mygpo/data/podcast.py

   1 #
   2 # This file is part of my.gpodder.org.
   3 #
   4 # my.gpodder.org is free software: you can redistribute it and/or modify it
   5 # under the terms of the GNU Affero General Public License as published by
   6 # the Free Software Foundation, either version 3 of the License, or (at your
   7 # option) any later version.
   8 #
   9 # my.gpodder.org is distributed in the hope that it will be useful, but
  10 # WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  11 # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
  12 # License for more details.
  13 #
  14 # You should have received a copy of the GNU Affero General Public License
  15 # along with my.gpodder.org. If not, see <http://www.gnu.org/licenses/>.
  16 #
  17
  18 from collections import Counter
  19 import random
  20 import logging
  21
  22 from django.conf import settings
  23
  24 from mygpo.podcasts.models import Podcast
  25 from mygpo.subscriptions.models import Subscription
  26 from mygpo import pubsub
  27
  28 logger = logging.getLogger(__name__)
  29
  30
  31 def calc_similar_podcasts(podcast, num=20, user_sample=100):
  32     """ Get a list of podcasts that seem to be similar to the given one.
  33
  34     The similarity is based on similar subscriptions; for performance
  35     reasons, only a sample of subscribers is considered """
  36
  37     logger.info('Calculating podcasts similar to {podcast}'.format(
  38         podcast=podcast))
  39
  40     # get all users that subscribe to this podcast
  41     user_ids = Subscription.objects.filter(podcast=podcast)\
  42                                    .order_by('user')\
  43                                    .distinct('user')\
  44                                    .values_list('user', flat=True)
  45     logger.info('Found {num_subscribers} subscribers, taking a sample '
  46         'of {sample_size}'.format(num_subscribers=len(user_ids),
  47                                   sample_size=user_sample))
  48
  49     # take a random sample of ``user_sample`` subscribers
  50     user_ids = list(user_ids)  # evaluate ValuesQuerySet
  51     random.shuffle(user_ids)
  52     user_ids = user_ids[:user_sample]
  53
  54     # get other podcasts that the user sample subscribes to
  55     podcasts = Counter()
  56     for user_id in user_ids:
  57         subscriptions = Podcast.objects\
  58             .filter(subscription__user__id__in=user_ids)\
  59             .distinct('pk')\
  60             .exclude(pk=podcast.pk)
  61         podcasts.update(Counter(subscriptions))
  62     logger.info('Found {num_podcasts}, returning top {num_results}'.format(
  63         num_podcasts=len(podcasts), num_results=num))
  64
  65     return podcasts.most_common(num)
  66
  67
  68 def subscribe_at_hub(podcast):
  69     """ Tries to subscribe to the given podcast at its hub """
  70
  71     if not podcast.hub:
  72         return
  73
  74     base_url = settings.DEFAULT_BASE_URL
  75
  76     if not base_url:
  77         logger.warn('Could not subscribe to podcast {podcast} '
  78                     'at hub {hub} because DEFAULT_BASE_URL is not '
  79                     'set.'.format(podcast=podcast, hub=podcast.hub))
  80         return
  81
  82     logger.info('subscribing to {podcast} at {hub}.'.format(podcast=podcast,
  83                                                            hub=podcast.hub))
  84     pubsub.subscribe(podcast, podcast.url, podcast.hub, base_url)