refactor: split up from mono app to more modular design

This commit is contained in:
2025-09-27 12:44:29 -04:00
parent 8da7853cca
commit d14e2ef3cc
12 changed files with 2373 additions and 0 deletions
+365
View File
@@ -0,0 +1,365 @@
"""
TV Series Processor for NFOGuard
Handles TV series processing and episode management
"""
import os
import glob
import re
from pathlib import Path
from typing import Optional, Dict, List, Set, Tuple, Any
from datetime import datetime
from core.database import NFOGuardDatabase
from core.nfo_manager import NFOManager
from core.path_mapper import PathMapper
from clients.sonarr_client import SonarrClient
from clients.external_clients import ExternalClientManager
from config.settings import config
from utils.logging import _log
class TVProcessor:
"""Handles TV series processing"""
def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, path_mapper: PathMapper):
self.db = db
self.nfo_manager = nfo_manager
self.path_mapper = path_mapper
self.sonarr = SonarrClient(
os.environ.get("SONARR_URL", ""),
os.environ.get("SONARR_API_KEY", "")
)
self.external_clients = ExternalClientManager()
def find_series_path(self, series_title: str, imdb_id: str, sonarr_path: str = None) -> Optional[Path]:
"""Find series directory path"""
# Try webhook path first
if sonarr_path:
container_path = self.path_mapper.sonarr_path_to_container_path(sonarr_path)
path_obj = Path(container_path)
if path_obj.exists():
return path_obj
# Search by IMDb ID or title
for media_path in config.tv_paths:
if not media_path.exists():
continue
# Search by IMDb ID
if imdb_id:
pattern = str(media_path / f"*[imdb-{imdb_id}]*")
matches = glob.glob(pattern)
if matches:
return Path(matches[0])
# Search by title
if series_title:
title_clean = series_title.lower().replace(" ", "").replace("-", "")
for item in media_path.iterdir():
if item.is_dir() and "[imdb-" in item.name.lower():
item_clean = item.name.lower().replace(" ", "").replace("-", "")
if title_clean in item_clean:
return item
return None
def process_series(self, series_path: Path) -> None:
"""Process a TV series directory"""
imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
if not imdb_id:
_log("ERROR", f"No IMDb ID found in series path: {series_path}")
return
_log("INFO", f"Processing TV series: {series_path.name}")
# Update database
self.db.upsert_series(imdb_id, str(series_path))
# Find video files
disk_episodes = self._find_disk_episodes(series_path)
_log("INFO", f"Found {len(disk_episodes)} episodes on disk")
# Get episode dates
episode_dates = self._gather_episode_dates(series_path, imdb_id, disk_episodes)
# Process episodes
for (season, episode), (aired, dateadded, source) in episode_dates.items():
if (season, episode) in disk_episodes:
# Create NFO
if config.manage_nfo:
season_dir = series_path / config.tv_season_dir_format.format(season=season)
self.nfo_manager.create_episode_nfo(
season_dir,
season, episode, aired, dateadded, source, config.lock_metadata
)
# Update file mtimes
if config.fix_dir_mtimes and dateadded:
video_files = disk_episodes[(season, episode)]
for video_file in video_files:
self.nfo_manager.set_file_mtime(video_file, dateadded)
# Save to database
self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, source, True)
# Skip season.nfo and tvshow.nfo creation - focus only on episode NFOs
pass
_log("INFO", f"Completed processing TV series: {series_path.name}")
def _extract_series_title_from_path(self, series_path: Path) -> Optional[str]:
"""Extract series title from directory path, removing year and IMDb ID"""
name = series_path.name
# Remove IMDb ID part: [imdb-ttXXXXXX] or [ttXXXXXX]
name = re.sub(r'\s*\[imdb-?tt\d+\]', '', name, flags=re.IGNORECASE)
name = re.sub(r'\s*\[tt\d+\]', '', name, flags=re.IGNORECASE)
# Remove year in parentheses: (YYYY)
name = re.sub(r'\s*\(\d{4}\)', '', name)
