lyrics-ebook 0.1

data/lib/wiki_lyrics/lyrics_LyricsDownload.rb

@@ -0,0 +1,118 @@
+# Copyright (C) 2007 by Sergio Pistone
+# sergio_pistone@yahoo.com.ar
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "utils/htmlentities"
+require "lyrics"
+
+class LyricsDownload < Lyrics
+
+	@@white_chars = "'\"¿?¡!()[].,;:-/& "
+
+	def LyricsDownload.site_host()
+		return "www.lyricsdownload.com"
+	end
+
+	def LyricsDownload.site_name()
+		return "Lyrics Download"
+	end
+
+	def LyricsDownload.lyrics_test_data()
+		return [
+			Request.new( "Nirvana", "Smells Like Teen Spirit", "Nevermind" ),
+			Request.new( "Radiohead", "Optimistic", "Kid A" ),
+			Request.new( "Massive Attack", "Protection", "Protection" ),
+			Request.new( "Portishead", "Wandering Star", "Dummy" ),
+		]
+	end
+
+	def cleanup_artist( artist )
+		artist = artist.gsub( /^the /i, "" )
+		Strings.remove_vocal_accents!( artist )
+		artist.gsub!( "&", "and" )
+		artist.tr!( @@white_chars, " " )
+		artist.strip!()
+		artist.tr!( " ", "-" )
+		return artist
+	end
+
+	def cleanup_title( title )
+		title = Strings.remove_vocal_accents( title )
+		title.gsub!( "&", "and" )
+		title.tr!( @@white_chars, " " )
+		title.strip!()
+		title.tr!( " ", "-" )
+		return title
+	end
+
+	def build_lyrics_fetch_data( request )
+		artist = cleanup_title( request.artist )
+		title = cleanup_title( request.title )
+		return FetchPageData.new( "http://#{site_host()}/#{artist}-#{title}-lyrics.html" )
+	end
+
+	def parse_lyrics( response, page_body )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+		page_body.tr_s!( "’", "'" )
+# 		page_body.tr_s!( "‘", "'" )
+
+		if (md = /<title>([^<]+) - ([^<]+) LYRICS ?<\/title>/i.match( page_body ))
+			response.artist, response.title = md[1].strip(), md[2].strip()
+		end
+
+		return if ! page_body.gsub!( /^.*<div class="KonaBody" ><div id="div_customCSS">/, "" )
+		return if ! page_body.gsub!( /<\/div> ?<\/div>.*$/, "" )
+
+		page_body.gsub!( /\ ?<br ?\/?> ?/i, "\n" )
+		page_body.strip!()
+
+		response.lyrics = page_body
+
+	end
+
+	def build_suggestions_fetch_data( request )
+		artist = cleanup_artist( request.artist )
+		return FetchPageData.new( "http://#{site_host()}/#{artist}-lyrics.html" )
+	end
+
+	def parse_suggestions( request, page_body, page_url )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+		page_body.tr_s!( "’", "'" )
+
+		suggestions = []
+
+		return suggestions if ! page_body.sub!( /^.*Lyrics list aplhabetically:<\/font><\/td>/, "" )
+		return suggestions if ! page_body.sub!( /<\/ul> ?<\/td> ?<\/tr> ?<\/table> ?<center><div>.*$/, "" )
+
+		page_body.split( "</li>" ).each() do |entry|
+			if (md = /<a class="txt_1" href="([^"]+)"><font size=2>([^<]+) Lyrics<\/font><\/a>/.match( entry ))
+				suggestions << Suggestion.new( request.artist, md[2], "http://#{site_host()}/#{md[1]}" )
+			end
+		end
+
+		return suggestions
+
+	end
+
+end

data/lib/wiki_lyrics/lyrics_LyricsMania.rb

@@ -0,0 +1,141 @@
+# Copyright (C) 2007-2008 by
+# Davide Lo Re <boyska@gmail.com>
+# Sergio Pistone <sergio_pistone@yahoo.com.ar>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "lyrics"
+
+require "cgi"
+
+class LyricsMania < Lyrics
+
+	def LyricsMania.site_host()
+		return "www.lyricsmania.com"
+	end
+
+	def LyricsMania.site_name()
+		return "LyricsMania"
+	end
+
+	def LyricsMania.lyrics_test_data()
