backend/app/scrapers/nspd_bulk_client.py

@@ -48,17 +48,21 @@ _SEMAPHORE = asyncio.Semaphore(3)
 # Таймаут подключения и чтения
 DEFAULT_TIMEOUT = httpx.Timeout(30.0, connect=10.0)
 
-# Headers из HAR audit 2026-05-15
+# Headers — exact match to legacy nspd_lite.py (proven to bypass NSPD WAF
+# on VPS IP since April 2026). All-lowercase keys + cache-control + Chrome 144
+# UA. Initial HAR-extracted headers (Pascal-Case, Chrome 148, no cache-control)
+# were blocked 50/50 в pilot run v2 (job_id=2, all 403 WAF).
 DEFAULT_HEADERS: dict[str, str] = {
-    "User-Agent": (
+    "accept": "*/*",
+    "accept-language": "en-US,en;q=0.9,ru-RU;q=0.8,ru;q=0.7,es;q=0.6",
+    "cache-control": "no-cache",
+    "pragma": "no-cache",
+    "referer": "https://nspd.gov.ru/map?thematic=PKK",
+    "origin": "https://nspd.gov.ru",
+    "user-agent": (
         "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
-        "(KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36"
+        "(KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36"
     ),
-    "Referer": "https://nspd.gov.ru/map",
-    "Accept": "*/*",
-    "Accept-Language": "ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7",
-    "x-timezone": "Europe/Moscow",
-    # Origin только для POST endpoints — не включаем для GET (лишний header)
 }
 
 # Retry settings