# Clean up extra spaces
name = ' '.join(name.split())
return name.strip() if name.strip() else None
def _find_disk_episodes(self, series_path: Path) -> Dict[Tuple[int, int], List[Path]]:
"""Find all episodes on disk and return mapping of (season, episode) -> [video_files]"""
episodes = {}
if not series_path.exists():
return episodes
video_extensions = {'.mkv', '.mp4', '.avi', '.m4v', '.mov', '.ts'}
# Define regex pattern for episode files
episode_pattern = re.compile(
r'.*[sS](\d{1,2})[eE](\d{1,3}).*|.*(\d{1,2})x(\d{1,3}).*'
)
for item in series_path.rglob('*'):
if item.is_file() and item.suffix.lower() in video_extensions:
# Try to extract season/episode from filename
match = episode_pattern.match(item.name)
if match:
if match.group(1) and match.group(2): # SxxExx format
season = int(match.group(1))
episode = int(match.group(2))
elif match.group(3) and match.group(4): # NxNN format
season = int(match.group(3))
episode = int(match.group(4))
else:
continue
key = (season, episode)
if key not in episodes:
episodes[key] = []
episodes[key].append(item)
return episodes
def _gather_episode_dates(self, series_path: Path, imdb_id: str, disk_episodes: Dict[Tuple[int, int], List[Path]]) -> Dict[Tuple[int, int], Tuple[Optional[str], Optional[str], str]]:
"""Gather episode air dates and date added information"""
episode_dates = {}
# Get data from Sonarr first if available
sonarr_episodes = self._get_sonarr_episodes(imdb_id)
# Get data from external sources for missing information
for (season, episode) in disk_episodes:
aired = None
dateadded = None
source = "unknown"
# Try Sonarr first
if (season, episode) in sonarr_episodes:
sonarr_data = sonarr_episodes[(season, episode)]
aired = sonarr_data.get('airDate')
dateadded = sonarr_data.get('dateAdded')
if dateadded:
source = "sonarr"
# Fallback to external sources if needed
if not aired:
external_aired = self.external_clients.get_episode_air_date(imdb_id, season, episode)
if external_aired:
aired = external_aired
if not dateadded:
source = "external"
# Use air date as fallback for dateadded if available
if not dateadded and aired:
dateadded = aired
source = f"{source}_fallback" if source != "unknown" else "aired_fallback"
episode_dates[(season, episode)] = (aired, dateadded, source)
return episode_dates
def _get_sonarr_episodes(self, imdb_id: str) -> Dict[Tuple[int, int], Dict[str, Any]]:
"""Get episode information from Sonarr"""
try:
series_data = self.sonarr.get_series_by_imdb(imdb_id)
if not series_data:
return {}
series_id = series_data.get('id')
if not series_id:
return {}
episodes = self.sonarr.get_episodes(series_id)
episode_map = {}
for episode in episodes:
season = episode.get('seasonNumber', 0)
episode_num = episode.get('episodeNumber', 0)
if season > 0 and episode_num > 0:
episode_map[(season, episode_num)] = {
'airDate': episode.get('airDate'),
'dateAdded': episode.get('episodeFile', {}).get('dateAdded') if episode.get('hasFile') else None
}
return episode_map
except Exception as e:
_log("ERROR", f"Failed to get Sonarr episodes for {imdb_id}: {e}")
return {}
def process_season(self, series_path: str, season_name: str) -> Dict[str, Any]:
"""Process a specific season"""
series_path_obj = Path(series_path)
if not series_path_obj.exists():
raise FileNotFoundError(f"Series path not found: {series_path}")
season_path = series_path_obj / season_name
if not season_path.exists():
raise FileNotFoundError(f"Season directory not found: {season_path}")
# Extract season number from directory name
season_match = re.search(r'(\d+)', season_name)
if not season_match:
raise ValueError(f"Could not extract season number from: {season_name}")
season_num = int(season_match.group(1))
# Get series IMDb ID
imdb_id = self.nfo_manager.parse_imdb_from_path(series_path_obj)
if not imdb_id:
raise ValueError(f"No IMDb ID found in series path: {series_path}")
_log("INFO", f"Processing season {season_num} of series: {series_path_obj.name}")
# Find episodes in this season
disk_episodes = self._find_disk_episodes(series_path_obj)
season_episodes = {k: v for k, v in disk_episodes.items() if k[0] == season_num}
if not season_episodes:
return {"status": "no_episodes", "season": season_num, "episodes_found": 0}
# Get episode dates
episode_dates = self._gather_episode_dates(series_path_obj, imdb_id, season_episodes)
# Process episodes
processed_count = 0
for (season, episode), (aired, dateadded, source) in episode_dates.items():
if (season, episode) in season_episodes:
# Create NFO
if config.manage_nfo:
self.nfo_manager.create_episode_nfo(
season_path,
season, episode, aired, dateadded, source, config.lock_metadata
)
# Update file mtimes
if config.fix_dir_mtimes and dateadded:
video_files = season_episodes[(season, episode)]
for video_file in video_files:
self.nfo_manager.set_file_mtime(video_file, dateadded)
# Save to database
self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, source, True)
processed_count += 1
_log("INFO", f"Processed {processed_count} episodes in season {season_num}")
return {
"status": "success",
"season": season_num,
"episodes_found": len(season_episodes),
"episodes_processed": processed_count
}
def process_episode(self, series_path: str, season_name: str, episode_name: str) -> Dict[str, Any]:
"""Process a specific episode"""
series_path_obj = Path(series_path)
if not series_path_obj.exists():
raise FileNotFoundError(f"Series path not found: {series_path}")
season_path = series_path_obj / season_name
if not season_path.exists():
raise FileNotFoundError(f"Season directory not found: {season_path}")
episode_path = season_path / episode_name
if not episode_path.exists():
raise FileNotFoundError(f"Episode file not found: {episode_path}")
# Extract season and episode numbers
season_match = re.search(r'(\d+)', season_name)
episode_match = re.search(r'[sS](\d+)[eE](\d+)|(\d+)x(\d+)', episode_name)
if not season_match:
raise ValueError(f"Could not extract season number from: {season_name}")
if not episode_match:
raise ValueError(f"Could not extract episode number from: {episode_name}")
season_num = int(season_match.group(1))
if episode_match.group(1) and episode_match.group(2): # SxxExx format
episode_num = int(episode_match.group(2))
elif episode_match.group(3) and episode_match.group(4): # NxNN format
episode_num = int(episode_match.group(4))
else:
raise ValueError(f"Could not parse episode number from: {episode_name}")
# Get series IMDb ID
imdb_id = self.nfo_manager.parse_imdb_from_path(series_path_obj)
if not imdb_id:
raise ValueError(f"No IMDb ID found in series path: {series_path}")
_log("INFO", f"Processing episode S{season_num:02d}E{episode_num:02d} of series: {series_path_obj.name}")
# Get episode data
disk_episodes = {(season_num, episode_num): [episode_path]}
episode_dates = self._gather_episode_dates(series_path_obj, imdb_id, disk_episodes)
if (season_num, episode_num) not in episode_dates:
return {"status": "no_data", "season": season_num, "episode": episode_num}
aired, dateadded, source = episode_dates[(season_num, episode_num)]
# Create NFO
if config.manage_nfo:
self.nfo_manager.create_episode_nfo(
season_path,
season_num, episode_num, aired, dateadded, source, config.lock_metadata
)
# Update file mtime
if config.fix_dir_mtimes and dateadded:
self.nfo_manager.set_file_mtime(episode_path, dateadded)
# Save to database
self.db.upsert_episode_date(imdb_id, season_num, episode_num, aired, dateadded, source, True)
_log("INFO", f"Processed episode S{season_num:02d}E{episode_num:02d}")
return {
"status": "success",
"season": season_num,
"episode": episode_num,
"aired": aired,
"dateadded": dateadded,
"source": source
}