sbcrumb/nfoguard
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

debug: Add comprehensive debugging for title extraction
Local Docker Build (Dev) / build-dev (pull_request) Successful in 19s
Details

Browse Source 
- Add detailed debug logging to _extract_title_from_filename() method
- Log file search, regex pattern matching, and title cleanup process
- Fix Tier 2 processing to call _get_episode_metadata() for title extraction
- Add debug logging to _get_episode_metadata() to trace execution flow
- Include both .mkv and .mp4 file checking with detailed logs

This should help identify why title extraction isn't working for
recreated NFO files and provide visibility into the extraction process.
This commit is contained in:
SBCrumb
2025-09-25 09:07:14 -04:00
parent 632ce32cd1
commit 5f3dd3ce20
1 changed files with 30 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nfoguard.py
+30 -8
View File
@@ -654,12 +654,14 @@ class TVProcessor:
source = existing_episode["source"]
aired = existing_episode.get("aired")
# Create NFO with existing data (no enhanced metadata needed)
# Create NFO with existing data, but try to add title from filename if missing
if config.manage_nfo and dateadded:
# Try to extract title from filename as fallback for Tier 2 processing
enhanced_metadata = self._get_episode_metadata(None, season_num, episode_num, season_path)
self.nfo_manager.create_episode_nfo(
season_path,
season_num, episode_num, aired, dateadded, source, config.lock_metadata,
None # No enhanced metadata for database-cached episodes
enhanced_metadata # Include filename-extracted title if available
)
# Update file mtime if enabled
@@ -777,10 +779,15 @@ class TVProcessor:
# If no title from Sonarr, try to extract from filename
if not metadata["title"] and season_dir:
_log("DEBUG", f"📁 No title from Sonarr for S{season_num:02d}E{episode_num:02d}, trying filename extraction")
filename_title = self._extract_title_from_filename(season_dir, season_num, episode_num)
if filename_title:
metadata["title"] = filename_title
_log("INFO", f"Using filename-extracted title for S{season_num:02d}E{episode_num:02d}: '{filename_title}'")
_log("INFO", f"✅ Using filename-extracted title for S{season_num:02d}E{episode_num:02d}: '{filename_title}'")
else:
_log("DEBUG", f"⚠️ No filename title extracted for S{season_num:02d}E{episode_num:02d}")
elif metadata["title"]:
_log("DEBUG", f"✅ Using Sonarr title for S{season_num:02d}E{episode_num:02d}: '{metadata['title']}'")
# Return metadata if we have at least some information
if any(metadata.values()):
@@ -794,36 +801,51 @@ class TVProcessor:
import re
# Look for video files matching this episode
season_pattern = f"S{season_num:02d}E{episode_num:02d}"
_log("DEBUG", f"🔍 Searching for title in files for {season_pattern} in directory: {season_dir}")
for video_file in season_dir.glob("*.mkv"):
filename = video_file.name
_log("DEBUG", f"🔍 Checking file: {filename}")
if season_pattern in filename:
_log("DEBUG", f"✅ Found matching file: {filename}")
# Pattern: SeriesName-S01E01-Episode Title[WEBDL-1080p][AAC2.0][h264].mkv
# Extract the part between season/episode and the first bracket
match = re.search(rf'{season_pattern}-(.*?)\[', filename)
pattern = rf'{season_pattern}-(.*?)\['
_log("DEBUG", f"🔍 Using regex pattern: {pattern}")
match = re.search(pattern, filename)
if match:
title = match.group(1).strip()
_log("DEBUG", f"🔍 Raw extracted title: '{title}'")
# Clean up common encoding artifacts and separators
title = title.replace('-', ' ').strip()
if title:
_log("DEBUG", f"Extracted title from filename: '{title}' for {season_pattern}")
_log("INFO", f"✅ Extracted title from filename: '{title}' for {season_pattern}")
return title
else:
_log("DEBUG", f"⚠️ Title was empty after cleanup")
else:
_log("DEBUG", f"⚠️ Regex pattern didn't match filename")
# Also check .mp4 files
for video_file in season_dir.glob("*.mp4"):
filename = video_file.name
_log("DEBUG", f"🔍 Checking .mp4 file: {filename}")
if season_pattern in filename:
match = re.search(rf'{season_pattern}-(.*?)\[', filename)
_log("DEBUG", f"✅ Found matching .mp4 file: {filename}")
pattern = rf'{season_pattern}-(.*?)\['
match = re.search(pattern, filename)
if match:
title = match.group(1).strip()
_log("DEBUG", f"🔍 Raw extracted title from .mp4: '{title}'")
title = title.replace('-', ' ').strip()
if title:
_log("DEBUG", f"Extracted title from filename: '{title}' for {season_pattern}")
_log("INFO", f"✅ Extracted title from .mp4 filename: '{title}' for {season_pattern}")
return title
except Exception as e:
_log("DEBUG", f"Error extracting title from filename for S{season_num:02d}E{episode_num:02d}: {e}")
_log("ERROR", f"Error extracting title from filename for S{season_num:02d}E{episode_num:02d}: {e}")
_log("DEBUG", f"⚠️ No title found in filenames for {season_pattern}")
return None
def _gather_season_episode_dates(self, series_path: Path, imdb_id: str, season_num: int, disk_episodes: Dict[Tuple[int, int], List[Path]], series_metadata: Optional[Dict[str, Any]] = None) -> Dict[Tuple[int, int], Tuple[Optional[str], Optional[str], str]]: