def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
url = self.BASE_URL % (lyrics.title, lyrics.artist)
utilities.log(debug, "%s: searching url %s" % (__title__, url))
data = urllib.urlopen(url).read()
songmatch = re.search('song-title.*?<em>(.*?)</em>',
data,
flags=re.DOTALL)
track = songmatch.group(1)
artistmatch = re.search('artist-title.*?<em>(.*?)</em>',
data,
flags=re.DOTALL)
name = artistmatch.group(1)
urlmatch = re.search("down-lrc-btn.*?':'(.*?)'",
data,
flags=re.DOTALL)
found_url = urlmatch.group(1)
if (difflib.SequenceMatcher(None, lyrics.artist.lower(),
name.lower()).ratio() > 0.8
) and (difflib.SequenceMatcher(None, lyrics.title.lower(),
track.lower()).ratio() > 0.8):
lyr = urllib.urlopen(self.LRC_URL % found_url).read()
else:
return False
except:
return False
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
url = 'http://www.lyrdb.com/karaoke/?q=%s+%s&action=search' %(lyrics.artist.replace(' ','+').lower(), lyrics.title.replace(' ','+').lower())
f = urllib.urlopen(url)
Page = f.read()
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
links_query = re.compile('<tr><td class="tresults"><a href="/karaoke/([0-9]+).htm">(.*?)</td><td class="tresults">(.*?)</td>')
urls = re.findall(links_query, Page)
links = []
for x in urls:
if (difflib.SequenceMatcher(None, song.artist.lower(), x[2].lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, song.title.lower(), x[1].lower()).ratio() > 0.8):
links.append( ( x[2] + ' - ' + x[1], x[0], x[2], x[1] ) )
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
lyr = self.get_lyrics_from_list(links[0])
if not lyr:
return False
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
filename = lyrics.filename.decode("utf-8")
ext = os.path.splitext(filename)[1].lower()
lry = None
try:
if ext == '.mp3':
lry = getLyrics3(filename)
except:
pass
if lry:
enc = chardet.detect(lry)
lyrics.lyrics = lry.decode(enc['encoding'])
else:
if ext == '.mp3':
lry = getID3Lyrics(filename)
elif ext == '.flac':
lry = getFlacLyrics(filename)
elif ext == '.m4a':
lry = getMP4Lyrics(filename)
if not lry:
return False
lyrics.lyrics = lry
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
filename = lyrics.filename.decode("utf-8")
ext = os.path.splitext(filename)[1].lower()
lry = None
try:
if ext == '.mp3':
lry = getLyrics3(filename)
except:
pass
if lry:
enc = chardet.detect(lry)
lyrics.lyrics = lry.decode(enc['encoding'])
else:
if ext == '.mp3':
lry = getID3Lyrics(filename)
elif ext == '.flac':
lry = getFlacLyrics(filename)
elif ext == '.m4a':
lry = getMP4Lyrics(filename)
if not lry:
return False
lyrics.lyrics = lry
return True
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
headers = {'Content-Type': 'text/xml; charset=utf-8'}
request = urllib2.Request(
ALSONG_URL, ALSONG_TMPL % (lyrics.title, lyrics.artist),
headers)
response = urllib2.urlopen(request)
Page = response.read()
except:
return False
tree = xml.parseString(Page)
try:
name = tree.getElementsByTagName(
'strArtistName')[0].childNodes[0].data
track = tree.getElementsByTagName('strTitle')[0].childNodes[0].data
except:
return False
if (difflib.SequenceMatcher(
None, lyrics.artist.lower(),
name.lower()).ratio() > 0.8) and (difflib.SequenceMatcher(
None, lyrics.title.lower(), track.lower()).ratio() > 0.8):
lyr = tree.getElementsByTagName(
'strLyric')[0].childNodes[0].data.replace('<br>', '\n')
lyrics.lyrics = lyr.encode('utf-8')
return True
return False
def buildLyrics(lyrics):
from lxml import etree
xml = etree.XML(u'<lyrics></lyrics>')
etree.SubElement(xml, "artist").text = lyrics.artist
etree.SubElement(xml, "album").text = lyrics.album
etree.SubElement(xml, "title").text = lyrics.title
etree.SubElement(
xml, "syncronized").text = 'True' if __syncronized__ else 'False'
etree.SubElement(xml, "grabber").text = lyrics.source
lines = lyrics.lyrics.splitlines()
for line in lines:
line2 = re.sub(
u'[^\u0020-\uD7FF\u0009\u000A\u000D\uE000-\uFFFD\u10000-\u10FFFF]+',
'', line)
etree.SubElement(xml, "lyric").text = line2
utilities.log(
True,
utilities.convert_etree(
etree.tostring(xml,
encoding='UTF-8',
pretty_print=True,
xml_declaration=True)))
sys.exit(0)
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
url = self.BASE_URL % (urllib.quote(
lyrics.title), urllib.quote((lyrics.artist)))
xml_str = urllib.urlopen(url).read()
lrcid_pattern = re.compile(r'<lrcid>(.+?)</lrcid>')
lrcid = int(re.search(lrcid_pattern, xml_str).group(1))
if lrcid == 0:
return False
lrc_url = self.LRC_URL % (lrcid / 100, lrcid)
lyr = urllib.urlopen(lrc_url).read()
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
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
url = self.BASE_URL % (urllib.quote(lyrics.title), urllib.quote((lyrics.artist)))