+		return [
+			Request.new( "Nirvana", "Lounge Act", "Nevermind" ),
+			Request.new( "Radiohead", "Idioteque", "Kid A" ),
+			Request.new( "Pearl Jam", "Porch", "Ten" ),
+			Request.new( "The Smashing Pumpkins", "Mayonaise", "Siamese Dream" ),
+		]
+	end
+
+	def LyricsMania.build_song_add_url( request )
+		return "http://#{site_host()}/add.html"
+	end
+
+	def LyricsMania.build_google_feeling_lucky_url( artist, title=nil )
+		query =  Strings.google_search_quote( artist )
+		query << " " << Strings.google_search_quote( title + " lyrics" ) if title
+		return Strings.build_google_feeling_lucky_url( query, site_host() )
+	end
+
+	def build_lyrics_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist, request.title ) )
+	end
+
+	def lyrics_page_valid?( request, page_body, page_url )
+		md = /<title>([^<]+) Lyrics<\/title>/i.match( page_body )
+		return false if ! md
+		page_title = Strings.normalize( md[1] )
+		return	page_title.index( Strings.normalize( request.artist ) ) &&
+				page_title.index( Strings.normalize( request.title ) )
+	end
+
+	def parse_lyrics( response, page_body )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		return if ! page_body.sub!( /^.* lyrics<\/h3>/, "" ) # metadata
+
+		metadata = {}
+		["artist", "album"].each() do |key|
+			if (md =/#{key}: <b><a href=[^>]+>([^<]+)<\/a><\/b>/i.match( page_body ))
+				metadata[key.downcase()] = md[1].strip().sub( /\ *lyrics$/, "" )
+			end
+		end
+		["year", "title"].each() do |key|
+			if (md =/#{key}: ([^<]+)<(br|\/td)>/i.match( page_body ))
+				metadata[key.downcase()] = md[1].strip()
+			end
+		end
+
+		response.artist = metadata["artist"] if metadata.include?( "artist" )
+		response.title = metadata["title"] if metadata.include?( "title" )
+		response.album = metadata["album"] if metadata.include?( "album" )
+		response.year = metadata["year"] if metadata.include?( "year" )
+
+		md = /<\/span> ?<\/center>(.*)<center> ?<span style/.match( page_body )
+		return if ! md
+
+		page_body = md[1]
+		page_body.sub!( /&#91;.+ Lyrics on http:\/\/#{site_host()}\/ &#93;/, "" )
+		page_body.sub!( /^.*<\/a>/, "" ) # additional (optional) crap at the beginning
+		page_body.gsub!( /<u>&lt;a[^<]+&lt;\/a&gt;<\/u>/, "" ) # yet more crap
+		page_body.gsub!( /\ ?<br ?\/?> ?/i, "\n" )
+		page_body.sub!( /^\ ?<strong>Lyrics to [^<]+<\/strong> :<\/?br> */i, "" )
+
+		page_body.strip!()
+
+		response.lyrics = page_body
+
+	end
+
+	def build_suggestions_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist ) )
+	end
+
+	def suggestions_page_valid?( request, page_body, page_url )
+		md = /<title>([^<]+) Lyrics<\/title>/i.match( page_body )
+		return md ? Strings.normalize( md[1] ).index( Strings.normalize( request.artist ) ) : nil
+	end
+
+	# returns an array of maps with following keys: url, artist, title
+	def parse_suggestions( request, page_body, page_url )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		suggestions = []
+
+		# remove table with other artists at the bottom
+		return suggestions if ! page_body.sub!( /(.*)<table.*/, "\\1" )
+
+		md = /<table width=100%>(.*)<\/table>/.match( page_body )
+		return suggestions if ! md
+
+		md[1].split( /<a href=/ ).each() do |entry|
+			if (md = /"(\/lyrics\/[^"]+)" title="[^"]+"> ?([^>]+) lyrics<\/a><br>/.match( entry ))
