[booblyrics] new backend seeklyrics

This commit is contained in:
Julien Veyssier 2013-03-07 18:04:02 +01:00
commit 35645793e0
7 changed files with 246 additions and 5 deletions

View file

@ -0,0 +1,3 @@
from .backend import SeeklyricsBackend
__all__ = ['SeeklyricsBackend']

View file

@ -0,0 +1,48 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2013 Julien Veyssier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.capabilities.lyrics import ICapLyrics
from weboob.tools.backend import BaseBackend
from .browser import SeeklyricsBrowser
from urllib import quote_plus
from contextlib import closing
from gzip import GzipFile
__all__ = ['SeeklyricsBackend']
class SeeklyricsBackend(BaseBackend, ICapLyrics):
NAME = 'seeklyrics'
MAINTAINER = u'Julien Veyssier'
EMAIL = 'julien.veyssier@aiur.fr'
VERSION = '0.f'
DESCRIPTION = 'SeekLyrics lyrics website'
LICENSE = 'AGPLv3+'
BROWSER = SeeklyricsBrowser
def create_default_browser(self):
return self.create_browser()
def get_lyrics(self, id):
return self.browser.get_lyrics(id)
def iter_lyrics(self, pattern):
return self.browser.iter_lyrics(quote_plus(pattern.encode('utf-8')))

View file

@ -0,0 +1,47 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2013 Julien Veyssier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.browser import BaseBrowser
from .pages import ResultsPage, SonglyricsPage
__all__ = ['SeeklyricsBrowser']
class SeeklyricsBrowser(BaseBrowser):
DOMAIN = 'www.seeklyrics.com'
PROTOCOL = 'http'
ENCODING = 'iso-8859-1'
USER_AGENT = BaseBrowser.USER_AGENTS['wget']
PAGES = {
'http://www.seeklyrics.com/search.php.*': ResultsPage,
'http://www.seeklyrics.com/lyrics/.*': SonglyricsPage,
}
def iter_lyrics(self, pattern):
self.location('http://www.seeklyrics.com/search.php?q=%s&t=1' % pattern.encode('utf-8'))
assert self.is_on_page(ResultsPage)
return self.page.iter_lyrics()
def get_lyrics(self, id):
self.location('http://www.seeklyrics.com/lyrics/%s.html' % id)
assert self.is_on_page(SonglyricsPage)
return self.page.get_lyrics(id)

View file

@ -0,0 +1,68 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2013 Julien Veyssier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
try:
from urlparse import parse_qs
except ImportError:
from cgi import parse_qs # NOQA
from urlparse import urlsplit
from weboob.capabilities.lyrics import SongLyrics
from weboob.capabilities.base import NotAvailable, NotLoaded
from weboob.tools.browser import BasePage
__all__ = ['ResultsPage','SonglyricsPage']
class ResultsPage(BasePage):
def iter_lyrics(self):
first = True
for tr in self.parser.select(self.document.getroot(),'table[title~=Results] tr'):
if first:
first = False
continue
artist = NotAvailable
ftitle = self.parser.select(tr,'a > font > font',1)
title = ftitle.getparent().getparent().text_content()
id = ftitle.getparent().getparent().attrib.get('href','').replace('/lyrics/','').replace('.html','')
aartist = self.parser.select(tr,'a')[-1]
artist = aartist.text
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
class SonglyricsPage(BasePage):
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
l_artitle = self.parser.select(self.document.getroot(),'table.text td > b > h2')
if len(l_artitle) > 0:
artitle = l_artitle[0].text.split(' Lyrics by ')
artist = artitle[1]
title = artitle[0]
content = self.parser.select(self.document.getroot(),'div#songlyrics',1).text_content().strip()
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics

View file

@ -0,0 +1,40 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2013
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.test import BackendTest
from weboob.capabilities.base import NotLoaded
from random import choice
class SeeklyricsTest(BackendTest):
BACKEND = 'seeklyrics'
def test_search(self):
l_lyrics = list(self.backend.iter_lyrics('Complainte'))
for songlyrics in l_lyrics:
assert songlyrics.id
assert songlyrics.title
assert songlyrics.artist
assert songlyrics.content is NotLoaded
full_lyr = self.backend.get_lyrics(songlyrics.id)
assert full_lyr.id
assert full_lyr.title
assert full_lyr.artist
assert full_lyr.content is not NotLoaded