feat: Enhance magnet parsing to handle mixed prefixes and add site configuration support

Author: Zzackllack

app/api/qbittorrent/torrents.py

@@ -62,18 +62,21 @@ def torrents_add(
 
     magnet = urls.splitlines()[0].strip()
     logger.debug(f"Parsing magnet: {magnet}")
-    payload = parse_magnet(magnet)
-
-    # Determine which prefix is used (aw_ or sto_)
-    prefix = "aw" if "aw_slug" in payload else "sto"
-
-    slug = payload[f"{prefix}_slug"]
-    season = int(payload[f"{prefix}_s"])
-    episode = int(payload[f"{prefix}_e"])
-    language = payload[f"{prefix}_lang"]
-    site = payload.get(f"{prefix}_site", "aniworld.to" if prefix == "aw" else "s.to")
-    name = payload.get("dn", f"{slug}.S{season:02d}E{episode:02d}.{language}")
-    xt = payload["xt"]
+    try:
+        payload = parse_magnet(magnet)
+        prefix = "aw" if "aw_slug" in payload else "sto"
+
+        slug = payload[f"{prefix}_slug"]
+        season = int(payload[f"{prefix}_s"])
+        episode = int(payload[f"{prefix}_e"])
+        language = payload[f"{prefix}_lang"]
+        site = payload.get(f"{prefix}_site", "aniworld.to" if prefix == "aw" else "s.to")
+        name = payload.get("dn", f"{slug}.S{season:02d}E{episode:02d}.{language}")
+        xt = payload["xt"]
+    except (KeyError, ValueError) as exc:
+        logger.warning(f"Malformed magnet parameters: {exc}")
+        raise HTTPException(status_code=400, detail="malformed magnet parameters") from exc
+
     btih = xt.split(":")[-1].lower()
 
     logger.info(

app/api/torznab/api.py

@@ -10,6 +10,7 @@
 from sqlmodel import Session
 
 from app.config import (
+    CATALOG_SITE_CONFIGS,
     TORZNAB_CAT_ANIME,
     TORZNAB_RETURN_TEST_RESULT,
     TORZNAB_TEST_EPISODE,
@@ -24,6 +25,23 @@
 from .utils import _build_item, _caps_xml, _require_apikey, _rss_root
 
 
+def _default_languages_for_site(site: str) -> List[str]:
+    """
+    Return the default language preference ordering for a catalogue site.
+    Falls back to AniWorld defaults when a site-specific mapping is not found.
+    """
+    cfg = CATALOG_SITE_CONFIGS.get(site)
+    if cfg:
+        languages = cfg.get("default_languages")
+        if isinstance(languages, list) and languages:
+            # return a shallow copy to avoid accidental mutation of config state
+            return list(languages)
+    fallback = CATALOG_SITE_CONFIGS.get("aniworld.to", {}).get(
+        "default_languages", ["German Dub", "German Sub", "English Sub"]
+    )
+    return list(fallback)
+
+
 @router.get("/api", response_class=FastAPIResponse)
 def torznab_api(
     request: Request,
@@ -120,12 +138,7 @@ def torznab_api(
                     session, slug=slug, season=season_i, episode=ep_i, site=site_found
                 )
 
-                # Default languages based on site
-                if site_found == "s.to":
-                    default_langs = ["German Dub", "English Dub", "German Sub"]
-                else:
-                    default_langs = ["German Dub", "German Sub", "English Sub"]
-
+                default_langs = _default_languages_for_site(site_found)
                 candidate_langs: List[str] = (
                     cached_langs if cached_langs else default_langs
                 )
@@ -260,12 +273,7 @@ def torznab_api(
         session, slug=slug, season=season_i, episode=ep_i, site=site_found
     )
 
-    # Default languages based on site
-    if site_found == "s.to":
-        default_langs = ["German Dub", "English Dub", "German Sub"]
-    else:
-        default_langs = ["German Dub", "German Sub", "English Sub"]
-
+    default_langs = _default_languages_for_site(site_found)
     candidate_langs: List[str] = cached_langs if cached_langs else default_langs
     logger.debug(
         f"Candidate languages for slug '{slug}', season {season_i}, episode {ep_i}, site '{site_found}': {candidate_langs}"

app/config.py

@@ -1,5 +1,6 @@
-import sys
 import os
+from copy import deepcopy
+from typing import Any
 from pathlib import Path
 from dotenv import load_dotenv
 from loguru import logger
@@ -283,9 +284,7 @@ def _ensure_dir(candidates: list[Path], label: str) -> Path:
 ).strip()
 
