def mb_complete_media(self, obj, mb_id, excludes=()):
log = logging.getLogger('util.importer.mb_complete_media')
log.info('complete media, m: %s | mb_id: %s' % (obj.name, mb_id))
#raw_input("Press Enter to continue...")
time.sleep(1.1)
inc = ('artists', 'url-rels', 'aliases', 'tags', 'recording-rels', 'artist-rels', 'work-level-rels', 'artist-credits')
url = 'http://%s/ws/2/recording/%s/?fmt=json&inc=%s' % (MUSICBRAINZ_HOST, mb_id, "+".join(inc))
r = requests.get(url)
result = r.json()
print '*****************************************************************'
print '*****************************************************************'
print '*****************************************************************'
self.pp.pprint(result)
print '*****************************************************************'
print '*****************************************************************'
print '*****************************************************************'
# self.pp.pprint(result)
if 'relations' in result:
for relation in result['relations']:
# map artists
if 'artist' in relation:
print 'artist: %s' % relation['artist']['name']
print 'mb_id: %s' % relation['artist']['id']
print 'role: %s' % relation['type']
print
time.sleep(0.1)
l_as = lookup.artist_by_mb_id(relation['artist']['id'])
l_a = None
#if len(l_as) < 1 and relation['artist']['id'] not in self.mb_completed:
if len(l_as) < 1 and relation['artist']['id'] not in excludes:
self.mb_completed.append(relation['artist']['id'])
l_a = Artist(name=relation['artist']['name'])
l_a.save()
url = 'http://musicbrainz.org/artist/%s' % relation['artist']['id']
print 'musicbrainz_url: %s' % url
rel = Relation(content_object=l_a, url=url)
rel.save()
print 'artist created'
if len(l_as) == 1:
print 'got artist!'
l_a = l_as[0]
print l_as[0]
profession = None
if 'type' in relation:
profession, created = Profession.objects.get_or_create(name=relation['type'])
""""""
if l_a:
mea, created = MediaExtraartists.objects.get_or_create(artist=l_a, media=obj, profession=profession)
l_a = self.mb_complete_artist(l_a, relation['artist']['id'])
#self.pp.pprint(relation['artist']['name'])
tags = result.get('tags', ())
for tag in tags:
log.debug('got tag: %s' % (tag['name']))
Tag.objects.add_tag(obj, '"%s"' % tag['name'])
# add mb relation
mb_url = 'http://musicbrainz.org/recording/%s' % (mb_id)
try:
rel = Relation.objects.get(object_id=obj.pk, url=mb_url)
except:
log.debug('relation not here yet, add it: %s' % (mb_url))
rel = Relation(content_object=obj, url=mb_url)
rel.save()
return obj
def mb_complete_artist(self, obj, mb_id):
log = logging.getLogger('util.importer.mb_complete_artist')
log.info('complete artist, a: %s | mb_id: %s' % (obj.name, mb_id))
self.mb_completed.append(mb_id)
inc = ('url-rels', 'tags')
url = 'http://%s/ws/2/artist/%s/?fmt=json&inc=%s' % (MUSICBRAINZ_HOST, mb_id, "+".join(inc))
r = requests.get(url)
result = r.json()
print '#########################################################################'
self.pp.pprint(result)
discogs_url = None
discogs_image = None
valid_relations = ('wikipedia', 'allmusic', 'BBC Music page', 'social network', 'official homepage', 'youtube', 'myspace',)
relations = result.get('relations', ())
for relation in relations:
if relation['type'] == 'discogs':
log.debug('got discogs url for artist: %s' % relation['url'])
discogs_url = relation['url']
if relation['type'] in valid_relations:
log.debug('got %s url for artist: %s' % (relation['type'], relation['url']))
try:
rel = Relation.objects.get(object_id=obj.pk, url=relation['url'])
except:
rel = Relation(content_object=obj, url=relation['url'])
if relation['type'] == 'official homepage':
rel.service = 'official'
rel.save()
if discogs_url:
try:
rel = Relation.objects.get(object_id=obj.pk, url=discogs_url)
except:
rel = Relation(content_object=obj, url=discogs_url)
rel.save()
# try to get image
try:
discogs_image = discogs_image_by_url(discogs_url, 'resource_url')
log.debug('discogs image located at: %s' % discogs_image)
except:
pass
# try to load & assign image
if discogs_image:
try:
img = filer_extra.url_to_file(discogs_image, obj.folder)
obj.main_image = img
obj.save()
except:
log.info('unable to assign discogs image')
if discogs_url:
discogs_id = None
try:
# TODO: not sure if always working
discogs_id = discogs_id_by_url(discogs_url)
log.info('extracted discogs id: %s' % discogs_id)
except:
pass
if discogs_id:
url = 'http://api.discogs.com/artists/%s' % discogs_id
r = requests.get(url)
dgs_result = r.json()
self.pp.pprint(dgs_result)
"""
styles = dgs_result.get('styles', ())
for style in styles:
log.debug('got style: %s' % (style))
Tag.objects.add_tag(obj, '"%s"' % style)
"""
profile = dgs_result.get('profile', None)
if profile:
obj.biography = profile
realname = dgs_result.get('realname', None)
if realname:
obj.real_name = realname
"""
verry hackish part here, just as proof-of-concept
"""
aliases = dgs_result.get('aliases', ())
for alias in aliases:
try:
log.debug('got alias: %s' % alias['name'])
