maxenceg2m/iTunes
1
0
Fork 0
Code Issues 2 Pull Requests Projects Releases Wiki Activity

ruff

Browse Source
This commit is contained in:
Maxence G. de Montauzan
2025-10-22 10:09:41 +02:00
parent 93b3632bb4
commit ce680beeb3
1 changed files with 147 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

226
iTunesParser.py
View File

@@ -42,14 +42,13 @@ for use in the D3.js JavaScript library.
"""
import argparse
import datetime
import hashlib
import io
import json
import os
import plistlib
import sys
import argparse
import hashlib
class SetEncoder(json.JSONEncoder):
@@ -66,9 +65,10 @@ class ITunesParser:
"""
Parse an iTunes Library and produce JSON - for ELS
"""
SONG_INDEX = 'itunes-songs'
ALBUM_INDEX = 'itunes-albums'
ARTIST_INDEX = 'itunes-artists'
SONG_INDEX = "itunes-songs"
ALBUM_INDEX = "itunes-albums"
ARTIST_INDEX = "itunes-artists"
# TODO Put variables in a config files or in a python library
def __init__(self):
@@ -91,8 +91,8 @@ class ITunesParser:
- Tracks
- ...
"""
plist = plistlib.load(open(library_file, 'rb'))
return plist['Tracks']
plist = plistlib.load(open(library_file, "rb"))
return plist["Tracks"]
def parse(self, library_file):
"""
@@ -105,24 +105,20 @@ class ITunesParser:
for _, track in tracks.items():
# Filter out any non-music
if track['Track Type'] != 'File':
if track["Track Type"] != "File":
continue
if 'Podcast' in track or 'Has Video' in track:
if "Podcast" in track or "Has Video" in track:
continue
# Each keeped track are stored
self._tracks[track['Persistent ID']] = track
self._tracks[track["Persistent ID"]] = track
# Retrieve for each track artist information
self._process_artist(track)
# Retrieve for each track album information
self._process_album(track)
ret = {
'songs': self._tracks,
'albums': self._albums,
'artists': self._artists
}
ret = {"songs": self._tracks, "albums": self._albums, "artists": self._artists}
return ret
def _process_artist(self, track):
@@ -130,105 +126,111 @@ class ITunesParser:
Process artists in the track part of library and return a JSON formated for a bulk ELS request
"""
if 'Album Artist' not in track and 'Artist' not in track:
if "Album Artist" not in track and "Artist" not in track:
return
akey = track['Album Artist'] if 'Album Artist' in track else track['Artist']
akey = track["Album Artist"] if "Album Artist" in track else track["Artist"]
# Add artist
if akey not in self._artists:
a_id = self.calc_id(akey)
# Key is used to increment/precise some information
# So we use artist name as a key to avoid calculating an ID for each track
self._artists[akey] = {
'Persistent ID': a_id,
'Name': akey,
'Artist': akey,
'Track Count': 0,
'Play Count': 0,
'Rating': 0,
'Genre': set(),
'Album': set()
"Persistent ID": a_id,
"Name": akey,
"Artist": akey,
"Track Count": 0,
"Play Count": 0,
"Rating": 0,
"Genre": set(),
"Album": set(),
}
# Compute information
play_count = track['Play Count'] if 'Play Count' in track else 0
play_count = track["Play Count"] if "Play Count" in track else 0
rating = track['Rating'] if 'Rating' in track else 0
rating = self.calc_average(rating, self._artists[akey]['Rating'], self._artists[akey]['Track Count'])
rating = track["Rating"] if "Rating" in track else 0
rating = self.calc_average(
rating, self._artists[akey]["Rating"], self._artists[akey]["Track Count"]
)
self._artists[akey]['Track Count'] += 1
self._artists[akey]['Rating'] = rating
self._artists[akey]['Play Count'] += play_count
self._artists[akey]["Track Count"] += 1
self._artists[akey]["Rating"] = rating
self._artists[akey]["Play Count"] += play_count
if 'Genre' in track:
if "Genre" in track:
# Split up the Genres
genre_parts = track['Genre'].split('/')
self._artists[akey]['Genre'] |= set(genre_parts)
genre_parts = track["Genre"].split("/")
self._artists[akey]["Genre"] |= set(genre_parts)
if 'Album' in track:
self._artists[akey]['Album'].add(track['Album'])
if "Album" in track:
self._artists[akey]["Album"].add(track["Album"])
def _process_album(self, track):
"""
Process albums in the track part of library and return a JSON formated for a bulk ELS request
"""
if 'Album' not in track:
if "Album" not in track:
return
akey = track['Album']
akey = track["Album"]
if akey not in self._albums:
a_id = self.calc_id(akey)
# Key is used to increment/precise some information
# So we use album name as a key to avoid calculating an ID for each track
self._albums[akey] = {
'Persistent ID': a_id,
'Name': akey,
'Album': akey,
'Track Count': 0,
'Play Count': 0,
'Genre': set(),
'Artist': set(),
'Avg Bit Rate': track['Bit Rate'],
'Min Bit Rate': track['Bit Rate'],
"Persistent ID": a_id,
"Name": akey,
"Album": akey,
"Track Count": 0,
"Play Count": 0,
"Genre": set(),
"Artist": set(),
"Avg Bit Rate": track["Bit Rate"],
"Min Bit Rate": track["Bit Rate"],
# 'Album Artist': '',
'Total Time': 0,
'Location': ''
"Total Time": 0,
"Location": "",
}
# Compute information
play_count = track['Play Count'] if 'Play Count' in track else 0
play_count = track["Play Count"] if "Play Count" in track else 0
total_time = track['Total Time'] if 'Total Time' in track else 0
total_time = track["Total Time"] if "Total Time" in track else 0
avg_bitrate = self.calc_average(track['Bit Rate'], self._albums[akey]['Avg Bit Rate'], self._albums[akey]['Track Count'])
avg_bitrate = self.calc_average(
track["Bit Rate"],
self._albums[akey]["Avg Bit Rate"],
self._albums[akey]["Track Count"],
)
self._albums[akey]['Avg Bit Rate'] = avg_bitrate
self._albums[akey]['Track Count'] += 1
self._albums[akey]['Play Count'] += play_count
self._albums[akey]['Total Time'] += total_time
self._albums[akey]["Avg Bit Rate"] = avg_bitrate
self._albums[akey]["Track Count"] += 1
self._albums[akey]["Play Count"] += play_count
self._albums[akey]["Total Time"] += total_time
self._albums[akey]['Location'] = os.path.dirname(track['Location'])
self._albums[akey]["Location"] = os.path.dirname(track["Location"])
if self._albums[akey]['Min Bit Rate'] > track['Bit Rate']:
self._albums[akey]['Min Bit Rate'] = track['Bit Rate']
if self._albums[akey]["Min Bit Rate"] > track["Bit Rate"]:
self._albums[akey]["Min Bit Rate"] = track["Bit Rate"]
if 'Genre' in track:
if "Genre" in track:
# Split up the Genres
genre_parts = track['Genre'].split('/')
self._albums[akey]['Genre'] |= set(genre_parts)
genre_parts = track["Genre"].split("/")
self._albums[akey]["Genre"] |= set(genre_parts)
if 'Artist' in track:
self._albums[akey]['Artist'].add(track['Artist'])
if "Artist" in track:
self._albums[akey]["Artist"].add(track["Artist"])
if 'Album Rating' in track:
self._albums[akey]['Album Rating'] = track['Album Rating']
if "Album Rating" in track:
self._albums[akey]["Album Rating"] = track["Album Rating"]
if 'Album Rating Computed' in track:
self._albums[akey]['Album Rating Computed'] = track['Album Rating Computed']
if "Album Rating Computed" in track:
self._albums[akey]["Album Rating Computed"] = track["Album Rating Computed"]
if 'Album Artist' in track:
self._albums[akey]['Album Artist'] = track['Album Artist']
if "Album Artist" in track:
self._albums[akey]["Album Artist"] = track["Album Artist"]
@classmethod
def calc_average(cls, added_value, current_value, nb_values):
@@ -243,7 +245,7 @@ class ITunesParser:
Calculate a MD5 sum from a key as ID
"""
md5 = hashlib.md5()
md5.update(key.encode('UTF-8'))
md5.update(key.encode("UTF-8"))
return md5.hexdigest()
@@ -254,10 +256,10 @@ class WriteElsJson:
Write artists data to another JSON file
"""
file_artist = io.open(output_file, 'wb')
file_artist = io.open(output_file, "wb")
for _, artist in artists.items():
persistent_id = artist['Persistent ID']
artist['Rating'] = round(artist['Rating'])
persistent_id = artist["Persistent ID"]
artist["Rating"] = round(artist["Rating"])
json_track_index = {
"index": {"_index": ITunesParser.ARTIST_INDEX, "_id": persistent_id}
@@ -265,8 +267,10 @@ class WriteElsJson:
# file_artist.write(bytes(json.dumps(json_track_index, indent=None, cls=SetEncoder), 'UTF-8'))
# file_artist.write(bytes("\n", 'UTF-8'))
file_artist.write(bytes(json.dumps(artist, indent=None, cls=SetEncoder), 'UTF-8'))
file_artist.write(bytes("\n", 'UTF-8'))
file_artist.write(
