def search_artist(self, artist_page, callback, *data):
"""Search for the link to the page of artist in artists_page
"""
if artist_page is None:
callback (None, *data)
return
artist_page = artist_page.decode('iso-8859-1')
link_section = re.split ('tban.js', artist_page, 1)[1]
pattern_link = '<a href="'
pattern_artist = '([^"]*)">*([^<]*)<'
links = re.split (pattern_link, link_section.lower())
links.pop(0)
best_match = ()
smvalue_bestmatch = 0
for line in links:
artist = re.findall(pattern_artist, line)
if len(artist) == 0:
continue
artist_link, artist_name = artist[0]
artist_url = 'http://www.darklyrics.com/%s' % (artist_link)
if artist_link[:5] == 'http:':
continue
artist_name = artist_name.strip()
smvalue = stringmatch.string_match (artist_name, self.artist_ascii)
if smvalue > min_artist_match and smvalue > smvalue_bestmatch:
best_match = (smvalue, artist_url, artist_name)
smvalue_bestmatch = smvalue
if not best_match:
# Lyrics are located in external site
callback (None, *data)
return
loader = rb.Loader ()
self.artist = best_match[2]
loader.get_url (best_match[1], self.search_song, callback, *data)
def search_artist(self, artist_page, callback, *data):
"""Search for the link to the page of artist in artists_page
"""
if artist_page is None:
callback(None, *data)
return
artist_page = artist_page.decode('iso-8859-1')
link_section = re.split('tban.js', artist_page, 1)[1]
pattern_link = '<a href="'
pattern_artist = '([^"]*)">*([^<]*)<'
links = re.split(pattern_link, link_section.lower())
links.pop(0)
best_match = ()
smvalue_bestmatch = 0
for line in links:
artist = re.findall(pattern_artist, line)
if len(artist) == 0:
continue
artist_link, artist_name = artist[0]
artist_url = 'http://www.darklyrics.com/%s' % (artist_link)
if artist_link[:5] == 'http:':
continue
artist_name = artist_name.strip()
smvalue = stringmatch.string_match(artist_name, self.artist_ascii)
if smvalue > min_artist_match and smvalue > smvalue_bestmatch:
best_match = (smvalue, artist_url, artist_name)
smvalue_bestmatch = smvalue
if not best_match:
# Lyrics are located in external site
callback(None, *data)
return
loader = rb.Loader()
self.artist = best_match[2]
loader.get_url(best_match[1], self.search_song, callback, *data)
def search_song (self, songlist, callback, *data):
"""If artist's page is found, search_song looks for the song.
The artist page contains a list of all the albums and
links to the songs lyrics from this.
"""
if songlist is None:
callback (None, *data)
return
songlist = songlist.decode('iso-8859-1')
# Search for all the <a>
# filter for those that has the artist name string_match
# and for those which its content is artist string_match
# Sort by values given from string_match
# and get the best
link_section = re.split('LYRICS</h1>', songlist)[1]
link_section = link_section.lower()
pattern_song = '<a href="../lyrics/(.*)/(.*).html#([^"]+)">(.*)</a>'
matches = re.findall (pattern_song.lower(), link_section)
best_match = ""
for line in matches:
artist, album, number, title = line
smvalue = stringmatch.string_match (title.lower().replace(' ', '' ),
self.title.lower().replace(' ', ''))
if smvalue > min_song_match:
best_match = self.SongFound(smvalue,
title,
number,
album,
artist)
break
if not best_match:
callback (None, *data)
return
loader = rb.Loader ()
url = 'http://www.darklyrics.com/lyrics/%s/%s.html' % (best_match.artist, best_match.album)
self.title = best_match.title
self.titlenumber = best_match.number
loader.get_url (url, self.parse_lyrics, callback, *data)
def search_song(self, songlist, callback, *data):
"""If artist's page is found, search_song looks for the song.
The artist page contains a list of all the albums and
links to the songs lyrics from this.
"""
if songlist is None:
callback(None, *data)
return
songlist = songlist.decode('iso-8859-1')
# Search for all the <a>
# filter for those that has the artist name string_match
# and for those which its content is artist string_match
# Sort by values given from string_match
# and get the best
link_section = re.split('LYRICS</h1>', songlist)[1]
link_section = link_section.lower()
pattern_song = '<a href="../lyrics/(.*)/(.*).html#([^"]+)">(.*)</a>'
matches = re.findall(pattern_song.lower(), link_section)
best_match = ""
for line in matches:
artist, album, number, title = line
smvalue = stringmatch.string_match(
title.lower().replace(' ', ''),
self.title.lower().replace(' ', ''))
if smvalue > min_song_match:
best_match = self.SongFound(smvalue, title, number, album,
artist)
break
if not best_match:
callback(None, *data)
return
loader = rb.Loader()
url = 'http://www.darklyrics.com/lyrics/%s/%s.html' % (
best_match.artist, best_match.album)
self.title = best_match.title
self.titlenumber = best_match.number
loader.get_url(url, self.parse_lyrics, callback, *data)