xml_str = urllib.urlopen(url).read()
lrcid_pattern = re.compile(r'<lrcid>(.+?)</lrcid>')
lrcid = int(re.search(lrcid_pattern, xml_str).group(1))
if lrcid == 0:
return False
lrc_url = self.LRC_URL % (lrcid/100, lrcid)
lyr = urllib.urlopen(lrc_url).read()
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
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
# replace ampersands and the like
for exp in LYRIC_ARTIST_REPLACE:
p = re.compile(exp[0])
artist = p.sub(exp[1], lyrics.artist)
for exp in LYRIC_TITLE_REPLACE:
p = re.compile(exp[0])
title = p.sub(exp[1], lyrics.title)
# strip things like "(live at Somewhere)", "(accoustic)", etc
for exp in LYRIC_TITLE_STRIP:
p = re.compile(exp)
title = p.sub('', title)
# compress spaces
title = title.strip().replace('`', '').replace('/', '')
artist = artist.strip().replace('`', '').replace('/', '')
try:
url = self.LIST_URL % (
ttpClient.EncodeArtTit(artist.replace(' ', '').lower()),
ttpClient.EncodeArtTit(title.replace(' ', '').lower()))
f = urlopen(url)
Page = f.read().decode('utf-8')
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
links_query = re.compile(
'<lrc id=\"(.*?)\" artist=\"(.*?)\" title=\"(.*?)\"></lrc>')
urls = re.findall(links_query, Page)
links = []
for x in urls:
if (difflib.SequenceMatcher(None, artist.lower(),
x[1].lower()).ratio()
> 0.8) and (difflib.SequenceMatcher(
None, title.lower(), x[2].lower()).ratio() > 0.8):
links.append((x[1] + ' - ' + x[2], x[0], x[1], x[2]))
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
for link in links:
lyr = self.get_lyrics_from_list(link)
if lyr and lyr.startswith(b'['):
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
return False
def main():
global debug
parser = OptionParser()
parser.add_option('-v', "--version", action="store_true", default=False,
dest="version", help="Display version and author")
parser.add_option('-t', "--test", action="store_true", default=False,
dest="test", help="Perform self-test for dependencies.")
parser.add_option('-s', "--search", action="store_true", default=False,
dest="search", help="Search for lyrics.")
parser.add_option('-a', "--artist", metavar="ARTIST", default=None,
dest="artist", help="Artist of track.")
parser.add_option('-b', "--album", metavar="ALBUM", default=None,
dest="album", help="Album of track.")
parser.add_option('-n', "--title", metavar="TITLE", default=None,
dest="title", help="Title of track.")
parser.add_option('-f', "--filename", metavar="FILENAME", default=None,
dest="filename", help="Filename of track.")
parser.add_option('-d', '--debug', action="store_true", default=False,
dest="debug", help=("Show debug messages"))
opts, args = parser.parse_args()
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
if opts.debug:
debug = True
if opts.version:
buildVersion()
if opts.test:
performSelfTest()
if opts.artist:
lyrics.artist = opts.artist
if opts.album:
lyrics.album = opts.album
if opts.title:
lyrics.title = opts.title
if opts.filename:
lyrics.filename = opts.filename
if (len(args) > 0):
utilities.log('ERROR: invalid arguments found')
sys.exit(1)
fetcher = LyricsFetcher()
if fetcher.get_lyrics(lyrics):
buildLyrics(lyrics)
sys.exit(0)
else:
utilities.log(True, "No lyrics found for this track")
sys.exit(1)
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
request = Request(
self.url % (quote(lyrics.artist), '%20', quote(lyrics.title)))
request.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0'
)
req = urlopen(request)
response = req.read().decode('utf-8')
except:
return False
req.close()
data = simplejson.loads(response)
try:
self.page = data['response']['hits'][0]['result']['url']
except:
return False
utilities.log(debug, "%s: search url: %s" % (__title__, self.page))
try:
request = Request(self.page)
request.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0'
)
req = urlopen(request)
response = req.read().decode('utf-8')
except:
return False
req.close()
matchcode = re.search(u'<div class="lyrics">(.*?)</div>',
response,
flags=re.DOTALL)
try:
lyricscode = (matchcode.group(1))
htmlparser = html_parser.HTMLParser()
lyricstext = htmlparser.unescape(lyricscode).replace(
u'<br />', u'\n')
templyr = re.sub(u'<[^<]+?>', '', lyricstext)
lyr = re.sub(u'\[(.*?)\]', '', templyr)
lyrics.lyrics = lyr.strip().replace(u'\n\n\n', u'\n\n')
return True
except:
return False
def main():
global debug
parser = OptionParser()
parser.add_option('-v', "--version", action="store_true", default=False,
dest="version", help="Display version and author")
parser.add_option('-t', "--test", action="store_true", default=False,
dest="test", help="Test grabber with a know good search")
parser.add_option('-s', "--search", action="store_true", default=False,
dest="search", help="Search for lyrics.")
