def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN + artist_tuple[1]))
albums = soup.select('span.mw-headline')
if not album_tuple[
0]: # If album has no name and is in a "Other Songs" category
for album in albums:
if not album('a'):
songs = album.parent
elif not album_tuple[1]: # If album has a name, but no link to go to
for album in albums:
if album('a')[0].string == album_tuple[0]:
songs = album.parent
else:
songs = soup.select('a[href=%s]' % album_tuple[1])[0].parent.parent
while (type(songs) is not Tag) or (songs.name != 'ol'
and songs.name != 'ul'):
try:
songs = songs.nextSibling
if type(songs) is Tag and songs.name == 'h2':
raise AttributeError
except AttributeError:
songs = None
break
ret = []
if songs:
for song in songs('a'):
if song['href'].find('action=edit') > -1:
continue
ret.append((song.string, song['href']))
return ret
def getArtists():
soup = BeautifulSoup(
getHtml('http://www.uta-net.com/user/search_index/name.html'))
artists = soup.select('.album td a')
return [(artist.string,
'http://www.uta-net.com/user/search_index/' + artist['href'])
for artist in artists]
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL+album_tuple[1]))
albums = soup.select('.album')
for album in albums:
if album.h2.strong.string[1:-1] == album_tuple[0]:
return [(song.string, song['href'][3:-2]) for song in album.select('a')]
return None
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN+artist_tuple[1]))
albums = soup.select('span.mw-headline')
if not album_tuple[0]: # If album has no name and is in a "Other Songs" category
for album in albums:
if not album('a'):
songs = album.parent
elif not album_tuple[1]: # If album has a name, but no link to go to
for album in albums:
if album('a')[0].string == album_tuple[0]:
songs = album.parent
else:
songs = soup.select('a[href=%s]'%album_tuple[1])[0].parent.parent
while (type(songs) is not Tag) or (songs.name != 'ol' and songs.name != 'ul'):
try:
songs = songs.nextSibling
if type(songs) is Tag and songs.name == 'h2':
raise AttributeError
except AttributeError:
songs = None
break
ret = []
if songs:
for song in songs('a'):
if song['href'].find('action=edit') > -1:
continue
ret.append((song.string, song['href']))
return ret
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL + album_tuple[1]))
albums = soup.select('.album')
for album in albums:
if album.h2.strong.string[1:-1] == album_tuple[0]:
return [(song.string, song['href'][3:-2])
for song in album.select('a')]
return None
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL+song_tuple[1]))
songs = soup.select('.lyrics h3')
for song in songs:
if song.string[song.string.index(' ')+1:] == song_tuple[0]:
lyrics = []
while song.next_sibling.name not in ['h3','div','a']:
song = song.next_sibling
lyrics += [song]
return cleanLyricList(lyrics)
return None
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(artist_tuple[1]))
albums = soup.select('.sidebar_right_2c a')
ret = []
for album in albums:
try:
ret.append((album.img['title'], album['href']))
except Exception as e:
# This just means its not an album
pass # PASSU
return ret
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(artist_tuple[1]))
albums = soup.select('.sidebar_right_2c a')
ret = []
for album in albums:
try:
ret.append((album.img['title'], album['href']))
except Exception as e:
# This just means its not an album
pass # PASSU
return ret
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL + song_tuple[1]))
songs = soup.select('.lyrics h3')
for song in songs:
if song.string[song.string.index(' ') + 1:] == song_tuple[0]:
lyrics = []
while song.next_sibling.name not in ['h3', 'div', 'a']:
song = song.next_sibling
lyrics += [song]
return cleanLyricList(lyrics)
return None
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(album_tuple[1]).decode('shift_jisx0213'), "html.parser")
albums = soup.select('td.font_base_size_L strong')
