Add module for Europarl videos

We currently support committees and other events.
TODO: support plenary sessions
TODO: latest and search

Signed-off-by: François Revol <revol@free.fr>
Signed-off-by: Romain Bignon <romain@symlink.me>

modules/europarl/__init__.py

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

modules/europarl/backend.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+# Copyright(C) 2012 François Revol
+#
+# 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, BaseVideo
+from weboob.tools.backend import BaseBackend
+from weboob.capabilities.collection import ICapCollection, CollectionNotFound
+
+from .browser import EuroparlBrowser
+from .video import EuroparlVideo
+
+
+__all__ = ['EuroparlBackend']
+
+
+class EuroparlBackend(BaseBackend, ICapVideo, ICapCollection):
+    NAME = 'europarl'
+    MAINTAINER = u'François Revol'
+    EMAIL = 'revol@free.fr'
+    VERSION = '0.d'
+    DESCRIPTION = 'Europarl parliamentary video streaming website'
+    LICENSE = 'AGPLv3+'
+    BROWSER = EuroparlBrowser
+
+    def get_video(self, _id):
+        with self.browser:
+            return self.browser.get_video(_id)
+
+    SORTBY = ['relevance', 'rating', 'views', 'time']
+
+    # def search_videos(self, pattern, sortby=ICapVideo.SEARCH_RELEVANCE, nsfw=False, max_results=None):
+    #     with self.browser:
+    #         return self.browser.search_videos(pattern, self.SORTBY[sortby])
+
+    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(EuroparlVideo.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
+
+    def iter_resources(self, objs, split_path):
+        if BaseVideo in objs:
+            collection = self.get_collection(objs, split_path)
+            if collection.path_level == 0:
+                yield self.get_collection(objs, [u'latest'])
+            if collection.split_path == [u'latest']:
+                for video in self.browser.latest_videos():
+                    yield video
+
+    def validate_collection(self, objs, collection):
+        if collection.path_level == 0:
+            return
+        if BaseVideo in objs and collection.split_path == [u'latest']:
+            collection.title = u'Latest Europarl videos'
+            return
+        raise CollectionNotFound(collection.split_path)
+
+    OBJECTS = {EuroparlVideo: fill_video}

modules/europarl/browser.py

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+# Copyright(C) 2012 François Revol
+#
+# 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.index import IndexPage
+from .pages import VideoPage
+from .video import EuroparlVideo
+
+
+__all__ = ['EuroparlBrowser']
+
+
+class EuroparlBrowser(BaseBrowser):
+    DOMAIN = 'europarl.europa.eu'
+    ENCODING = None
+    PAGES = {r'http://[w\.]*europarl\.europa\.eu/ep-live/(?P<lang>\w+)/committees/video\?.*event=(?P<id>[^&]+).*': VideoPage,
+             r'http://[w\.]*europarl\.europa\.eu/ep-live/(?P<lang>\w+)/other-events/video\?.*event=(?P<id>[^&]+).*': VideoPage
+#TODO:plenaries
+#            r'http://[w\.]*europarl\.europa\.eu/ep-live/(?P<lang>\w+)/plenary/video\?.*date=(?P<id>[^&]+).*': VideoPage
+#            r'http://[w\.]*europarl\.europa\.eu/ep-live/(?P<lang>\w+)/plenary/video\?.*debate=(?P<id>[^&]+).*': VideoPage
+            }
+
+    @id2url(EuroparlVideo.id2url)
+    def get_video(self, url, video=None):
+        self.location(url)
+        return self.page.get_video(video)
+
+    # def search_videos(self, pattern, sortby):
+    #     return None
+    #     self.location(self.buildurl('http://europarltv.europa.eu/en/search%s' % sortby, query=pattern.encode('utf-8')))
+    #     assert self.is_on_page(IndexPage)
+    #     return self.page.iter_videos()
+
+    # def latest_videos(self):
+    #     self.home()
+    #     assert self.is_on_page(IndexPage)
+    #     return self.page.iter_videos()

