mkv-episode-matcher 0.1.11__tar.gz → 0.1.13__tar.gz

mkv_episode_matcher-0.1.13/.python-version

@@ -0,0 +1 @@
+3.12

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mkv-episode-matcher
-Version: 0.1.11
+Version: 0.1.13
 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
@@ -11,22 +11,19 @@ Project-URL: Issues, https://github.com/Jsakkos/mkv-episode-matcher/issues
 Project-URL: Source, https://github.com/Jsakkos/mkv-episode-matcher
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.8
+Requires-Python: >=3.12
 Description-Content-Type: text/x-rst
-Requires-Dist: requests
-Requires-Dist: loguru
-Requires-Dist: pillow
-Requires-Dist: configparser
-Requires-Dist: tmdb_client
-Requires-Dist: pytesseract
-Requires-Dist: opensubtitlescom
+Requires-Dist: configparser>=7.1.0
+Requires-Dist: ffmpeg>=1.4
+Requires-Dist: loguru>=0.7.2
+Requires-Dist: numpy>=2.1.3
+Requires-Dist: opensubtitlescom>=0.1.5
+Requires-Dist: pytesseract>=0.3.13
+Requires-Dist: requests>=2.32.3
+Requires-Dist: tmdb-client>=0.0.1
 
 ===================
 MKV Episode Matcher

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/mkv_episode_matcher/episode_matcher.py

@@ -8,7 +8,7 @@ from mkv_episode_matcher.__main__ import CACHE_DIR, CONFIG_FILE
 from mkv_episode_matcher.config import get_config
 from mkv_episode_matcher.mkv_to_srt import convert_mkv_to_srt
 from mkv_episode_matcher.tmdb_client import fetch_show_id
-from mkv_episode_matcher.utils import check_filename, cleanup_ocr_files, get_subtitles
+from mkv_episode_matcher.utils import check_filename, cleanup_ocr_files, get_subtitles,clean_text
 
 
 # hash_data = {}
@@ -16,46 +16,70 @@ from mkv_episode_matcher.utils import check_filename, cleanup_ocr_files, get_sub
 def process_show(season=None, dry_run=False, get_subs=False):
     """
     Process the show by downloading episode images and finding matching episodes.
-
     Args:
         season (int, optional): The season number to process. If provided, only that season will be processed. Defaults to None.
-        force (bool, optional): Whether to force re-processing of episodes even if they already exist. Defaults to False.
         dry_run (bool, optional): Whether to perform a dry run without actually processing the episodes. Defaults to False.
-        threshold (float, optional): The threshold value for matching episodes. Defaults to None.
+        get_subs (bool, optional): Whether to download subtitles for the episodes. Defaults to False.
     """
     config = get_config(CONFIG_FILE)
     show_dir = config.get("show_dir")
-    show_name = os.path.basename(show_dir)
+    show_name = clean_text(os.path.basename(show_dir))
     logger.info(f"Processing show '{show_name}'...")
+    
     show_id = fetch_show_id(show_name)
-
     if show_id is None:
         logger.error(f"Could not find show '{os.path.basename(show_dir)}' on TMDb.")
         return
+
+    # Get all season directories
     season_paths = [
         os.path.join(show_dir, d)
         for d in os.listdir(show_dir)
         if os.path.isdir(os.path.join(show_dir, d))
     ]
+
+    # Filter seasons to only include those with .mkv files
+    valid_season_paths = []
+    for season_path in season_paths:
+        mkv_files = [
+            f for f in os.listdir(season_path)
+            if f.endswith(".mkv")
+        ]
+        if mkv_files:
+            valid_season_paths.append(season_path)
+
+    if not valid_season_paths:
+        logger.warning(f"No seasons with .mkv files found in show '{show_name}'")
+        return
+
     logger.info(
-        f"Found {len(season_paths)} seasons for show '{os.path.basename(show_dir)}'"
+        f"Found {len(valid_season_paths)} seasons with .mkv files for show '{show_name}'"
     )
+
+    # Extract season numbers from valid paths
     seasons_to_process = [
-        int(os.path.basename(season_path).split()[-1]) for season_path in season_paths
+        int(os.path.basename(season_path).split()[-1]) 
+        for season_path in valid_season_paths
     ]
+
     if get_subs:
         get_subtitles(show_id, seasons=set(seasons_to_process))
+
     if season is not None:
+        # If specific season requested, check if it has .mkv files
+        season_path = os.path.join(show_dir, f"Season {season}")
+        if season_path not in valid_season_paths:
+            logger.warning(f"Season {season} has no .mkv files to process")
+            return
+        
         mkv_files = [
-            os.path.join(show_dir, season)
-            for f in os.listdir(show_dir)
+            os.path.join(season_path, f)
+            for f in os.listdir(season_path)
             if f.endswith(".mkv")
         ]
-
-        season_path = os.path.join(show_dir, f"Season {season}")
     else:
-        for season_path in os.listdir(show_dir):
-            season_path = os.path.join(show_dir, season_path)
+        # Process all valid seasons
+        for season_path in valid_season_paths:
             mkv_files = [
                 os.path.join(season_path, f)
                 for f in os.listdir(season_path)