 # S.to (series)
-STO_BASE_URL = os.getenv(
-    "STO_BASE_URL", "https://s.to"
-).strip()  # valid options are https://s.to, https://serienstream.to and http://186.2.175.5
+STO_BASE_URL = os.getenv("STO_BASE_URL", "https://s.to").strip()
 STO_ALPHABET_HTML = Path(
     os.getenv("STO_ALPHABET_HTML", DATA_DIR / "sto-alphabeth.html")
 )
@@ -323,6 +322,35 @@ def _ensure_dir(candidates: list[Path], label: str) -> Path:
     f"RELEASE_GROUP_ANIWORLD={RELEASE_GROUP_ANIWORLD}, RELEASE_GROUP_STO={RELEASE_GROUP_STO}"
 )
 
+_DEFAULT_SITE_CONFIGS: dict[str, dict[str, Any]] = {
+    "aniworld.to": {
+        "base_url": ANIWORLD_BASE_URL,
+        "alphabet_html": ANIWORLD_ALPHABET_HTML,
+        "alphabet_url": ANIWORLD_ALPHABET_URL,
+        "titles_refresh_hours": ANIWORLD_TITLES_REFRESH_HOURS,
+        "default_languages": ["German Dub", "German Sub", "English Sub"],
+        "release_group": RELEASE_GROUP_ANIWORLD,
+    },
+    "s.to": {
+        "base_url": STO_BASE_URL,
+        "alphabet_html": STO_ALPHABET_HTML,
+        "alphabet_url": STO_ALPHABET_URL,
+        "titles_refresh_hours": STO_TITLES_REFRESH_HOURS,
+        "default_languages": ["German Dub", "English Dub", "German Sub"],
+        "release_group": RELEASE_GROUP_STO,
+    },
+}
+
+CATALOG_SITE_CONFIGS: dict[str, dict[str, Any]] = {}
+for site in CATALOG_SITES_LIST:
+    base_cfg = _DEFAULT_SITE_CONFIGS.get(site)
+    if not base_cfg:
+        logger.warning(
+            f"No built-in configuration for catalogue site '{site}'. Provide environment overrides to enable it."
+        )
+        continue
+    CATALOG_SITE_CONFIGS[site] = deepcopy(base_cfg)
+
 # ---- Provider-Fallback ----
 # Kommagetrennte Liste, z. B. "VOE,Filemoon,Streamtape,Vidmoly,SpeedFiles,Doodstream,LoadX,Luluvdo,Vidoza"
 # Reihenfolge = Priorität

app/core/scheduler.py

@@ -190,7 +190,7 @@ def schedule_download(req: dict) -> str:
         raise RuntimeError("executor not available")
 
     with Session(engine) as s:
-        job = create_job(s)
+        job = create_job(s, source_site=req.get("site"))
 
     stop_event = threading.Event()
     fut = EXECUTOR.submit(_run_download, job.id, req, stop_event)

app/db/models.py

@@ -1,20 +1,12 @@
 from __future__ import annotations
-import sys
-import os
+
 from typing import Optional, Literal, Generator, Any, List
 from datetime import datetime, timezone, timedelta
 from uuid import uuid4
 from loguru import logger
+from app.utils.logger import config as configure_logger
 
-LOG_LEVEL = os.environ.get("LOG_LEVEL", "INFO").upper()
-logger.remove()
-logger.add(
-    sys.stdout,
-    level=LOG_LEVEL,
-    colorize=True,
-    format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | "
-    "<cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> - <level>{message}</level>",
-)
+configure_logger()
 
 from sqlmodel import SQLModel, Field, Session, create_engine, select, Column, JSON
 from sqlalchemy.orm import registry as sa_registry
@@ -146,9 +138,82 @@ class ClientTask(ModelBase, table=True):
 logger.debug("SQLModel engine created.")
 
