def concatenate_query_and_dates(start_date, end_date):
date_query = u""
if start_date:
testa = datetime.datetime.strptime(start_date, u'%Y-%m-%d').date()
testb = datetime.datetime.strptime(end_date, u'%Y-%m-%d').date()
date_query = mc.publish_date_query(testa, testb, True, True)
return date_query
def split_story_count(user_mc_key, q='*', last_n_days=None):
start_date = None
end_date = None
if last_n_days is not None:
start_date = datetime.datetime.today() - datetime.timedelta(
last_n_days)
end_date = YESTERDAY
fq = mc.publish_date_query(start_date, end_date, True, True)
else:
fq = None
results = _cached_split_story_counts(q, fq)
if last_n_days is None:
if len(results['counts']) > 0:
# if we are getting ALL stories, make sure bad dates don't give us super old / future ones
start_date = max(
MC_START_DATE,
datetime.datetime.strptime(results['counts'][0]['date'],
mc.SENTENCE_PUBLISH_DATE_FORMAT))
end_date = min(
YESTERDAY,
datetime.datetime.strptime(results['counts'][-1]['date'],
mc.SENTENCE_PUBLISH_DATE_FORMAT))
results['counts'] = add_missing_dates_to_split_story_counts(
results['counts'], start_date, end_date)
results['total_story_count'] = sum([r['count'] for r in results['counts']])
return results
def concatenate_query_and_dates(start_date, end_date):
date_query = ""
if start_date:
testa = datetime.datetime.strptime(start_date, '%Y-%m-%d').date()
testb = datetime.datetime.strptime(end_date, '%Y-%m-%d').date()
date_query = mc.publish_date_query(testa, testb, True, True)
return date_query
def dates_as_filter_query(start_date, end_date):
date_query = ""
if start_date:
testa = datetime.datetime.strptime(start_date, '%Y-%m-%d').date()
testb = datetime.datetime.strptime(end_date, '%Y-%m-%d').date()
date_query = mc.publish_date_query(testa, testb, True, True)
return date_query
def _cached_featured_collections():
featured_collections = []
for tags_id in FEATURED_COLLECTION_LIST:
coll = mc.tag(tags_id)
coll['id'] = tags_id
source_count_estimate = _cached_media_with_tag_page(tags_id, 0)
coll['media_count'] = len(source_count_estimate)
how_lively_is_this_collection = 0
# story count
for media in source_count_estimate:
one_weeks_before_now = datetime.datetime.now() - datetime.timedelta(days=7)
start_date = one_weeks_before_now
end_date = datetime.datetime.now()
publish_date = mc.publish_date_query(start_date,
end_date,
True, True)
media_query = "(media_id:{})".format(media['media_id']) + " AND (+" + publish_date + ")"
how_lively_is_this_collection += _cached_source_story_count(user_mediacloud_key(), media_query)
# approximate liveliness - if there are more stories than 100, we know this is a reasonably active source/collection
if how_lively_is_this_collection > 100:
break
coll['story_count'] = how_lively_is_this_collection
featured_collections.append(coll)
return featured_collections
def concatenate_query_and_dates(start_date, end_date):
testa = datetime.datetime.strptime(start_date, '%Y-%m-%d').date()
testb = datetime.datetime.strptime(end_date, '%Y-%m-%d').date()
publish_date = mc.publish_date_query(testa, testb, True, True)
return publish_date