/notification"
 ZIPAIR_NOTIF     = "https://www.zipair.net/en/notification/{id}"
 
 # Keywords that must ALL appear (case-insensitive) in a notification page
@@ -36,9 +37,14 @@ HEADERS = {
         "Chrome/124.0.0.0 Safari/537.36"
     ),
     "Accept":          "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
-    "Accept-Language": "en-US,en;q=0.9",
+    "Accept-Language": "en-US,en;q=0.9,ja;q=0.8",
     "Accept-Encoding": "gzip, deflate, br",
     "Connection":      "keep-alive",
+    "Referer":         "https://www.zipair.net/",
+    "Sec-Fetch-Dest":  "document",
+    "Sec-Fetch-Mode":  "navigate",
+    "Sec-Fetch-Site":  "same-origin",
+    "Upgrade-Insecure-Requests": "1",
 }
 
 # ── Helpers ─────────────────────────────────────────────────────────────────
@@ -67,12 +73,22 @@ def get_notification_ids_from_sitemap() -> list[int]:
     """Parse the ZIPAIR sitemap and return all notification IDs found."""
     print("Fetching sitemap …")
     xml = fetch(ZIPAIR_SITEMAP)
-    if not xml:
-        print("  Sitemap unavailable.", file=sys.stderr)
-        return []
+    if xml:
         ids = [int(m) for m in re.findall(r"/notification/(\d+)", xml)]
+        if ids:
             ids = sorted(set(ids))
-    print(f"  Found {len(ids)} notification IDs in sitemap (max={ids[-1] if ids else 'n/a'})")
+            print(f"  Found {len(ids)} notification IDs in sitemap (max={ids[-1]})")
+            return ids
+
+    # Fallback: scrape the notification listing page
+    print("  Sitemap unavailable, trying notification listing page …")
+    html = fetch(ZIPAIR_NOTIF_LIST)
+    if not html:
+        print("  Notification listing page also unavailable.", file=sys.stderr)
+        return []
+    ids = [int(m) for m in re.findall(r"/notification/(\d+)", html)]
+    ids = sorted(set(ids))
+    print(f"  Found {len(ids)} notification IDs from listing page (max={ids[-1] if ids else 'n/a'})")
     return ids