So that was the hard way to get data. Now, lets access rap lyrics the easy way using an api that was written for rap genius, courtesy Ed Forson, you can read more about it http://genius-api.com/
In [ ]:
import urllib
import urllib2
import json
import pprint #for pretty print of json files
url = 'http://genius-api.com/api/artistInfo'
values = {'name' : 'Gza',
'genre' : 'rap'}
data = urllib.urlencode(values)
req = urllib2.Request(url, data)
In [ ]:
response = urllib2.urlopen(req)
In [ ]:
the_page = response.read()
In [ ]:
decoded_data = json.loads(the_page)
In [ ]:
print json.dumps(decoded_data, sort_keys=True, indent=4)
In [ ]:
decoded_data.viewkeys()
In [ ]:
print json.dumps(decoded_data.get('songs'), sort_keys=True, indent=4)
In [ ]:
song_url = 'http://genius-api.com/api/songInfo' #Song information
artist_url = 'http://genius-api.com/api/artistInfo' #artist info
values = {'name' : 'Liquid Swords',
'genre' : 'rap'}
In [ ]:
data = urllib.urlencode(values)
req = urllib2.Request(song_url, data)
In [ ]:
response = urllib2.urlopen(req)
In [ ]:
song_info = response.read()
In [ ]:
decoded_data = json.loads(song_info)
In [ ]:
print json.dumps(decoded_data, sort_keys=True, indent=4)
In [ ]:
lyric_url = 'http://genius-api.com/api/lyricsInfo'
parameters = {'link':'http://rapgenius.com/Gza-liquid-swords-lyrics',
'genre' : 'rap'}
data = urllib.urlencode(parameters)
In [ ]:
req = urllib2.Request(lyric_url, data)
response = urllib2.urlopen(req)
lyric_info = response.read()
decoded_data = json.loads(lyric_info)
In [ ]:
print json.dumps(decoded_data, sort_keys=True, indent=4)
In [ ]:
decoded_data.viewkeys()
In [ ]:
print json.dumps(decoded_data.get('lyrics'), sort_keys=True, indent=4)
In [ ]:
Data_under_investigation = decoded_data.get('lyrics')
In [ ]:
Data_under_investigation.viewkeys()
In [ ]:
Data_under_investigation = decoded_data.get('lyrics').get('sections')
In [ ]:
print json.dumps(Data_under_investigation, sort_keys=True, indent=4)
In [ ]:
len(Data_under_investigation)
In [ ]:
print json.dumps(Data_under_investigation[0].get('verses')[0].get('content'), sort_keys=True, indent=4)
In [ ]:
print Data_under_investigation[1].get('verses')[0].get('content')
In [ ]:
len(Data_under_investigation)