def collection_source_split_stories(collection_id):
collections_query = "tags_id_media:{}".format(collection_id)
exclude_spidered_stories = " tags_id_media:{} AND NOT tags_id_stories:{}".format(
str(collection_id), TAG_SPIDERED_STORY)\
if 'separate_spidered' in request.args else collections_query
interval = 'day' # default, and not currently passed to the calls above
all_results = apicache.split_story_count(user_mediacloud_key(),
collections_query)
# same if request.args doesn't ask to exclude_spidered
non_spidered_results = apicache.split_story_count(
user_mediacloud_key(), exclude_spidered_stories)
all_stories = {
'total_story_count': all_results['total_story_count'],
'list': all_results['counts'],
}
partial_stories = {
'total_story_count': non_spidered_results['total_story_count'],
'list': non_spidered_results['counts'],
}
return jsonify({
'results': {
'all_stories': all_stories,
'partial_stories': partial_stories,
'interval': interval
}
})
def stream_split_stories_csv(user_mc_key, filename, q):
response = {
'story_splits': apicache.split_story_count(user_mc_key, q)['counts']
}
clean_results = [{
'date': trim_solr_date(item['date']),
'numStories': item['count']
} for item in response['story_splits']]
clean_results = sorted(clean_results, key=itemgetter('date'))
props = ['date', 'numStories']
return csv.stream_response(clean_results, props, filename)
def _source_story_split_count_job(info):
source = info['media']
q = "media_id:{}".format(source['media_id'])
split_stories = apicache.split_story_count(user_mediacloud_key(), q, 360)
source_data = {
'media_id': source['media_id'],
'media_name': source['name'],
'media_url': source['url'],
'total_story_count': split_stories['total_story_count'],
'splits_over_time': split_stories['counts'],
}
return source_data