Init repo with original Script
iTunesGraphParser.py is the original script source: https://github.com/cgmartin/iTunes-Library-Network-Graph.git
This commit is contained in:
239
iTunesParser.py
Normal file
239
iTunesParser.py
Normal file
@@ -0,0 +1,239 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
"""
|
||||
--> Parse library and just do JSON
|
||||
|
||||
iTunes Graph Parser
|
||||
|
||||
Parses an iTunes library XML file and generates a JSON file
|
||||
for use in the D3.js JavaScript library.
|
||||
|
||||
Example Track info:
|
||||
{
|
||||
'Album': 'Nirvana',
|
||||
'Persistent ID': 'A50FE1436726815C',
|
||||
'Track Number': 4,
|
||||
'Location': 'file://localhost/Users/foo/Music/iTunes/iTunes%20Music/Nirvana/Nirvana/04%20Sliver.mp3',
|
||||
'File Folder Count': 4,
|
||||
'Album Rating Computed': True,
|
||||
'Total Time': 134295,
|
||||
'Sample Rate': 44100,
|
||||
'Genre': 'Rock/Alternative',
|
||||
'Bit Rate': 236,
|
||||
'Kind': 'MPEG audio file',
|
||||
'Name': 'Sliver',
|
||||
'Artist': 'Nirvana',
|
||||
'Date Added': datetime.datetime(2006, 10, 11, 4, 31, 38),
|
||||
'Album Rating': 60,
|
||||
'Rating': 40,
|
||||
'Date Modified': datetime.datetime(2009, 7, 18, 4, 57, 41),
|
||||
'Library Folder Count': 1,
|
||||
'Year': 2002,
|
||||
'Track ID': 7459,
|
||||
'Size': 3972838,
|
||||
'Track Type': 'File',
|
||||
'Play Count': 2,
|
||||
'Play Date UTC': datetime.datetime(2009, 7, 18, 5, 00, 00)
|
||||
}
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import division
|
||||
from optparse import OptionParser
|
||||
|
||||
import os
|
||||
import io
|
||||
import plistlib
|
||||
import json
|
||||
import datetime
|
||||
|
||||
|
||||
class SetEncoder(json.JSONEncoder):
|
||||
def default(self, obj):
|
||||
if isinstance(obj, set):
|
||||
return list(obj)
|
||||
if isinstance(obj, datetime.datetime):
|
||||
return obj.isoformat()
|
||||
# encoded_object = int(mktime(obj.timetuple()))
|
||||
return json.JSONEncoder.default(self, obj)
|
||||
|
||||
|
||||
class ITunesParser:
|
||||
def __init__(self, libraryFile):
|
||||
self._albums = {}
|
||||
self._artists = {}
|
||||
self.libraryFile = libraryFile
|
||||
|
||||
def toJson(self):
|
||||
output = self._processSongs()
|
||||
|
||||
# self._writeArtists()
|
||||
# self._writeAlbums()
|
||||
|
||||
# return json.dumps(jsonObj, indent=indent, cls=SetEncoder)
|
||||
return output
|
||||
|
||||
def toJsonP(self, rating=4):
|
||||
json = self.toJson()
|
||||
jsonp = ';itgCallback(' + json + ');'
|
||||
return jsonp
|
||||
|
||||
|
||||
def _readTracks(self):
|
||||
pl = plistlib.readPlist(self.libraryFile)
|
||||
return pl['Tracks']
|
||||
|
||||
def _processSongs(self):
|
||||
tracks = self._readTracks()
|
||||
output = ""
|
||||
|
||||
for k in tracks:
|
||||
track = tracks[k]
|
||||
|
||||
# Filter out any non-music
|
||||
if track['Track Type'] != 'File':
|
||||
continue
|
||||
if 'Podcast' in track or 'Has Video' in track:
|
||||
continue
|
||||
|
||||
persistentId = track['Persistent ID']
|
||||
jsonTrackIndic = {
|
||||
"index": {"_index": "itunessongs", "_type": "song", "_id": persistentId}
|
||||
}
|
||||
|
||||
# Retrieve for each track artist information
|
||||
self._processArtist(track)
|
||||
# Retrieve for each track album information
|
||||
self._processAlbum(track)
|
||||
|
||||
output += json.dumps(jsonTrackIndic, indent=None, cls=SetEncoder)
|
||||
output += "\n"
|
||||
output += json.dumps(track, indent=None, cls=SetEncoder)
|
||||
output += "\n"
|
||||
return output
|
||||
|
||||
def _processArtist(self, track):
|
||||
if 'Artist' not in track:
|
||||
return
|
||||
|
||||
akey = track['Artist']
|
||||
# Add artist
|
||||
if akey not in self._artists:
|
||||
self._artists[akey] = {
|
||||
'id': len(self._artists),
|
||||
'name': akey,
|
||||
'count': 0, 'plays': 0, 'rating': 0,
|
||||
'genres': set()
|
||||
}
|
||||
|
||||
# Compute information
|
||||
rating = (track['Rating'] // 20) if 'Rating' in track else 0