+				suggestions << Suggestion.new( request.artist, md[2], "http://#{site_host()}#{md[1]}" )
+			end
+		end
+
+		return suggestions
+
+	end
+
+end

data/lib/wiki_lyrics/lyrics_Lyriki.rb

@@ -0,0 +1,287 @@
+# Copyright (C) 2006-2008 by Sergio Pistone
+# sergio_pistone@yahoo.com.ar
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "utils/http"
+require "gui/gui"
+require "mediawikilyrics"
+
+require "uri"
+require "cgi"
+
+class Lyriki < MediaWikiLyrics
+
+	def Lyriki.site_host()
+		return "www.lyriki.com"
+	end
+
+	def Lyriki.site_name()
+		return "Lyriki"
+	end
+
+	def Lyriki.control_page()
+		return "Lyriki:Wiki-Lyrics"
+	end
+
+	def parse_lyrics( response, page_body )
+
+		custom_data = {}
+
+		if (md = /\{\{\s*[Ss]ong\s*\|.*$/m.match( page_body ))
+
+			template_data = parse_template( md[0] )
+			template_data["params"].each() do |key, value|
+				custom_data[key.to_s()] = value
+				if value.is_a?( String )
+					value.gsub!( /<br ?\/?>/i, "; " ) if key != "song"
+					value.gsub!( /<\/?[^>]+\/?>/, " " )
+					value.tr_s!( " \n\r\t", " " )
+					value.strip!()
+				end
+			end
+
+			response.title = custom_data["song"] if custom_data.include?( "song" )
+
+			if custom_data["artist"].is_a?( String )
+				response.artist = custom_data["artist"]
+			elsif custom_data["artists"].is_a?( Array )
+				artist = ""
+				custom_data["artists"].each() do |token|
+					if token.is_a?( String )
+						artist << token.gsub( /\[\[|\]\]/, "" )
+					elsif token.is_a?( Hash ) && token["name"].downcase() == "song artist" && token["params"][1]
+						artist << token["params"][1]
+					end
+				end
+				artist.gsub!( /\s*<br *\/?>\s*/i, " " )
+				response.artist = artist
+			elsif custom_data["artists"].is_a?( String ) # this case is DEPRECATED by Lyriki guides
+				response.artist = custom_data["artists"].gsub( /\[\[|\]\]/, "" )
+			end
+
+			if custom_data["album"].is_a?( String )
+				response.album, response.year = custom_data["album"], custom_data["year"]
+			elsif custom_data["albums"].is_a?( Array )
+				custom_data["albums"].each() do |token|
+					if token.is_a?( String )
+						if (md = /([^:]+):(.+) \(([0-9]{4,4})\)/.match( token ))
+							response.album, response.year = md[2], md[3]
+							break
+						end
+					elsif token.is_a?( Hash )
+						if token["name"].downcase() == "song album" && token["params"][2] && token["params"][3]
+							response.album, response.year = token["params"][2], token["params"][3]
+							break
+						end
+					end
+				end
+			end
+
+		end
+
+		custom_data["reviewed"] = (/\{\{[Aa]utoGenerated\}\}/.match( page_body ) == nil)
+
+		if (md = /<lyrics>(.*)<\/lyrics>/im.match( page_body ))
+	 		page_body = md[1]
+			page_body.gsub!( /[ \t]*[\r\n][ \t]*/m, "\n" )
+		else
+			page_body.gsub!( /\{\{.*\}\}\n?/, "" )
+			page_body.gsub!( /\[\[Category:.*\]\]\n?/, "" )
+			page_body.gsub!( /\ *== *(External *Links|Links) *==.*$/im, "" )
+			page_body = page_body.split( "\n" ).collect() do |line|
+				if line.index( /\s/ ) == 0
+					"\n" + line
+				else
+					line
+				end
+			end.join( "" )
+			page_body.gsub!( /\s*<br ?\/?>\s*/i, "\n" )
+		end
+
+		response.lyrics = page_body if ! Strings.empty?( page_body )
+		response.custom_data = custom_data
+
+	end
+
+	def Lyriki.build_tracks( album_data )
+		ret = ""
+		album_data.tracks.each() do |track|
+			track_length = track.length > 0 ?
