refactor(tags): Simplify Simkl search logic and soft-fail when no results found

.dockerignore

@@ -1,62 +0,0 @@
-# Logs and temporary files
-
-Logs/
-logs/
-temp/
-\*.log
-
-# Sensitive files
-
-key_vault.db
-unshackle/WVDs/
-unshackle/PRDs/
-unshackle/cookies/
-_.prd
-_.wvd
-
-# Cache directories
-
-unshackle/cache/
-**pycache**/
-_.pyc
-_.pyo
-\*.pyd
-.Python
-
-# Development files
-
-.git/
-.gitignore
-.vscode/
-.idea/
-_.swp
-_.swo
-
-# Documentation and plans
-
-plan/
-CONTRIBUTING.md
-CONFIG.md
-AGENTS.md
-OLD-CHANGELOG.md
-cliff.toml
-
-# Installation scripts
-
-install.bat
-
-# Test files
-
-_test_
-_Test_
-
-# Virtual environments
-
-venv/
-env/
-.venv/
-
-# OS generated files
-
-.DS_Store
-Thumbs.db

Dockerfile

@@ -1,78 +0,0 @@
-FROM python:3.12-slim
-
-# Set environment variables to reduce image size
-ENV PYTHONDONTWRITEBYTECODE=1 \
-    PYTHONUNBUFFERED=1 \
-    UV_CACHE_DIR=/tmp/uv-cache
-
-# Add container metadata
-LABEL org.opencontainers.image.description="Docker image for Unshackle with all required dependencies for downloading media content"
-
-# Install base dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    wget \
-    gnupg \
-    git \
-    curl \
-    build-essential \
-    cmake \
-    pkg-config \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Set up repos for mkvtools and bullseye for ccextractor
-RUN wget -O /etc/apt/keyrings/gpg-pub-moritzbunkus.gpg https://mkvtoolnix.download/gpg-pub-moritzbunkus.gpg \
-    && echo "deb [signed-by=/etc/apt/keyrings/gpg-pub-moritzbunkus.gpg] https://mkvtoolnix.download/debian/ bookworm main" >> /etc/apt/sources.list \
-    && echo "deb-src [signed-by=/etc/apt/keyrings/gpg-pub-moritzbunkus.gpg] https://mkvtoolnix.download/debian/ bookworm main" >> /etc/apt/sources.list \
-    && echo "deb http://ftp.debian.org/debian bullseye main" >> /etc/apt/sources.list
-
-# Install all dependencies from apt
-RUN apt-get update && apt-get install -y \
-    ffmpeg \
-    ccextractor \
-    mkvtoolnix \
-    aria2 \
-    libmediainfo-dev \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install shaka packager
-RUN wget https://github.com/shaka-project/shaka-packager/releases/download/v2.6.1/packager-linux-x64 \
-    && chmod +x packager-linux-x64 \
-    && mv packager-linux-x64 /usr/local/bin/packager
-
-# Install N_m3u8DL-RE
-RUN wget https://github.com/nilaoda/N_m3u8DL-RE/releases/download/v0.3.0-beta/N_m3u8DL-RE_v0.3.0-beta_linux-x64_20241203.tar.gz \
-    && tar -xzf N_m3u8DL-RE_v0.3.0-beta_linux-x64_20241203.tar.gz \
-    && mv N_m3u8DL-RE /usr/local/bin/ \
-    && chmod +x /usr/local/bin/N_m3u8DL-RE \
-    && rm N_m3u8DL-RE_v0.3.0-beta_linux-x64_20241203.tar.gz
-
-# Create binaries directory and add symlinks for all required executables
-RUN mkdir -p /app/binaries && \
-    ln -sf /usr/bin/ffprobe /app/binaries/ffprobe && \
-    ln -sf /usr/bin/ffmpeg /app/binaries/ffmpeg && \
-    ln -sf /usr/bin/mkvmerge /app/binaries/mkvmerge && \
-    ln -sf /usr/local/bin/N_m3u8DL-RE /app/binaries/N_m3u8DL-RE && \
-    ln -sf /usr/local/bin/packager /app/binaries/packager && \
-    ln -sf /usr/local/bin/packager /usr/local/bin/shaka-packager && \
-    ln -sf /usr/local/bin/packager /usr/local/bin/packager-linux-x64
-
-# Install uv
-RUN pip install --no-cache-dir uv
-
-# Set working directory
-WORKDIR /app
-
-# Copy dependency files and README (required by pyproject.toml)
-COPY pyproject.toml uv.lock README.md ./
-
-# Copy source code first
-COPY unshackle/ ./unshackle/
-
-# Install dependencies with uv (including the project itself)
-RUN uv sync --frozen --no-dev
-
-# Set entrypoint to allow passing commands directly to unshackle
-ENTRYPOINT ["uv", "run", "unshackle"]
-CMD ["-h"]

README.md