mkv_episode_matcher-0.1.13/mkv_episode_matcher/notebooks/whisper.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "OSError",
+     "evalue": "[WinError 126] The specified module could not be found. Error loading \"c:\\Users\\Jonathan\\anaconda3\\envs\\whisper\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[1], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mwhisper\u001b[39;00m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mos\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\Jonathan\\anaconda3\\envs\\whisper\\Lib\\site-packages\\whisper\\__init__.py:8\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mwarnings\u001b[39;00m\n\u001b[0;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtyping\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m List, Optional, Union\n\u001b[1;32m----> 8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[0;32m      9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtqdm\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tqdm\n\u001b[0;32m     11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01maudio\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_audio, log_mel_spectrogram, pad_or_trim\n",
+      "File \u001b[1;32mc:\\Users\\Jonathan\\anaconda3\\envs\\whisper\\Lib\\site-packages\\torch\\__init__.py:148\u001b[0m\n\u001b[0;32m    146\u001b[0m                 err \u001b[38;5;241m=\u001b[39m ctypes\u001b[38;5;241m.\u001b[39mWinError(ctypes\u001b[38;5;241m.\u001b[39mget_last_error())\n\u001b[0;32m    147\u001b[0m                 err\u001b[38;5;241m.\u001b[39mstrerror \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m Error loading \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdll\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m or one of its dependencies.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m--> 148\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m err\n\u001b[0;32m    150\u001b[0m     kernel32\u001b[38;5;241m.\u001b[39mSetErrorMode(prev_error_mode)\n\u001b[0;32m    153\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_preload_cuda_deps\u001b[39m(lib_folder, lib_name):\n",
+      "\u001b[1;31mOSError\u001b[0m: [WinError 126] The specified module could not be found. Error loading \"c:\\Users\\Jonathan\\anaconda3\\envs\\whisper\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies."
+     ]
+    }
+   ],
+   "source": [
+    "import whisper\n",
+    "import os\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with 'MKV-GPU (Python 3.8.10)' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: 'conda install -n MKV-GPU ipykernel --update-deps --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "\n",
+    "if torch.cuda.is_available():\n",
+    "    print(f\"CUDA is available. Using GPU: {torch.cuda.get_device_name(0)}\")\n",
+    "else:\n",
+    "    print(\"CUDA is not available. Using CPU.\")\n",
+    "\n",
+    "# It will print out the GPU that you are using."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with 'MKV-GPU (Python 3.8.10)' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: 'conda install -n MKV-GPU ipykernel --update-deps --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "model = whisper.load_model(\"base\")  # Replace \"base\" with the desired model size\n",
+    "result = model.transcribe(r\"C:\\Users\\Jonathan\\output_audio.wav\")\n",
+    "\n",
+    "# Print or save the transcription\n",
+    "print(result[\"text\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with 'MKV-GPU (Python 3.8.10)' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: 'conda install -n MKV-GPU ipykernel --update-deps --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "# ffmpeg -i \"E:\\Video\\Seinfeld\\Season 5\\Seinfeld - Season 5 (Disc 1)-A1_t02.mkv\" -t 300 -map 0:a:0 -acodec pcm_s16le -ac 1 output_audio.wav\n",
+    "# works for make a .wav file of the first 5 mins"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "mkv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/mkv_episode_matcher/utils.py

@@ -229,3 +229,8 @@ def cleanup_ocr_files(show_dir):
         if os.path.exists(ocr_dir_path):
             logger.info(f"Cleaning up OCR files in {ocr_dir_path}")
             shutil.rmtree(ocr_dir_path)
+def clean_text(text):
+    # Remove brackets, parentheses, and their content
+    cleaned_text = re.sub(r'\[.*?\]|\(.*?\)|\{.*?\}', '', text)
+    # Strip leading/trailing whitespace
+    return cleaned_text.strip()