for album in albums:
if album.string == album_tuple[0]:
songs = album.find_parent("table").find_parent("table").select('.font_base_size a')
for song in songs:
subtags = song.select('*')
for tag in subtags:
tag.extract()
return [(song.string, 'http://sp.uta-net.com/search/kashi.php?TID='+song['href'][song['href'].index('ID=')+3:]) for song in songs]
return []
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN+song_tuple[1]))
lyricsdiv = soup.select('div.lyricbox')[0]
if lyricsdiv.select('a[href=/Category:Instrumental]'):
lyrics = "(Instrumental)"
else:
# Remove divs and crap from wiki lyrics box
for div in lyricsdiv('div'):
div.extract()
comments = lyricsdiv.find_all(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
return unescape(cleanLyricList(lyricsdiv.contents))
def getArtists():
ret = []
# Artist pages indexed by start letter
page_list = [chr(i) for i in range(97, 123)] + ['19']
for page in page_list:
sys.stdout.write(page)
sys.stdout.flush()
soup = BeautifulSoup(getHtml(DARKLYRICS_URL + page + ".html"))
artists = soup.select('.artists.fl a[href^=' + page + '/]')
ret += [(artist.string.title(), artist['href']) for artist in artists]
artists = soup.select('.artists.fr a[href^=' + page + '/]')
ret += [(artist.string.title(), artist['href']) for artist in artists]
# break
return ret
def getArtists():
ret = []
# Artist pages indexed by start letter
page_list = [chr(i) for i in range(97,123)] + ['19']
for page in page_list:
sys.stdout.write(page)
sys.stdout.flush()
soup = BeautifulSoup(getHtml(DARKLYRICS_URL + page + ".html"))
artists = soup.select('.artists.fl a[href^='+page+'/]')
ret += [(artist.string.title(), artist['href']) for artist in artists]
artists = soup.select('.artists.fr a[href^='+page+'/]')
ret += [(artist.string.title(), artist['href']) for artist in artists]
# break
return ret
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN + song_tuple[1]))
lyricsdiv = soup.select('div.lyricbox')[0]
if lyricsdiv.select('a[href=/Category:Instrumental]'):
lyrics = "(Instrumental)"
else:
# Remove divs and crap from wiki lyrics box
for div in lyricsdiv('div'):
div.extract()
comments = lyricsdiv.find_all(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
return unescape(cleanLyricList(lyricsdiv.contents))
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN+artist_tuple[1]))
albums = soup.select('span.mw-headline')
ret = []
for album in albums:
album_url = None
if album('a'):
album_name = album('a')[0].string
album_url = album('a')[0]['href']
else:
album_name = None
if album_url and album_url.find('action=edit') != -1:
album_url = None
ret.append((album_name, album_url))
return ret
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(WIKIA_DOMAIN + artist_tuple[1]))
albums = soup.select('span.mw-headline')
ret = []
for album in albums:
album_url = None
if album('a'):
album_name = album('a')[0].string
album_url = album('a')[0]['href']
else:
album_name = None
if album_url and album_url.find('action=edit') != -1:
album_url = None
ret.append((album_name, album_url))
return ret
def scrape():
next_song = WIKI_URL
d = datetime.datetime.now()
timestamp = '{:%Y-%m-%d_%H:%M:%S}'.format(d)
filename = 'lyricwiki_' + timestamp + '.json'
while next_song:
soup = BeautifulSoup(getHtml(next_song))
artists_a = soup.select('div#mw-pages')[0]('a')
artists = [(artist.string, artist['href']) for artist in artists_a]
sj = ScrapeJam(filename, 'lyricwiki_errs.log')
sj.scrape(artists, getAlbums, getSongs, getLyrics)
next_song = BASE_URL + soup.select('div#mw-pages')[0]('a')[0]['href']
if not 'pagefrom' in next_song:
break
def scrape():
next_song = WIKI_URL
d = datetime.datetime.now()
timestamp = '{:%Y-%m-%d_%H:%M:%S}'.format(d)
filename = 'lyricwiki_' + timestamp + '.json'
while next_song:
soup = BeautifulSoup(getHtml(next_song))
artists_a = soup.select('div#mw-pages')[0]('a')
