translate edit genre metadata to python

ads

audiobook_metadata/metadata_genre_remove_from_file.py

@@ -0,0 +1,192 @@
+#!/usr/bin/env python3
+
+import argparse
+import re
+import subprocess
+from pathlib import Path
+from datetime import datetime
+
+
+def get_genre(file_path):
+    try:
+        result = subprocess.run(
+            ["kid3-cli", "-c", "get genre", str(file_path)],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        return result.stdout.strip()
+    except Exception:
+        return ""
+
+
+def set_genre(file_path, genre):
+    subprocess.run(
+        [
+            "kid3-cli",
+            "-c",
+            "tag 2",
+            "-c",
+            f"set genre \"{genre}\"",
+            "-c",
+            "save",
+            str(file_path),
+        ],
+        check=False,
+    )
+
+
+def clean_genre(genre):
+
+    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)
+    genre = re.sub(r'(?i)^(hörspiele?|hoerspiele?)$', '', genre)
+    genre = re.sub(r'(?i)^spoken\s*word$', '', genre)
+    genre = re.sub(r'(?i)gesprochene\s*inhalte$', '', genre)
+    genre = re.sub(r'(?i)^speech$', '', genre)
+    genre = re.sub(r'Fanasie', 'Fantasie', genre)
+    genre = re.sub(r'Mit Videospiel', 'Videospielbezug', genre)
+    genre = re.sub(r'(?i)nonfiction', 'NonFiction', genre)
+
+    genre = re.sub(r'(?i)^speech$', '', genre)
+    genre = re.sub(r'(?i)^vocal$', '', genre)
+    genre = re.sub(r'(?i)^retail$', '', genre)
+    genre = re.sub(r'(?i)^other$', '', genre)
+    genre = re.sub(r'(?i)^misc$', '', genre)
+
+    genre = re.sub(r'(?i)^(sci[- ]?fi|sf)$', 'Science Fiction', genre)
+    genre = re.sub(r'(?i)^\(?science fiction\)?$', 'Science Fiction', genre)
+    genre = re.sub(r'Thrillers', 'Thriller', genre)
+    genre = re.sub(r"(?i)\bchildren'?s audiobooks?\b", "", genre)
+    genre = re.sub(r'^-\s*|\s*-$', '', genre)
+    genre = re.sub(r'(?i)Engelske\s*\sLydbånd', '', genre)
+    genre = re.sub(r'^FIC028000.*$', '', genre)
+    genre = re.sub(r'^800.*$', '', genre)
+    genre = re.sub(r'^Fantastic Beasts.*$', '', genre)
+    genre = re.sub(r'^and thei.*$', '', genre)
+    genre = re.sub(r'^those you.*$', '', genre)
+    # Normalize separators
+    genre = re.sub(
+        r'\s*[,&:/]\s*',
+        ';',
+        genre
+    )
+
+    genre = re.sub(
+        r'\s*;\s*',
+        '; ',
+        genre
+    )
+
+    # Trim punctuation / whitespace
+    genre = re.sub(
+        r'^[\s,;:\-]+',
+        '',
+        genre
+    )
+
+    genre = re.sub(
+        r'[\s,;\-]+$',
+        '',
+        genre
+    )
+
+    genre = genre.strip()
+    genre = genre.lstrip()
+
+    return genre
+
+def find_audio_files(library):
+    extensions = {".mp3", ".m4a", ".m4b"}
+
+    return [
+        p for p in Path(library).rglob("*")
+        if p.is_file() and p.suffix.lower() in extensions
+    ]
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Audiobook Genre Cleanup"
+    )
+
+    parser.add_argument(
+        "library",
+        help="Library path"
+    )
+
+    parser.add_argument(
+        "--delete",
+        action="store_true",
+        help="Update tags instead of reporting only"
+    )
+
+    parser.add_argument(
+        "--report",
+        default="/home/lucas/audiobook_genre_cleanup.txt",
+        help="Report file"
+    )
+
+    args = parser.parse_args()
+
+    files = find_audio_files(args.library)
+
+    total = len(files)
+    processed = 0
+    matches = 0
+    modified = 0
+
+    with open(args.report, "w", encoding="utf-8") as report:
+        report.write("Audiobook Genre Cleanup Report\n")
+        report.write(f"Generated: {datetime.now()}\n")
+        report.write(f"Library: {args.library}\n")
+        report.write(f"Total files: {total}\n\n")
+
+    for file in files:
+        processed += 1
+
+        if processed % 100 == 0:
+            print(f"Progress: {processed}/{total} files processed")
+
+        genre = get_genre(file)
+
+        if not genre:
+            continue
+
+        cleaned = clean_genre(genre)
+
+        if genre != cleaned:
+            matches += 1
+            status = "MATCH"
+
+            if args.delete:
+                set_genre(file, cleaned)
+                modified += 1
+                status = "UPDATED"
+
+            line = (
+                f'[{processed}/{total}] [{status}] '
+                f'{file} | OLD="{genre}" | NEW="{cleaned}"'
+            )
+
+            print(line)
+
+            with open(args.report, "a", encoding="utf-8") as report:
+                report.write(line + "\n")
+
+    with open(args.report, "a", encoding="utf-8") as report:
+        report.write("\n========== SUMMARY ==========\n")
+        report.write(f"Files scanned : {total}\n")
+        report.write(f"Matches found : {matches}\n")
+        report.write(f"Files updated : {modified}\n")
+
+    print("\n========== SUMMARY ==========")
+    print(f"Files scanned : {total}")
+    print(f"Matches found : {matches}")
+    print(f"Files updated : {modified}")
+    print(f"Report written to: {args.report}")
+
+
+if __name__ == "__main__":
+    main()