# TODO: improve! handle duplicates!
time.sleep(1.1)
r = requests.get(alias['resource_url'])
aa_result = r.json()
aa_discogs_url = aa_result.get('uri', None)
aa_name = aa_result.get('name', None)
aa_profile = aa_result.get('profile', None)
if aa_discogs_url and aa_name:
l_as = lookup.artist_by_relation_url(aa_discogs_url)
l_a = None
if len(l_as) < 1:
l_a = Artist(name=aa_name, biography=aa_profile)
l_a.save()
rel = Relation(content_object=l_a, url=aa_discogs_url)
rel.save()
if len(l_as) == 1:
l_a = l_as[0]
print l_as[0]
if l_a:
obj.aliases.add(l_a)
except:
pass
"""
verry hackish part here, just as proof-of-concept
"""
members = dgs_result.get('members', ())
for member in members:
try:
log.debug('got member: %s' % member['name'])
# TODO: improve! handle duplicates!
time.sleep(1.1)
r = requests.get(member['resource_url'])
ma_result = r.json()
ma_discogs_url = ma_result.get('uri', None)
ma_name = ma_result.get('name', None)
ma_profile = ma_result.get('profile', None)
if ma_discogs_url and ma_name:
l_as = lookup.artist_by_relation_url(ma_discogs_url)
l_a = None
if len(l_as) < 1:
l_a = Artist(name=ma_name, biography=ma_profile)
l_a.save()
rel = Relation(content_object=l_a, url=ma_discogs_url)
rel.save()
if len(l_as) == 1:
l_a = l_as[0]
print l_as[0]
if l_a:
ma = ArtistMembership.objects.get_or_create(parent=obj, child=l_a)
except:
pass
type = result.get('type', None)
if type:
log.debug('got type: %s' % (type))
obj.type = type
disambiguation = result.get('disambiguation', None)
if disambiguation:
log.debug('got disambiguation: %s' % (disambiguation))
obj.disambiguation = disambiguation
tags = result.get('tags', ())
for tag in tags:
log.debug('got tag: %s' % (tag['name']))
Tag.objects.add_tag(obj, '"%s"' % tag['name'])
# add mb relation
mb_url = 'http://musicbrainz.org/artist/%s' % (mb_id)
try:
rel = Relation.objects.get(object_id=obj.pk, url=mb_url)
except:
log.debug('relation not here yet, add it: %s' % (mb_url))
rel = Relation(content_object=obj, url=mb_url)
rel.save()
obj.save()
return obj
print ii_ids
ia = Artist.objects.filter(pk__in=ii_ids, name=artist)
print ia
log.info('found artist in import session: %s' % ia)
except:
ia = None
if ia and ia.count > 0:
a = ia[0]
# create artist if forced
if force_artist and not a:
log.info('artist, force creation: %s' % artist)
a = Artist(name=artist)
a.save()
a_created = True
# try to get artist by alibrary_id
if alibrary_artist_id and not a:
log.debug('artist, lookup by alibrary_artist_id: %s' % alibrary_artist_id)
try:
a = Artist.objects.get(pk=alibrary_artist_id)
log.debug('got artist: %s by alibrary_artist_id: %s' % (a.pk, alibrary_artist_id))
except Exception, e:
# print e
log.debug('could not get artist by alibrary_artist_id: %s' % alibrary_artist_id)
def mb_complete_artist(self, obj, mb_id):
log = logging.getLogger('util.importer.mb_complete_artist')
log.info('complete artist, a: %s | mb_id: %s' % (obj.name, mb_id))
self.mb_completed.append(mb_id)
inc = ('url-rels', 'tags')