parser.add_option('-a', "--artist", metavar="ARTIST", default=None,
dest="artist", help="Artist of track.")
parser.add_option('-b', "--album", metavar="ALBUM", default=None,
dest="album", help="Album of track.")
parser.add_option('-n', "--title", metavar="TITLE", default=None,
dest="title", help="Title of track.")
parser.add_option('-f', "--filename", metavar="FILENAME", default=None,
dest="filename", help="Filename of track.")
parser.add_option('-d', '--debug', action="store_true", default=False,
dest="debug", help=("Show debug messages"))
opts, args = parser.parse_args()
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
if opts.debug:
debug = True
if opts.version:
buildVersion()
if opts.test:
performSelfTest()
if opts.artist:
lyrics.artist = opts.artist
if opts.album:
lyrics.album = opts.album
if opts.title:
lyrics.title = opts.title
if opts.filename:
lyrics.filename = opts.filename
fetcher = LyricsFetcher()
if fetcher.get_lyrics(lyrics):
buildLyrics(lyrics)
sys.exit(0)
else:
utilities.log(True, "No lyrics found for this track")
sys.exit(1)
def get_lyrics(self, lyrics):
utilities.log(
debug, '%s: searching lyrics for %s - %s' %
(__title__, lyrics.artist, lyrics.title))
query = '%s+%s' % (urllib.quote_plus(
lyrics.artist), urllib.quote_plus(lyrics.title))
try:
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0',
'Referer': 'https://www.letssingit.com/'
}
request = urllib2.Request(self.url % query, None, headers)
req = urllib2.urlopen(request)
response = req.read()
utilities.log(False, response)
except:
return False
req.close()
matchcode = re.search('</TD><TD><A href="(.*?)"', response)
if matchcode:
lyricscode = (matchcode.group(1))
clean = lyricscode.lstrip('http://www.letssingit.com/').rsplit(
'-', 1)[0]
result = clean.replace('-lyrics-', ' ')
if (difflib.SequenceMatcher(None,
query.lower().replace('+', ''),
result.lower().replace(
'-', '')).ratio() > 0.8):
try:
request = urllib2.Request(lyricscode)
request.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0'
)
req = urllib2.urlopen(request)
resp = req.read()
except:
return False
req.close()
# remove addslots
resp = re.sub(r'<div id=adslot.*?</div>', '', resp)
# find all class=lyrics_part_name and class=lyrics_part_text parts
match = re.findall('<P class=lyrics_part_.*?>(.*?)</P>',
resp,
flags=re.DOTALL)
if len(match):
for line in match:
lyrics.lyrics += line.replace('<br>', '') + '\n'
else:
return False
return True
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
xml = "<?xml version=\"1.0\" encoding='utf-8'?>\r\n"
xml += "<search filetype=\"lyrics\" artist=\"%s\" title=\"%s\" " % (
lyrics.artist, lyrics.title)
xml += "ClientCharEncoding=\"utf-8\"/>\r\n"
md5hash = md5(xml + "Mlv1clt4.0").digest()
request = "\x02\x00\x04\x00\x00\x00%s%s" % (md5hash, xml)
del md5hash, xml
url = "http://www.viewlyrics.com:1212/searchlyrics.htm"
#url = "http://search.crintsoft.com/searchlyrics.htm"
req = urllib2.Request(url, request)
req.add_header("User-Agent", "MiniLyrics")
if self.proxy:
opener = urllib2.build_opener(urllib2.ProxyHandler(self.proxy))
else:
opener = urllib2.build_opener()
try:
response = opener.open(req).read()
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
print response
lrcList = self.miniLyricsParser(response)
links = []
for x in lrcList:
if (difflib.SequenceMatcher(None, song.artist.lower(),
x[0].lower()).ratio()
> 0.8) and (difflib.SequenceMatcher(
None, song.title.lower(), x[1].lower()).ratio() > 0.8):
links.append((x[0] + ' - ' + x[1], x[2], x[0], x[1]))
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
lyr = self.get_lyrics_from_list(links[0])
if not lyr:
return False
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
# replace ampersands and the like
for exp in LYRIC_ARTIST_REPLACE:
p = re.compile(exp[0])
artist = p.sub(exp[1], lyrics.artist)
for exp in LYRIC_TITLE_REPLACE:
p = re.compile(exp[0])
title = p.sub(exp[1], lyrics.title)
# strip things like "(live at Somewhere)", "(accoustic)", etc
for exp in LYRIC_TITLE_STRIP:
p = re.compile(exp)
title = p.sub('', title)
# compress spaces
title = title.strip().replace('`','').replace('/','')
artist = artist.strip().replace('`','').replace('/','')
try:
url = self.LIST_URL %(ttpClient.EncodeArtTit(artist.replace(' ','').lower()), ttpClient.EncodeArtTit(title.replace(' ','').lower()))
f = urllib.urlopen(url)
Page = f.read()
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
links_query = re.compile('<lrc id=\"(.*?)\" artist=\"(.*?)\" title=\"(.*?)\"></lrc>')
urls = re.findall(links_query, Page)
links = []
for x in urls:
if (difflib.SequenceMatcher(None, artist.lower(), x[1].lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, title.lower(), x[2].lower()).ratio() > 0.8):
links.append( ( x[1] + ' - ' + x[2], x[0], x[1], x[2] ) )
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
for link in links:
lyr = self.get_lyrics_from_list(link)
if lyr and lyr.startswith('['):
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
return False
def buildVersion():
from lxml import etree
version = etree.XML(u'<grabber></grabber>')
etree.SubElement(version, "name").text = __title__
etree.SubElement(version, "author").text = __author__
etree.SubElement(version, "command").text = 'ttplayer.py'
etree.SubElement(version, "type").text = 'lyrics'
etree.SubElement(version, "description").text = __description__
etree.SubElement(version, "version").text = __version__
etree.SubElement(version, "priority").text = __priority__
etree.SubElement(version, "syncronized").text = 'True' if __syncronized__ else 'False'
utilities.log(True, etree.tostring(version, encoding='UTF-8', pretty_print=True,
xml_declaration=True))
sys.exit(0)
def get_lyrics_from_list(self, link):
title, url, artist, song = link
try:
f = urllib.urlopen(url)
lyrics = f.read()
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 None
enc = chardet.detect(lyrics)
lyrics = lyrics.decode(enc['encoding'], 'ignore')
return lyrics
def get_lyrics_from_list(self, link):
title, Id, artist, song = link
utilities.log(debug, '%s %s %s' % (Id, artist, song))
try:
url = 'http://www.lyrdb.com/karaoke/downloadlrc.php?q=%s' % (Id)
f = urllib.urlopen(url)
Page = f.read()
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 None
return Page
def get_lyrics_from_list(self, link):
title,url,artist,song = link
try:
f = urllib.urlopen(url)
lyrics = f.read()
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 None
enc = chardet.detect(lyrics)
lyrics = lyrics.decode(enc['encoding'], 'ignore')
return lyrics
def buildLyrics(lyrics):
from lxml import etree
xml = etree.XML(u'<lyrics></lyrics>')
etree.SubElement(xml, "artist").text = lyrics.artist
etree.SubElement(xml, "album").text = lyrics.album
etree.SubElement(xml, "title").text = lyrics.title
etree.SubElement(xml, "syncronized").text = 'True' if __syncronized__ else 'False'
etree.SubElement(xml, "grabber").text = lyrics.source
lines = lyrics.lyrics.splitlines()
for line in lines:
etree.SubElement(xml, "lyric").text = line
utilities.log(True, etree.tostring(xml, encoding='UTF-8', pretty_print=True,
xml_declaration=True))
sys.exit(0)
def get_lyrics_from_list(self, link):
title, Id, artist, song = link
utilities.log(debug, '%s %s %s' %(Id, artist, song))
try:
url = 'http://www.lyrdb.com/karaoke/downloadlrc.php?q=%s' %(Id)
f = urllib.urlopen(url)
Page = f.read()
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 None
return Page
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
key = None
try:
ext = os.path.splitext(lyrics.filename.decode("utf-8"))[1].lower()
sup_ext = ['.mp3', '.ogg', '.wma', '.flac', '.ape', '.wav']
if ext in sup_ext:
key = gomClient.GetKeyFromFile(lyrics.filename)
if not key:
return False
url = GOM_URL % (
key,
urllib.quote(
remove_accents(
lyrics.title.decode('utf-8')).encode('euc-kr')),
(remove_accents(
lyrics.artist.decode('utf-8')).encode('euc-kr')))
response = urllib.urlopen(url)
Page = response.read()
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
if Page[:Page.find('>') + 1] != '<lyrics_reply result="0">':
return False
syncs = re.compile('<sync start="(\d+)">([^<]*)</sync>').findall(Page)
lyrline = []
lyrline.append("[ti:%s]" % lyrics.title)
lyrline.append("[ar:%s]" % lyrics.artist)
for sync in syncs:
# timeformat conversion
t = "%02d:%02d.%02d" % gomClient.mSecConv(int(sync[0]))
