add module cappedtv

Signed-off-by: Lord <lord@lordtoniok.com>
Signed-off-by: Romain Bignon <romain@symlink.me>

modules/cappedtv/__init__.py

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+from .backend import CappedBackend
+
+__all__ = ['CappedBackend']

modules/cappedtv/backend.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012 Lord
+#
+# This module is free software. It comes without any warranty, to
+# the extent permitted by applicable law. You can redistribute it
+# and/or modify it under the terms of the Do What The Fuck You Want
+# To Public License, Version 2, as published by Sam Hocevar. See
+# http://sam.zoy.org/wtfpl/COPYING for more details.
+
+
+from weboob.capabilities.video import ICapVideo
+from weboob.tools.backend import BaseBackend
+from .browser import CappedBrowser,CappedVideo
+
+
+__all__ = ['CappedBackend']
+
+
+class CappedBackend(BaseBackend, ICapVideo):
+    NAME = 'cappedtv'
+    MAINTAINER = 'Lord'
+    EMAIL = 'lord@lordtoniok.com'
+    VERSION = '0.b'
+    DESCRIPTION = 'Capped.tv demoscene website'
+    LICENSE = 'WTFPLv2'
+    BROWSER = CappedBrowser
+
+    def get_video(self, _id):
+        with self.browser:
+            return self.browser.get_video(_id)
+
+    def iter_search_results(self, pattern=None, sortby=ICapVideo.SEARCH_RELEVANCE, nsfw=None, max_results=None):
+        with self.browser:
+            return self.browser.iter_search_results(pattern)
+
+    def fill_video(self, video, fields):
+        if fields != ['thumbnail']:
+            with self.browser:
+                video = self.browser.get_video(CappedVideo.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 = {CappedVideo: fill_video}

modules/cappedtv/browser.py

@@ -0,0 +1,116 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012 Lord
+#
+# This module is free software. It comes without any warranty, to
+# the extent permitted by applicable law. You can redistribute it
+# and/or modify it under the terms of the Do What The Fuck You Want
+# To Public License, Version 2, as published by Sam Hocevar. See
+# http://sam.zoy.org/wtfpl/COPYING for more details.
+
+
+import urllib
+import datetime
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.misc import to_unicode
+from weboob.tools.browser import BasePage
+from weboob.tools.browser import BrokenPageError
+from weboob.tools.browser import BaseBrowser
+from weboob.tools.browser.decorators import id2url
+from weboob.capabilities.video import BaseVideo
+from weboob.tools.ordereddict import OrderedDict
+
+
+__all__ = ['CappedBrowser']
+
+
+class CappedVideo(BaseVideo):
+    def __init__(self, *args, **kwargs):
+        BaseVideo.__init__(self, *args, **kwargs)
+        self.nsfw = False
+        self.ext = 'mp4'
+
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://capped.tv/%s' % _id
+
+
+# parser for search pages
+class IndexPage(BasePage):
+    def iter_videos(self):
+        #Extracting meta data from results page
+        vidbackdrop_list = self.parser.select(self.document.getroot(), 'div.vidBackdrop    ')
+        for vidbackdrop in vidbackdrop_list:
+            url = self.parser.select(vidbackdrop, 'a', 1).attrib['href']
+            _id = url[2:]
+            title = self.parser.select(vidbackdrop, 'div.vidTitle a', 1).text
+            author = self.parser.select(vidbackdrop, 'div.vidAuthor a', 1).text
+            thumbnail_url = 'http://cdn.capped.tv/pre/%s.png' % _id
+            #we get the description field
+            duration_tmp = self.parser.select(vidbackdrop, 'div.vidInfo', 1)
+            #we remove tabs and spaces
+            duration_tmp2 = duration_tmp.text[7:]
+            #we remove all fields exept time
+            duration_tmp3 = duration_tmp2.split(' ')[0]
+            #we transform it in datetime format
+            parts = duration_tmp3.split(':')
+            if len(parts) == 1:
+                hours = minutes = 0
+                seconds = parts[0]
+            elif len(parts) == 2:
+                hours = 0
+                minutes , seconds = parts
+            elif len(parts) == 3:
+                hours, minutes, seconds = parts
+            else:
+                raise BrokenPageError('Unable to parse duration %r' % duration_tmp)
+
+            yield CappedVideo(_id=_id, title=title, author=author, thumbnail_url=thumbnail_url, duration=datetime.timedelta(hours=int(hours), minutes=int(minutes), seconds=int(seconds)))
+
+
+
+# parser for the video page
+class VideoPage(BasePage):
+    def get_video(self, video=None):
+        _id = to_unicode(self.group_dict['id'])
+        if video is None:
+            video = CappedVideo(_id)
+        title_tmp = self.parser.select(self.document.getroot(), 'title', 1)
+        video.title = to_unicode(title_tmp.text.strip())
+
+        # Videopages doesn't have duration information (only results pages)
+        video.duration = NotAvailable
+        video.url = 'http://cdn.capped.tv/vhq/%s.mp4' % _id
+        return video
+
+
+class CappedBrowser(BaseBrowser):
+    DOMAIN = 'capped.tv'
+    PROTOCOL = 'http'
+    ENCODING = None
+    PAGES = OrderedDict((
+            (r'http://capped\.tv', IndexPage),
+            (r'http://capped\.tv/newest', IndexPage),
+            (r'http://capped\.tv/mostviews', IndexPage),
+            (r'http://capped\.tv/leastviews', IndexPage),
+            (r'http://capped\.tv/monthtop', IndexPage),
+            (r'http://capped\.tv/monthbottom', IndexPage),
+            (r'http://capped\.tv/alpha', IndexPage),
+            (r'http://capped\.tv/ahpla', IndexPage),
+            (r'http://capped\.tv/search\?s\=(?P<pattern>.+)', IndexPage),
+            (r'http://capped\.tv/(?P<id>.+)', VideoPage),
+            ))
+
+    @id2url(CappedVideo.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 iter_search_results(self,pattern):
+        if not pattern:
+            self.home()
+        else:
+            self.location('/search?s=%s' % (urllib.quote_plus(pattern.encode('utf-8'))))
+        assert self.is_on_page(IndexPage)
+        return self.page.iter_videos()

modules/cappedtv/test.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012 Lord
+#
+# This module is free software. It comes without any warranty, to
+# the extent permitted by applicable law. You can redistribute it
+# and/or modify it under the terms of the Do What The Fuck You Want
+# To Public License, Version 2, as published by Sam Hocevar. See
+# http://sam.zoy.org/wtfpl/COPYING for more details.
+
+
+from weboob.tools.test import BackendTest
+
+
+__all__ = ['CappedTest']
+
+
+class CappedTest(BackendTest):
+    BACKEND = 'cappedtv'
+
+    def test_capped(self):
+        l = list(self.backend.iter_search_results('kewlers'))
+        self.assertTrue(len(l) > 0)
+        v = l[0]
+        self.backend.fillobj(v, ('url',))
+        self.assertTrue(v.url and v.url.startwith('http://'), 'URL for video "%s" not found' % (v.id, v.url))
+        self.backend.browser.openurl(v.url)