mkv-episode-matcher 0.3.3__py3-none-any.whl → 0.3.4__py3-none-any.whl

mkv_episode_matcher/subtitle_utils.py

@@ -0,0 +1,82 @@
+from typing import List, Optional, Union
+import os
+import re
+
+def generate_subtitle_patterns(series_name: str, season: int, episode: int) -> List[str]:
+    """
+    Generate various common subtitle filename patterns.
+    
+    Args:
+        series_name (str): Name of the series
+        season (int): Season number
+        episode (int): Episode number
+        
+    Returns:
+        List[str]: List of possible subtitle filenames
+    """
+    patterns = [
+        # Standard format: "Show Name - S01E02.srt"
+        f"{series_name} - S{season:02d}E{episode:02d}.srt",
+        
+        # Season x Episode format: "Show Name - 1x02.srt"
+        f"{series_name} - {season}x{episode:02d}.srt",
+        
+        # Separate season/episode: "Show Name - Season 1 Episode 02.srt"
+        f"{series_name} - Season {season} Episode {episode:02d}.srt",
+        
+        # Compact format: "ShowName.S01E02.srt"
+        f"{series_name.replace(' ', '')}.S{season:02d}E{episode:02d}.srt",
+        
+        # Numbered format: "Show Name 102.srt"
+        f"{series_name} {season:01d}{episode:02d}.srt",
+        
+        # Dot format: "Show.Name.1x02.srt"
+        f"{series_name.replace(' ', '.')}.{season}x{episode:02d}.srt",
+        
+        # Underscore format: "Show_Name_S01E02.srt"
+        f"{series_name.replace(' ', '_')}_S{season:02d}E{episode:02d}.srt",
+    ]
+    
+    return patterns
+
+def find_existing_subtitle(series_cache_dir: str, series_name: str, season: int, episode: int) -> Optional[str]:
+    """
+    Check for existing subtitle files in various naming formats.
+    
+    Args:
+        series_cache_dir (str): Directory containing subtitle files
+        series_name (str): Name of the series
+        season (int): Season number
+        episode (int): Episode number
+        
+    Returns:
+        Optional[str]: Path to existing subtitle file if found, None otherwise
+    """
+    patterns = generate_subtitle_patterns(series_name, season, episode)
+    
+    for pattern in patterns:
+        filepath = os.path.join(series_cache_dir, pattern)
+        if os.path.exists(filepath):
+            return filepath
+            
+    return None
+
+def sanitize_filename(filename: str) -> str:
+    """
+    Sanitize filename by removing/replacing invalid characters.
+    
+    Args:
+        filename (str): Original filename
+        
+    Returns:
+        str: Sanitized filename
+    """
+    # Replace problematic characters
+    filename = filename.replace(':', ' -')
+    filename = filename.replace('/', '-')
+    filename = filename.replace('\\', '-')
+    
+    # Remove any other invalid characters
+    filename = re.sub(r'[<>:"/\\|?*]', '', filename)
+    
+    return filename.strip()

mkv_episode_matcher/utils.py

@@ -10,7 +10,7 @@ from opensubtitlescom import OpenSubtitles
 from mkv_episode_matcher.__main__ import CACHE_DIR, CONFIG_FILE
 from mkv_episode_matcher.config import get_config
 from mkv_episode_matcher.tmdb_client import fetch_season_details
-
+from mkv_episode_matcher.subtitle_utils import find_existing_subtitle,sanitize_filename
 def get_valid_seasons(show_dir):
     """
     Get all season directories that contain MKV files.
@@ -128,20 +128,17 @@ def get_subtitles(show_id, seasons: set[int]):
     Args:
         show_id (int): The ID of the TV show.
         seasons (Set[int]): A set of season numbers for which subtitles should be retrieved.
-
-    Returns:
-        None
     """
-
     logger.info(f"Getting subtitles for show ID {show_id}")
     config = get_config(CONFIG_FILE)
     show_dir = config.get("show_dir")
-    series_name = os.path.basename(show_dir)
+    series_name = sanitize_filename(os.path.basename(show_dir))
     tmdb_api_key = config.get("tmdb_api_key")
     open_subtitles_api_key = config.get("open_subtitles_api_key")
     open_subtitles_user_agent = config.get("open_subtitles_user_agent")
     open_subtitles_username = config.get("open_subtitles_username")
     open_subtitles_password = config.get("open_subtitles_password")
+
     if not all([
         show_dir,
         tmdb_api_key,
@@ -151,63 +148,66 @@ def get_subtitles(show_id, seasons: set[int]):
         open_subtitles_password,
     ]):
         logger.error("Missing configuration settings. Please run the setup script.")
+        return
+
     try:
-        # Initialize the OpenSubtitles client
         subtitles = OpenSubtitles(open_subtitles_user_agent, open_subtitles_api_key)
-
-        # Log in (retrieve auth token)
         subtitles.login(open_subtitles_username, open_subtitles_password)
     except Exception as e:
         logger.error(f"Failed to log in to OpenSubtitles: {e}")
         return
+
     for season in seasons:
         episodes = fetch_season_details(show_id, season)
         logger.info(f"Found {episodes} episodes in Season {season}")
 
