diff --git a/audiobook_metadata/metadata_audiobooks_library.py b/audiobook_metadata/metadata_audiobooks_library.py index 0154a15..23b53ea 100755 --- a/audiobook_metadata/metadata_audiobooks_library.py +++ b/audiobook_metadata/metadata_audiobooks_library.py @@ -17,7 +17,6 @@ from mutagen.easyid3 import EasyID3 from mutagen.id3 import ID3, ID3NoHeaderError - logging.setLoggerClass(CustomLogger) logger: CustomLogger = logging.getLogger(__name__) # type: ignore[assignment] @@ -30,22 +29,25 @@ metadata_fields = [ "grouping", "albumartist", "description", - "title" + "title", ] SEP = r"\s*[-_:,.]+\s*" series_patterns = [ - rf'^(\d+){SEP}(.+)$', - rf'^(.+?){SEP}(\d+)$', - rf'^(.+?){SEP}(?:Book|Band|Volume)\s+(\d+)(?:{SEP}(.+))$' + rf"^(\d+){SEP}(.+)$", + rf"^(.+?){SEP}(\d+)$", + rf"^(.+?){SEP}(?:Book|Band|Volume)\s+(\d+)(?:{SEP}(.+))$", ] + + def ffmpeg_escape(path: Path) -> str: return str(path.resolve()).replace("'", r"'\''") + def clean_genre(genre): if not genre: return "" genre_old = genre - #genre = genre.lower() + # genre = genre.lower() genre = re.sub(r"(?i)^audio\s*books?$", "", genre) genre = re.sub(r"(?i)^audiobooks?;?$", "", genre) genre = re.sub(r"(?i)\b(hörb(uch|ücher)|hoerb(uch|uecher))\b", "", genre) @@ -88,6 +90,7 @@ def clean_genre(genre): logger.debug(f"Update genre from {genre_old} to {genre}") return genre + def ffmetadata_escape(value: str) -> str: return ( value.replace("\\", "\\\\") @@ -97,6 +100,7 @@ def ffmetadata_escape(value: str) -> str: .replace("\n", "\\\n") ) + def get_chapters(media: Path) -> list[dict]: result = subprocess.run( [ @@ -116,6 +120,7 @@ def get_chapters(media: Path) -> list[dict]: data = json.loads(result.stdout) return data.get("chapters", []) + def get_metadata_all(file: Path) -> dict[str, str]: metadata = {} try: @@ -152,6 +157,8 @@ def get_metadata_fields(file: Path, fields) -> dict[str, str]: print(f"Error getting metadata for {file}: {error}") return metadata + + def get_duration_ms(media: Path) -> int: duration = subprocess.check_output( [ @@ -169,6 +176,7 @@ def get_duration_ms(media: Path) -> int: return int(float(duration) * 1000) + def write_metadata(file, fields, values, dry_run=False): logger.debug(f"Writing metadata for {file}") changes = { @@ -196,11 +204,12 @@ def write_metadata(file, fields, values, dry_run=False): except Exception as e: logger.exception(f"Error writing metadata for {file}: {e}") -def normalize_name(name: str,series: str) -> str: + +def normalize_name(name: str, series: str) -> str: # Remove anything in (), [], {} name_out = "" - #name = re.sub( + # name = re.sub( # rf"^(?:{re.escape(series)}){SEP}|{SEP}(?:{re.escape(series)})$", # "", name, flags=re.IGNORECASE, ).strip() name = re.sub(r"\s*[\(\[\{].*?[\)\]\}]\s*", " ", name).strip() @@ -217,44 +226,53 @@ def normalize_name(name: str,series: str) -> str: else: name_out = name - pattern = rf'^(.+?){SEP}(?:Book|Band|Volume)\s+(\d+){SEP}(.+)$' + pattern = rf"^(.+?){SEP}(?:Book|Band|Volume)\s+(\d+){SEP}(.