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/mkv_episode_matcher.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mkv-episode-matcher
-Version: 0.1.11
+Version: 0.1.13
 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
@@ -11,22 +11,19 @@ Project-URL: Issues, https://github.com/Jsakkos/mkv-episode-matcher/issues
 Project-URL: Source, https://github.com/Jsakkos/mkv-episode-matcher
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.8
+Requires-Python: >=3.12
 Description-Content-Type: text/x-rst
-Requires-Dist: requests
-Requires-Dist: loguru
-Requires-Dist: pillow
-Requires-Dist: configparser
-Requires-Dist: tmdb_client
-Requires-Dist: pytesseract
-Requires-Dist: opensubtitlescom
+Requires-Dist: configparser>=7.1.0
+Requires-Dist: ffmpeg>=1.4
+Requires-Dist: loguru>=0.7.2
+Requires-Dist: numpy>=2.1.3
+Requires-Dist: opensubtitlescom>=0.1.5
+Requires-Dist: pytesseract>=0.3.13
+Requires-Dist: requests>=2.32.3
+Requires-Dist: tmdb-client>=0.0.1
 
 ===================
 MKV Episode Matcher

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/mkv_episode_matcher.egg-info/SOURCES.txt

@@ -1,11 +1,13 @@
 .gitattributes
 .gitignore
 .gitmodules
+.python-version
 .readthedocs.yml
 README.rst
 pyproject.toml
 setup.cfg
 setup.py
+uv.lock
 .github/funding.yml
 .github/workflows/python-publish.yml
 .vscode/settings.json
@@ -105,7 +107,6 @@ mkv_episode_matcher/__main__.py
 mkv_episode_matcher/config.py
 mkv_episode_matcher/episode_matcher.py
 mkv_episode_matcher/mkv_to_srt.py
-mkv_episode_matcher/requirements.txt
 mkv_episode_matcher/tmdb_client.py
 mkv_episode_matcher/utils.py
 mkv_episode_matcher.egg-info/PKG-INFO
@@ -125,4 +126,5 @@ mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/SubZero.py
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/post_processing.py
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/dictionaries/data.py
 mkv_episode_matcher/notebooks/get_subtitles_test.ipynb
+mkv_episode_matcher/notebooks/whisper.ipynb
 tests/__init__.py

mkv_episode_matcher-0.1.13/mkv_episode_matcher.egg-info/requires.txt

@@ -0,0 +1,8 @@
+configparser>=7.1.0
+ffmpeg>=1.4
+loguru>=0.7.2
+numpy>=2.1.3
+opensubtitlescom>=0.1.5
+pytesseract>=0.3.13
+requests>=2.32.3
+tmdb-client>=0.0.1

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/pyproject.toml

@@ -10,32 +10,27 @@ name = "mkv-episode-matcher"
 description = "The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly."
 dynamic = ["version"]
 readme = "README.rst"
-requires-python = ">=3.8"
-license = { text = "MIT" }
-keywords = []
 authors = [
   { name = "Jsakkos", email = "jonathansakkos@protonmail.com" },
 ]
+requires-python = ">=3.12"
+license = { text = "MIT" }
 classifiers = [
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
-  "Programming Language :: Python :: 3.10",
-  "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-
 dependencies = [
-  "requests",
-  "loguru",
-  "pillow",
-  "configparser",
-  "tmdb_client",
-  "pytesseract",
-  "opensubtitlescom",
+    "configparser>=7.1.0",
+    "ffmpeg>=1.4",
+    "loguru>=0.7.2",
+    "numpy>=2.1.3",
+    "opensubtitlescom>=0.1.5",
+    "pytesseract>=0.3.13",
+    "requests>=2.32.3",
+    "tmdb-client>=0.0.1",
 ]
 
 [project.urls]
@@ -69,7 +64,6 @@ omit = [
 ]
 
 [tool.coverage.paths]
-calcy = ["mkv-episode-matcher/mkv_episode_matcher", "*/mkv-episode-matcher/mkv_episode_matcher"]
 tests = ["tests", "*/mkv_episode_matcher/tests"]
 
 [tool.coverage.report]

{mkv_episode_matcher-0.1.11 → mkv_episode_matcher-0.1.13}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = mkv_episode_matcher
-version = 0.1.11
+version = 0.1.13
 author = Jonathan Sakkos
 author_email = jonathansakkos@protonmail.com
 description = The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.