Like 0
Fork 0

Last active 1693857166

A little python script using mutagen module and MusicBrainz APIs to recover ID3 tags for a mp3 file

Millefeuille revised this gist 1693857165. Go to revision

1 file changed, 17 insertions, 14 deletions

ID3Tagger.py

@@ -3,9 +3,10 @@ import datetime
3 3 import json
4 4 import urllib.request
5 5 import urllib.parse
6 + import acoustid
6 7 from mutagen.id3 import ID3NoHeaderError, ID3, TIT2, TALB, TPE2, TPE1, APIC, TRCK, TLEN, TDRC, TYER
7 8
8 - base_url = "https://musicbrainz.org/ws/2/recording/"
9 + base_url = "https://musicbrainz.org/ws/2"
9 10 cover_art_url = f"https://coverartarchive.org/release/"
10 11
11 12
@@ -14,9 +15,9 @@ def milliseconds_to_duration(milliseconds):
14 15 minutes, seconds = divmod(seconds, 60)
15 16 hours, minutes = divmod(minutes, 60)
16 17
17 - duration = "{:02}:{:02}:{:02}.{}".format(hours, minutes, seconds, milliseconds)
18 + music_duration = "{:02}:{:02}:{:02}.{}".format(hours, minutes, seconds, milliseconds)
18 19
19 - return duration
20 + return music_duration
20 21
21 22
22 23 def get_key(data, key):
@@ -50,7 +51,10 @@ def get_data_from_media(media, tags, title):
50 51 if media is None:
51 52 print("Found no media for this release, no additional data can be recovered")
52 53 return tags
53 - for track in media['track']:
54 + if 'tracks' not in media or len(media['tracks']) <=0:
55 + print("Found no track for this release, no additional data can be recovered")
56 + return tags
57 + for track in media['tracks']:
54 58 if track['title'] == title:
55 59 track_num = f"{track['number']}/{media['track-count']}"
56 60 print(f"TRCK={track_num}")
@@ -109,32 +113,31 @@ def main():
109 113 prog='metadataFetcher',
110 114 description='fetches metadata and writes it in a mp3 file'
111 115 )
116 + parser.add_argument('api_key')
112 117 parser.add_argument('filename')
113 - parser.add_argument('title')
114 - parser.add_argument('artist')
115 118 args = parser.parse_args()
116 119
120 + matches = list(acoustid.match(args.api_key, args.filename))
121 + if len(matches) <= 0:
122 + print("Could not get a match for the fingerprint, exiting...")
123 + exit(1)
124 +
117 125 try:
118 126 tags = ID3(args.filename)
119 127 except ID3NoHeaderError:
120 128 print("Adding ID3 header...")
121 129 tags = ID3()
122 130
123 - artist = urllib.parse.quote(args.artist)
124 - title = urllib.parse.quote(args.title)
125 - query = f"?query=artist:{artist}%20AND%20recording:{title}&fmt=json"
126 - with urllib.request.urlopen(f"{base_url}{query}") as response:
131 + with urllib.request.urlopen(f"{base_url}/recording/{matches[0][1]}?fmt=json&inc=releases+artists+media+artist-credits") as response:
127 132 body = response.read()
128 - data = json.loads(body)
129 -
130 - recording = get_recording(data)
133 + recording = json.loads(body)
131 134 tags = get_data_from_recording(recording, tags)
132 135
133 136 release = get_release(recording)
134 137 tags = get_data_from_release(release, tags)
135 138 if release is not None:
136 139 media = get_media(release)
137 - get_data_from_media(media, tags, title)
140 + get_data_from_media(media, tags, recording['title'])
138 141
139 142 tags.save()
140 143

Millefeuille revised this gist 1693844726. Go to revision

1 file changed, 1 deletion

ID3Tagger.py

@@ -14,7 +14,6 @@ def milliseconds_to_duration(milliseconds):
14 14 minutes, seconds = divmod(seconds, 60)
15 15 hours, minutes = divmod(minutes, 60)
16 16
17 - # Create a formatted string
18 17 duration = "{:02}:{:02}:{:02}.{}".format(hours, minutes, seconds, milliseconds)
19 18
20 19 return duration

Millefeuille revised this gist 1693844706. Go to revision

1 file changed, 144 insertions

ID3Tagger.py(file created)