@@ -42,45 +42,6 @@ uv tool install git+https://github.com/unshackle-dl/unshackle.git
 uvx unshackle --help   # or just `unshackle` once PATH updated
 ```
 
-### Docker Installation
-
-Run unshackle using our pre-built Docker image from GitHub Container Registry:
-
-```bash
-# Run with default help command
-docker run --rm ghcr.io/unshackle-dl/unshackle:latest
-
-# Check environment dependencies
-docker run --rm ghcr.io/unshackle-dl/unshackle:latest env check
-
-# Download content (mount directories for persistent data)
-docker run --rm \
-  -v "$(pwd)/unshackle/downloads:/app/downloads" \
-  -v "$(pwd)/unshackle/cookies:/app/unshackle/cookies" \
-  -v "$(pwd)/unshackle/services:/app/unshackle/services" \
-  -v "$(pwd)/unshackle/WVDs:/app/unshackle/WVDs" \
-  -v "$(pwd)/unshackle/PRDs:/app/unshackle/PRDs" \
-  -v "$(pwd)/unshackle/unshackle.yaml:/app/unshackle.yaml" \
-  ghcr.io/unshackle-dl/unshackle:latest dl SERVICE_NAME CONTENT_ID
-
-# Run interactively for configuration
-docker run --rm -it \
-  -v "$(pwd)/unshackle/cookies:/app/unshackle/cookies" \
-  -v "$(pwd)/unshackle/services:/app/unshackle/services" \
-  -v "$(pwd)/unshackle.yaml:/app/unshackle.yaml" \
-  ghcr.io/unshackle-dl/unshackle:latest cfg
-```
-
-**Alternative: Build locally**
-
-```bash
-# Clone and build your own image
-git clone https://github.com/unshackle-dl/unshackle.git
-cd unshackle
-docker build -t unshackle .
-docker run --rm unshackle env check
-```
-
 > [!NOTE]
 > After installation, you may need to add the installation path to your PATH environment variable if prompted.
 

unshackle/commands/dl.py

@@ -143,7 +143,7 @@ class dl:
         "-l",
         "--lang",
         type=LANGUAGE_RANGE,
-        default="en",
+        default="orig",
         help="Language wanted for Video and Audio. Use 'orig' to select the original language, e.g. 'orig,en' for both original and English.",
     )
     @click.option(
@@ -436,6 +436,7 @@ class dl:
         **__: Any,
     ) -> None:
         self.tmdb_searched = False
+        self.search_source = None
         start_time = time.time()
 
         # Check if dovi_tool is available when hybrid mode is requested
@@ -493,34 +494,34 @@ class dl:
                 if self.tmdb_id:
                     tmdb_title = tags.get_title(self.tmdb_id, kind)
                 else:
-                    self.tmdb_id, tmdb_title = tags.search_tmdb(title.title, title.year, kind)
+                    self.tmdb_id, tmdb_title, self.search_source = tags.search_show_info(title.title, title.year, kind)
                     if not (self.tmdb_id and tmdb_title and tags.fuzzy_match(tmdb_title, title.title)):
                         self.tmdb_id = None
                 if list_ or list_titles:
                     if self.tmdb_id:
                         console.print(
                             Padding(
-                                f"TMDB -> {tmdb_title or '?'} [bright_black](ID {self.tmdb_id})",
+                                f"Search -> {tmdb_title or '?'} [bright_black](ID {self.tmdb_id})",
                                 (0, 5),
                             )
                         )
                     else:
-                        console.print(Padding("TMDB -> [bright_black]No match found[/]", (0, 5)))
+                        console.print(Padding("Search -> [bright_black]No match found[/]", (0, 5)))
                 self.tmdb_searched = True
 
             if isinstance(title, Movie) and (list_ or list_titles) and not self.tmdb_id:
-                movie_id, movie_title = tags.search_tmdb(title.name, title.year, "movie")
+                movie_id, movie_title, _ = tags.search_show_info(title.name, title.year, "movie")
                 if movie_id:
                     console.print(
                         Padding(
-                            f"TMDB -> {movie_title or '?'} [bright_black](ID {movie_id})",
+                            f"Search -> {movie_title or '?'} [bright_black](ID {movie_id})",
                             (0, 5),
                         )
                     )
                 else:
-                    console.print(Padding("TMDB -> [bright_black]No match found[/]", (0, 5)))
+                    console.print(Padding("Search -> [bright_black]No match found[/]", (0, 5)))
 
-            if self.tmdb_id:
+            if self.tmdb_id and getattr(self, 'search_source', None) != 'simkl':
                 kind = "tv" if isinstance(title, Episode) else "movie"
                 tags.external_ids(self.tmdb_id, kind)
                 if self.tmdb_year:

unshackle/core/config.py

@@ -85,6 +85,8 @@ class Config:
 
         self.set_terminal_bg: bool = kwargs.get("set_terminal_bg", False)
         self.tag: str = kwargs.get("tag") or ""
+        self.tag_group_name: bool = kwargs.get("tag_group_name", True)
+        self.tag_imdb_tmdb: bool = kwargs.get("tag_imdb_tmdb", True)
         self.tmdb_api_key: str = kwargs.get("tmdb_api_key") or ""
         self.update_checks: bool = kwargs.get("update_checks", True)
         self.update_check_interval: int = kwargs.get("update_check_interval", 24)

unshackle/core/tracks/subtitle.py

@@ -870,7 +870,18 @@ class Subtitle(Track):
         elif sdh_method == "filter-subs":
             # Force use of filter-subs
             sub = Subtitles(self.path)
-            sub.filter(rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=True, rm_author=True)
+            try:
+                sub.filter(rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=True, rm_author=True)
+            except ValueError as e:
+                if "too many values to unpack" in str(e):
+                    # Retry without name removal if the error is due to multiple colons in time references
+                    # This can happen with lines like "at 10:00 and 2:00"
+                    sub = Subtitles(self.path)
+                    sub.filter(
+                        rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=False, rm_author=True
+                    )
+                else:
+                    raise
             sub.save()
             return
         elif sdh_method == "auto":
@@ -906,7 +917,18 @@ class Subtitle(Track):
             )
         else:
             sub = Subtitles(self.path)
-            sub.filter(rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=True, rm_author=True)
+            try:
+                sub.filter(rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=True, rm_author=True)
+            except ValueError as e:
+                if "too many values to unpack" in str(e):
+                    # Retry without name removal if the error is due to multiple colons in time references
+                    # This can happen with lines like "at 10:00 and 2:00"
+                    sub = Subtitles(self.path)
+                    sub.filter(
+                        rm_fonts=True, rm_ast=True, rm_music=True, rm_effects=True, rm_names=False, rm_author=True
+                    )
+                else:
+                    raise
             sub.save()
 
     def reverse_rtl(self) -> None:

unshackle/core/utils/tags.py

@@ -44,6 +44,89 @@ def fuzzy_match(a: str, b: str, threshold: float = 0.8) -> bool:
     return ratio >= threshold
 
 
+def search_simkl(title: str, year: Optional[int], kind: str) -> Tuple[Optional[dict], Optional[str], Optional[int]]:
+    """Search Simkl API for show information by filename (no auth required)."""