+)$" match = re.match(pattern, name, re.IGNORECASE) if match: name_out1 = match.group(1).strip() name_out3 = match.group(3).strip() - if score_match_jaccard(words(name_out1), words(series)) > score_match_jaccard(words(name_out3), words(series)): + if score_match_jaccard(words(name_out1), words(series)) > score_match_jaccard( + words(name_out3), words(series) + ): return name_out3 else: return name_out1 return name_out + def cleanup(text: str) -> str: # Collapse repeated punctuation groups like ", ,", ". .", "! !", "? ?" while True: - new_text = re.sub(r'([.,!?;:-])(?:\s+\1)+', r'\1', text) + new_text = re.sub(r"([.,!?;:-])(?:\s+\1)+", r"\1", text) if new_text == text: break text = new_text # Optional: normalize multiple spaces - text = re.sub(r'\s{2,}', ' ', text) + text = re.sub(r"\s{2,}", " ", text) return text.strip() + def get_empty_keys(data: dict) -> str: empty_keys = [str(key) for key, value in data.items() if not value] return f"Empty: {', '.join(empty_keys)}" if empty_keys else "" + def get_codec_bitrate(file: Path) -> tuple[str, str]: info = json.loads( subprocess.check_output( [ "ffprobe", - "-v", "error", - "-select_streams", "a:0", - "-show_entries", "stream=codec_name,bit_rate", - "-of", "json", + "-v", + "error", + "-select_streams", + "a:0", + "-show_entries", + "stream=codec_name,bit_rate", + "-of", + "json", str(file), ], text=True, @@ -269,8 +287,8 @@ def get_codec_bitrate(file: Path) -> tuple[str, str]: class Audiobook: - def __init__(self, book_path: Path, library_root_path : Path) -> None: - self.title: str|list = "" + def __init__(self, book_path: Path, library_root_path: Path) -> None: + self.title: str | list = "" self.metadata_original = None self.series_num = None self.pdf_file = None @@ -285,7 +303,7 @@ class Audiobook: self.size = 0 self.firstFile = None self.changed = None - self. metadata = {} + self.metadata = {} self.artist = "" self.genre = "" self.composer = "" @@ -310,9 +328,10 @@ class Audiobook: self.pdf_file = pdfs[0] if len(pdfs) == 1 else None self.files_extra = [ - file - for file in self.bookPath.glob("*") if file.suffix.lower() not in AUDIO_SUFFIXES - ] + file + for file in self.bookPath.glob("*") + if file.suffix.lower() not in AUDIO_SUFFIXES + ] self.firstFile = self.get_first_file() self.size = sum( file.stat().st_size @@ -323,7 +342,9 @@ class Audiobook: self.singleFile = self.fileConunt == 1 # Metadata self.load_metadata() - logger.info(f"Found {self.bookPath.name}, {self.fileConunt} files, {get_empty_keys(self.metadata)}") + logger.info( + f"Found {self.bookPath.name}, {self.fileConunt} files, {get_empty_keys(self.metadata)}" + ) self.changed = False def __repr__(self): @@ -347,7 +368,7 @@ class Audiobook: self.comment = self.metadata["comment"] self.genre = self.metadata["genre"] if "#" in self.metadata["grouping"]: - self.series, self.series_num = self.metadata["grouping"].rsplit("#", 1) + self.series, self.series_num = self.metadata["grouping"].rsplit("#", 1) self.series = self.series.strip() self.series_and_num = self.metadata["grouping"] artist = self.metadata.get("artist", "").strip() @@ -428,9 +449,7 @@ class Audiobook: self.metadata = get_metadata_all(self.get_first_file()) self.metadata_original = self.metadata.copy() self.write_fields_from_metadata() - logger.trace( - f"Load metadata {self.metadata}" - ) + logger.trace(f"Load metadata {self.metadata}") def fix_artist_dir(self): rel_path = self.bookPath.relative_to(self.library_root_path).parts @@ -438,8 +457,8 @@ class Audiobook: logger.trace(f"No artist tag for {self.name}") return if len(rel_path) < 2: - desired_path,desired_name = self.generate_dir_from_metadata() - self.move(desired_path,desired_name) + desired_path, desired_name = self.generate_dir_from_metadata() + self.move(desired_path, desired_name) logger.debug(f"Artist not visible in folder structure: {rel_path}") def fix_artist_from_comment(self): @@ -479,14 +498,14 @@ class Audiobook: self.comment = (self.comment[: m.start()] + self.comment[m.end() :]).strip( " .,;\n" ) - self.comment = cleanup(self.comment) + self.comment = cleanup(self.comment) if not self.artist: self.artist = artist self.changed = True elif self.artist != artist: logger.warning( - f"{red_tag("Action Required")} artist {artist} found not matching {self.artist} for {self.bookPath}" + f"{red_tag('Action Required')} artist {artist} found not matching {self.artist} for {self.bookPath}" ) self.action_required = True else: @@ -503,12 +522,15 @@ class Audiobook: if not self.artist or force_artist_from_path: self.changed = True self.artist = rel_path[0] - logger.info(f"[Updated] artist {self.artist} found in path for {self.bookPath}") + logger.info( + f"[Updated] artist {self.artist} found in path for {self.bookPath}" + ) def fix_composer_from_comment(self): m = re.search( r"(?:read\s+by:?|" r"spoken\s+by:?|" + r"erzähler:?|" r"narrated\s+by:?|" r"gesprochen\s+von:?|" r"gelesen\s+von)\s+([^\n.,;]+)", @@ -522,7 +544,7 @@ class Audiobook: self.comment = (self.comment[: m.start()] + self.comment[m.end() :]).strip( " .,;\n" ) - self.comment = cleanup(self.comment) + self.comment = cleanup(self.comment) if not self.composer or len(self.composer) < 5: logger.info(f"[Updated] composer found in comment for {self.name}") self.composer = m.group(1).strip() @@ -548,9 +570,11 @@ class Audiobook: def fix_name(self): if not self.name: - self.name = normalize_name(self.bookPath.name,self.series) + self.name = normalize_name(self.bookPath.name, self.series) self.changed = True - logger.info(f"[Updated] name {self.name} found in path for {self.bookPath}")# + logger.info( + f"[Updated] name {self.name} found in path for {self.bookPath}" + ) # return name = normalize_name(self.name, self.series) if name != self.name: @@ -562,7 +586,7 @@ class Audiobook: if self.series_and_num: logger.trace(f"{self.name} already has series: {self.series_and_num}") rel_path = self.bookPath.relative_to(self.library_root_path).parts - number="" + number = "" if len(rel_path) <= 2: logger.trace(f"No series found for {self.name}") return @@ -578,7 +602,7 @@ class Audiobook: number = match.group(2) or match.group(3) break number_str = "" - and_number ="" + and_number = "" if not number: logger.trace(f"No series number found for {self.name}") else: @@ -587,9 +611,11 @@ class Audiobook: self.series_num = number if self.series_and_num != rel_path[1] + number_str: self.series_and_num = rel_path[1] + number_str - self.series =rel_path[1] + self.series = rel_path[1] self.changed = True - logger.info(f"[Updated] series{and_number} found for {self.name} to {self.series_and_num}") + logger.info( + f"[Updated] series{and_number} found for {self.name} to {self.series_and_num}" + ) return def fix_genre(self): @@ -607,7 +633,7 @@ class Audiobook: new_name = f"{desired_name_stem}{file.suffix.lower()}" else: new_name = f"{number:0{padding}d} - {desired_name_stem}{file.suffix}" - self.files[number-1] = file.rename(desired_path / new_name) + self.files[number - 1] = file.rename(desired_path / new_name) for file in self.files_extra: if file.suffix.lower() in {".cue", ".log"} or file in { self.epub_file, @@ -628,13 +654,13 @@ class Audiobook: self.pdf_file = new_file if self.bookPath != desired_path: - logger.debug(f"Moving {self.bookPath} to {desired_path}") remaining = list(self.bookPath.iterdir()) if not remaining: self.bookPath.rmdir() else: - logger.warning(f"{red_tag('Action Required')} old path not empty after move: " + logger.warning( + f"{red_tag('Action Required')} old path not empty after move: " f"{self.bookPath}: {remaining}" ) self.bookPath = desired_path @@ -642,7 +668,7 @@ class Audiobook: self.firstFile = self.get_first_file() def generate_dir_from_metadata(self): - composer ="" + composer = "" name = self.name if self.composer: composer = f" (by {self.composer})" @@ -655,8 +681,15 @@ class Audiobook: series = self.series_and_num.split("#") number = f"{series[1]} - " series = series[0].rstrip() - desired_path = self.library_root_path / self.artist.replace("/", "_") / series.replace("/", "_") / f"{number}{name}".replace("/", "_") - desired_name_stem = self.artist + " - " + self.name + composer + self.bookPath.suffix + desired_path = ( + self.library_root_path + / self.artist.replace("/", "_") + / series.replace("/", "_") + / f"{number}{name}".replace("/", "_") + ) + desired_name_stem = ( + self.artist + " - " + self.name + composer + self.bookPath.suffix + ) desired_name_stem = desired_name_stem.replace("/", "_") return desired_path, desired_name_stem @@ -666,11 +699,11 @@ class Audiobook: logger.warning(f"Action required, resolve before creating m4b file") return if output_file_final.exists(): - logger.info(f"{red_tag("SKIP")} {output_file_final}") + logger.info(f"{red_tag('SKIP')} {output_file_final}") logger.info("Book already present") return - logger.info(f"{blue_tag("create")} {output_file_final}") + logger.info(f"{blue_tag('create')} {output_file_final}") with tempfile.TemporaryDirectory(dir=self.library_root_path.parent) as tmp: tmpdir = Path(tmp) @@ -717,9 +750,13 @@ class Audiobook: for key, value in self.metadata.items(): if key == "title": - mf.write(f"{ffmetadata_escape(key)}={ffmetadata_escape(self.metadata["album"])}\n") + mf.write( + f"{ffmetadata_escape(key)}={ffmetadata_escape(self.metadata['album'])}\n" + ) else: - mf.write(f"{ffmetadata_escape(key)}={ffmetadata_escape(value)}\n") + mf.write( + f"{ffmetadata_escape(key)}={ffmetadata_escape(value)}\n" + ) for info in file_info: media = info["media"] media_name = info["media"].name @@ -818,15 +855,13 @@ class Audiobook: self.changed = False self.size = Path(output_file_final).stat().st_size logger.info( - f"{green_tag("SUCCESS")} - {self.bookPath.name} - delete media files" + f"{green_tag('SUCCESS')} - {self.bookPath.name} - delete media files" ) else: logger.error( - f"{red_tag("ERROR")} - {self.bookPath.name} - Code: {result.returncode}, Stderr: {result.stderr}" + f"{red_tag('ERROR')} - {self.bookPath.name} - Code: {result.returncode}, Stderr: {result.stderr}" ) - - def write_metadata(self, keys=None, dry_run=False): if self.action_required: logger.warning(f"Action required, resolve before writing metadata file") @@ -836,18 +871,20 @@ class Audiobook: keys = [] for key, value in self.metadata.items(): if self.metadata_original.get(key) != value: - if not isinstance(value,list): + if not isinstance(value, list): keys.append(key) self.metadata_original = self.metadata.copy() values = [self.metadata[key] for key in keys] - if (not keys or not values) and self.metadata_original.get("title") != self.title: + if (not keys or not values) and self.metadata_original.get( + "title" + ) != self.title: logger.trace(f"Nothing to write to file for {self.name}") return if keys: for file in self.files: write_metadata(file, keys, values, dry_run) - if isinstance( self.title, list ): - for title,file in zip(self.title, self.files): + if isinstance(self.title, list): + for