support repositories to manage backends (closes #747)

modules/dailymotion/__init__.py

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

modules/dailymotion/backend.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 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
+
+from .browser import DailymotionBrowser
+from .video import DailymotionVideo
+
+
+__all__ = ['DailymotionBackend']
+
+
+class DailymotionBackend(BaseBackend, ICapVideo):
+    NAME = 'dailymotion'
+    MAINTAINER = 'Romain Bignon'
+    EMAIL = 'romain@weboob.org'
+    VERSION = '0.a'
+    DESCRIPTION = 'Dailymotion videos website'
+    LICENSE = 'AGPLv3+'
+    BROWSER = DailymotionBrowser
+
+    def get_video(self, _id):
+        with self.browser:
+            return self.browser.get_video(_id)
+
+    SORTBY = ['relevance', 'rated', 'visited', None]
+    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, 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(DailymotionVideo.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 = {DailymotionVideo: fill_video}

modules/dailymotion/browser.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 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 urllib import quote_plus
+
+from weboob.tools.browser import BaseBrowser
+from weboob.tools.browser.decorators import id2url
+
+from .pages import IndexPage, VideoPage
+from .video import DailymotionVideo
+
+
+__all__ = ['DailymotionBrowser']
+
+
+class DailymotionBrowser(BaseBrowser):
+    DOMAIN = 'dailymotion.com'
+    ENCODING = None
+    PAGES = {r'http://[w\.]*dailymotion\.com/?': IndexPage,
+             r'http://[w\.]*dailymotion\.com/(\w+/)?search/.*': IndexPage,
+             r'http://[w\.]*dailymotion\.com/video/(?P<id>.+)': VideoPage,
+            }
+
+    @id2url(DailymotionVideo.id2url)
+    def get_video(self, url, video=None):
+        self.location(url)
+        return self.page.get_video(video)
+
+    def iter_search_results(self, pattern, sortby):
+        if not pattern:
+            self.home()
+        else:
+            if sortby is None:
+                url = '/search/%s/1' % quote_plus(pattern.encode('utf-8'))
+            else:
+                url = '/%s/search/%s/1' % (sortby, quote_plus(pattern.encode('utf-8')))
+            self.location(url)
+
+        assert self.is_on_page(IndexPage)
+        return self.page.iter_videos()

modules/dailymotion/pages.py

@@ -0,0 +1,112 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 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 urllib
+import re
+
+from weboob.tools.capabilities.thumbnail import Thumbnail
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.misc import html2text
+from weboob.tools.browser import BasePage, BrokenPageError
+
+
+from .video import DailymotionVideo
+
+
+__all__ = ['IndexPage', 'VideoPage']
+
+
+class IndexPage(BasePage):
+    def iter_videos(self):
+        for div in self.parser.select(self.document.getroot(), 'div.dmpi_video_item'):
+            _id = 0
+            for cls in div.attrib['class'].split():
+                if cls.startswith('id_'):
+                    _id = int(cls[3:])
+                    break
+
+            if _id == 0:
+                self.browser.logger.warning('Unable to find the ID of a video')
+                continue
+
+            video = DailymotionVideo(int(_id))
+            video.title = self.parser.select(div, 'h3 a', 1).text
+            video.author = self.parser.select(div, 'div.dmpi_user_login', 1).find('a').text
+            video.description = html2text(self.parser.tostring(self.parser.select(div, 'div.dmpi_video_description', 1))).strip()
+            try:
+                parts = self.parser.select(div, 'div.duration', 1).text.split(':')
+            except BrokenPageError:
+                # it's probably a live, np.
+                video.duration = NotAvailable
+            else:
+                if len(parts) == 1:
+                    seconds = parts[0]
+                    hours = minutes = 0
+                elif len(parts) == 2:
+                    minutes, seconds = parts
+                    hours = 0
+                elif len(parts) == 3:
+                    hours, minutes, seconds = parts
+                else:
+                    raise BrokenPageError('Unable to parse duration %r' % self.parser.select(div, 'div.duration', 1).text)
+                video.duration = datetime.timedelta(hours=int(hours), minutes=int(minutes), seconds=int(seconds))
+            url = self.parser.select(div, 'img.dmco_image', 1).attrib['src']
+            video.thumbnail = Thumbnail(url)
+
+            rating_div = self.parser.select(div, 'div.small_stars', 1)
+            video.rating_max = self.get_rate(rating_div)
+            video.rating = self.get_rate(rating_div.find('div'))
+            # XXX missing date
+            video.date = NotAvailable
+            yield video
+
+    def get_rate(self, div):
+        m = re.match('width: *(\d+)px', div.attrib['style'])
+        if m:
+            return int(m.group(1))
+        else:
+            self.browser.logger.warning('Unable to parse rating: %s' % div.attrib['style'])
+            return 0
+
+class VideoPage(BasePage):
+    def get_video(self, video=None):
+        if video is None:
+            video = DailymotionVideo(self.group_dict['id'])
+
+        div = self.parser.select(self.document.getroot(), 'div#content', 1)
+
+        video.title = self.parser.select(div, 'span.title', 1).text
+        video.author = self.parser.select(div, 'a.name', 1).text
+        try:
+            video.description = self.parser.select(div, 'div#video_description', 1).text
+        except BrokenPageError:
+            video.description = u''
+        for script in self.parser.select(self.document.getroot(), 'div.dmco_html'):
+            if 'id' in script.attrib and script.attrib['id'].startswith('container_player_'):
+                text = script.find('script').text
+                mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', text)
+                if mobj is None:
+                    mobj = re.search('"sdURL":.*?"(.*?)"', urllib.unquote(text))
+                    mediaURL = mobj.group(1).replace("\\", "")
+                else:
+                    mediaURL = urllib.unquote(mobj.group(1))
+                video.url = mediaURL
+
+        return video

modules/dailymotion/test.py

@@ -0,0 +1,32 @@
+# -*- 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 DailymotionTest(BackendTest):
+    BACKEND = 'dailymotion'
+
+    def test_dailymotion(self):
+        l = list(self.backend.iter_search_results('chirac'))
+        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)

modules/dailymotion/video.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 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.capabilities.video import BaseVideo
+
+
+__all__ = ['DailymotionVideo']
+
+
+class DailymotionVideo(BaseVideo):
+    def __init__(self, *args, **kwargs):
+        BaseVideo.__init__(self, *args, **kwargs)
+        self.ext = 'flv'
+
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://www.dailymotion.com/video/%s' % _id