first version of arretsurimages module. Search does not work and download name of the file is incorrect. Don't know why.

Signed-off-by: franek <franek@chicour.net>

modules/arretsurimages/__init__.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013      franek
+#
+# 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 ArretSurImagesBackend
+
+
+__all__ = ['ArretSurImagesBackend']

modules/arretsurimages/backend.py

@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013      franek
+#
+# 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 ICapVideo, BaseVideo
+from weboob.capabilities.collection import ICapCollection, CollectionNotFound
+from weboob.tools.backend import BaseBackend, BackendConfig
+from weboob.tools.value import ValueBackendPassword
+
+from .browser import ArretSurImagesBrowser
+from .video import ArretSurImagesVideo
+
+__all__ = ['ArretSurImagesBackend']
+
+
+class ArretSurImagesBackend(BaseBackend, ICapVideo, ICapCollection):
+    NAME = 'arretsurimages'
+    DESCRIPTION = u'arretsurimages website'
+    MAINTAINER = u'franek'
+    EMAIL = 'franek@chicour.net'
+    VERSION = '0.f'
+
+    CONFIG = BackendConfig(ValueBackendPassword('login',    label='email', masked=False),
+                           ValueBackendPassword('password', label='Password'))
+    BROWSER = ArretSurImagesBrowser
+    
+    def create_default_browser(self):
+        return self.create_browser(self.config['login'].get(), self.config['password'].get())
+    
+    def search_videos(self, pattern, sortby=ICapVideo.SEARCH_RELEVANCE, nsfw=False, max_results=None):
+        with self.browser:
+            return self.browser.search_videos(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(ArretSurImagesVideo.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 = {ArretSurImagesVideo: fill_video}

modules/arretsurimages/browser.py

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013      franek
+#
+# 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, BrowserIncorrectPassword
+from weboob.tools.browser.decorators import id2url
+
+from .pages import VideoPage, IndexPage, LoginPage, LoginRedirectPage
+from .video import ArretSurImagesVideo
+
+
+__all__ = ['ArretSurImagesBrowser']
+
+
+class ArretSurImagesBrowser(BaseBrowser):
+    PROTOCOL = 'http'
+    DOMAIN = 'www.arretsurimages.net'
+    ENCODING = None
+
+    PAGES = {
+        '%s://%s/contenu.php\?id=.+' % (PROTOCOL, DOMAIN): VideoPage,
+        '%s://%s/emissions.php' % (PROTOCOL, DOMAIN): IndexPage,
+        '%s://%s/forum/login.php' % (PROTOCOL, DOMAIN): LoginPage,
+        '%s://%s/forum/index.php' % (PROTOCOL, DOMAIN): LoginRedirectPage,
+    }
+    
+    def home(self):
+        self.location('http://www.arretsurimages.net')
+
+    def search_videos(self, pattern):
+        self.location(self.buildurl('/emissions.php'))
+        assert self.is_on_page(IndexPage)
+        return self.page.iter_videos()
+        
+    @id2url(ArretSurImagesVideo.id2url)
+    def get_video(self, url, video=None):
+        self.login()
+        self.location(url)
+        return self.page.get_video(video)
+        
+    def is_logged(self):
+        return self.is_on_page(LoginPage) == False
+
+    def login(self):
+        if not self.is_on_page(LoginPage):
+            self.location('http://www.arretsurimages.net/forum/login.php', no_login=True)
+
+        self.page.login(self.username, self.password)
+
+        if not self.is_logged():
+            raise BrowserIncorrectPassword()        
+

modules/arretsurimages/pages.py

@@ -0,0 +1,119 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013      franek
+#
+# 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 re
+import mechanize
+
+from weboob.capabilities.base import UserError
+from weboob.tools.browser import BasePage, BrokenPageError
+from weboob.tools.capabilities.thumbnail import Thumbnail
+from weboob.capabilities import NotAvailable
+
+
+__all__ = ['IndexPage', 'VideoPage', 'ForbiddenVideo', 'LoginPage', 'LoginRedirectPage']
+
+from .video import ArretSurImagesVideo
+
+
+class IndexPage(BasePage):
+    def iter_videos(self):
+        videos = self.document.getroot().cssselect("div[class=bloc-contenu-8]")
+        for div in videos:
+            title = self.parser.select(div, 'a.typo-titre', 1).text_content().replace('  ', ' ')
+            m = re.match(r'/contenu.php\?id=(.*)', div.find('a').attrib['href'])
+            _id = ''
+            if m:
+                _id = m.group(1)
+
+
+            video = ArretSurImagesVideo(_id)
+            video.title = unicode(title)
+            video.rating = None
+            video.rating_max = None
+
+            thumb = self.parser.select(div, 'img', 1)
+            video.thumbnail = Thumbnail(u'http://www.arretsurimages.net' + thumb.attrib['src'])
+
+            yield video
+
+class ForbiddenVideo(UserError):
+    pass
+
+
+class VideoPage(BasePage):
+    def is_logged(self):
+        try:
+            self.parser.select(self.document.getroot(), '#user-info', 1)
+        except BrokenPageError:
+            return False
+        else:
+            return True
+
+    def on_loaded(self):
+        if not self.is_logged():
+            raise ForbiddenVideo('This video or group may contain content that is inappropriate for some users')
+
+    def get_video(self, video=None):
+        if not video:
+            video = ArretSurImagesVideo(self.get_id)
+        video.title = unicode(self.get_title())
+        video.url = unicode(self.get_url())
+        video.set_empty_fields(NotAvailable)
+        return video
+
+    def get_title(self):
+        title = self.document.getroot().cssselect('div[id=titrage-contenu] h1')[0].text
+        return title;
+        
+    def get_id(self):
+        m = self.URL_REGEXP.match(self['url'])
+        if m:
+            return self.create_id(m.group(1))
+        self.logger.warning('Unable to parse ID')
+        return 0
+        
+    def get_url(self):
+        obj = self.parser.select(self.document.getroot(), 'a.bouton-telecharger', 1)
+        firstUrl = obj.attrib['href']
+        doc = self.browser.get_document(self.browser.openurl(firstUrl))
+        links = doc.xpath('//a');
+        url = None;
+        i = 1
+        for link in links :
+            # we take the second link of the page
+            if i == 2:
+                url = link.attrib['href']
+            i=i+1
+        return url
+        
+class LoginPage(BasePage):
+    def login(self, username, password):
+        response = self.browser.response()
+        response.set_data(response.get_data().replace("<br/>", "<br />")) #Python mechanize is broken, fixing it.
+        self.browser.set_response(response)
+        self.browser.select_form(nr=0)
+        self.browser.form.set_all_readonly(False) 
+        self.browser['redir'] = '/forum/index.php'
+        self.browser['username'] = username
+        self.browser['password'] = password
+        self.browser.submit()        
+
+
+class LoginRedirectPage(BasePage):
+    pass

modules/arretsurimages/test.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013      franek
+#
+# 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 ArretSurImagesTest(BackendTest):
+    BACKEND = 'arretsurimages'
+
+    def test_arretsurimages(self):
+        raise NotImplementedError()

modules/arretsurimages/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__ = ['ArretSurImagesVideo']
+
+
+class ArretSurImagesVideo(BaseVideo):
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://www.arretsurimages.net/contenu.php?id=%s' % _id