|
||||
plays = track['Play Count'] if 'Play Count' in track else 0
|
||||
|
||||
self._artists[akey]['count'] += 1
|
||||
self._artists[akey]['rating'] += rating
|
||||
self._artists[akey]['plays'] += plays
|
||||
|
||||
if 'Genre' not in track:
|
||||
return
|
||||
|
||||
# Split up the Genres
|
||||
genreParts = track['Genre'].split('/')
|
||||
self._artists[akey]['genres'] |= set(genreParts)
|
||||
return
|
||||
|
||||
def _processAlbum(self, track):
|
||||
if 'Album' not in track:
|
||||
return
|
||||
|
||||
akey = track['Album']
|
||||
if akey not in self._albums:
|
||||
self._albums[akey] = {
|
||||
'id': len(self._albums),
|
||||
'name': akey,
|
||||
'count': 0, 'plays': 0, 'rating': 0,
|
||||
'genres': set(),
|
||||
'artist': set()
|
||||
}
|
||||
|
||||
# Compute information
|
||||
rating = (track['Rating'] // 20) if 'Rating' in track else 0
|
||||
plays = track['Play Count'] if 'Play Count' in track else 0
|
||||
|
||||
self._albums[akey]['count'] += 1
|
||||
self._albums[akey]['rating'] += rating
|
||||
self._albums[akey]['plays'] += plays
|
||||
|
||||
if 'Genre' not in track:
|
||||
return
|
||||
|
||||
# Split up the Genres
|
||||
genreParts = track['Genre'].split('/')
|
||||
self._albums[akey]['genres'] |= set(genreParts)
|
||||
|
||||
## Add different artists
|
||||
if 'Artist' not in track:
|
||||
return
|
||||
self._albums[akey]['artist'].add(track['Artist'])
|
||||
return
|
||||
|
||||
# def _writeArtists(self):
|
||||
# fileArtist = io.open('es-artist-data.json', 'wb')
|
||||
# for a in self._artists:
|
||||
# jsonTrackIndic = {
|
||||
# "index": {"_index": "itunessongs", "_type": "artist"}
|
||||
# }
|
||||
# fileArtist.write(json.dumps(jsonTrackIndic, indent=None, cls=SetEncoder))
|
||||
# fileArtist.write("\n")
|
||||
# fileArtist.write(json.dumps(self._artists[a], indent=None, cls=SetEncoder))
|
||||
# fileArtist.write("\n")
|
||||
# fileArtist.close()
|
||||
|
||||
# def _writeAlbums(self):
|
||||
# fileAlbums = io.open('es-albums-data.json', 'wb')
|
||||
# for a in self._albums:
|
||||
# jsonTrackIndic = {
|
||||
# "index": {"_index": "itunessongs", "_type": "album"}
|
||||
# }
|
||||
# fileAlbums.write(json.dumps(jsonTrackIndic, indent=None, cls=SetEncoder))
|
||||
# fileAlbums.write("\n")
|
||||
# fileAlbums.write(json.dumps(self._albums[a], indent=None, cls=SetEncoder))
|
||||
# fileAlbums.write("\n")
|
||||
# fileAlbums.close()
|
||||
|
||||
#### main block ####
|
||||
|
||||
# Default input & output files
|
||||
defaultLibraryFile = os.path.expanduser('iTunesMiniLibrary.xml')
|
||||
defaultOutputFile = os.path.dirname(os.path.realpath(__file__)) + '/es-music-data.json'
|
||||
|
||||
# Get options
|
||||
parser = OptionParser(version="%prog 1.0")
|
||||
parser.add_option('-f', '--file', dest='file', type='string',
|
||||
help='iTunes Library XML file path',
|
||||
default=defaultLibraryFile)
|
||||
parser.add_option('-o', '--output', dest='output', type='string',
|
||||
help='Output to file (default=./js/music-data.json)',
|
||||
default=defaultOutputFile)
|
||||
parser.add_option('-c', '--console', dest='console', action='store_true',
|
||||
help='Output to console instead of file')
|
||||
parser.add_option('-p', '--jsonp', dest='jsonp', action='store_true',
|
||||
help='Output in JSON-P format')
|
||||
parser.add_option('-v', '--verbose', dest='verbose', action='store_true',
|
||||
help='Verbose output')
|
||||
|
||||
if __name__ == '__main__':
|
||||
(options, args) = parser.parse_args()
|
||||
|
||||
itunesParser = ITunesParser(options.file)
|
||||
if options.jsonp:
|
||||
output = itunesParser.toJsonP()
|
||||
else:
|
||||
output = itunesParser.toJson()
|
||||
|
||||
if options.console:
|
||||
print(output)
|
||||
else:
|
||||
with io.open(options.output, 'wb') as outfile:
|
||||
outfile.write(output)
|
||||
print('JSON data written to: ' + options.output)
|
||||
Reference in New Issue
Block a user