add module jacquieetmichel

AUTHORS

@@ -40,7 +40,7 @@ Christophe Benz <christophe.benz@gmail.com>
         * Bouygues, INA, SFR and Youtube modules maintainer.
 
 Roger Philibert <roger.philibert@gmail.com>
-        * Ehentai, Izneo, OKC and Youjizz modules maintainer.
+        * Ehentai, Izneo, JacquieEtMichel, OKC and Youjizz modules maintainer.
 
 Nicolas Duhamel <nicolas@jombi.fr>
         * BP, CanalPlus and Orange modules maintainer.

modules/jacquieetmichel/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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 JacquieEtMichelBackend
+
+__all__ = ['JacquieEtMichelBackend']

modules/jacquieetmichel/backend.py

@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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 ICapVideo, BaseVideo
+from weboob.capabilities.collection import ICapCollection, CollectionNotFound
+from weboob.tools.backend import BaseBackend
+
+from .browser import JacquieEtMichelBrowser
+from .video import JacquieEtMichelVideo
+
+
+__all__ = ['JacquieEtMichelBackend']
+
+
+class JacquieEtMichelBackend(BaseBackend, ICapVideo, ICapCollection):
+    NAME = 'jacquieetmichel'
+    MAINTAINER = u'Roger Philibert'
+    EMAIL = 'roger.philibert@gmail.com'
+    VERSION = '0.h'
+    DESCRIPTION = 'Jacquie et Michel TV'
+    LICENSE = 'AGPLv3+'
+    BROWSER = JacquieEtMichelBrowser
+
+    def get_video(self, _id):
+        with self.browser:
+            video = self.browser.get_video(_id)
+        return video
+
+    def search_videos(self, pattern, sortby=ICapVideo.SEARCH_RELEVANCE, nsfw=False):
+        if not nsfw:
+            return iter([])
+
+        with self.browser:
+            return self.browser.search_videos(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(JacquieEtMichelVideo.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_nsfw'])
+            if collection.split_path == [u'latest_nsfw']:
+                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_nsfw']:
+            collection.title = u'Latest Jacquie & Michel videos (NSFW)'
+            return
+        raise CollectionNotFound(collection.split_path)
+
+    OBJECTS = {JacquieEtMichelVideo: fill_video}

modules/jacquieetmichel/browser.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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/>.
+
+import urllib
+
+from weboob.tools.browser import BaseBrowser
+from weboob.tools.browser.decorators import id2url
+
+from .video import JacquieEtMichelVideo
+from .pages import VideoPage, ResultsPage
+
+
+__all__ = ['JacquieEtMichelBrowser']
+
+
+class JacquieEtMichelBrowser(BaseBrowser):
+    DOMAIN = u'jacquieetmicheltv.net'
+    ENCODING = None
+    PAGES = {r'https?://.*jacquieetmicheltv.net/': ResultsPage,
+             r'https?://.*jacquieetmicheltv.net/videolist/.*': ResultsPage,
+             r'https?://.*jacquieetmicheltv.net/showvideo/(?P<id>\d+)/.*': VideoPage,
+            }
+
+    @id2url(JacquieEtMichelVideo.id2url)
+    def get_video(self, url, video=None):
+        self.location(url)
+        assert self.is_on_page(VideoPage), 'Should be on video page.'
+        return self.page.get_video(video)
+
+    def search_videos(self, pattern):
+        self.location('/videolist/searchmodevideo/query%s/' % (urllib.quote(pattern.encode('utf-8'))))
+        assert self.is_on_page(ResultsPage)
+        return self.page.iter_videos()
+
+    def latest_videos(self):
+        self.home()
+        assert self.is_on_page(ResultsPage)
+        return self.page.iter_videos()

modules/jacquieetmichel/pages.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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/>.
+
+
+import re
+
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.capabilities.thumbnail import Thumbnail
+from weboob.tools.browser import BasePage, BrokenPageError
+from weboob.tools.misc import to_unicode
+
+from .video import JacquieEtMichelVideo
+
+
+__all__ = ['ResultsPage', 'VideoPage']
+
+
+class ResultsPage(BasePage):
+    def iter_videos(self):
+        for span in self.document.xpath('//ul[@id="list"]/li'):
+            a = self.parser.select(span, 'a', 1)
+            url = a.attrib['href']
+            _id = re.sub(r'/showvideo/(\d+)/.*', r'\1', url)
+
+            video = JacquieEtMichelVideo(_id)
+
+            video.thumbnail = Thumbnail(unicode(span.find('.//img').attrib['src']))
+
+            title_el = self.parser.select(span, 'h2', 1)
+            video.title = to_unicode(title_el.text.strip())
+            video.description = self.parser.tocleanstring(span.xpath('.//div[@class="desc"]')[0])
+            video.set_empty_fields(NotAvailable, ('url,'))
+
+            yield video
+
+
+class VideoPage(BasePage):
+    def get_video(self, video=None):
+        _id = to_unicode(self.group_dict['id'])
+        if video is None:
+            video = JacquieEtMichelVideo(_id)
+        title_el = self.parser.select(self.document.getroot(), 'h1', 1)
+        video.title = to_unicode(title_el.text.strip())
+        video.description = self.document.xpath('//meta[@name="description"]')[0].attrib['content']
+
+        for script in self.document.xpath('.//script'):
+            if script.text is None:
+                continue
+            m = re.search('"(http://[^"]+.mp4)"', script.text, re.MULTILINE)
+            if m:
+                video.url = to_unicode(m.group(1))
+                break
+
+        if not video.url:
+            raise BrokenPageError('Unable to find URL')
+
+        video.set_empty_fields(NotAvailable)
+
+        return video

modules/jacquieetmichel/test.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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.tools.test import BackendTest
+from weboob.capabilities.video import BaseVideo
+
+
+class JacquieEtMichelTest(BackendTest):
+    BACKEND = 'jacquieetmichel'
+
+    def test_search(self):
+        self.assertTrue(len(list(self.backend.search_videos('anus', nsfw=False))) == 0)
+
+        l = list(self.backend.search_videos('anus', nsfw=True))
+        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_nsfw']))
+        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/jacquieetmichel/video.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 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
+
+
+__all__ = ['JacquieEtMichelVideo']
+
+
+class JacquieEtMichelVideo(BaseVideo):
+    def __init__(self, *args, **kwargs):
+        BaseVideo.__init__(self, *args, **kwargs)
+        self.ext = u'mp4'
+        self.nsfw = True
+
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://jacquieetmicheltv.net/showvideo/%s/t/' % _id