 
+def _migrate_episode_availability_table() -> None:
+    """
+    Ensure the episodeavailability table includes the site column in its primary key.
+    Performs an in-place SQLite migration when running against an existing database
+    created before multi-site support was introduced.
+    """
+    try:
+        with engine.begin() as conn:
+            table_present = conn.exec_driver_sql(
+                "SELECT name FROM sqlite_master WHERE type='table' AND name='episodeavailability'"
+            ).fetchone()
+            if not table_present:
+                logger.debug(
+                    "episodeavailability table not found; no migration necessary."
+                )
+                return
+
+            columns = conn.exec_driver_sql(
+                "PRAGMA table_info('episodeavailability')"
+            ).fetchall()
+            if any(col[1] == "site" for col in columns):
+                logger.debug(
+                    "episodeavailability table already contains 'site' column."
+                )
+                return
+
+            logger.info(
+                "Migrating episodeavailability table to include site column."
+            )
+            conn.exec_driver_sql(
+                """
+                CREATE TABLE episodeavailability_new (
+                    slug TEXT NOT NULL,
+                    season INTEGER NOT NULL,
+                    episode INTEGER NOT NULL,
+                    language TEXT NOT NULL,
+                    site TEXT NOT NULL DEFAULT 'aniworld.to',
+                    available BOOLEAN NOT NULL,
+                    height INTEGER,
+                    vcodec TEXT,
+                    provider TEXT,
+                    checked_at DATETIME NOT NULL,
+                    extra JSON,
+                    PRIMARY KEY (slug, season, episode, language, site)
+                )
+                """
+            )
+            conn.exec_driver_sql(
+                """
+                INSERT INTO episodeavailability_new (
+                    slug, season, episode, language, site,
+                    available, height, vcodec, provider, checked_at, extra
+                )
+                SELECT
+                    slug, season, episode, language,
+                    'aniworld.to' AS site,
+                    available, height, vcodec, provider, checked_at, extra
+                FROM episodeavailability
+                """
+            )
+            conn.exec_driver_sql("DROP TABLE episodeavailability")
+            conn.exec_driver_sql(
+                "ALTER TABLE episodeavailability_new RENAME TO episodeavailability"
+            )
+            logger.success(
+                "episodeavailability table migrated to include site column."
+            )
+    except Exception as exc:
+        logger.error(f"Failed to migrate episodeavailability table: {exc}")
+        raise
+
+
 def create_db_and_tables() -> None:
     logger.debug("Creating DB and tables if not exist.")
     try:
+        _migrate_episode_availability_table()
         # Use this module's private metadata
         ModelBase.metadata.create_all(engine)
         logger.success("Database and tables created or already exist.")
@@ -180,10 +245,13 @@ def dispose_engine() -> None:
 
 
 # --- Jobs CRUD
-def create_job(session: Session) -> Job:
+def create_job(session: Session, *, source_site: Optional[str] = None) -> Job:
     logger.debug("Creating new job entry in DB.")
     try:
-        job = Job()
+        job_kwargs: dict[str, Any] = {}
+        if source_site:
+            job_kwargs["source_site"] = source_site
+        job = Job(**job_kwargs)
         session.add(job)
         session.commit()
         session.refresh(job)

app/utils/magnet.py

@@ -116,16 +116,21 @@ def parse_magnet(magnet: str) -> Dict[str, str]:
         flat[k] = v[0]
         logger.debug(f"Magnet param parsed: {k}={v[0]}")
 
-    # Determine which prefix is used
-    has_aw = any(k.startswith("aw_") for k in flat.keys())
-    has_sto = any(k.startswith("sto_") for k in flat.keys())
-
-    if has_aw:
-        prefix = "aw"
-    elif has_sto:
-        prefix = "sto"
-    else:
-        # Backward compatibility: default to aw_
+    # Determine which prefix is used while rejecting mixed usage
+    prefix: str | None = None
+    for key in flat.keys():
+        if key.startswith("aw_"):
+            if prefix and prefix != "aw":
+                logger.error("Magnet contains mixed prefixes: aw_ and sto_")
+                raise ValueError("mixed magnet prefixes: aw_ and sto_")
+            prefix = "aw"
+        elif key.startswith("sto_"):
+            if prefix and prefix != "sto":
+                logger.error("Magnet contains mixed prefixes: aw_ and sto_")
+                raise ValueError("mixed magnet prefixes: aw_ and sto_")
+            prefix = "sto"
+    if prefix is None:
+        # Backward compatibility: default to aw_ when no explicit prefix detected
         prefix = "aw"
 
     # Check required params