title, file in zip(self.title, self.files): write_metadata(file, ["title"], [title], dry_run) self.changed = False @@ -860,14 +897,19 @@ class Audiobook: self.title = [] padding = len(str(len(self.files))) for idx, file in enumerate(self.files): - self.title.append(f"{self.name} - {idx+1:0{padding}d}") + self.title.append(f"{self.name} - {idx + 1:0{padding}d}") class AudiobookLibrary: def __init__( - self, library_path: Path, sql_database_path: Path, dry_run: bool, path_filter:str="", logfilename: str = "audiobook_library.log" + self, + library_path: Path, + sql_database_path: Path, + dry_run: bool, + path_filter: str = "", + logfilename: str = "audiobook_library.log", ): - self.path_filter=path_filter + self.path_filter = path_filter self.sql_database_instance = self.SqlDatabase(sql_database_path) self.dry_run = dry_run logging.setLoggerClass(CustomLogger) @@ -1013,7 +1055,7 @@ class AudiobookLibrary: for file in book.get("audioFiles"): comment = file.get("metaTags").get("tagComment") if comment and len(comment) < 40: - logger.debug(f"Fix short comment for {book.get("title")}") + logger.debug(f"Fix short comment for {book.get('title')}") comment = "" file["metaTags"]["tagComment"] = comment @@ -1076,12 +1118,13 @@ class AudiobookLibrary: media_files = [ file for file in self.libraryPath.rglob("*") - if file.is_file() and file.suffix.lower() in AUDIO_SUFFIXES and \ - self.path_filter in str(file) + if file.is_file() + and file.suffix.lower() in AUDIO_SUFFIXES + and self.path_filter in str(file) ] dirs = {file.parent for file in media_files} for directory in dirs: - self.add(Audiobook(directory,self.libraryPath)) + self.add(Audiobook(directory, self.libraryPath)) for audiobook in self.audiobooks: audiobook.init_book() @@ -1093,7 +1136,7 @@ class AudiobookLibrary: for audiobook in self.audiobooks: if audiobook.changed: logger.trace(f"Writing metadata: {audiobook.name}") - audiobook.write_metadata(keys,dry_run=self.dry_run) + audiobook.write_metadata(keys, dry_run=self.dry_run) def fix_artist_dir(self): for book in self.audiobooks: @@ -1104,7 +1147,7 @@ class AudiobookLibrary: desired_path, desired_name = book.generate_dir_from_metadata() book.move(desired_path, desired_name, dry_run) - def fix_artists(self,force_artist_from_path=False): + def fix_artists(self, force_artist_from_path=False): for book in self.audiobooks: book.fix_artist_from_comment() book.fix_artist_from_path(force_artist_from_path) @@ -1137,9 +1180,7 @@ class AudiobookLibrary: for book in self.audiobooks: book.fix_series() - def create_m4b_from_dir( - self, keep_originals: bool = False - ) -> None: + def create_m4b_from_dir(self, keep_originals: bool = False) -> None: audiobooks = self.audiobooks jobs = [audiobook for audiobook in audiobooks if not audiobook.singleFile] for audiobook in jobs: @@ -1163,14 +1204,11 @@ class AudiobookLibrary: logger.exception(f"Failed to create m4b for {audiobook.name}") - def main(): parser = argparse.ArgumentParser(description="Audiobook Directory Processing") parser.add_argument("library", type=Path, help="Library path") - - parser.add_argument( "-ll", "--log-level", @@ -1254,8 +1292,9 @@ def main(): logger.error(f"Database is not a file: {database_path}") return - library = AudiobookLibrary(library_dir, database_path, args.dry_run, - path_filter=args.path_filter) + library = AudiobookLibrary( + library_dir, database_path, args.dry_run, path_filter=args.path_filter + ) if args.fix_db: library.sql_database_instance.init()