Merge lp:~vuhieple/rhythmbox/plugin-lyrics into lp:rhythmbox

[Le Vu Hiep]

I added two working parsers for the lyrics plugin and edited the LyricsSites.py to include those ones.

[Jonathan Matthew (jmatthew)]

Thanks, but I don't accept patches this way. Please open a bug in GNOME bugzilla and attach a patch there.

Also, it appears you've based your changes to LyricsSites.py on an old version of the file. Please make sure you base your changes on the current code.

review: Disapprove

Unmerged revisions

7879. By Le Vu Hiep on 2012-02-13

Some new parsers for rhythmbox fetching Vietnamese and English lyrics)

=== modified file 'plugins/lyrics/LyricsSites.py'
--- plugins/lyrics/LyricsSites.py	2011-12-19 09:41:45 +0000
+++ plugins/lyrics/LyricsSites.py	2012-02-13 17:49:28 +0000
@@ -25,21 +25,22 @@
 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA.
 
 
+from LyrcParser import LyrcParser
 from AstrawebParser import AstrawebParser
+from LeoslyricsParser import LeoslyricsParser
 from WinampcnParser import WinampcnParser
 from TerraParser import TerraParser
-from DarkLyricsParser import DarkLyricsParser
-
-from gi.repository import RB
-
-import gettext
-gettext.install('rhythmbox', RB.locale_dir())
+from ZingParser import ZingParser
+from MaxiParser import MaxiParser
 
 lyrics_sites = [
+	{ 'id': 'lyrc.com.ar', 		'class': LyrcParser, 		'name': _("Lyrc (lyrc.com.ar)") 		},
 	{ 'id': 'astraweb.com', 	'class': AstrawebParser, 	'name': _("Astraweb (www.astraweb.com)") 	},
+	{ 'id': 'leoslyrics.com', 	'class': LeoslyricsParser, 	'name': _("Leo's Lyrics (www.leoslyrics.com)") 	},
 	{ 'id': 'winampcn.com', 	'class': WinampcnParser, 	'name': _("WinampCN (www.winampcn.com)") 	},
 	{ 'id': 'terra.com.br',		'class': TerraParser,		'name': _("TerraBrasil (terra.com.br)")		},
-	{ 'id': 'darklyrics.com',	'class': DarkLyricsParser,	'name': _("Dark Lyrics (darklyrics.com)")	}
-
+	{ 'id': 'mp3.zing.vn',		'class': ZingParser,		'name': _("ZingVietNam (mp3.zing.vn)")		},
+	{ 'id': 'maxilyrics.com',	'class': MaxiParser,		'name': _("MaxiLyrics (MaxiLyrics)")		}
+	
 ]
 
 
=== added file 'plugins/lyrics/MaxiParser.py'
--- plugins/lyrics/MaxiParser.py	1970-01-01 00:00:00 +0000
+++ plugins/lyrics/MaxiParser.py	2012-02-13 17:49:28 +0000
@@ -0,0 +1,82 @@
+# -*- Mode: python; coding: utf-8; tab-width: 8; indent-tabs-mode: t; -*-
+#
+# Copyright (C) 2012 Le Vu Hiep
+#
+# 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, or (at your option)
+# any later version.
+#
+# The Rhythmbox authors hereby grant permission for non-GPL compatible
+# GStreamer plugins to be used and distributed together with GStreamer
+# and Rhythmbox. This permission is above and beyond the permissions granted
+# by the GPL license by which Rhythmbox is covered. If you modify this code
+# you may extend this exception to your version of the code, but you are not
+# obligated to do so. If you do not wish to do so, delete this exception
+# statement from your 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA.
+
+import urllib2
+import rb
+import re
+import sys
+import urllib
+import HTMLParser
+
+class MaxiParser (object):
+	def __init__(self, artist, title):
+		self.artist = artist
+		self.title = title
+
+	def search(self, callback, *data):
+		artist = urllib.quote(self.artist)
+		title = urllib.quote(self.title)
+		title =	re.sub('(\-|\.wav|\.mp3|\.mid\.wma)','',title)
+
+		if re.search('[uU]nknown',artist):
+			join = urllib.quote('-')
+			content = '%s' % (title)
+
+		else:
+			join = urllib.quote('-')
+			content = '%s%s%s' % (title, join, artist)
+	
+		path ='https://www.google.com/search?sclient=psy-ab&hl=vi&safe=off&source=hp&q='+content+'+site:maxilyrics.com&pbx=1&oq='+content+'+site:maxilyrics.com&aq=f&aqi=&aql=&gs_sm=e&gs_upl=3203972l3209682l9l3209897l17l17l0l0l0l0l190l1691l14.3l17l0&fp=1&biw=1280&bih=640&cad=b&btnI=1&bav=on.2,or.r_gc.r_pw.r_cp.,cf.osb&tch=1&ech=1&psi=9e8vT5_5OcOaiAfk47i7Dg.1328541646416.3'
+	    	req_headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:6.0) Gecko/20100101 Firefox/6.0','Cookie': 'Hello Google','Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8','Accept-Language': 'en-us,en;q=0.5','Accept-Encoding': 'gzip,deflate','Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7','Connection': 'keep-alive','Referer': 'http://www.google.com/search?sourceid=chrome&ie=UTF-8&q='+content}
+    		req  = urllib2.Request(path, headers=req_headers)
+		response = urllib2.urlopen(req)
+		lyrURL = response.info().getheader('Location')
+		self.got_lyrics(lyrURL, callback, *data)
+#		self.parse_lyrics(lyrURL)
+
+	def got_lyrics(self, url, callback, *data):
+		if url is None:
+			callback(None, *data)
+                        return
+                if url is not None:
+			callback(self.parse_lyrics(url), *data)
+		else:
+			callback(None, *data)
+
+	def parse_lyrics(self, uRL):
+#	   	print "Final URL: ===> " + uRL
+		lyrics = urllib.urlopen(uRL).read()
+		lyrics = re.split('<div class=\"contentdiv_leftbox_data\">', lyrics)[1] 
+		lyrics = re.split('</div>', lyrics)[0]
+		lyrics = re.sub('<[Bb][Rr] />', '\n', lyrics)
+		lyrics = re.sub('^\\s{1,}','',lyrics)
+
+		unen = HTMLParser.HTMLParser()
+		lyrics = unen.unescape(lyrics)
+		lyrics += "\n\nGet from MaxiLyrics"
+#		print lyrics
+		return lyrics
 