+				"|#{track.length / 60}:#{track.length % 60 < 10 ? "0#{track.length % 60}" : track.length % 60}" :
+				""
+			track_artist = cleanup_title_token( track.artist )
+			track_title  = cleanup_title_token( track.title )
+			if album_data.various_artists?
+				ret += "# {{song link va|#{track_artist}|#{track_title}#{track_length}}}\n"
+			else
+				ret += "# {{song link|#{track_artist}|#{track_title}#{track_length}}}\n"
+			end
+		end
+		return ret
+	end
+
+	def Lyriki.build_album_page( reviewed, artist, album, year, month, day, tracks, album_art )
+
+		raise ArgumentError if Strings.empty?( artist ) || Strings.empty?( album ) || Strings.empty?( tracks )
+
+		s_name = get_sort_name( album )
+		s_letter = get_sort_letter( album )
+
+		album_art = nil if ! year || album_art == build_album_art_name( artist, album, year, "jpg", false )
+
+		contents = \
+		"#{reviewed ? "" : "{{autoGenerated}}\n"}" \
+		"{{Album\n" \
+		"| album    = #{album}\n" \
+		"| artist   = #{artist}\n" \
+		"| released = #{build_date( year, month, day )}\n" \
+		"#{album_art ? "| image    = #{album_art}\n" : ""}" \
+		"| tracks   =\n"
+
+		return \
+		"#{contents}" \
+		"#{tracks.strip()}\n" \
+		"}}\n" \
+		"\n" \
+		"{{C:Album|#{s_letter}|#{s_name}}}"
+	end
+
+	def Lyriki.build_song_page( reviewed, artist, title, album, year, credits, lyricist, lyrics )
+
+		raise ArgumentError if artist == nil || title == nil
+
+		s_name = get_sort_name( title )
+		s_letter = get_sort_letter( title )
+		year = year.to_i() <= 1900 ? "" : year.to_s()
+
+		song_page = reviewed ? "": "{{autoGenerated}}\n"
+
+		if (md = /^([^\s].*)\s+feat\.\s+([^\s].*)$/i.match( artist.strip() ))
+			artist, fartist = md[1].strip(), md[2]
+			song_page <<
+			"{{Song\n" \
+			"| song     = #{title}\n" \
+			"| artists  = {{song artist|#{artist}}}<br />feat. {{song artist|#{fartist}}}\n" \
+			"| albums   = {{song album|#{artist}|#{album}|#{year}}}\n" \
+			"| credits  = #{credits.to_s().split( "; " ).join( "<br />" )}\n" \
+			"| lyricist = #{lyricist.to_s().split( "; " ).join( "<br />" )}\n" \
+			"}}\n" \
+		else
+			song_page <<
+			"{{Song\n" \
+			"| song     = #{title}\n" \
+			"| artist   = #{artist}\n" \
+			"| album    = #{album}\n" \
+			"| year     = #{year}\n" \
+			"| credits  = #{credits.to_s().split( "; " ).join( "<br />" )}\n" \
+			"| lyricist = #{lyricist.to_s().split( "; " ).join( "<br />" )}\n" \
+			"}}\n" \
+		end
+
+		return song_page <<
+		"\n" \
+		"<lyrics>#{Strings.empty?( lyrics ) ? "<tt>(Instrumental)</tt>" : lyrics}</lyrics>\n" \
+		"\n" \
+		"{{C:Song|#{s_letter}|#{s_name}}}"
+	end
+
+	def Lyriki.build_album_art_name( artist, album, year, extension="jpg", cleanup=true )
+		if cleanup
