/usr/lib/rhythmbox/plugins/lyrics/TerraParser.py is in rhythmbox-plugins 3.0.2-0ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | # -*- Mode: python; coding: utf-8; tab-width: 8; indent-tabs-mode: t; -*-
#
# Copyright (C) 2009 Hardy Beltran Monasterios
#
# 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.parse
import rb
import re
import sys
# Deal with html entities and utf-8
# code taken from django/utils/text.py
from html.entities import name2codepoint
pattern = re.compile("&(#?\w+?);")
def _replace_entity(match):
text = match.group(1)
if text[0] == u'#':
text = text[1:]
try:
if text[0] in u'xX':
c = int(text[1:], 16)
else:
c = int(text)
return chr(c)
except ValueError:
return match.group(0)
else:
try:
return chr(name2codepoint[text])
except (ValueError, KeyError):
return match.group(0)
def unescape_entities(text):
return pattern.sub(_replace_entity, text)
class TerraParser (object):
def __init__(self, artist, title):
self.artist = artist
self.title = title
def search(self, callback, *data):
path = 'http://letras.mus.br/'
artist = urllib.parse.quote(self.artist)
title = urllib.parse.quote(self.title)
join = urllib.parse.quote(' - ')
wurl = 'winamp.php?t=%s%s%s' % (artist, join, title)
print("search URL: " + 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('utf-8')
if re.search('Música não encontrada', result):
print("not found")
callback (None, *data)
elif re.search('<div id="letra">', result):
callback(self.parse_lyrics(result), *data)
else:
callback (None, *data)
else:
callback (None, *data)
def parse_lyrics(self, source):
def unspace(x):
return " ".join(x.split())
def untag(x):
return re.sub('<.*?>', '', x)
source = re.split('<div id="letra">', source)[1]
source = re.split('</?div.*?>', source)
# source[1] = artist+title
# source[2] = lyrics
header = "".join(source[1].splitlines())
# <h1><a>title</a></h1> <h2><a>artist</a></h2>
bits = re.findall('<h.>(.*?)</h.>', header)
artistitle = unspace(untag(" - ".join(bits)))
lyrics = unescape_entities(artistitle) + "\n" + unescape_entities(untag(source[2]))
lyrics += "\n\nEsta letra foi disponibilizada pelo site\nhttp://letras.mus.br"
return lyrics
|