@@ -0,0 +1,144 @@
1 + import argparse
2 + import datetime
3 + import json
4 + import urllib.request
5 + import urllib.parse
6 + from mutagen.id3 import ID3NoHeaderError, ID3, TIT2, TALB, TPE2, TPE1, APIC, TRCK, TLEN, TDRC, TYER
7 +
8 + base_url = "https://musicbrainz.org/ws/2/recording/"
9 + cover_art_url = f"https://coverartarchive.org/release/"
10 +
11 +
12 + def milliseconds_to_duration(milliseconds):
13 + seconds, milliseconds = divmod(milliseconds, 1000)
14 + minutes, seconds = divmod(seconds, 60)
15 + hours, minutes = divmod(minutes, 60)
16 +
17 + # Create a formatted string
18 + duration = "{:02}:{:02}:{:02}.{}".format(hours, minutes, seconds, milliseconds)
19 +
20 + return duration
21 +
22 +
23 + def get_key(data, key):
24 + if key not in data or len(data[key]) <= 0:
25 + return None
26 + return data[key][0]
27 +
28 +
29 + def get_recording(data):
30 + return get_key(data, 'recordings')
31 +
32 +
33 + def get_release(recording):
34 + return get_key(recording, 'releases')
35 +
36 +
37 + def get_media(release):
38 + return get_key(release, 'media')
39 +
40 +
41 + def concat_artists(data):
42 + if 'artist-credit' not in data or len(data['artist-credit']) <= 0:
43 + return None
44 + artists = []
45 + for artist in data['artist-credit']:
46 + artists.append(artist['name'])
47 + return ",".join(artists)
48 +
49 +
50 + def get_data_from_media(media, tags, title):
51 + if media is None:
52 + print("Found no media for this release, no additional data can be recovered")
53 + return tags
54 + for track in media['track']:
55 + if track['title'] == title:
56 + track_num = f"{track['number']}/{media['track-count']}"
57 + print(f"TRCK={track_num}")
58 + tags["TRCK"] = TRCK(encoding=3, text=track_num)
59 + return tags
60 +
61 +
62 + def get_data_from_release(release, tags):
63 + if release is None:
64 + print("Found no release for this recording, no additional data can be recovered")
65 + return tags
66 + print(f"TALB={release['title']}")
67 + tags["TALB"] = TALB(encoding=3, text=release['title'])
68 + release_artists = concat_artists(release)
69 + if release_artists is None:
70 + print("Found no artist for this release")
71 + else:
72 + print(f"TPE2={release_artists}")
73 + tags["TPE2"] = TPE2(encoding=3, text=release_artists)
74 + try:
75 + with urllib.request.urlopen(f"{cover_art_url}{release['id']}/front") as cover_art_response:
76 + print(f"APIC={cover_art_url}{release['id']}/front")
77 + tags["APIC"] = APIC(3, 'image/jpeg', 3, 'Front cover', cover_art_response.read())
78 + except:
79 + print("Found no cover art for this release")
80 + return tags
81 +
82 +
83 + def get_data_from_recording(recording, tags):
84 + if recording is None:
85 + print("Got no match for this recording, exiting...")
86 + exit(1)
87 + print(f"TIT2={recording['title']}")
88 + tags["TIT2"] = TIT2(encoding=3, text=recording['title'])
89 + if 'length' in recording:
90 + print(f"TLEN={milliseconds_to_duration(recording['length'])}")
91 + tags["TLEN"] = TLEN(encoding=3, text=milliseconds_to_duration(recording['length']))
92 + track_artists = concat_artists(recording)
93 + if track_artists is None:
94 + print("Found no artist for this track")
95 + else:
96 + print(f"TPE1={track_artists}")
97 + tags["TPE1"] = TPE1(encoding=3, text=track_artists)
98 + if 'first-release-date' not in recording:
99 + print("Found no release date for this recording")
100 + return tags
101 + release_date: datetime.date = datetime.date.fromisoformat(recording['first-release-date'])
102 + print(f"TDRC/TYER={release_date.year}")
103 + tags["TYER"] = TYER(encoding=3, text=f"{release_date.year}")
104 + tags["TDRC"] = TDRC(encoding=3, text=f"{release_date.year}")
105 + return tags
106 +
107 +
108 + def main():
109 + parser = argparse.ArgumentParser(
110 + prog='metadataFetcher',
111 + description='fetches metadata and writes it in a mp3 file'
112 + )
113 + parser.add_argument('filename')
114 + parser.add_argument('title')
115 + parser.add_argument('artist')
116 + args = parser.parse_args()
117 +
118 + try:
119 + tags = ID3(args.filename)
120 + except ID3NoHeaderError:
121 + print("Adding ID3 header...")
122 + tags = ID3()
123 +
124 + artist = urllib.parse.quote(args.artist)
125 + title = urllib.parse.quote(args.title)
126 + query = f"?query=artist:{artist}%20AND%20recording:{title}&fmt=json"
127 + with urllib.request.urlopen(f"{base_url}{query}") as response:
128 + body = response.read()
129 + data = json.loads(body)
130 +
131 + recording = get_recording(data)
132 + tags = get_data_from_recording(recording, tags)
133 +
134 + release = get_release(recording)
135 + tags = get_data_from_release(release, tags)
136 + if release is not None:
137 + media = get_media(release)
138 + get_data_from_media(media, tags, title)
139 +
140 + tags.save()
141 +
142 +
143 + if __name__ == '__main__':
144 + main()
Newer Older

Powered by Opengist ⋅ Load: 43ms