url = 'http://%s/ws/2/artist/%s/?fmt=json&inc=%s' % (
MUSICBRAINZ_HOST, mb_id, "+".join(inc))
r = requests.get(url)
result = r.json()
print '#########################################################################'
self.pp.pprint(result)
discogs_url = None
discogs_image = None
valid_relations = (
'wikipedia',
'allmusic',
'BBC Music page',
'social network',
'official homepage',
'youtube',
'myspace',
)
relations = result.get('relations', ())
for relation in relations:
if relation['type'] == 'discogs':
log.debug('got discogs url for artist: %s' % relation['url'])
discogs_url = relation['url']
if relation['type'] in valid_relations:
log.debug('got %s url for artist: %s' %
(relation['type'], relation['url']))
try:
rel = Relation.objects.get(object_id=obj.pk,
url=relation['url'])
except:
rel = Relation(content_object=obj, url=relation['url'])
if relation['type'] == 'official homepage':
rel.service = 'official'
rel.save()
if discogs_url:
try:
rel = Relation.objects.get(object_id=obj.pk, url=discogs_url)
except:
rel = Relation(content_object=obj, url=discogs_url)
rel.save()
# try to get image
try:
discogs_image = discogs_image_by_url(discogs_url,
'resource_url')
log.debug('discogs image located at: %s' % discogs_image)
except:
pass
# try to load & assign image
if discogs_image:
try:
img = filer_extra.url_to_file(discogs_image, obj.folder)
obj.main_image = img
obj.save()
except:
log.info('unable to assign discogs image')
if discogs_url:
discogs_id = None
try:
# TODO: not sure if always working
discogs_id = discogs_id_by_url(discogs_url)
log.info('extracted discogs id: %s' % discogs_id)
except:
pass
if discogs_id:
url = 'http://api.discogs.com/artists/%s' % discogs_id
r = requests.get(url)
dgs_result = r.json()
self.pp.pprint(dgs_result)
"""
styles = dgs_result.get('styles', ())
for style in styles:
log.debug('got style: %s' % (style))
Tag.objects.add_tag(obj, '"%s"' % style)
"""
profile = dgs_result.get('profile', None)
if profile:
obj.biography = profile
realname = dgs_result.get('realname', None)
if realname:
obj.real_name = realname
"""
verry hackish part here, just as proof-of-concept
"""
aliases = dgs_result.get('aliases', ())
for alias in aliases:
try:
log.debug('got alias: %s' % alias['name'])
# TODO: improve! handle duplicates!
time.sleep(1.1)
r = requests.get(alias['resource_url'])
aa_result = r.json()
aa_discogs_url = aa_result.get('uri', None)
aa_name = aa_result.get('name', None)
aa_profile = aa_result.get('profile', None)
if aa_discogs_url and aa_name:
l_as = lookup.artist_by_relation_url(
aa_discogs_url)
l_a = None
if len(l_as) < 1:
l_a = Artist(name=aa_name,
biography=aa_profile)
l_a.save()
rel = Relation(content_object=l_a,
url=aa_discogs_url)
rel.save()
if len(l_as) == 1:
l_a = l_as[0]
print l_as[0]
if l_a:
obj.aliases.add(l_a)
except:
pass
"""
verry hackish part here, just as proof-of-concept
"""
members = dgs_result.get('members', ())
for member in members:
try:
log.debug('got member: %s' % member['name'])