=== added file 'plugins/lyrics/ZingParser.py'
--- plugins/lyrics/ZingParser.py	1970-01-01 00:00:00 +0000
+++ plugins/lyrics/ZingParser.py	2012-02-13 17:49:28 +0000
@@ -0,0 +1,96 @@
+# -*- Mode: python; coding: utf-8; tab-width: 8; indent-tabs-mode: t; -*-
+#
+# Copyright (C) 2011 Le Vu Hiep
+#
+# 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, or (at your option)
+# any later version.
+#
+# The Rhythmbox authors hereby grant permission for non-GPL compatible
+# GStreamer plugins to be used and distributed together with GStreamer
+# and Rhythmbox. This permission is above and beyond the permissions granted
+# by the GPL license by which Rhythmbox is covered. If you modify this code
+# you may extend this exception to your version of the code, but you are not
+# obligated to do so. If you do not wish to do so, delete this exception
+# statement from your 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA.
+
+import urllib
+import rb
+import re
+import sys
+import unicodedata
+
+
+class ZingParser (object):
+	def __init__(self, artist, title):
+		self.artist = artist
+		self.title = title
+
+	def search(self, callback, *data):
+		path = 'http://mp3.zing.vn/tim-kiem/bai-hat.html'
+		artist = urllib.quote(self.artist)
+		title = urllib.quote(self.title)
+		title = re.sub('(\-|\.wav|\.mp3|\.mid\.wma)','',title)
+
+                if re.search('[uU]nknown',artist):
+                        content = '%s' % (title)
+
+                else:
+                        join = urllib.quote('-')
+                        content = '%s%s%s' % (title, join, artist)
+
+		wurl = '?q='+content+'&filter=4&search_type=bai-hat'
+		print "search URL: " + path + wurl
+
+		loader = rb.Loader()
+		loader.get_url (path + wurl, self.got_lyrics, callback, *data)
+
+	def got_lyrics(self, result, callback, *data):
+		
+		if result is None:
+			callback (None, *data)
+			return
+		if result is not None:
+			result = result.decode('iso-8859-1').encode('UTF-8')
+
+			if re.search('<strong>0</strong>', result):
+				print "======NO SONG FOUND===="
+				callback (None, *data)
+
+			elif re.search('<div class="first-search-song">', result):
+                                print "=======FOUND========="
+				callback(self.parse_lyrics(result), *data)
+			else:
+				callback (None, *data)
+		else:
+			callback (None, *data)
+
+	def parse_lyrics(self, source):
+		
+
+		source = re.split('\<div\ class\=\"first-search-song\"\>',source)[1]
+		source = re.split('href\=\"',source)[1]
+		source = re.split('\"\>',source)[0]
+		mylink = 'http://mp3.zing.vn' + source
+       	        print "search URL: " + mylink
+		lyrics = urllib.urlopen(mylink).read()
+
+		lyrics = re.split('</span></span>', lyrics)[1] 
+		lyrics = re.split('</p>', lyrics)[0]
+		lyrics = re.sub('<[Bb][Rr] />', '', lyrics)
+		lyrics = re.sub('^\\s{1,}','',lyrics)
+		lyrics += "\n\nGet from Zing"
+#		print lyrics	
+		
+		return lyrics