Add curl fallback for protected HLS segments

provider_downloader.py

@@ -10,6 +10,7 @@ import shutil
 import subprocess
 import sys
 import time
+import urllib.error
 from urllib.parse import urljoin, urlparse
 import urllib.request
 from pathlib import Path
@@ -19,6 +20,7 @@ PROJECT_ROOT = Path(__file__).resolve().parent
 BRIDGE = PROJECT_ROOT / "providers" / "bridge.js"
 PROVIDERS = ("anikoto", "anineko", "pahe")
 RETRYABLE_HTTP_STATUS = {408, 425, 429, 500, 502, 503, 504}
+CURL_STATUS_MARKER = b"\nKAIZOKU_HTTP_STATUS:"
 
 
 def clean_component(value, default="Anime"):
@@ -212,10 +214,75 @@ def request_headers(headers=None, referer=None):
     return merged
 
 
+def curl_candidates():
+    configured = str(os.environ.get("KAIZOKU_CURL_BIN") or "").strip()
+    names = [
+        configured,
+        "curl_chrome120",
+        "curl_chrome116",
+        "curl_chrome110",
+        "curl-impersonate",
+        "curl",
+    ]
+    candidates = []
+    for name in names:
+        if not name or name in candidates:
+            continue
+        resolved = shutil.which(name)
+        if resolved:
+            candidates.append(resolved)
+    return candidates
+
+
+def curl_fetch_bytes(url, headers=None, timeout=30):
+    candidates = curl_candidates()
+    if not candidates:
+        raise RuntimeError("curl is not available for media fetch fallback.")
+    clean_headers = request_headers(headers)
+    last_error = None
+    for curl_bin in candidates:
+        cmd = [
+            curl_bin,
+            "--location",
+            "--silent",
+            "--show-error",
+            "--max-time",
+            str(max(1, int(timeout or 30))),
+        ]
+        for key, value in clean_headers.items():
+            if value:
+                cmd.extend(["--header", f"{key}: {value}"])
+        cmd.extend(["--write-out", f"{CURL_STATUS_MARKER.decode('ascii')}%{{http_code}}", "--output", "-", str(url)])
+        proc = subprocess.run(cmd, capture_output=True, check=False)
+        payload, marker, status_bytes = proc.stdout.rpartition(CURL_STATUS_MARKER)
+        if marker:
+            try:
+                status = int(status_bytes.strip() or b"0")
+            except ValueError:
+                status = 0
+        else:
+            payload = proc.stdout
+            status = 0
+        if 200 <= status < 300 and proc.returncode == 0:
+            return payload
+        message = (proc.stderr or b"curl media fetch failed").decode("utf-8", errors="replace").strip()
+        last_error = urllib.error.HTTPError(str(url), status or 0, message, hdrs={}, fp=None)
+    raise last_error or RuntimeError("curl media fetch failed.")
+
+
 def fetch_bytes(url, headers=None, timeout=30):
+    client = str(os.environ.get("KAIZOKU_MEDIA_HTTP_CLIENT") or "auto").strip().lower()
+    if client == "curl":
+        return curl_fetch_bytes(url, headers=headers, timeout=timeout)
     request = urllib.request.Request(url, headers=request_headers(headers))
-    with urllib.request.urlopen(request, timeout=timeout) as response:
-        return response.read()
+    try:
+        with urllib.request.urlopen(request, timeout=timeout) as response:
+            return response.read()
+    except urllib.error.HTTPError as exc:
+        if client != "urllib" and exc.code == 403 and curl_candidates():
+            print(f"urllib media fetch got HTTP 403; retrying with curl fallback.", file=sys.stderr, flush=True)
+            return curl_fetch_bytes(url, headers=headers, timeout=timeout)
+        raise
 
 
 def int_env(name, default, minimum=0):