# TODO: improve! handle duplicates!
time.sleep(1.1)
r = requests.get(member['resource_url'])
ma_result = r.json()
ma_discogs_url = ma_result.get('uri', None)
ma_name = ma_result.get('name', None)
ma_profile = ma_result.get('profile', None)
if ma_discogs_url and ma_name:
l_as = lookup.artist_by_relation_url(
ma_discogs_url)
l_a = None
if len(l_as) < 1:
l_a = Artist(name=ma_name,
biography=ma_profile)
l_a.save()
rel = Relation(content_object=l_a,
url=ma_discogs_url)
rel.save()
if len(l_as) == 1:
l_a = l_as[0]
print l_as[0]
if l_a:
ma = ArtistMembership.objects.get_or_create(
parent=obj, child=l_a)
except:
pass
type = result.get('type', None)
if type:
log.debug('got type: %s' % (type))
obj.type = type
disambiguation = result.get('disambiguation', None)
if disambiguation:
log.debug('got disambiguation: %s' % (disambiguation))
obj.disambiguation = disambiguation
tags = result.get('tags', ())
for tag in tags:
log.debug('got tag: %s' % (tag['name']))
Tag.objects.add_tag(obj, '"%s"' % tag['name'])
# add mb relation
mb_url = 'http://musicbrainz.org/artist/%s' % (mb_id)
try:
rel = Relation.objects.get(object_id=obj.pk, url=mb_url)
except:
log.debug('relation not here yet, add it: %s' % (mb_url))
rel = Relation(content_object=obj, url=mb_url)
rel.save()
obj.save()
return obj
def mb_complete_media(self, obj, mb_id, excludes=()):
log = logging.getLogger('util.importer.mb_complete_media')
log.info('complete media, m: %s | mb_id: %s' % (obj.name, mb_id))
#raw_input("Press Enter to continue...")
time.sleep(1.1)
inc = ('artists', 'url-rels', 'aliases', 'tags', 'recording-rels',
'artist-rels', 'work-level-rels', 'artist-credits')
url = 'http://%s/ws/2/recording/%s/?fmt=json&inc=%s' % (
MUSICBRAINZ_HOST, mb_id, "+".join(inc))
r = requests.get(url)
result = r.json()
print '*****************************************************************'
print '*****************************************************************'
print '*****************************************************************'
self.pp.pprint(result)
print '*****************************************************************'
print '*****************************************************************'
print '*****************************************************************'
# self.pp.pprint(result)
if 'relations' in result:
for relation in result['relations']:
# map artists
if 'artist' in relation:
print 'artist: %s' % relation['artist']['name']
print 'mb_id: %s' % relation['artist']['id']
print 'role: %s' % relation['type']
print
time.sleep(0.1)
l_as = lookup.artist_by_mb_id(relation['artist']['id'])
l_a = None
#if len(l_as) < 1 and relation['artist']['id'] not in self.mb_completed:
if len(l_as
) < 1 and relation['artist']['id'] not in excludes:
self.mb_completed.append(relation['artist']['id'])
l_a = Artist(name=relation['artist']['name'])
l_a.save()
url = 'http://musicbrainz.org/artist/%s' % relation[
'artist']['id']
print 'musicbrainz_url: %s' % url
rel = Relation(content_object=l_a, url=url)
rel.save()
print 'artist created'
if len(l_as) == 1:
print 'got artist!'
l_a = l_as[0]
print l_as[0]
profession = None
if 'type' in relation:
profession, created = Profession.objects.get_or_create(
name=relation['type'])
""""""
if l_a:
mea, created = MediaExtraartists.objects.get_or_create(
artist=l_a, media=obj, profession=profession)
l_a = self.mb_complete_artist(l_a,
relation['artist']['id'])
#self.pp.pprint(relation['artist']['name'])
tags = result.get('tags', ())
for tag in tags:
log.debug('got tag: %s' % (tag['name']))
Tag.objects.add_tag(obj, '"%s"' % tag['name'])
# add mb relation
mb_url = 'http://musicbrainz.org/recording/%s' % (mb_id)
try:
rel = Relation.objects.get(object_id=obj.pk, url=mb_url)
except:
log.debug('relation not here yet, add it: %s' % (mb_url))
rel = Relation(content_object=obj, url=mb_url)
rel.save()
return obj
print 'ii_ids: '
print ii_ids
ia = Artist.objects.filter(pk__in=ii_ids, name=artist)
print ia
log.info('found artist in import session: %s' % ia)
except:
ia = None
if ia and ia.count > 0:
a = ia[0]
# create artist if forced
if force_artist and not a:
log.info('artist, force creation: %s' % artist)
a = Artist(name=artist)
a.save()
a_created = True
# try to get artist by alibrary_id
if alibrary_artist_id and not a:
log.debug('artist, lookup by alibrary_artist_id: %s' %
alibrary_artist_id)
try:
a = Artist.objects.get(pk=alibrary_artist_id)
log.debug('got artist: %s by alibrary_artist_id: %s' %
(a.pk, alibrary_artist_id))
except Exception, e:
# print e
log.debug('could not get artist by alibrary_artist_id: %s' %
alibrary_artist_id)
def mb_complete_media_task(obj, mb_id, mb_release_id, excludes=()):
log = logging.getLogger('util.importer.mb_complete_media')
log.info('complete media, m: %s | mb_id: %s' % (obj.name, mb_id))
#raw_input("Press Enter to continue...")