modules/europarl/pages.py

@@ -0,0 +1,120 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+# Copyright(C) 2012 François Revol
+#
+# 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.mech import ClientForm
+ControlNotFoundError = ClientForm.ControlNotFoundError
+
+from weboob.tools.browser import BasePage
+
+import re
+import datetime
+
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.browser import BrokenPageError
+
+from .video import EuroparlVideo
+
+
+
+__all__ = ['VideoPage']
+
+class VideoPage(BasePage):
+    def get_video(self, video=None):
+        if video is None:
+            video = EuroparlVideo(self.group_dict['id'])
+        video.title = unicode(self.get_title())
+        video.url = unicode(self.get_url())
+        self.set_details(video)
+
+        video.set_empty_fields(NotAvailable)
+        return video
+
+    def get_url(self):
+        # search for <input id="codeUrl">
+        # TODO: plenaries can be downloaded as mp4...
+        obj = self.parser.select(self.document.getroot(), 'input#codeUrl', 1)
+        if obj is None:
+            return None
+        return obj.attrib['value']
+
+    def get_title(self):
+        obj = self.parser.select(self.document.getroot(), 'h1#player_subjectTitle')
+        if len(obj) < 1:
+            obj = self.parser.select(self.document.getroot(), 'title')
+            if len(obj) < 1:
+                return None
+        title = obj[0].text.strip()
+        obj = self.parser.select(self.document.getroot(), 'span.ep_subtitle')
+        if len(obj) < 1:
+            return title
+
+        for span in self.parser.select(obj[0], 'span.ep_acronym, span.ep_theme'):
+            if span.text_content():
+                title += ' ' + span.text_content().strip()
+        
+        return title
+
+    def set_details(self, v):
+        v.author = u'European Parliament'
+        obj = self.parser.select(self.document.getroot(), 'meta[name=available]', 1)
+        if obj is not None:
+            value = obj.attrib['content']
+            print value
+            m = re.match('(\d\d)-(\d\d)-(\d\d\d\d)\s*(\d\d):(\d\d)', value)
+            if not m:
+                raise BrokenPageError('Unable to parse datetime: %r' % value)
+            day = m.group(1)
+            month = m.group(2)
+            year = m.group(3)
+            hour = m.group(4)
+            minute = m.group(5)
+            v.date = datetime.datetime(year=int(year),
+                                       month=int(month),
+                                       day=int(day),
+                                       hour=int(hour),
+                                       minute=int(minute))
+            
+        obj = self.parser.select(self.document.getroot(), 'span.ep_subtitle', 1)
+        if obj is not None:
+            span = self.parser.select(obj, 'span.ep_date', 1)
+            value = span.text
+            m = re.match('(\d\d):(\d\d)\s*\/\s*(\d\d):(\d\d)\s*-\s*(\d\d)-(\d\d)-(\d\d\d\d)', value)
+            if not m:
+                raise BrokenPageError('Unable to parse datetime: %r' % value)
+            bhour = m.group(1)
+            bminute = m.group(2)
+            ehour = m.group(3)
+            eminute = m.group(4)
+            day = m.group(5)
+            month = m.group(6)
+            year = m.group(7)
+            
+            start = datetime.datetime(year=int(year),
+                                      month=int(month),
+                                      day=int(day),
+                                      hour=int(bhour),
+                                      minute=int(bminute))
+            end = datetime.datetime(year=int(year),
+                                    month=int(month),
+                                    day=int(day),
+                                    hour=int(ehour),
+                                    minute=int(eminute))
+
+            v.duration = end - start

modules/europarl/test.py

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+# Copyright(C) 2012 François Revol
+#
+# 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.video import BaseVideo
+
+
+class EuroparlTest(BackendTest):
+    BACKEND = 'europarl'
+
+    # def test_search(self):
+    #     l = list(self.backend.search_videos('neelie kroes'))
+    #     self.assertTrue(len(l) > 0)
+    #     v = l[0]
+    #     self.backend.fillobj(v, ('url',))
+    #     self.assertTrue(v.url and v.url.startswith('http://'), 'URL for video "%s" not found: %s' % (v.id, v.url))
+    #     self.backend.browser.openurl(v.url)
+
+    # def test_latest(self):
+    #     l = list(self.backend.iter_resources([BaseVideo], [u'latest']))
+    #     self.assertTrue(len(l) > 0)
+    #     v = l[0]
+    #     self.backend.fillobj(v, ('url',))
+    #     self.assertTrue(v.url and v.url.startswith('http://'), 'URL for video "%s" not found: %s' % (v.id, v.url))

modules/europarl/video.py

@@ -0,0 +1,50 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Roger Philibert
+#
+# 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
+
+import re
+
+__all__ = ['EuroparlVideo']
+
+
+class EuroparlVideo(BaseVideo):
+    def __init__(self, *args, **kwargs):
+        BaseVideo.__init__(self, *args, **kwargs)
+        self.ext = u'wmv'
+
+    @classmethod
+    def id2url(cls, _id):
+        m = re.match('.*-COMMITTEE-.*', _id)
+        if m:
+            return u'http://www.europarl.europa.eu/ep-live/en/committees/video?event=%s&format=wmv' % _id
+        m = re.match('.*-SPECIAL-.*', _id)
+        if m:
+            return u'http://www.europarl.europa.eu/ep-live/en/other-events/video?event=%s&format=wmv' % _id
+        # XXX: not yet supported
+        m = re.match('\d\d-\d\d-\d\d\d\d', _id)
+        if m:
+            return u'http://www.europarl.europa.eu/ep-live/en/plenary/video?date=%s' % _id
+        # XXX: not yet supported
+        m = re.match('\d+', _id)
+        if m:
+            return u'http://www.europarl.europa.eu/ep-live/en/plenary/video?debate=%s' % _id
+        return None
+