+    log.debug("Searching Simkl for %r (%s, %s)", title, kind, year)
+
+    # Construct appropriate filename based on type
+    filename = f"{title}"
+    if year:
+        filename = f"{title} {year}"
+
+    if kind == "tv":
+        filename += " S01E01.mkv"
+    else:  # movie
+        filename += " 2160p.mkv"
+
+    try:
+        resp = requests.post("https://api.simkl.com/search/file", json={"file": filename}, headers=HEADERS, timeout=30)
+        resp.raise_for_status()
+        data = resp.json()
+        log.debug("Simkl API response received")
+
+        # Handle case where SIMKL returns empty list (no results)
+        if isinstance(data, list):
+            log.debug("Simkl returned list (no matches) for %r", filename)
+            return None, None, None
+
+        # Handle TV show responses
+        if data.get("type") == "episode" and "show" in data:
+            show_info = data["show"]
+            show_title = show_info.get("title")
+            show_year = show_info.get("year")
+
+            # Verify title matches and year if provided
+            if not fuzzy_match(show_title, title):
+                log.debug("Simkl title mismatch: searched %r, got %r", title, show_title)
+                return None, None, None
+            if year and show_year and abs(year - show_year) > 1:  # Allow 1 year difference
+                log.debug("Simkl year mismatch: searched %d, got %d", year, show_year)
+                return None, None, None
+
+            tmdb_id = show_info.get("ids", {}).get("tmdbtv")
+            if tmdb_id:
+                tmdb_id = int(tmdb_id)
+            log.debug("Simkl -> %s (TMDB ID %s)", show_title, tmdb_id)
+            return data, show_title, tmdb_id
+
+        # Handle movie responses
+        elif data.get("type") == "movie" and "movie" in data:
+            movie_info = data["movie"]
+            movie_title = movie_info.get("title")
+            movie_year = movie_info.get("year")
+
+            # Verify title matches and year if provided
+            if not fuzzy_match(movie_title, title):
+                log.debug("Simkl title mismatch: searched %r, got %r", title, movie_title)
+                return None, None, None
+            if year and movie_year and abs(year - movie_year) > 1:  # Allow 1 year difference
+                log.debug("Simkl year mismatch: searched %d, got %d", year, movie_year)
+                return None, None, None
+
+            ids = movie_info.get("ids", {})
+            tmdb_id = ids.get("tmdb") or ids.get("moviedb")
+            if tmdb_id:
+                tmdb_id = int(tmdb_id)
+            log.debug("Simkl -> %s (TMDB ID %s)", movie_title, tmdb_id)
+            return data, movie_title, tmdb_id
+
+    except (requests.RequestException, ValueError, KeyError) as exc:
+        log.debug("Simkl search failed: %s", exc)
+
+    return None, None, None
+
+
+def search_show_info(title: str, year: Optional[int], kind: str) -> Tuple[Optional[int], Optional[str], Optional[str]]:
+    """Search for show information, trying Simkl first, then TMDB fallback. Returns (tmdb_id, title, source)."""
+    simkl_data, simkl_title, simkl_tmdb_id = search_simkl(title, year, kind)
+
+    if simkl_data and simkl_title and fuzzy_match(simkl_title, title):
+        return simkl_tmdb_id, simkl_title, "simkl"
+
+    tmdb_id, tmdb_title = search_tmdb(title, year, kind)
+    return tmdb_id, tmdb_title, "tmdb"
+
+
 def search_tmdb(title: str, year: Optional[int], kind: str) -> Tuple[Optional[int], Optional[str]]:
     api_key = _api_key()
     if not api_key:
@@ -202,10 +285,8 @@ def tag_file(path: Path, title: Title, tmdb_id: Optional[int] | None = None) ->
     log.debug("Tagging file %s with title %r", path, title)
     standard_tags: dict[str, str] = {}
     custom_tags: dict[str, str] = {}
-    # To add custom information to the tags
-    # custom_tags["Text to the left side"] = "Text to the right side"
 
-    if config.tag:
+    if config.tag and config.tag_group_name:
         custom_tags["Group"] = config.tag
     description = getattr(title, "description", None)
     if description:
@@ -216,12 +297,6 @@ def tag_file(path: Path, title: Title, tmdb_id: Optional[int] | None = None) ->
             description = truncated + "..."
