Created
November 20, 2010 17:57
-
-
Save valpackett/708012 to your computer and use it in GitHub Desktop.
Fetching full lyrics from LyricWiki
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(* | |
Getting Lyrics | |
by myfreeweb | |
thanks to pepelsbey for "Year to Album Sort", based on it | |
*) | |
tell application "iTunes" | |
set sel to selection | |
if sel is not {} then | |
set ofi to fixed indexing | |
set fixed indexing to true | |
repeat with thisTrack in sel | |
try | |
tell thisTrack to set lyrics to my {do shell script "getlyrics.py '" & artist & "' '" & name & "'"} | |
on error m | |
log m | |
end try | |
end repeat | |
set fixed indexing to ofi | |
else | |
display dialog return & "Select tracks" buttons {"Cancel"} default button 1 with icon 0 giving up after 15 | |
return | |
end if | |
end tell |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
import urllib2 | |
from BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Comment | |
from soupselect import select # http://code.google.com/p/soupselect/ | |
def get_lyrics(artist, track): | |
"""Fetches lyric page from LyricsWiki, parses it, | |
returns the lyrics. | |
""" | |
try: | |
src = urllib2.urlopen('http://lyrics.wikia.com/%s:%s' % ( | |
artist.replace(' ', '_'), track.replace(' ', '_'))) | |
parsed = BeautifulSoup(src) | |
comments = parsed.findAll(text=lambda text:isinstance(text, Comment)) | |
ringtones = parsed.findAll(attrs={'class': 'rtMatcher'}) | |
[node.extract() for node in comments + ringtones] | |
box = select(parsed, '.lyricbox')[0] | |
text = unicode(box.decodeContents()).replace('<br />', '\n') | |
text = BeautifulStoneSoup(text, convertEntities=BeautifulStoneSoup.HTML_ENTITIES) | |
except: | |
text = '' | |
return text | |
if __name__ == '__main__': | |
if len(sys.argv) != 3: | |
print "Wrong args. Syntax: getlyrics.py \"artist\" \"track\"" | |
else: | |
print get_lyrics(sys.argv[1], sys.argv[2]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment