Millefeuille / ID3Tagger

import argparse import datetime import json import urllib.request import urllib.parse import acoustid from mutagen.id3 import ID3NoHeaderError, ID3, TIT2, TALB, TPE2, TPE1, APIC, TRCK, TLEN, TDRC, TYER base_url = "https://musicbrainz.org/ws/2" cover_art_url = f"https://coverartarchive.org/release/" def milliseconds_to_duration(milliseconds): seconds, milliseconds = divmod(milliseconds, 1000) minutes, seconds = divmod(seconds, 60) hours, minutes = divmod(minutes, 60) music_duration = "{:02}:{:02}:{:02}.{}".format(hours, minutes, seconds, milliseconds) return music_duration def get_key(data, key): if key not in data or len(data[key]) <= 0: return None return data[key][0] def get_recording(data): return get_key(data, 'recordings') def get_release(recording): return get_key(recording, 'releases') def get_media(release): return get_key(release, 'media') def concat_artists(data): if 'artist-credit' not in data or len(data['artist-credit']) <= 0: return None artists = [] for artist in data['artist-credit']: artists.append(artist['name']) return ",".join(artists) def get_data_from_media(media, tags, title): if media is None: print("Found no media for this release, no additional data can be recovered") return tags if 'tracks' not in media or len(media['tracks']) <=0: print("Found no track for this release, no additional data can be recovered") return tags for track in media['tracks']: if track['title'] == title: track_num = f"{track['number']}/{media['track-count']}" print(f"TRCK={track_num}") tags["TRCK"] = TRCK(encoding=3, text=track_num) return tags def get_data_from_release(release, tags): if release is None: print("Found no release for this recording, no additional data can be recovered") return tags print(f"TALB={release['title']}") tags["TALB"] = TALB(encoding=3, text=release['title']) release_artists = concat_artists(release) if release_artists is None: print("Found no artist for this release") else: print(f"TPE2={release_artists}") tags["TPE2"] = TPE2(encoding=3, text=release_artists) try: with urllib.request.urlopen(f"{cover_art_url}{release['id']}/front") as cover_art_response: print(f"APIC={cover_art_url}{release['id']}/front") tags["APIC"] = APIC(3, 'image/jpeg', 3, 'Front cover', cover_art_response.read()) except: print("Found no cover art for this release") return tags def get_data_from_recording(recording, tags): if recording is None: print("Got no match for this recording, exiting...") exit(1) print(f"TIT2={recording['title']}") tags["TIT2"] = TIT2(encoding=3, text=recording['title']) if 'length' in recording: print(f"TLEN={milliseconds_to_duration(recording['length'])}") tags["TLEN"] = TLEN(encoding=3, text=milliseconds_to_duration(recording['length'])) track_artists = concat_artists(recording) if track_artists is None: print("Found no artist for this track") else: print(f"TPE1={track_artists}") tags["TPE1"] = TPE1(encoding=3, text=track_artists) if 'first-release-date' not in recording: print("Found no release date for this recording") return tags release_date: datetime.date = datetime.date.fromisoformat(recording['first-release-date']) print(f"TDRC/TYER={release_date.year}") tags["TYER"] = TYER(encoding=3, text=f"{release_date.year}") tags["TDRC"] = TDRC(encoding=3, text=f"{release_date.year}") return tags def main(): parser = argparse.ArgumentParser( prog='metadataFetcher', description='fetches metadata and writes it in a mp3 file' ) parser.add_argument('api_key') parser.add_argument('filename') args = parser.parse_args() matches = list(acoustid.match(args.api_key, args.filename)) if len(matches) <= 0: print("Could not get a match for the fingerprint, exiting...") exit(1) try: tags = ID3(args.filename) except ID3NoHeaderError: print("Adding ID3 header...") tags = ID3() with urllib.request.urlopen(f"{base_url}/recording/{matches[0][1]}?fmt=json&inc=releases+artists+media+artist-credits") as response: body = response.read() recording = json.loads(body) tags = get_data_from_recording(recording, tags) release = get_release(recording) tags = get_data_from_release(release, tags) if release is not None: media = get_media(release) get_data_from_media(media, tags, recording['title']) tags.save() if __name__ == '__main__': main()