def createGraphForEventArtistsAndGenres(store,repo_name,events):
count =0
allArtistUris = []
for event in events:
eventAlreadyExists = sesame_repository.doesEventWithIdExist(repo_name,event["id"])
if not eventAlreadyExists:
eventUriRef = URIRef("http://facebook.com/"+event["id"])
gevent = Graph(store=store,identifier=eventUriRef)
if "eventdata" in event.keys():
if("description" in event["eventdata"].keys()):
description = event["eventdata"]["description"]
genres = dbpedia.extractMusicGenreNamesFromText(description)
for dbpediaGenreUri in genres:
gevent.add((eventUriRef,ns["genre"],URIRef(dbpediaGenreUri)))
artists = dbpedia_spotlight.getArtistEntities(description)
for artistUri in artists:
gevent.add((eventUriRef,ns["relatedArtist"],URIRef(artistUri)))
if artistUri not in allArtistUris:
allArtistUris.append(artistUri)
count = count+1
# if count==15:
# break
print "processed artists for "+str(count)+" out of "+str(len(events))+" events"
# if count==2:
# break
#now add soundcloud tracks id data to all artists
count = 0
soundcloudClient = soundcloud_get_tracks.getSoundcloudClient()
for artistUri in allArtistUris:
extractArtistInfoAndAddToGraph(store,artistUri,soundcloudClient)
count = count+1
print "processed artist info for "+str(count)+" out of "+str(len(allArtistUris))+" artists"
def extractArtistsFromText(text): foundDbpediaArtists = dbpedia_spotlight.getArtistEntities(text) return foundDbpediaArtists