[subtitle] beginning backend opensubtitles

modules/opensubtitles/__init__.py

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

modules/opensubtitles/backend.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 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.subtitle import ICapSubtitle
+from weboob.tools.backend import BaseBackend
+
+from .browser import OpensubtitlesBrowser
+
+from urllib import quote_plus
+
+__all__ = ['OpensubtitlesBackend']
+
+
+class OpensubtitlesBackend(BaseBackend, ICapSubtitle):
+    NAME = 'opensubtitles'
+    MAINTAINER = u'Julien Veyssier'
+    EMAIL = 'julien.veyssier@aiur.fr'
+    VERSION = '0.f'
+    DESCRIPTION = 'Opensubtitles subtitle website'
+    LICENSE = 'AGPLv3+'
+    LANGUAGE_CONV = {'fr':'fre','en':'eng'}
+    BROWSER = OpensubtitlesBrowser
+
+    def create_default_browser(self):
+        return self.create_browser()
+
+    def get_subtitle(self, id):
+        return self.browser.get_subtitle(id)
+
+    def get_subtitle_file(self, id):
+        subtitle = self.browser.get_subtitle(id)
+        if not subtitle:
+            return None
+
+        return self.browser.openurl(subtitle.url.encode('utf-8')).read()
+
+    def iter_subtitles(self, language, pattern):
+        if language not in self.LANGUAGE_CONV.keys():
+            return []
+        return self.browser.iter_subtitles(language,quote_plus(pattern.encode('utf-8')))

modules/opensubtitles/browser.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 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 SubtitlesPage, SearchPage
+
+
+__all__ = ['OpensubtitlesBrowser']
+
+
+class OpensubtitlesBrowser(BaseBrowser):
+    DOMAIN = 'www.opensubtitles.org'
+    PROTOCOL = 'http'
+    ENCODING = 'utf-8'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
+    PAGES = {
+        'http://www.opensubtitles.org.*search2/sublanguageid.*moviename.*': SearchPage,
+        'http://www.opensubtitles.org.*search/sublanguageid.*idmovie.*': SubtitlesPage,
+        'http://www.opensubtitles.org.*search/imdbid.*/sublanguageid.*/moviename.*' : SubtitlesPage
+        }
+    LANGUAGE_CONV = {'fr':'fre','en':'eng'}
+
+    def iter_subtitles(self, language, pattern):
+        lang = self.LANGUAGE_CONV[language]
+        self.location('http://www.opensubtitles.org/search2/sublanguageid-%s/moviename-%s' % (lang,pattern.encode('utf-8')))
+        assert self.is_on_page(SearchPage) or self.is_on_page(SubtitlesPage)
+        return self.page.iter_subtitles(language,pattern)
+
+    def get_subtitle(self, id):
+        ids = id.split('|')
+        id_movie = ids[0]
+        id_file = ids[1]
+        self.location('http://www.opensubtitles.org/search/sublanguageid-all/idmovie-%s' % id_movie)
+        assert self.is_on_page(SubtitlesPage)
+        return self.page.get_subtitle(id_file)

modules/opensubtitles/test.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 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.test import BackendTest
+from weboob.capabilities.base import NotLoaded
+
+import urllib
+from random import choice
+
+class OpensubtitlesTest(BackendTest):
+    BACKEND = 'opensubtitles'
+
+    def test_subtitle(self):
+        subtitles = list(self.backend.iter_subtitles('fr','spiderman'))
+        assert (len(subtitles) > 0)
+        for subtitle in subtitles:
+            path, qs = urllib.splitquery(subtitle.url)
+            assert path.endswith('.zip')
+
+        # get the file of a random sub
+        if len(subtitles):
+            subtitle = choice(subtitles)
+            self.backend.get_subtitle_file(subtitle.id)