diff --git a/modules/parolesmusique/__init__.py b/modules/parolesmusique/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..f4a6efb2fe58003c613caafa67111e5018df761c --- /dev/null +++ b/modules/parolesmusique/__init__.py @@ -0,0 +1,3 @@ +from .backend import ParolesmusiqueBackend + +__all__ = ['ParolesmusiqueBackend'] diff --git a/modules/parolesmusique/backend.py b/modules/parolesmusique/backend.py new file mode 100644 index 0000000000000000000000000000000000000000..c564989e11530b062f0a60e5f1db40c8a74afd32 --- /dev/null +++ b/modules/parolesmusique/backend.py @@ -0,0 +1,46 @@ +# -*- 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 . + +from weboob.capabilities.lyrics import ICapLyrics +from weboob.tools.backend import BaseBackend + +from .browser import ParolesmusiqueBrowser + +from urllib import quote_plus + +__all__ = ['ParolesmusiqueBackend'] + + +class ParolesmusiqueBackend(BaseBackend, ICapLyrics): + NAME = 'parolesmusique' + MAINTAINER = u'Julien Veyssier' + EMAIL = 'julien.veyssier@aiur.fr' + VERSION = '0.f' + DESCRIPTION = 'paroles-musique lyrics website' + LICENSE = 'AGPLv3+' + BROWSER = ParolesmusiqueBrowser + + def create_default_browser(self): + return self.create_browser() + + def get_lyrics(self, id): + return self.browser.get_lyrics(id) + + def iter_lyrics(self, criteria, pattern): + return self.browser.iter_lyrics(criteria,pattern.encode('utf-8')) diff --git a/modules/parolesmusique/browser.py b/modules/parolesmusique/browser.py new file mode 100644 index 0000000000000000000000000000000000000000..df8ec4ce0820ec635bcb058faa948b87e3f940f2 --- /dev/null +++ b/modules/parolesmusique/browser.py @@ -0,0 +1,50 @@ +# -*- 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 . + + +from weboob.tools.browser import BaseBrowser + +from .pages import SongResultsPage, SonglyricsPage, ArtistResultsPage, ArtistSongsPage, HomePage + + +__all__ = ['ParolesmusiqueBrowser'] + + +class ParolesmusiqueBrowser(BaseBrowser): + DOMAIN = 'www.paroles-musique.com' + PROTOCOL = 'http' + ENCODING = 'utf-8' + USER_AGENT = BaseBrowser.USER_AGENTS['wget'] + PAGES = { + 'http://www.paroles-musique.com': HomePage, + 'http://www.paroles-musique.com/lyrics-paroles-0-.*,0.php': SongResultsPage, + 'http://www.paroles-musique.com/lyrics-paroles-.*-0,0.php': ArtistResultsPage, + 'http://www.paroles-musique.com/paroles-.*p[0-9]*': SonglyricsPage, + 'http://www.paroles-musique.com/paroles-.*-lyrics,a[0-9]*': ArtistSongsPage, + } + + def iter_lyrics(self, criteria, pattern): + self.location('http://www.paroles-musique.com') + assert self.is_on_page(HomePage) + return self.page.iter_lyrics(criteria,pattern) + + def get_lyrics(self, id): + self.location('http://www.paroles-musique.com/paroles-%s' % id) + assert self.is_on_page(SonglyricsPage) + return self.page.get_lyrics(id) diff --git a/modules/parolesmusique/pages.py b/modules/parolesmusique/pages.py new file mode 100644 index 0000000000000000000000000000000000000000..9f3354acea84f97e4410aaeb407ee6999560a4dd --- /dev/null +++ b/modules/parolesmusique/pages.py @@ -0,0 +1,93 @@ +# -*- 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 . + + +from weboob.capabilities.lyrics import SongLyrics +from weboob.capabilities.base import NotAvailable, NotLoaded +from weboob.tools.browser import BasePage + + +__all__ = ['SongResultsPage','SonglyricsPage', 'ArtistResultsPage', 'ArtistSongsPage', 'HomePage'] + + +class HomePage(BasePage): + def iter_lyrics(self,criteria,pattern): + self.browser.select_form(name='rechercher') + if criteria == 'artist': + self.browser['termes_a'] = pattern + else: + self.browser['termes_t'] = pattern + self.browser.submit() + assert self.browser.is_on_page(SongResultsPage) or self.browser.is_on_page(ArtistResultsPage) + for lyr in self.browser.page.iter_lyrics(): + yield lyr + +class ArtistResultsPage(BasePage): + def iter_lyrics(self): + for link in self.parser.select(self.document.getroot(),'div.cont_cat table a.std'): + artist = unicode(link.text_content()) + self.browser.location('http://www.paroles-musique.com%s'%link.attrib.get('href','')) + assert self.browser.is_on_page(ArtistSongsPage) + for lyr in self.browser.page.iter_lyrics(artist): + yield lyr + + +class ArtistSongsPage(BasePage): + def iter_lyrics(self,artist): + for link in self.parser.select(self.document.getroot(),'div.cont_catA div.art_scroll a'): + href = link.attrib.get('href','') + if href.startswith('./paroles'): + title = unicode(link.text) + id = href.replace('./paroles-','') + songlyrics = SongLyrics(id, title) + songlyrics.artist = artist + songlyrics.content = NotLoaded + yield songlyrics + + +class SongResultsPage(BasePage): + def iter_lyrics(self): + first = True + for tr in self.parser.select(self.document.getroot(),'div.cont_cat table tr'): + if first: + first = False + continue + artist = NotAvailable + links = self.parser.select(tr,'a.std') + title = unicode(links[0].text) + id = links[0].attrib.get('href','').replace('/paroles-','') + artist = unicode(links[1].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 + content = unicode(self.parser.select(self.document.getroot(),'div#lyr_scroll',1).text_content().strip()) + infos = self.parser.select(self.document.getroot(),'h2.lyrics > font') + artist = unicode(infos[0].text) + title = unicode(infos[1].text) + songlyrics = SongLyrics(id, title) + songlyrics.artist = artist + songlyrics.content = content + return songlyrics diff --git a/modules/parolesmusique/test.py b/modules/parolesmusique/test.py new file mode 100644 index 0000000000000000000000000000000000000000..88b89bc5adb548cd8e10ba943a11efc344cf25c7 --- /dev/null +++ b/modules/parolesmusique/test.py @@ -0,0 +1,46 @@ +# -*- 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 . + +from weboob.tools.test import BackendTest +from weboob.capabilities.base import NotLoaded + +class SeeklyricsTest(BackendTest): + BACKEND = 'parolesmusique' + + def test_search_song_n_get(self): + l_lyrics = list(self.backend.iter_lyrics('song','chien')) + 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 + + + def test_search_artist(self): + l_lyrics = list(self.backend.iter_lyrics('artist','boris')) + for songlyrics in l_lyrics: + assert songlyrics.id + assert songlyrics.title + assert songlyrics.artist + assert songlyrics.content is NotLoaded diff --git a/modules/seeklyrics/test.py b/modules/seeklyrics/test.py index d8d656b6d8dfe501cd28eff13fb7848b787bfb3c..cbbe3a0c5ae65507d4868458118b830b0e93c86b 100644 --- a/modules/seeklyrics/test.py +++ b/modules/seeklyrics/test.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright(C) 2013 +# Copyright(C) 2013 Julien Veyssier # # This file is part of weboob. #