         for episode in range(1, episodes + 1):
             logger.info(f"Processing Season {season}, Episode {episode}...")
+            
             series_cache_dir = os.path.join(CACHE_DIR, "data", series_name)
             os.makedirs(series_cache_dir, exist_ok=True)
+            
+            # Check for existing subtitle in any supported format
+            existing_subtitle = find_existing_subtitle(
+                series_cache_dir, series_name, season, episode
+            )
+            
+            if existing_subtitle:
+                logger.info(f"Subtitle already exists: {os.path.basename(existing_subtitle)}")
+                continue
+                
+            # Default to standard format for new downloads
             srt_filepath = os.path.join(
                 series_cache_dir,
                 f"{series_name} - S{season:02d}E{episode:02d}.srt",
             )
-            if not os.path.exists(srt_filepath):
-                # get the episode info from TMDB
-                url = f"https://api.themoviedb.org/3/tv/{show_id}/season/{season}/episode/{episode}?api_key={tmdb_api_key}"
-                response = requests.get(url)
-                response.raise_for_status()
-                episode_data = response.json()
-                episode_data["name"]
-                episode_id = episode_data["id"]
-                # search for the subtitle
-                response = subtitles.search(tmdb_id=episode_id, languages="en")
-                if len(response.data) == 0:
-                    logger.warning(
-                        f"No subtitles found for {series_name} - S{season:02d}E{episode:02d}"
-                    )
-
-                for subtitle in response.data:
-                    subtitle_dict = subtitle.to_dict()
-                    # Remove special characters and convert to uppercase
-                    filename_clean = re.sub(
-                        r"\W+", " ", subtitle_dict["file_name"]
-                    ).upper()
-                    if f"E{episode:02d}" in filename_clean:
-                        logger.info(f"Original filename: {subtitle_dict['file_name']}")
-                        srt_file = subtitles.download_and_save(subtitle)
-                        series_name = series_name.replace(":", " -")
-                        shutil.move(srt_file, srt_filepath)
-                        logger.info(f"Subtitle saved to {srt_filepath}")
-                        break
-                    else:
-                        continue
-            else:
-                logger.info(
-                    f"Subtitle already exists for {series_name} - S{season:02d}E{episode:02d}"
+
+            # get the episode info from TMDB
+            url = f"https://api.themoviedb.org/3/tv/{show_id}/season/{season}/episode/{episode}?api_key={tmdb_api_key}"
+            response = requests.get(url)
+            response.raise_for_status()
+            episode_data = response.json()
+            episode_id = episode_data["id"]
+            
+            # search for the subtitle
+            response = subtitles.search(tmdb_id=episode_id, languages="en")
+            if len(response.data) == 0:
+                logger.warning(
+                    f"No subtitles found for {series_name} - S{season:02d}E{episode:02d}"
                 )
                 continue
 
+            for subtitle in response.data:
+                subtitle_dict = subtitle.to_dict()
+                # Remove special characters and convert to uppercase
+                filename_clean = re.sub(r"\W+", " ", subtitle_dict["file_name"]).upper()
+                if f"E{episode:02d}" in filename_clean:
+                    logger.info(f"Original filename: {subtitle_dict['file_name']}")
+                    srt_file = subtitles.download_and_save(subtitle)
+                    shutil.move(srt_file, srt_filepath)
+                    logger.info(f"Subtitle saved to {srt_filepath}")
+                    break
+
 
 def cleanup_ocr_files(show_dir):
     """
@@ -236,7 +236,7 @@ def clean_text(text):
     # Strip leading/trailing whitespace
     return cleaned_text.strip()
 
-
+@logger.catch
 def process_reference_srt_files(series_name):
     """
     Process reference SRT files for a given series.

