def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
artist = utilities.deAccent(lyrics.artist)
title = utilities.deAccent(lyrics.title)
try: # below is borowed from XBMC Lyrics
url = "http://www.lyricsmode.com/lyrics/%s/%s/%s.html" % (artist.lower()[:1], artist.lower().replace("&","and").replace(" ","_"), title.lower().replace("&","and").replace(" ","_"))
lyrics_found = False
while True:
utilities.log(debug, "%s: search url: %s" % (__title__, url))
song_search = urllib.urlopen(url).read()
if song_search.find("<p id=\"lyrics_text\" class=\"ui-annotatable\">") >= 0:
break
if lyrics_found:
# if we're here, we found the lyrics page but it didn't
# contains the lyrics part (licensing issue or some bug)
return False
# Let's try to use the research box if we didn't yet
if not 'search' in url:
url = "http://www.lyricsmode.com/search.php?what=songs&s=" + urllib.quote_plus(title.lower())
else:
# the search gave more than on result, let's try to find our song
url = ""
start = song_search.find('<!--output-->')
end = song_search.find('<!--/output-->', start)
results = self.search_results_regex.findall(song_search, start, end)
for result in results:
if result[0].lower() in artist.lower():
url = "http://www.lyricsmode.com" + result[1]
lyrics_found = True
break
if not url:
# Is there a next page of results ?
match = self.next_results_regex.search(song_search[end:])
if match:
url = "http://www.lyricsmode.com/search.php" + match.group(1)
else:
return False
lyr = song_search.split("<p id=\"lyrics_text\" class=\"ui-annotatable\">")[1].split('</p><p id=\"lyrics_text_selected\">')[0]
lyr = self.clean_br_regex.sub( "\n", lyr ).strip()
lyr = self.clean_lyrics_regex.sub( "", lyr ).strip()
lyr = self.normalize_lyrics_regex.sub( lambda m: unichr( int( m.group( 1 ) ) ), lyr.decode("ISO-8859-1") )
lir = []
for line in lyr.splitlines():
line.strip()
if line.find("Lyrics from:") < 0:
lir.append(line)
lyr = u"\n".join( lir )
if lyr.startswith('These lyrics are missing'):
return False
lyrics.lyrics = lyr
return True
except:
utilities.log(True, "%s: %s::%s (%d) [%s]" % (
__title__, self.__class__.__name__,
sys.exc_info()[ 2 ].tb_frame.f_code.co_name,
sys.exc_info()[ 2 ].tb_lineno,
sys.exc_info()[ 1 ]
))
return False
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
artist = utilities.deAccent(lyrics.artist)
title = utilities.deAccent(lyrics.title)
try: # below is borowed from XBMC Lyrics
url = "http://www.lyricsmode.com/lyrics/%s/%s/%s.html" % (
artist.lower()[:1], artist.lower().replace("&", "and").replace(
" ", "_"), title.lower().replace("&", "and").replace(
" ", "_"))
lyrics_found = False
while True:
utilities.log(debug, "%s: search url: %s" % (__title__, url))
song_search = urllib.urlopen(url).read()
if song_search.find(
"<p id=\"lyrics_text\" class=\"ui-annotatable\">"
) >= 0:
break
if lyrics_found:
# if we're here, we found the lyrics page but it didn't
# contains the lyrics part (licensing issue or some bug)
return False
# Let's try to use the research box if we didn't yet
if not 'search' in url:
url = "http://www.lyricsmode.com/search.php?what=songs&s=" + urllib.quote_plus(
title.lower())
else:
# the search gave more than on result, let's try to find our song
url = ""
start = song_search.find('<!--output-->')
end = song_search.find('<!--/output-->', start)
results = self.search_results_regex.findall(
song_search, start, end)
for result in results:
if result[0].lower() in artist.lower():
url = "http://www.lyricsmode.com" + result[1]
lyrics_found = True
break
if not url:
# Is there a next page of results ?
match = self.next_results_regex.search(
song_search[end:])
if match:
url = "http://www.lyricsmode.com/search.php" + match.group(
1)
else:
return False
lyr = song_search.split(
"<p id=\"lyrics_text\" class=\"ui-annotatable\">")[1].split(
'</p><p id=\"lyrics_text_selected\">')[0]
lyr = self.clean_br_regex.sub("\n", lyr).strip()
lyr = self.clean_lyrics_regex.sub("", lyr).strip()
lyr = self.normalize_lyrics_regex.sub(
lambda m: unichr(int(m.group(1))), lyr.decode("ISO-8859-1"))
lir = []
for line in lyr.splitlines():
line.strip()
if line.find("Lyrics from:") < 0:
lir.append(line)
lyr = u"\n".join(lir)
if lyr.startswith('These lyrics are missing'):
return False
lyrics.lyrics = lyr
return True
except:
utilities.log(
True, "%s: %s::%s (%d) [%s]" %
(__title__, self.__class__.__name__,
sys.exc_info()[2].tb_frame.f_code.co_name,
sys.exc_info()[2].tb_lineno, sys.exc_info()[1]))
return False