# unescape string
try:
s = unicode(sync[1], "euc-kr").encode("utf-8").replace(
"'", "'").replace(""", '"')
lyrline.append("[%s]%s" % (t, s))
except:
pass
lyrics.lyrics = '\n'.join(lyrline)
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
links = self.search(lyrics.artist, lyrics.title);
if(links == None or len(links) == 0):
return False;
elif len(links) > 1:
lyrics.list = links
lyr = self.get_lyrics_from_list(links[0])
if not lyr:
return False
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True;
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
xml ="<?xml version=\"1.0\" encoding='utf-8'?>\r\n"
xml+="<search filetype=\"lyrics\" artist=\"%s\" title=\"%s\" " % (lyrics.artist, lyrics.title)
xml+="ClientCharEncoding=\"utf-8\"/>\r\n"
md5hash = md5(xml+"Mlv1clt4.0").digest()
request = "\x02\x00\x04\x00\x00\x00%s%s" % (md5hash, xml)
del md5hash,xml
url = "http://www.viewlyrics.com:1212/searchlyrics.htm"
#url = "http://search.crintsoft.com/searchlyrics.htm"
req = urllib2.Request(url,request)
req.add_header("User-Agent", "MiniLyrics")
if self.proxy:
opener = urllib2.build_opener(urllib2.ProxyHandler(self.proxy))
else:
opener = urllib2.build_opener()
try:
response = opener.open(req).read()
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
print response
lrcList = self.miniLyricsParser(response)
links = []
for x in lrcList:
if (difflib.SequenceMatcher(None, song.artist.lower(), x[0].lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, song.title.lower(), x[1].lower()).ratio() > 0.8):
links.append( ( x[0] + ' - ' + x[1], x[2], x[0], x[1] ) )
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
lyr = self.get_lyrics_from_list(links[0])
if not lyr:
return False
enc = chardet.detect(lyr)
lyr = lyr.decode(enc['encoding'], 'ignore')
lyrics.lyrics = lyr
return True
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
from bs4 import BeautifulSoup
except:
utilities.log(True, "Failed to import BeautifulSoup. This grabber requires python-bs4")
return False
try:
request = urlopen(self.url % quote_plus(lyrics.artist))
response = request.read()
except:
return False
request.close()
soup = BeautifulSoup(response, 'html.parser')
url = ''
for link in soup.find_all('a'):
if link.string and link.get('href').startswith('artist/'):
url = 'http://www.lyrics.com/' + link.get('href')
break
if url:
utilities.log(debug, "%s: Artist url is %s" % (__title__, url))
try:
req = urlopen(url)
resp = req.read().decode('utf-8')
except:
return False
req.close()
soup = BeautifulSoup(resp, 'html.parser')
url = ''
for link in soup.find_all('a'):
if link.string and link.get('href').startswith('/lyric/') and (difflib.SequenceMatcher(None, link.string.lower(), lyrics.title.lower()).ratio() > 0.8):
url = 'http://www.lyrics.com' + link.get('href')
break
if url:
utilities.log(debug, "%s: Song url is %s" % (__title__, url))
try:
req2 = urlopen(url)
resp2 = req2.read().decode('utf-8')
except:
return False
req2.close()
matchcode = re.search(u'<pre.*?>(.*?)</pre>', resp2, flags=re.DOTALL)
if matchcode:
lyricscode = (matchcode.group(1))
lyr = re.sub(u'<[^<]+?>', '', lyricscode)
lyrics.lyrics = lyr.replace('\\n','\n')
return True
return False
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
from bs4 import BeautifulSoup
except:
utilities.log(True, "Failed to import BeautifulSoup. This grabber requires python-bs4")
return False
try:
request = urllib2.urlopen(self.url % urllib.quote_plus(lyrics.artist))
response = request.read()
except:
return False
request.close()
soup = BeautifulSoup(response, 'html.parser')
url = ''
for link in soup.find_all('a'):
if link.string and link.get('href').startswith('artist/'):
url = 'http://www.lyrics.com/' + link.get('href')
break
if url:
utilities.log(debug, "%s: Artist url is %s" % (__title__, url))
try:
req = urllib2.urlopen(url)
resp = req.read()
except:
return False
req.close()
soup = BeautifulSoup(resp, 'html.parser')
url = ''
for link in soup.find_all('a'):
if link.string and link.get('href').startswith('/lyric/') and (difflib.SequenceMatcher(None, link.string.lower(), lyrics.title.lower()).ratio() > 0.8):