{mkv_episode_matcher-0.3.3.dist-info → mkv_episode_matcher-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mkv-episode-matcher
-Version: 0.3.3
+Version: 0.3.4
 Summary: The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
 Home-page: https://github.com/Jsakkos/mkv-episode-matcher
 Author: Jonathan Sakkos

{mkv_episode_matcher-0.3.3.dist-info → mkv_episode_matcher-0.3.4.dist-info}/RECORD

@@ -6,8 +6,9 @@ mkv_episode_matcher/episode_identification.py,sha256=NopEkcBFFUjjrAujogeVcdISv8U
 mkv_episode_matcher/episode_matcher.py,sha256=BJ76DPxsmZs-KfHZZ_0WvKSBZWXsUEO6lW34YdYEaxM,3979
 mkv_episode_matcher/mkv_to_srt.py,sha256=4yxBHRVhgVby0UtQ2aTXGuoQpid8pkgjMIaHU6GCdzc,10857
 mkv_episode_matcher/speech_to_text.py,sha256=-bnGvmtPCKyHFPEaXwIcEYTf_P13rNpAJA-2UFeRFrs,2806
+mkv_episode_matcher/subtitle_utils.py,sha256=rYSbd393pKYQW0w4sXgals02WFGqMYYYkQHDbEkWF8c,2666
 mkv_episode_matcher/tmdb_client.py,sha256=LbMCgjmp7sCbrQo_CDlpcnryKPz5S7inE24YY9Pyjk4,4172
-mkv_episode_matcher/utils.py,sha256=YthQByumTL5eGdFTJMoI8csAe4Vc-sPo8XqOKzbj4g4,13975
+mkv_episode_matcher/utils.py,sha256=Txnn24ou7Pg3iMq9WrT3nwBRlRP8JEuZQ2ZYW7uesp4,13972
 mkv_episode_matcher/libraries/pgs2srt/.gitignore,sha256=mt3uxWYZaFurMw_yGE258gWhtGKPVR7e3Ll4ALJpyj4,23
 mkv_episode_matcher/libraries/pgs2srt/README.md,sha256=olb25G17tj0kxPgp_LcH5I2QWXjgP1m8JFyjYRGz4UU,1374
 mkv_episode_matcher/libraries/pgs2srt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -18,8 +19,8 @@ mkv_episode_matcher/libraries/pgs2srt/requirements.txt,sha256=sg87dqWw_qpbwciw-M
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/SubZero.py,sha256=geT1LXdVd8yED9zoJ9K1XfP2JzGcM7u1SslHYrJI09o,10061
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/post_processing.py,sha256=GKtVy_Lxv-z27mkRG8pJF2znKWXwZTot7jL6kN-zIxM,10503
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/dictionaries/data.py,sha256=AlJHUYXl85J95OzGRik-AHVfzDd7Q8BJCvD4Nr8kRIk,938598
-mkv_episode_matcher-0.3.3.dist-info/METADATA,sha256=bAgcQzwsAaYHZ9YgKdTtSB1KtKjc0Y4Ylx_mQyll-I4,4640
-mkv_episode_matcher-0.3.3.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-mkv_episode_matcher-0.3.3.dist-info/entry_points.txt,sha256=IglJ43SuCZq2eQ3shMFILCkmQASJHnDCI3ogohW2Hn4,64
-mkv_episode_matcher-0.3.3.dist-info/top_level.txt,sha256=XRLbd93HUaedeWLtkyTvQjFcE5QcBRYa3V-CfHrq-OI,20
-mkv_episode_matcher-0.3.3.dist-info/RECORD,,
+mkv_episode_matcher-0.3.4.dist-info/METADATA,sha256=QPa0StsF0ADrzxSEswvQ4tTbBkztRjR82hNFsXnJwCc,4640
+mkv_episode_matcher-0.3.4.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+mkv_episode_matcher-0.3.4.dist-info/entry_points.txt,sha256=IglJ43SuCZq2eQ3shMFILCkmQASJHnDCI3ogohW2Hn4,64
+mkv_episode_matcher-0.3.4.dist-info/top_level.txt,sha256=XRLbd93HUaedeWLtkyTvQjFcE5QcBRYa3V-CfHrq-OI,20
+mkv_episode_matcher-0.3.4.dist-info/RECORD,,