bytes(json.dumps(artist, indent=None, cls=SetEncoder), "UTF-8")
)
file_artist.write(bytes("\n", "UTF-8"))
file_artist.close()
@staticmethod
@@ -275,10 +279,10 @@ class WriteElsJson:
Write albums data to another JSON file
"""
file_albums = io.open(output_file, 'wb')
file_albums = io.open(output_file, "wb")
for _, album in albums.items():
persistent_id = album['Persistent ID']
album['Avg Bit Rate'] = round(album['Avg Bit Rate'])
persistent_id = album["Persistent ID"]
album["Avg Bit Rate"] = round(album["Avg Bit Rate"])
json_track_index = {
"index": {"_index": ITunesParser.ALBUM_INDEX, "_id": persistent_id}
@@ -286,8 +290,10 @@ class WriteElsJson:
# file_albums.write(bytes(json.dumps(json_track_index, indent=None, cls=SetEncoder), 'UTF-8'))
# file_albums.write(bytes("\n", 'UTF-8'))
file_albums.write(bytes(json.dumps(album, indent=None, cls=SetEncoder), 'UTF-8'))
file_albums.write(bytes("\n", 'UTF-8'))
file_albums.write(
bytes(json.dumps(album, indent=None, cls=SetEncoder), "UTF-8")
)
file_albums.write(bytes("\n", "UTF-8"))
file_albums.close()
@staticmethod
@@ -295,7 +301,7 @@ class WriteElsJson:
"""
Write songs to a JSON
"""
file = io.open(output_file, 'wb')
file = io.open(output_file, "wb")
for persistent_id, song in songs.items():
json_track_index = {
"index": {"_index": ITunesParser.SONG_INDEX, "_id": persistent_id}
@@ -303,43 +309,57 @@ class WriteElsJson:
# file.write(bytes(json.dumps(json_track_index, indent=None, cls=SetEncoder), 'UTF-8'))
# file.write(bytes("\n", 'UTF-8'))
file.write(bytes(json.dumps(song, indent=None, cls=SetEncoder), 'UTF-8'))
file.write(bytes("\n", 'UTF-8'))
file.write(bytes(json.dumps(song, indent=None, cls=SetEncoder), "UTF-8"))
file.write(bytes("\n", "UTF-8"))
file.close()
#### main block ####
# Default input & output files
DEFAULT_LIBRARY_FILE_NAME = 'iTunesLibrary.xml'
DEFAULT_OUTPUT_FILE_NAME = '/es-music-data.json'
DEFAULT_LIBRARY_FILE_NAME = "iTunesLibrary.xml"
DEFAULT_OUTPUT_FILE_NAME = "/es-music-data.json"
DEFAULT_LIBRARY_FILE = os.path.expanduser(DEFAULT_LIBRARY_FILE_NAME)
DEFAULT_OUTPUT_FILE = os.path.dirname(os.path.realpath(__file__)) + DEFAULT_OUTPUT_FILE_NAME
DEFAULT_OUTPUT_FILE = (
os.path.dirname(os.path.realpath(__file__)) + DEFAULT_OUTPUT_FILE_NAME
)
# Get options
parser = argparse.ArgumentParser(description="""
parser = argparse.ArgumentParser(
description="""
Parse an iTunes XML library file to produce JSON file for ELS bulk operation.
""")
parser.add_argument('-f', '--file', default=DEFAULT_LIBRARY_FILE,
help='iTunes Library XML file path (default: ./' + DEFAULT_LIBRARY_FILE_NAME + ')')
parser.add_argument('-o', '--output', default=DEFAULT_OUTPUT_FILE,
help='Output to file (default: .' + DEFAULT_OUTPUT_FILE_NAME + ')')
parser.add_argument('-c', '--console', action='store_true',
help='Output to console instead of file')
"""
)
parser.add_argument(
"-f",
"--file",
default=DEFAULT_LIBRARY_FILE,
help="iTunes Library XML file path (default: ./" + DEFAULT_LIBRARY_FILE_NAME + ")",
)
parser.add_argument(
"-o",
"--output",
default=DEFAULT_OUTPUT_FILE,
help="Output to file (default: ." + DEFAULT_OUTPUT_FILE_NAME + ")",
)
parser.add_argument(
"-c", "--console", action="store_true", help="Output to console instead of file"
)
# parser.add_argument('-v', '--verbose', action='store_true',
# help='Verbose output')
# help='Verbose output')
if __name__ == '__main__':
if __name__ == "__main__":
args = parser.parse_args()
print("Parsing file '{}'...".format(args.file))
print(f"Parsing file '{args.file}'...")
itunes_parser = ITunesParser().parse(args.file)
print("Writing JSON files...")
WriteElsJson.write_songs(itunes_parser['songs'], "es-songs.jsonl")
WriteElsJson.write_artists(itunes_parser['artists'], "es-artists.jsonl")
WriteElsJson.write_albums(itunes_parser['albums'], "es-albums.jsonl")
WriteElsJson.write_songs(itunes_parser["songs"], "es-songs.jsonl")
WriteElsJson.write_artists(itunes_parser["artists"], "es-artists.jsonl")
WriteElsJson.write_albums(itunes_parser["albums"], "es-albums.jsonl")
print('Done!')
print("Done!")
# if args.console:
# print(output)