+			artist = cleanup_title_token( artist )
+			album = cleanup_title_token( album )
+		end
+		album_art_name = "AlbumArt-#{artist}-#{album}_(#{year})#{Strings.empty?( extension ) ? "" : ".#{extension.strip()}"}".gsub( " ", "_" )
+		return Strings.remove_invalid_filename_chars( album_art_name )
+	end
+
+	def Lyriki.build_album_art_description( artist, album, year, cleanup=true )
+		if cleanup
+			artist = cleanup_title_token( artist )
+			album = cleanup_title_token( album )
+		end
+		return "#{artist}:#{album} (#{year})"
+	end
+
+	def Lyriki.find_album_art_name( artist, album, year )
+
+		normalized_artist = cleanup_title_token( artist )
+		Strings.remove_invalid_filename_chars!( normalized_artist )
+		Strings.normalize!( normalized_artist )
+		normalized_artist.gsub!( " ", "" )
+
+		normalized_album = cleanup_title_token( album )
+		Strings.remove_invalid_filename_chars!( normalized_album )
+		Strings.normalize!( normalized_album )
+		normalized_album.gsub!( " ", "" )
+
+		year = year.to_s().strip()
+
+		artist = cleanup_title_token( artist )
+		Strings.remove_invalid_filename_chars!( artist )
+		search_url = "http://#{site_host()}/index.php?ns6=1&search=#{CGI.escape( artist )}&searchx=Search&limit=500"
+		response, search_url = HTTP.fetch_page_get( search_url )
+
+		return nil if response == nil || response.body() == nil
+
+		candidates = []
+		parse_search_results( response.body(), true ).each() do |result|
+
+			next if result[@@SEARCH_RESULT_TITLE].index( "Image:" ) != 0
+
+			normalized_title = Strings.normalize( result[@@SEARCH_RESULT_TITLE] )
+			normalized_title.gsub!( " ", "" )
+
+			matches = 0
+			idx1 = normalized_title.index( "albumart" )
+			matches += 1 if idx1
+			idx1 = idx1 ? idx1 + "albumart".size : 0
+			idx2 = normalized_title.index( normalized_artist, idx1 )
+			matches += 4 if idx2
+			idx2 = idx2 ? idx2 + normalized_artist.size : idx1
+			idx3 = normalized_title.index( normalized_album, idx2 )
+			next if idx3 == nil
+			idx3 = idx3 ? idx3 + normalized_album.size : idx2
+			idx3 = normalized_title.index( year, idx3 )
+			matches += 2 if idx3
+
+			candidates.insert( -1, [ matches, result[@@SEARCH_RESULT_TITLE] ] )
+		end
+
+		if candidates.size > 0
+			candidates.sort!() { |x,y| y[0] <=> x[0] }
+			return URI.decode( candidates[0][1].slice( "Image:".size..-1 ).gsub( " ", "_" ) )
+		else
+			return nil
+		end
+	end
+
+	def Lyriki.cleanup_title_token!( title, downcase=false )
+		title.gsub!( /\[[^\]\[]*\]/, "" )
+		title.gsub!( /[\[|\]].*$/, "" )
+		title.gsub!( /`|´|’/, "'" )
+		title.gsub!( /''|«|»/, "\"" )
+		title.squeeze!( " " )
+		title.strip!()
+		title.gsub!( "+", "and" )
+		Strings.titlecase!( title, true, downcase )
+		return title
+	end
+
+end