url = 'http://www.lyrics.com' + link.get('href')
break
if url:
utilities.log(debug, "%s: Song url is %s" % (__title__, url))
try:
req2 = urllib2.urlopen(url)
resp2 = req2.read()
except:
return False
req2.close()
matchcode = re.search('<pre.*?>(.*?)</pre>', resp2, flags=re.DOTALL)
if matchcode:
lyricscode = (matchcode.group(1))
lyr = re.sub('<[^<]+?>', '', lyricscode)
lyrics.lyrics = lyr.replace('\\n','\n')
return True
return False
def get_lyrics_from_list(self, link):
title,Id,artist,song = link
utilities.log(debug, '%s %s %s' %(Id, artist, song))
try:
url = self.LYRIC_URL %(int(Id),ttpClient.CodeFunc(int(Id), artist + song), random.randint(0,0xFFFFFFFFFFFF))
f = urllib.urlopen(url)
Page = f.read()
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 None
if Page.startswith('['):
return Page
return ''
def performSelfTest():
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Dire Straits'
lyrics.album = 'Brothers In Arms'
lyrics.title = 'Money For Nothing'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def performSelfTest():
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Dagon'
lyrics.album = 'Terraphobic'
lyrics.title = 'Cut To The Heart'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def performSelfTest():
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Robb Benson'
lyrics.album = 'Demo Tracks'
lyrics.title = 'Lone Rock'
lyrics.filename = os.path.dirname(os.path.abspath(__file__)) + '/examples/taglyrics.mp3'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def performSelfTest():
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Robb Benson'
lyrics.album = 'Demo Tracks'
lyrics.title = 'Lone Rock'
lyrics.filename = os.path.dirname(os.path.abspath(__file__)) + '/examples/taglyrics.mp3'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
request = urllib2.Request(self.url % (urllib2.quote(lyrics.artist), '%20', urllib2.quote(lyrics.title)))
request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0')
req = urllib2.urlopen(request)
response = req.read()
except:
return False
req.close()
data = simplejson.loads(response)
try:
self.page = data['response']['hits'][0]['result']['url']
except:
return False
utilities.log(debug, "%s: search url: %s" % (__title__, self.page))
try:
request = urllib2.Request(self.page)
request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0')
req = urllib2.urlopen(request)
response = req.read()
except:
return False
req.close()
matchcode = re.search('<div class="lyrics">(.*?)</div>', response, flags=re.DOTALL)
try:
lyricscode = (matchcode.group(1))
htmlparser = HTMLParser.HTMLParser()
lyricstext = htmlparser.unescape(lyricscode).replace('<br />', '\n')
templyr = re.sub('<[^<]+?>', '', lyricstext)
lyr = re.sub('\[(.*?)\]', '', templyr)
lyrics.lyrics = lyr.strip().replace('\n\n\n', '\n\n')
return True
except:
return False
def getLyricsGeneric(filename):
try:
import taglib
except:
utilities.log(True, "Failed to import taglib. This grabber requires "
"pytaglib TagLib bindings for Python. "
"https://github.com/supermihi/pytaglib")
return None
try:
utilities.log(debug, "%s: trying to open %s" % (__title__, filename))
f = taglib.File(filename)
# see if we can find a lyrics tag
for tag in f.tags:
if tag.startswith('LYRICS'):
return f.tags[tag][0]
return None
except:
return None
def performSelfTest():
try:
import taglib
except:
utilities.log(
True, "Failed to import taglib. This grabber requires "
"pytaglib ? TagLib bindings for Python. "
"https://github.com/supermihi/pytaglib")
sys.exit(1)
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Robb Benson'
lyrics.album = 'Demo Tracks'
lyrics.title = 'Lone Rock'
lyrics.filename = os.path.dirname(
os.path.abspath(__file__)) + '/examples/taglyrics.mp3'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def performSelfTest():
try:
from bs4 import BeautifulSoup
except:
utilities.log(
True,
"Failed to import BeautifulSoup. This grabber requires python-bs4")
sys.exit(1)
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Dire Straits'
lyrics.album = 'Brothers In Arms'
lyrics.title = 'Money For Nothing'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
buildLyrics(lyrics)
