support repositories to manage backends (closes #747)

modules/arte/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# 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 .backend import ArteBackend
+
+__all__ = ['ArteBackend']

modules/arte/backend.py

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# 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 __future__ import with_statement
+
+from weboob.capabilities.video import ICapVideo
+from weboob.tools.backend import BaseBackend, BackendConfig
+from weboob.tools.value import Value
+
+from .browser import ArteBrowser
+from .video import ArteVideo
+
+
+__all__ = ['ArteBackend']
+
+
+class ArteBackend(BaseBackend, ICapVideo):
+    NAME = 'arte'
+    MAINTAINER = 'Romain Bignon'
+    EMAIL = 'romain@weboob.org'
+    VERSION = '0.a'
+    DESCRIPTION = 'Arte french TV'
+    LICENSE = 'AGPLv3+'
+    CONFIG = BackendConfig(Value('lang', label='Lang of videos',
+                                 choices={'fr': 'French', 'de': 'Deutsch', 'en': 'English'}, default='fr'),
+                           Value('quality', label='Quality of videos', choices=['hd', 'sd'], default='hd'))
+    BROWSER = ArteBrowser
+
+    def create_default_browser(self):
+        return self.create_browser(lang=self.config['lang'].get(), quality=self.config['quality'].get())
+
+    def get_video(self, _id):
+        with self.browser:
+            return self.browser.get_video(_id)
+
+    def iter_search_results(self, pattern=None, sortby=ICapVideo.SEARCH_RELEVANCE, nsfw=False, max_results=None):
+        with self.browser:
+            return self.browser.iter_search_results(pattern)
+
+    def fill_video(self, video, fields):
+        if fields != ['thumbnail']:
+            # if we don't want only the thumbnail, we probably want also every fields
+            with self.browser:
+                video = self.browser.get_video(ArteVideo.id2url(video.id), video)
+        if 'thumbnail' in fields and video.thumbnail:
+            with self.browser:
+                video.thumbnail.data = self.browser.readurl(video.thumbnail.url)
+
+        return video
+
+    OBJECTS = {ArteVideo: fill_video}

modules/arte/browser.py

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# 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 weboob.tools.browser.decorators import id2url
+
+from .pages import IndexPage, VideoPage
+from .video import ArteVideo
+
+
+__all__ = ['ArteBrowser']
+
+
+class ArteBrowser(BaseBrowser):
+    DOMAIN = u'videos.arte.tv'
+    ENCODING = None
+    PAGES = {r'http://videos.arte.tv/\w+/videos/arte7.*': IndexPage,
+             r'http://videos.arte.tv/\w+/do_search/videos/.*': IndexPage,
+             r'http://videos.arte.tv/\w+/videos/(?P<id>.+)\.html': VideoPage
+            }
+
+    SEARCH_LANG = {'fr': 'recherche', 'de':'suche', 'en': 'search'}
+
+    def __init__(self, lang, quality, *args, **kwargs):
+        BaseBrowser.__init__(self, *args, **kwargs)
+        self.lang = lang
+        self.quality = quality
+
+    @id2url(ArteVideo.id2url)
+    def get_video(self, url, video=None):
+        self.location(url)
+        return self.page.get_video(video, self.lang, self.quality)
+
+    def home(self):
+        self.location('http://videos.arte.tv/fr/videos/arte7')
+
+    def iter_search_results(self, pattern):
+        if not pattern:
+            self.home()
+        else:
+            self.location(self.buildurl('/%s/do_search/videos/%s' % (self.lang, self.SEARCH_LANG[self.lang]), q=pattern.encode('utf-8')))
+        assert self.is_on_page(IndexPage)
+        return self.page.iter_videos()

modules/arte/pages.py

@@ -0,0 +1,114 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# 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/>.
+
+
+import datetime
+import re
+import urllib
+
+from weboob.tools.browser import BasePage, BrokenPageError
+
+
+from .video import ArteVideo
+
+
+__all__ = ['IndexPage', 'VideoPage']
+
+
+class IndexPage(BasePage):
+    def iter_videos(self):
+        videos = self.document.getroot().cssselect("div[class=video]")
+        for div in videos:
+            title = div.find('h2').find('a').text
+            m = re.match(r'/fr/videos/(.*)\.html', div.find('h2').find('a').attrib['href'])
+            _id = ''
+            if m:
+                _id = m.group(1)
+            rating = rating_max = 0
+            rates = self.parser.select(div, 'div[class=rateContainer]', 1)
+            for r in rates.findall('div'):
+                if 'star-rating-on' in r.attrib['class']:
+                    rating += 1
+                rating_max += 1
+
+            video = ArteVideo(_id)
+            video.title = title
+            video.rating = rating
+            video.rating_max = rating_max
+
+            thumb = self.parser.select(div, 'img[class=thumbnail]', 1)
+            video.thumbnail_url = 'http://videos.arte.tv' + thumb.attrib['src']
+
+            try:
+                parts = self.parser.select(div, 'div.duration_thumbnail', 1).text.split(':')
+                if len(parts) == 2:
+                    hours = 0
+                    minutes, seconds = parts
+                elif len(parts) == 3:
+                    hours, minutes, seconds = parts
+                else:
+                    raise BrokenPageError('Unable to parse duration %r' % parts)
+            except BrokenPageError:
+                pass
+            else:
+                video.duration = datetime.timedelta(hours=int(hours), minutes=int(minutes), seconds=int(seconds))
+
+            yield video
+
+class VideoPage(BasePage):
+    def get_video(self, video=None, lang='fr', quality='hd'):
+        if not video:
+            video = ArteVideo(self.group_dict['id'])
+        video.title = self.get_title()
+        video.url = self.get_url(lang, quality)
+        return video
+
+    def get_title(self):
+        return self.document.getroot().cssselect('h2')[0].text
+
+    def get_url(self, lang, quality):
+        obj = self.parser.select(self.document.getroot(), 'object', 1)
+        movie_url = self.parser.select(obj, 'param[name=movie]', 1)
+        xml_url = urllib.unquote(movie_url.attrib['value'].split('videorefFileUrl=')[-1])
+
+        doc = self.browser.get_document(self.browser.openurl(xml_url))
+        videos_list = self.parser.select(doc.getroot(), 'video')
+        videos = {}
+        for v in videos_list:
+            videos[v.attrib['lang']] = v.attrib['ref']
+
+        if lang in videos:
+            xml_url = videos[lang]
+        else:
+            xml_url = videos.popitem()[1]
+
+        doc = self.browser.get_document(self.browser.openurl(xml_url))
+
+        obj = self.parser.select(doc.getroot(), 'urls', 1)
+        videos_list = self.parser.select(obj, 'url')
+        urls = {}
+        for v in videos_list:
+            urls[v.attrib['quality']] = v.text
+
+        if quality in urls:
+            video_url = urls[quality]
+        else:
+            video_url = urls.popitem()[1]
+
+        return video_url

modules/arte/test.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# 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
+
+class ArteTest(BackendTest):
+    BACKEND = 'arte'
+
+    def test_arte(self):
+        l = list(self.backend.iter_search_results('arte'))
+        if len(l) > 0:
+            v = l[0]
+            self.backend.fillobj(v, ('url',))
+            self.assertTrue(v.url and v.url.startswith('rtmp://'), 'URL for video "%s" not found: %s' % (v.id, v.url))

modules/arte/video.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Christophe Benz
+#
+# 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.video import BaseVideo
+
+
+__all__ = ['ArteVideo']
+
+
+class ArteVideo(BaseVideo):
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://videos.arte.tv/fr/videos/%s.html' % _id