time.sleep(1.1)
inc = ('artists', 'url-rels', 'aliases', 'tags', 'recording-rels', 'artist-rels', 'work-level-rels', 'artist-credits')
url = 'http://%s/ws/2/recording/%s/?fmt=json&inc=%s' % (MUSICBRAINZ_HOST, mb_id, "+".join(inc))
r = requests.get(url)
result = r.json()
print '*****************************************************************'
print url
print '*****************************************************************'
# get release based information (to map track- and disc-number)
inc = ('recordings',)
url = 'http://%s/ws/2/release/%s/?fmt=json&inc=%s' % (MUSICBRAINZ_HOST, mb_release_id, "+".join(inc))
r = requests.get(url)
result_release = r.json()
print '*****************************************************************'
print url
print '*****************************************************************'
print(result)
print
print(result_release)
print '*****************************************************************'
if DEBUG_WAIT:
raw_input("Press Enter to continue...")
# loop release recordings, trying to get our track...
if 'media' in result_release:
disc_index = 0
media_index = 0
media_offset = 0
for disc in result_release['media']:
for m in disc['tracks']:
x_mb_id = m['recording']['id']
x_pos = m['number']
if x_mb_id == mb_id:
"""
print 'id: %s' % x_mb_id
print 'pos: %s' % x_pos
print 'disc_index: %s' % disc_index
print 'media_offset: %s' % media_offset
print 'final pos: %s' % (int(media_offset) + int(x_pos))
"""
try:
obj.tracknumber = (int(media_offset) + int(x_pos))
except:
pass
try:
obj.mediamumber = int(disc_index)
except:
pass
media_index =+ 1
disc_index += 1
media_offset += int(disc['track-count'])
if DEBUG_WAIT:
raw_input("Press Enter to continue...")
if 'relations' in result:
for relation in result['relations']:
# map artists
if 'artist' in relation:
print 'artist: %s' % relation['artist']['name']
print 'mb_id: %s' % relation['artist']['id']
print 'role: %s' % relation['type']
print
time.sleep(0.1)
l_as = lookup.artist_by_mb_id(relation['artist']['id'])
l_a = None
if len(l_as) < 1 and relation['artist']['id'] not in excludes:
#instance.mb_completed.append(relation['artist']['id'])
l_a = Artist(name=relation['artist']['name'])
l_a.save()
url = 'http://musicbrainz.org/artist/%s' % relation['artist']['id']
print 'musicbrainz_url: %s' % url
rel = Relation(content_object=l_a, url=url)
rel.save()
print 'artist created'
if len(l_as) == 1:
print 'got artist!'
l_a = l_as[0]
print l_as[0]
profession = None
if 'type' in relation:
profession, created = Profession.objects.get_or_create(name=relation['type'])
""""""
if l_a:
mea, created = MediaExtraartists.objects.get_or_create(artist=l_a, media=obj, profession=profession)
if USE_CELERYD:
mb_complete_artist_task.delay(l_a, relation['artist']['id'])
else:
mb_complete_artist_task(l_a, relation['artist']['id'])
tags = result.get('tags', ())
for tag in tags:
log.debug('got tag: %s' % (tag['name']))
Tag.objects.add_tag(obj, '"%s"' % tag['name'])
# add mb relation
mb_url = 'http://musicbrainz.org/recording/%s' % (mb_id)
try:
rel = Relation.objects.get(object_id=obj.pk, url=mb_url)
except:
log.debug('relation not here yet, add it: %s' % (mb_url))
rel = Relation(content_object=obj, url=mb_url)
rel.save()
return obj