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def performSelfTest():
try:
import taglib
except:
utilities.log(True, "Failed to import taglib. This grabber requires "
"pytaglib ? TagLib bindings for Python. "
"https://github.com/supermihi/pytaglib")
sys.exit(1)
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Robb Benson'
lyrics.album = 'Demo Tracks'
lyrics.title = 'Lone Rock'
lyrics.filename = os.path.dirname(os.path.abspath(__file__)) + '/examples/taglyrics.mp3'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
headers = {'Content-Type':'text/xml; charset=utf-8'}
request = urllib2.Request(ALSONG_URL, ALSONG_TMPL % (lyrics.title, lyrics.artist), headers)
response = urllib2.urlopen(request)
Page = response.read()
except:
return False
tree = xml.parseString(Page)
try:
name = tree.getElementsByTagName('strArtistName')[0].childNodes[0].data
track = tree.getElementsByTagName('strTitle')[0].childNodes[0].data
except:
return False
if (difflib.SequenceMatcher(None, lyrics.artist.lower(), name.lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, lyrics.title.lower(), track.lower()).ratio() > 0.8):
lyr = tree.getElementsByTagName('strLyric')[0].childNodes[0].data.replace('<br>','\n')
lyrics.lyrics = lyr.encode('utf-8')
return True
return False
def get_lyrics(self, lyrics):
utilities.log(debug, "%s: searching lyrics for %s - %s - %s" % (__title__, lyrics.artist, lyrics.album, lyrics.title))
key = None
try:
ext = os.path.splitext(lyrics.filename.decode("utf-8"))[1].lower()
sup_ext = ['.mp3', '.ogg', '.wma', '.flac', '.ape', '.wav']
if ext in sup_ext:
key = gomClient.GetKeyFromFile(lyrics.filename)
if not key:
return False
url = GOM_URL %(key, urllib.quote(remove_accents(lyrics.title.decode('utf-8')).encode('euc-kr')), (remove_accents(lyrics.artist.decode('utf-8')).encode('euc-kr')))
response = urllib.urlopen(url)
Page = response.read()
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
if Page[:Page.find('>')+1] != '<lyrics_reply result="0">':
return False
syncs = re.compile('<sync start="(\d+)">([^<]*)</sync>').findall(Page)
lyrline = []
lyrline.append( "[ti:%s]" %lyrics.title )
lyrline.append( "[ar:%s]" %lyrics.artist )
for sync in syncs:
# timeformat conversion
t = "%02d:%02d.%02d" % gomClient.mSecConv( int(sync[0]) )
# unescape string
try:
s = unicode(sync[1], "euc-kr").encode("utf-8").replace("'","'").replace(""",'"')
lyrline.append( "[%s]%s" %(t,s) )
except:
pass
lyrics.lyrics = '\n'.join( lyrline )
return True
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
url = 'http://www.lyrdb.com/karaoke/?q=%s+%s&action=search' % (
lyrics.artist.replace(
' ', '+').lower(), lyrics.title.replace(' ', '+').lower())
f = urllib.urlopen(url)
Page = f.read()
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
links_query = re.compile(
'<tr><td class="tresults"><a href="/karaoke/([0-9]+).htm">(.*?)</td><td class="tresults">(.*?)</td>'
)
urls = re.findall(links_query, Page)
links = []
for x in urls:
if (difflib.SequenceMatcher(None, song.artist.lower(),
x[2].lower()).ratio()
> 0.8) and (difflib.SequenceMatcher(
None, song.title.lower(), x[1].lower()).ratio() > 0.8):
links.append((x[2] + ' - ' + x[1], x[0], x[2], x[1]))
if len(links) == 0:
return False
elif len(links) > 1:
lyrics.list = links
lyr = self.get_lyrics_from_list(links[0])
if not lyr:
return False
lyrics.lyrics = lyr
return True
def getLyrics3(filename):
#Get lyrics embed with Lyrics3/Lyrics3V2 format
#See: http://id3.org/Lyrics3
#http://id3.org/Lyrics3v2
utilities.log(
debug, "%s: trying %s" %
(__title__, "lyrics embed with Lyrics3/Lyrics3V2 format"))
f = File(filename)
f.seek(-128 - 9, os.SEEK_END)
buf = f.read(9)
if (buf != "LYRICS200" and buf != "LYRICSEND"):
f.seek(-9, os.SEEK_END)
buf = f.read(9)
if (buf == "LYRICSEND"):
""" Find Lyrics3v1 """
f.seek(-5100 - 9 - 11, os.SEEK_CUR)
buf = f.read(5100 + 11)
f.close()
start = buf.find("LYRICSBEGIN")
elif (buf == "LYRICS200"):
""" Find Lyrics3v2 """
f.seek(-9 - 6, os.SEEK_CUR)
size = int(f.read(6))
f.seek(-size - 6, os.SEEK_CUR)
buf = f.read(11)
if (buf == "LYRICSBEGIN"):
buf = f.read(size - 11)
tags = []
while buf != '':
tag = buf[:3]
length = int(buf[3:8])
