feat: VOSTFR/VO/FRENCH detection and subtitle embedding

Query Arte Player API before each download to determine available stream
versions. Select lang tag (VOSTFR > VO, FRENCH if audio is fr). Embed
French subtitles as default MKV track when VOSTFR. All output now .mkv.

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

arte_api.py

@@ -278,6 +278,35 @@ async def fetch_concerts(page: int = 1, search: str = "", page_size: int = 24, c
     }
 
 
+def get_versions(pid: str) -> list[dict]:
+    """Fetch available stream versions from Arte Player API for a programme ID."""
+    try:
+        raw = _fetch_url(
+            PLAYER_API.format(pid=pid),
+            headers={"User-Agent": _HEADERS["User-Agent"], "Accept": "application/json"},
+        )
+        data = json.loads(raw)
+        streams = data["data"]["attributes"].get("streams") or []
+        return streams[0].get("versions") or [] if streams else []
+    except Exception as ex:
+        logger.debug("Failed to get versions for %s: %s", pid, ex)
+        return []
+
+
+def select_lang_tag(versions: list[dict]) -> str:
+    """
+    Determine UNFR language tag from stream versions.
+    FR audio → FRENCH, non-FR + FR subs → VOSTFR, otherwise → VO.
+    """
+    if not versions:
+        return "VO"
+    if any(v.get("audioLanguage") == "fr" for v in versions):
+        return "FRENCH"
+    if any(v.get("subtitleLanguage") == "fr" for v in versions):
+        return "VOSTFR"
+    return "VO"
+
+
 async def invalidate_cache() -> int:
     _cache["ts"] = 0
     try:

downloader.py

@@ -9,7 +9,10 @@ from pathlib import Path
 
 import yt_dlp
 
+from arte_api import get_versions, select_lang_tag
+
 OUTPUT_DIR = "/data/Arte"
+_PID_RE = re.compile(r"\b(\d{6}-\d{3}-[A-Z])\b")
 DB_PATH = "data/arte_dl.db"
 
 Path("data").mkdir(exist_ok=True)
@@ -39,12 +42,10 @@ def _slugify(s: str) -> str:
     return s.strip(".")
 
 
-def build_release_name(title: str, subtitle: str, year: int | None, info: dict) -> str:
+def build_release_name(title: str, subtitle: str, year: int | None, info: dict, lang_tag: str = "VO") -> str:
+    """Build a proper UNFR/scene release name.
+    Format: Title.Event.Year.LANG.Resolution.WEB-DL.x264.AAC-ReMoRa.mkv
     """
-    Build a proper UNFR/scene release name.
-    Format: Title.Event.Year.FRENCH.Resolution.WEBRip.x264.AAC-ReMoRa.mp4
-    """
-    # Strip year from both title and subtitle to avoid duplication
     t = re.sub(r"\b" + str(year) + r"\b", "", title).strip() if year else title
     name = _slugify(t)
 
@@ -57,7 +58,6 @@ def build_release_name(title: str, subtitle: str, year: int | None, info: dict)
 
     year_str = str(year) if year else ""
 
-    # Resolution from yt-dlp info
     height = info.get("height") or 0
     if height >= 2160:
         res = "2160p"
@@ -68,7 +68,6 @@ def build_release_name(title: str, subtitle: str, year: int | None, info: dict)
     else:
         res = f"{height}p" if height else "1080p"
 
-    # Video codec (avc1 = H.264, hev1/hvc1/hevc = H.265)
     vcodec = (info.get("vcodec") or "").lower()
     if "hevc" in vcodec or "h265" in vcodec or "hev1" in vcodec or "hvc1" in vcodec:
         vc = "HEVC"
@@ -77,9 +76,9 @@ def build_release_name(title: str, subtitle: str, year: int | None, info: dict)
     else:
         vc = "x264"
 
-    parts = [name, year_str, res, "WEB-DL", vc, "AAC"]
+    parts = [name, year_str, lang_tag, res, "WEB-DL", vc, "AAC"]
     base = ".".join(p for p in parts if p)
-    return f"{base}-ReMoRa.mp4"
+    return f"{base}-ReMoRa.mkv"
 
 
 class DownloadManager:
@@ -192,6 +191,13 @@ class DownloadManager:
         with _db() as conn:
             conn.execute("UPDATE downloads SET state='downloading' WHERE id=?", (dl_id,))
 
+        # Determine language tag from Arte Player API before downloading
+        pid_m = _PID_RE.search(url)
+        lang_tag = "VO"
+        if pid_m:
+            versions = get_versions(pid_m.group(1))
+            lang_tag = select_lang_tag(versions)
+
         # For HLS, yt-dlp downloads video then audio separately.
         # After the first stream finishes, stay in "processing" to avoid
         # resetting progress to 0% when the audio stream starts.
@@ -216,19 +222,30 @@ class DownloadManager:
         ydl_opts = {
             "outtmpl": f"{out_dir}/%(title)s.%(ext)s",
             "format": "bestvideo[vcodec^=avc1]+bestaudio/bestvideo+bestaudio/best",
-            "merge_output_format": "mp4",
+            "merge_output_format": "mkv",
             "progress_hooks": [hook],
             "quiet": True,
             "no_warnings": True,
         }
+        if lang_tag == "VOSTFR":
+            ydl_opts.update({
+                "writesubtitles": True,
+                "subtitleslangs": ["fr"],
+                "embedsubtitles": True,
+                # Set first subtitle track as default in MKV
+                "postprocessor_args": {"ffmpeg_o": ["-disposition:s:0", "default"]},
+            })
 
         try:
             with yt_dlp.YoutubeDL(ydl_opts) as ydl:
                 info = ydl.extract_info(url, download=True)
                 orig_path = Path(ydl.prepare_filename(info))
 
-            # Rename to proper release name
-            release_name = build_release_name(title, subtitle, year, info)
+            # yt-dlp renames to .mkv after merge; prepare_filename may return .mp4
+            if not orig_path.exists():
+                orig_path = orig_path.with_suffix(".mkv")
+
+            release_name = build_release_name(title, subtitle, year, info, lang_tag)
             dest_path = orig_path.parent / release_name
             if orig_path.exists() and orig_path != dest_path:
                 if dest_path.exists():