artists = [(artist.string, artist['href']) for artist in artists_a]
sj = ScrapeJam(filename, 'lyricwiki_errs.log')
sj.scrape(artists, getAlbums, getSongs, getLyrics)
next_song = BASE_URL + soup.select('div#mw-pages')[0]('a')[0]['href']
if not 'pagefrom' in next_song:
break
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(song_tuple[1], False,
'Mozilla/5.0 (Linux; U; Android 4.0.3; ko-kr; LG-L160L Build/IML74K) AppleWebkit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'))
lyrics = soup.select('#kashi_main')[0]
lyrics.div.extract()
return cleanLyricList(lyrics.contents)
songs = soup.select('.lyrics h3')
for song in songs:
if song.string[song.string.index(' ')+1:] == song_tuple[0]:
lyrics = []
while song.next_sibling.name not in ['h3','div','a']:
song = song.next_sibling
lyrics += [song]
return cleanLyricList(lyrics)
return ""
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(
getHtml(album_tuple[1]).decode('shift_jisx0213'), "html.parser")
albums = soup.select('td.font_base_size_L strong')
for album in albums:
if album.string == album_tuple[0]:
songs = album.find_parent("table").find_parent("table").select(
'.font_base_size a')
for song in songs:
subtags = song.select('*')
for tag in subtags:
tag.extract()
return [
(song.string, 'http://sp.uta-net.com/search/kashi.php?TID=' +
song['href'][song['href'].index('ID=') + 3:])
for song in songs
]
return []
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(
getHtml(
song_tuple[1], False,
'Mozilla/5.0 (Linux; U; Android 4.0.3; ko-kr; LG-L160L Build/IML74K) AppleWebkit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'
))
lyrics = soup.select('#kashi_main')[0]
lyrics.div.extract()
return cleanLyricList(lyrics.contents)
songs = soup.select('.lyrics h3')
for song in songs:
if song.string[song.string.index(' ') + 1:] == song_tuple[0]:
lyrics = []
while song.next_sibling.name not in ['h3', 'div', 'a']:
song = song.next_sibling
lyrics += [song]
return cleanLyricList(lyrics)
return ""
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL+artist_tuple[1]))
albums = soup.select('.album h2 strong')
return [(album.string[1:-1], artist_tuple[1]) for album in albums]
def getArtists():
soup = BeautifulSoup(getHtml('http://www.uta-net.com/user/search_index/name.html'))
artists = soup.select('.album td a')
return [(artist.string, 'http://www.uta-net.com/user/search_index/'+artist['href']) for artist in artists]
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(artist_tuple[1]).decode('shift_jisx0213'), "html.parser")
albums = soup.select('td.font_base_size_L strong')
return [(album.string, artist_tuple[1]) for album in albums]
def getAlbums(artist_tuple):
soup = BeautifulSoup(getHtml(DARKLYRICS_URL + artist_tuple[1]))
albums = soup.select('.album h2 strong')
return [(album.string[1:-1], artist_tuple[1]) for album in albums]
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(NIGHTWISH_URL+album_tuple[1]))
songs = soup.select('.box250 .textsmall li a')
return [(song.string, song['href']) for song in songs]
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(NIGHTWISH_URL + song_tuple[1]))
lyricsoup = soup.select('.content_main_2c .text')[0]
return cleanLyricList(lyricsoup.contents)
def getSongs(artist_tuple, album_tuple):
soup = BeautifulSoup(getHtml(NIGHTWISH_URL + album_tuple[1]))
songs = soup.select('.box250 .textsmall li a')
return [(song.string, song['href']) for song in songs]
def getLyrics(artist_tuple, album_tuple, song_tuple):
soup = BeautifulSoup(getHtml(NIGHTWISH_URL+song_tuple[1]))
lyricsoup = soup.select('.content_main_2c .text')[0]
return cleanLyricList(lyricsoup.contents)
def getAlbums(artist_tuple):
soup = BeautifulSoup(
getHtml(artist_tuple[1]).decode('shift_jisx0213'), "html.parser")
albums = soup.select('td.font_base_size_L strong')
return [(album.string, artist_tuple[1]) for album in albums]