         custom_tags["Description"] = description
 
-    api_key = _api_key()
-    if not api_key:
-        log.debug("No TMDB API key set; applying basic tags only")
-        _apply_tags(path, custom_tags)
-        return
-
     if isinstance(title, Movie):
         kind = "movie"
         name = title.name
@@ -234,32 +309,60 @@ def tag_file(path: Path, title: Title, tmdb_id: Optional[int] | None = None) ->
         _apply_tags(path, custom_tags)
         return
 
-    tmdb_title: Optional[str] = None
-    if tmdb_id is None:
-        tmdb_id, tmdb_title = search_tmdb(name, year, kind)
-        log.debug("Search result: %r (ID %s)", tmdb_title, tmdb_id)
-        if not tmdb_id or not tmdb_title or not fuzzy_match(tmdb_title, name):
-            log.debug("TMDB search did not match; skipping external ID lookup")
+    if config.tag_imdb_tmdb:
+        # If tmdb_id is provided (via --tmdb), skip Simkl and use TMDB directly
+        if tmdb_id is not None:
+            log.debug("Using provided TMDB ID %s for tags", tmdb_id)
+        else:
+            # Try Simkl first for automatic lookup
+            simkl_data, simkl_title, simkl_tmdb_id = search_simkl(name, year, kind)
+
+            if simkl_data and simkl_title and fuzzy_match(simkl_title, name):
+                log.debug("Using Simkl data for tags")
+                if simkl_tmdb_id:
+                    tmdb_id = simkl_tmdb_id
+
+                show_ids = simkl_data.get("show", {}).get("ids", {})
+                if show_ids.get("imdb"):
+                    standard_tags["IMDB"] = f"https://www.imdb.com/title/{show_ids['imdb']}"
+                if show_ids.get("tvdb"):
+                    standard_tags["TVDB"] = f"https://thetvdb.com/dereferrer/series/{show_ids['tvdb']}"
+                if show_ids.get("tmdbtv"):
+                    standard_tags["TMDB"] = f"https://www.themoviedb.org/tv/{show_ids['tmdbtv']}"
+
+        # Use TMDB API for additional metadata (either from provided ID or Simkl lookup)
+        api_key = _api_key()
+        if not api_key:
+            log.debug("No TMDB API key set; applying basic tags only")
             _apply_tags(path, custom_tags)
             return
 
-    tmdb_url = f"https://www.themoviedb.org/{'movie' if kind == 'movie' else 'tv'}/{tmdb_id}"
-    standard_tags["TMDB"] = tmdb_url
-    try:
-        ids = external_ids(tmdb_id, kind)
-    except requests.RequestException as exc:
-        log.debug("Failed to fetch external IDs: %s", exc)
-        ids = {}
-    else:
-        log.debug("External IDs found: %s", ids)
+        tmdb_title: Optional[str] = None
+        if tmdb_id is None:
+            tmdb_id, tmdb_title = search_tmdb(name, year, kind)
+            log.debug("TMDB search result: %r (ID %s)", tmdb_title, tmdb_id)
+            if not tmdb_id or not tmdb_title or not fuzzy_match(tmdb_title, name):
+                log.debug("TMDB search did not match; skipping external ID lookup")
+                _apply_tags(path, custom_tags)
+                return
 
-    imdb_id = ids.get("imdb_id")
-    if imdb_id:
-        standard_tags["IMDB"] = f"https://www.imdb.com/title/{imdb_id}"
-    tvdb_id = ids.get("tvdb_id")
-    if tvdb_id:
-        tvdb_prefix = "movies" if kind == "movie" else "series"
-        standard_tags["TVDB"] = f"https://thetvdb.com/dereferrer/{tvdb_prefix}/{tvdb_id}"
+        tmdb_url = f"https://www.themoviedb.org/{'movie' if kind == 'movie' else 'tv'}/{tmdb_id}"
+        standard_tags["TMDB"] = tmdb_url
+        try:
+            ids = external_ids(tmdb_id, kind)
+        except requests.RequestException as exc:
+            log.debug("Failed to fetch external IDs: %s", exc)
+            ids = {}
+        else:
+            log.debug("External IDs found: %s", ids)
+
+        imdb_id = ids.get("imdb_id")
+        if imdb_id:
+            standard_tags["IMDB"] = f"https://www.imdb.com/title/{imdb_id}"
+        tvdb_id = ids.get("tvdb_id")
+        if tvdb_id:
+            tvdb_prefix = "movies" if kind == "movie" else "series"
+            standard_tags["TVDB"] = f"https://thetvdb.com/dereferrer/{tvdb_prefix}/{tvdb_id}"
 
     merged_tags = {
         **custom_tags,
@@ -269,6 +372,8 @@ def tag_file(path: Path, title: Title, tmdb_id: Optional[int] | None = None) ->
 
 
 __all__ = [
+    "search_simkl",
+    "search_show_info",
     "search_tmdb",
     "get_title",
     "get_year",

unshackle/unshackle-example.yaml

@@ -1,6 +1,12 @@
 # Group or Username to postfix to the end of all download filenames following a dash
 tag: user_tag
 
+# Enable/disable tagging with group name (default: true)
+tag_group_name: true
+
+# Enable/disable tagging with IMDB/TMDB/TVDB details (default: true)
+tag_imdb_tmdb: true
+
 # Set terminal background color (custom option not in CONFIG.md)
 set_terminal_bg: false