def download_lyrics(artist_name):
word_to_indices = {}
title_to_lines = {}
song_lyrics = pylyrics3.get_artist_lyrics(artist_name)
for title, lyrics in song_lyrics.items():
lines = split_lines(lyrics)
title_to_lines[title] = lines
add_word_indices_to_dict(title, lines, word_to_indices)
write_out_json(artist_name, word_to_indices, title_to_lines)
def getlyrics():
blinklyrics = pylyrics3.get_artist_lyrics('Blink-182')
for k, v in blinklyrics.items():
print(v)
with open('blinklyrics.txt', 'w') as file:
file.write(json.dumps(blinklyrics))
with open("blinklyric.txt", 'w') as f:
for value in blinklyrics.items():
f.write(value)
def save_manowar_lyrics():
manowar_lyrics = pylyrics3.get_artist_lyrics('manowar')
# filter non-english
filtered = {
song: lyrics
for song, lyrics in manowar_lyrics.items() if 'Version' not in song
}
with path('data', 'manowar.json') as file_path:
with open(file_path, 'w', encoding='utf-8') as file:
json.dump(filtered, file)
def get_lyrics(artist_name): # Gets raw lyrics in lowercase.
albums = {}
artist_lyrics = pylyrics3.get_artist_lyrics(artist_name, albums=True)
for album_key, album_val in artist_lyrics.items():
albums[album_key] = {}
for track_key, track_val in album_val.items():
if track_val:
albums[album_key][track_key] = track_val.lower()
return albums
def get_lyrics(artist):
try:
filename = artist.replace(" ", "_") # No spaces in filename
if "/" in filename: # Prevent making another directory for names such as AC/DC
filename = filename.replace("/", "-")
if Path('database/' + filename).exists(
): # Prevent double work (remove a file if you want to rebuild its DB)
print("Database for " + filename + " is already there.")
else:
print("Writing database for " + filename)
with open('database/' + filename, 'w') as file:
lyrics = pylyrics3.get_artist_lyrics(artist)
for x in lyrics:
file.write(lyrics[x]) # Write all lyrics to file
except Exception as error:
print(artist + " threw an exception")
print(error)
def scrape_lyrics(artist, genre):
"""TODO: Wrapper for pylyrics3 query
:artist: artist name (string)
:genre: genre (string)
:returns: returns a list of lists with artist name, genre, song name and lyrics.
"""
holder = []
tmp_artist_songs = pyl.get_artist_lyrics(artist)
total_songs = len(tmp_artist_songs)
song_counter = 0
for song in tqdm(tmp_artist_songs):
print("Scraping {} - {} out of {}".format(song, song_counter,
total_songs))
song_counter += 1
tmp_song_array = [artist, genre, song, tmp_artist_songs[song]]
holder.append(tmp_song_array)
return holder
def download_artist_lyrics(argv):
os.mkdir(argv)
lyrics = pyl.get_artist_lyrics(argv)
f = open('../data/' + argv + '.txt', 'w')
json.dump(lyrics, f)
def test_compound_artist(self):
'''Test that collaborative songs ("Artist1 & Artist2") are included '''
l = pylyrics3.get_artist_lyrics('bon iver')
# typo on lyricwiki :(
self.assertTrue('Roslyn' in l.keys() or 'Rosyln' in l.keys())
def test_singles_and_soundtracks(self):
'''Certan artists were throwing a TypeError on a None response, in
addition to not including singles and soundtrack sections.'''
l = pylyrics3.get_artist_lyrics('troye sivan')
self.assertTrue('Strawberries & Cigarettes' in l)
newData = pd.DataFrame(columns=[
'Artist', 'Genre', 'Band Popularity', 'Song', 'Year', 'Song Popularity',
'Lyrics', 'pyYear', 'pyLyrics'
])
numMatched = 0
for idx, artist in enumerate(artists):
# if idx > 50:
# break
print("Getting data for %s, artist %d of %d: %f s" %
(artist, idx, len(artists), time.time() - start))
artistSongs = data.loc[data['Artist'] == artist]
artist_clean = artist.strip().lower().replace(',', '')
try:
songdict = pylyrics3.get_artist_lyrics(artist_clean, albums=True)
if songdict != None:
numMatched += 1
pyArtistSongs, pyArtistYears, lyrics = generateSongList(songdict)
pyYear = []
pyLyrics = []
for idx, song in enumerate(artistSongs['Song']):
songLower = re.sub('[\n?()\"\'-,.#$%~@^&*_+={};:<>]', '', song)
songLower = songLower.lower()
if songLower in pyArtistSongs:
pyYear.append(
pyArtistYears[pyArtistSongs.index(songLower)])
pyLyrics.append(lyrics[pyArtistSongs.index(songLower)])
else:
def test_album(self):
'''PyLyrics3 parses albums with tracks'''
bon_iver = pylyrics3.get_artist_lyrics('Bon Iver', albums=True)
self.assertTrue('22, a Million (2016)' in bon_iver)
self.assertTrue(len(bon_iver['22, a Million (2016)']) > 2)
import os
import pylyrics3 as pl
directory = "./lyrics/"
if not os.path.exists(directory):
os.makedirs(directory)
search = pl.get_artist_lyrics("The wonder years")
for i in search.keys():
songname = i
lyrics = search[i]
file = open(directory + songname + ".txt", "w")
file.write(i + "\n\n")
file.write("-------------------------------\n\n")
file.write(lyrics)
file.close()
if c in str(validFilenameChars))
artist_list = "../data/hiphop_artists.txt"
with open(artist_list, "r") as f:
data = f.readlines()
for line in data:
artists.append(line.strip())
print(artists)
lyrics = {}
i = 0
for artist in artists:
print(artist)
dictionary = pylyrics3.get_artist_lyrics(artist)
artist = removeDisallowedFilenameChars(artist)
if dictionary is not None:
print("==========================")
lyrics[artist] = dictionary
j = 0
for song in dictionary:
song_file = removeDisallowedFilenameChars(song)
print(song)
filename = "../data/hiphopdata" + slugify(artist) + "/" + slugify(
song_file) + ".txt"
if not os.path.exists(os.path.dirname(filename)):
try:
os.makedirs(os.path.dirname(filename))
def test_album(self):
'''PyLyrics3 parses albums with tracks'''
bon_iver = pylyrics3.get_artist_lyrics('Bon Iver', albums=True)
self.assertTrue('22, a Million (2016)' in bon_iver)
self.assertTrue(len(bon_iver['22, a Million (2016)']) > 2)
def test_get_artist(self):
'''PyLyrics3 can grab all tracks by an artist + odd capitalization'''
l = pylyrics3.get_artist_lyrics('lORDE')
self.assertTrue('Tennis Court' in l)
self.assertTrue('you think that' in l['Tennis Court'])
def test_get_artist(self):
'''PyLyrics3 can grab all tracks by an artist + odd capitalization'''
l = pylyrics3.get_artist_lyrics('lORDE')
self.assertTrue('Tennis Court' in l)
self.assertTrue('you think that' in l['Tennis Court'])
import pylyrics3
import string
artist = 'bon iver'
file = artist.replace(" ", "_")
file2 = artist.replace(" ", "_") + "_stripped"
lyrics = pylyrics3.get_artist_lyrics(artist)
def scrape(outputfile):
with open(outputfile, 'w') as db:
for x in lyrics:
db.write(lyrics[x])
# remove duplicate lines an punctuation
def remove_dupes(inputfile, outputfile):
lines_seen = set() # holds lines already seen
outfile = open(outputfile, "a")
remove = dict.fromkeys(map(ord, string.punctuation)) # remove punctuation
for line in open(inputfile, "r"):
if line not in lines_seen: # not a duplicate
outfile.write(line.translate(remove))
lines_seen.add(line)
outfile.close()
scrape(file)
remove_dupes(file, file2)