Preserve HLS media session cookies

provider_downloader.py

@@ -3,12 +3,15 @@
 """Download episodes from Kaizoku's StrawVerse-compatible provider bridge."""
 
 import argparse
+import atexit
+import http.cookiejar
 import json
 import os
 import re
 import shutil
 import subprocess
 import sys
+import tempfile
 import time
 import urllib.error
 from urllib.parse import urljoin, urlparse
@@ -21,6 +24,8 @@ 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:"
+MEDIA_COOKIE_JAR = http.cookiejar.CookieJar()
+MEDIA_CURL_COOKIE_DIR = None
 
 
 def clean_component(value, default="Anime"):
@@ -214,6 +219,28 @@ def request_headers(headers=None, referer=None):
     return merged
 
 
+def media_request(url, headers=None):
+    request = urllib.request.Request(url, headers=request_headers(headers))
+    MEDIA_COOKIE_JAR.add_cookie_header(request)
+    return request
+
+
+def media_cookie_header(url):
+    request = urllib.request.Request(url)
+    MEDIA_COOKIE_JAR.add_cookie_header(request)
+    return request.get_header("Cookie") or ""
+
+
+def curl_cookie_file():
+    global MEDIA_CURL_COOKIE_DIR
+    if MEDIA_CURL_COOKIE_DIR is None:
+        MEDIA_CURL_COOKIE_DIR = tempfile.TemporaryDirectory(prefix="kaizoku-media-cookies-")
+        atexit.register(MEDIA_CURL_COOKIE_DIR.cleanup)
+        cookie_file = Path(MEDIA_CURL_COOKIE_DIR.name) / "cookies.txt"
+        cookie_file.touch(mode=0o600)
+    return Path(MEDIA_CURL_COOKIE_DIR.name) / "cookies.txt"
+
+
 def curl_candidates():
     def candidate_score(name):
         text = Path(str(name or "")).name
@@ -279,8 +306,13 @@ def curl_fetch_bytes(url, headers=None, timeout=30):
     if not candidates:
         raise RuntimeError("curl is not available for media fetch fallback.")
     last_error = None
+    failures = []
+    cookie_file = curl_cookie_file()
     for curl_bin in candidates:
         clean_headers = curl_request_headers(curl_bin, headers)
+        cookie_header = media_cookie_header(url)
+        if cookie_header and not any(str(key).lower() == "cookie" for key in clean_headers):
+            clean_headers["Cookie"] = cookie_header
         cmd = [
             curl_bin,
             "--location",
@@ -288,6 +320,10 @@ def curl_fetch_bytes(url, headers=None, timeout=30):
             "--show-error",
             "--max-time",
             str(max(1, int(timeout or 30))),
+            "--cookie",
+            str(cookie_file),
+            "--cookie-jar",
+            str(cookie_file),
         ]
         for key, value in clean_headers.items():
             if value:
@@ -305,7 +341,12 @@ def curl_fetch_bytes(url, headers=None, timeout=30):
             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()
+        client_name = Path(curl_bin).name
+        detail = (proc.stderr or b"").decode("utf-8", errors="replace").strip()
+        failures.append(f"{client_name}: HTTP {status or 0}" if status else f"{client_name}: exit {proc.returncode}")
+        message = "; ".join(failures)
+        if detail:
+            message = f"{message} ({detail})"
         last_error = urllib.error.HTTPError(str(url), status or 0, message, hdrs={}, fp=None)
     raise last_error or RuntimeError("curl media fetch failed.")
 
@@ -314,9 +355,10 @@ 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))
+    request = media_request(url, headers=headers)
     try:
         with urllib.request.urlopen(request, timeout=timeout) as response:
+            MEDIA_COOKIE_JAR.extract_cookies(response, request)
             return response.read()
     except urllib.error.HTTPError as exc:
         if client != "urllib" and exc.code == 403 and curl_candidates():