support repositories to manage backends (closes #747)

modules/canalplus/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 CanalplusBackend
+
+__all__ = ['CanalplusBackend']

modules/canalplus/backend.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 CanalplusBrowser
+from .pages import CanalplusVideo
+
+from weboob.capabilities.collection import ICapCollection
+
+
+__all__ = ['CanalplusBackend']
+
+
+class CanalplusBackend(BaseBackend, ICapVideo, ICapCollection):
+    NAME = 'canalplus'
+    MAINTAINER = 'Nicolas Duhamel'
+    EMAIL = 'nicolas@jombi.fr'
+    VERSION = '0.a'
+    DESCRIPTION = 'Canal plus french TV'
+    LICENSE = 'AGPLv3+'
+    CONFIG = BackendConfig(Value('quality', label='Quality of videos', choices=['hd', 'sd'], default='hd'))
+    BROWSER = CanalplusBrowser
+
+    def create_default_browser(self):
+        return self.create_browser(quality=self.config['quality'].get())
+
+    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 get_video(self, _id):
+        with self.browser:
+            return self.browser.get_video(_id)
+
+    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(CanalplusVideo.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 = {CanalplusVideo: fill_video}
+
+    def iter_resources(self, splited_path):
+        with self.browser:
+            return self.browser.iter_resources(splited_path)

modules/canalplus/browser.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 urllib
+
+import lxml.etree
+
+from weboob.tools.browser import BaseBrowser
+from weboob.tools.browser.decorators import id2url
+
+from .pages import InitPage, CanalplusVideo, VideoPage
+
+from weboob.capabilities.collection import Collection, CollectionNotFound
+
+__all__ = ['CanalplusBrowser']
+
+
+class XMLParser(object):
+     def parse(self, data, encoding=None):
+        if encoding is None:
+            parser = None
+        else:
+            parser = lxml.etree.XMLParser(encoding=encoding, strip_cdata=False)
+        return lxml.etree.XML(data.get_data(), parser)
+
+
+class CanalplusBrowser(BaseBrowser):
+    DOMAIN = u'service.canal-plus.com'
+    ENCODING = 'utf-8'
+    PAGES = {
+        r'http://service.canal-plus.com/video/rest/initPlayer/cplus/': InitPage,
+        r'http://service.canal-plus.com/video/rest/search/cplus/.*': VideoPage,
+        r'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/(?P<id>.+)': VideoPage,
+        r'http://service.canal-plus.com/video/rest/getMEAs/cplus/.*': VideoPage,
+        }
+
+    #We need lxml.etree.XMLParser for read CDATA
+    PARSER = XMLParser()
+    FORMATS = {
+        'sd': 'BAS_DEBIT',
+        'hd': 'HD',
+        }
+
+    def __init__(self, quality, *args, **kwargs):
+        BaseBrowser.__init__(self, parser= self.PARSER, *args, **kwargs)
+        if quality in self.FORMATS:
+            self.quality = self.FORMATS[quality]
+        else:
+            self.quality = 'HD'
+
+    def home(self):
+        self.location('http://service.canal-plus.com/video/rest/initPlayer/cplus/')
+
+    def iter_search_results(self, pattern):
+        self.location('http://service.canal-plus.com/video/rest/search/cplus/' + urllib.quote_plus(pattern.encode('utf-8')))
+        return self.page.iter_results()
+
+    @id2url(CanalplusVideo.id2url)
+    def get_video(self, url, video=None):
+        self.location(url)
+        return self.page.get_video(video, self.quality)
+
+    def iter_resources(self, splited_path):
+        self.home()
+        collections = self.page.collections
+
+        def walk_res(path, collections):
+            if len(path) == 0 or not isinstance(collections, (list, Collection)):
+                return collections
+            i = path[0]
+            if i not in [collection.title for collection in collections]:
+                raise CollectionNotFound()
+
+            return walk_res(path[1:], [collection.children for collection in collections if collection.title == i][0])
+
+        return walk_res(splited_path, collections)

modules/canalplus/pages/__init__.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 .initpage import InitPage
+from .video import CanalplusVideo
+from .videopage import VideoPage
+
+__all__ = ['InitPage', 'VideoPage',  'CanalplusVideo']

modules/canalplus/pages/initpage.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 BasePage
+
+from weboob.capabilities.collection import Collection
+
+__all__ = ['InitPage']
+
+
+class InitPage(BasePage):
+    
+    def on_loaded(self):
+        self.collections = []
+        
+        def do(id):
+            self.browser.location("http://service.canal-plus.com/video/rest/getMEAs/cplus/" + id)
+            return self.browser.page.iter_channel()
+
+        ### Parse liste des channels
+        for elem in self.document[2].getchildren():
+            coll = Collection()
+            for e in elem.getchildren():
+                if e.tag == "NOM":
+                    coll.title = e.text.strip().encode('utf-8')
+                elif e.tag == "SELECTIONS":
+                    for select in e:
+                        sub = Collection(title=select[1].text.strip().encode('utf-8'))
+                        sub.id = select[0].text
+                        sub.children = do
+                        coll.appendchild(sub)
+            self.collections.append(coll)

modules/canalplus/pages/video.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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__ = ['CanalplusVideo']
+
+
+class CanalplusVideo(BaseVideo):
+    swf_player = False
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' % _id

modules/canalplus/pages/videopage.py

@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Nicolas Duhamel
+#
+# 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 datetime import datetime
+
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.capabilities.thumbnail import Thumbnail
+from weboob.tools.browser import BasePage
+from .video import CanalplusVideo
+
+
+__all__ = ['VideoPage']
+
+
+class VideoPage(BasePage):
+    def parse_video(self, el, video=None, quality=None):
+        _id = el.find('ID').text
+        if _id == '-1':
+            # means the video is not found
+            return None
+
+        if not video:
+            video = CanalplusVideo(_id)
+
+        infos = el.find('INFOS')
+        video.title = u''
+        for part in infos.find('TITRAGE'):
+            if len(part.text.strip()) == 0:
+                continue
+            if len(video.title) > 0:
+                video.title += u' — '
+            video.title += part.text.strip()
+        video.description = infos.find('DESCRIPTION').text
+
+        media = el.find('MEDIA')
+        url = media.find('IMAGES').find('PETIT').text
+        if url:
+            video.thumbnail = Thumbnail(url)
+        else:
+            video.thumbnail = NotAvailable
+        lastest_format = None
+        for format in media.find('VIDEOS'):
+            if format.text is None:
+                continue
+            if format.tag == quality:
+                video.url = format.text
+                break
+            lastest_format = format
+        if not video.url and lastest_format is not None:
+            video.url = lastest_format.text
+
+        day, month, year = map(int, infos.find('PUBLICATION').find('DATE').text.split('/'))
+        hour, minute, second = map(int, infos.find('PUBLICATION').find('HEURE').text.split(':'))
+        video.date = datetime(year, month, day, hour, minute, second)
+
+        return video
+
+    def iter_results(self):
+        for vid in self.document.getchildren():
+            yield self.parse_video(vid)
+
+    def iter_channel(self):
+        for vid in self.document.getchildren():
+	        yield self.parse_video_channel(vid)
+
+    def parse_video_channel(self,el):
+        _id = el[0].text
+        video = CanalplusVideo(_id)
+        video.title = el[2][3][0].text
+        video.date = datetime.now()
+        return video
+
+
+    def get_video(self, video, quality):
+        _id = self.group_dict['id']
+        for vid in self.document.getchildren():
+            if not _id in vid.find('ID').text:
+                continue
+            return self.parse_video(vid, video, quality)

modules/canalplus/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 CanalPlusTest(BackendTest):
+    BACKEND = 'canalplus'
+
+    def test_canalplus(self):
+        l = list(self.backend.iter_search_results('guignol'))
+        self.assertTrue(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))