content = buf[8:8 + length]
if (tag == 'LYR'):
return content
buf = buf[8 + length:]
f.close()
return None
def getLyricsGeneric(filename):
try:
import taglib
except:
utilities.log(
True, "Failed to import taglib. This grabber requires "
"pytaglib TagLib bindings for Python. "
"https://github.com/supermihi/pytaglib")
return None
try:
utilities.log(debug, "%s: trying to open %s" % (__title__, filename))
f = taglib.File(filename)
# see if we can find a lyrics tag
for tag in f.tags:
if tag.startswith('LYRICS'):
return f.tags[tag][0]
return None
except:
return None
def getLyrics3(filename):
#Get lyrics embed with Lyrics3/Lyrics3V2 format
#See: http://id3.org/Lyrics3
#http://id3.org/Lyrics3v2
utilities.log(debug, "%s: trying %s" % (__title__, "lyrics embed with Lyrics3/Lyrics3V2 format"))
f = File(filename)
f.seek(-128-9, os.SEEK_END)
buf = f.read(9)
if (buf != "LYRICS200" and buf != "LYRICSEND"):
f.seek(-9, os.SEEK_END)
buf = f.read(9)
if (buf == "LYRICSEND"):
""" Find Lyrics3v1 """
f.seek(-5100-9-11, os.SEEK_CUR)
buf = f.read(5100+11)
f.close();
start = buf.find("LYRICSBEGIN")
elif (buf == "LYRICS200"):
""" Find Lyrics3v2 """
f.seek(-9-6, os.SEEK_CUR)
size = int(f.read(6))
f.seek(-size-6, os.SEEK_CUR)
buf = f.read(11)
if(buf == "LYRICSBEGIN"):
buf = f.read(size-11)
tags=[]
while buf!= '':
tag = buf[:3]
length = int(buf[3:8])
content = buf[8:8+length]
if (tag == 'LYR'):
return content
buf = buf[8+length:]
f.close();
return None
def performSelfTest():
try:
from bs4 import BeautifulSoup
except:
utilities.log(True, "Failed to import BeautifulSoup. This grabber requires python-bs4")
sys.exit(1)
found = False
lyrics = utilities.Lyrics()
lyrics.source = __title__
lyrics.syncronized = __syncronized__
lyrics.artist = 'Dire Straits'
lyrics.album = 'Brothers In Arms'
lyrics.title = 'Money For Nothing'
fetcher = LyricsFetcher()
found = fetcher.get_lyrics(lyrics)
if found:
utilities.log(True, "Everything appears in order.")
sys.exit(0)
utilities.log(True, "The lyrics for the test search failed!")
sys.exit(1)
def get_lyrics(self, lyrics):
utilities.log(
debug, "%s: searching lyrics for %s - %s - %s" %
(__title__, lyrics.artist, lyrics.album, lyrics.title))
try:
request = Request(
self.url % (quote(lyrics.artist), '%20', quote(lyrics.title)))
request.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 10.0; rv:77.0) Gecko/20100101 Firefox/77.0'
)
req = urlopen(request)
response = req.read().decode('utf-8')
except:
return False
req.close()
data = simplejson.loads(response)
try:
name = data['response']['hits'][0]['result']['primary_artist'][
'name']
track = data['response']['hits'][0]['result']['title']
if (difflib.SequenceMatcher(None, lyrics.artist.lower(),
name.lower()).ratio() > 0.8
) and (difflib.SequenceMatcher(None, lyrics.title.lower(),
track.lower()).ratio() > 0.8):
self.page = data['response']['hits'][0]['result']['url']
else:
return None
except:
return False
utilities.log(debug, "%s: search url: %s" % (__title__, self.page))
try:
request = Request(self.page)
request.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 10.0; rv:77.0) Gecko/20100101 Firefox/77.0'
)
req = urlopen(request)
response = req.read()
except:
return False
req.close()
try:
htmlparser = html_parser.HTMLParser()
response = htmlparser.unescape(response.decode('utf-8'))
except:
# may be necessary for python 3.10
response = html.unescape(response.decode('utf-8'))
matchcode = re.search(u'<div class="[lL]yrics.*?">(.*?)</div>',
response,
flags=re.DOTALL)
try:
lyricscode = (matchcode.group(1))
lyr = re.sub('<[^<]+?>', '', lyricscode)
lyrics.lyrics = lyr.replace('\\n', '\n').strip()
return True
except:
return False
def getMP4Lyrics(filename):
utilities.log(
debug, "%s: trying %s" % (__title__, "lyrics embed with MP4 format"))
# just use the generic taglib method for now
return getLyricsGeneric(filename)
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 getMP4Lyrics(filename):
utilities.log(debug, "%s: trying %s" % (__title__, "lyrics embed with MP4 format"))
# just use the generic taglib method for now
return getLyricsGeneric(filename)
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
