def cached_geotag_count(query):
user_mc = user_admin_mediacloud_client()
res = user_mc.storyTagCount(query, [QUERY_LAST_MONTH, QUERY_ENGLISH_LANGUAGE], tag_sets_id=tag_utl.GEO_TAG_SET)
full_count = apicache.timeperiod_story_count(query, QUERY_LAST_MONTH)['count']
for r in res:
r['pct'] = (float(r['count'])/float(full_count))
r['value'] = (float(r['count']))
return res
def cached_geotag_count(user_mc_key, query):
user_mc = user_admin_mediacloud_client()
res = user_mc.storyTagCount(query, [QUERY_LAST_MONTH, QUERY_ENGLISH_LANGUAGE], tag_sets_id=tag_utl.GEO_TAG_SET)
full_count = apicache.timeperiod_story_count(user_mc, query, QUERY_LAST_MONTH)['count']
res = [r for r in res if int(r['tag'].split('_')[1]) in list(COUNTRY_GEONAMES_ID_TO_APLHA3.keys())]
for r in res:
geonamesId = int(r['tag'].split('_')[1])
if geonamesId not in list(COUNTRY_GEONAMES_ID_TO_APLHA3.keys()): # only include countries
continue
r['geonamesId'] = geonamesId
r['alpha3'] = COUNTRY_GEONAMES_ID_TO_APLHA3[geonamesId]
r['pct'] = (float(r['count'])/float(full_count))
r['value'] = (float(r['count']))
for hq in HIGHCHARTS_KEYS:
if hq['properties']['iso-a3'] == r['alpha3']:
r['iso-a2'] = hq['properties']['iso-a2']
return res
def _media_list_edit_job(media):
user_mc = user_admin_mediacloud_client()
# latest scrape job
scrape_jobs = user_mc.feedsScrapeStatus(media['media_id'])
latest_scrape_job = None
if len(scrape_jobs['job_states']) > 0:
latest_scrape_job = scrape_jobs['job_states'][0]
# active feed count
feeds = source_feed_list(media['media_id'])
active_syndicated_feeds = [f for f in feeds if f['active'] and f['type'] == 'syndicated']
active_feed_count = len(active_syndicated_feeds)
query = "media_id:{}".format(media['media_id'])
full_count = apicache.timeperiod_story_count(user_mc, query, QUERY_LAST_YEAR)['count']
# add the details to the media object and return it
media['latest_scrape_job'] = latest_scrape_job
media['active_feed_count'] = active_feed_count
media['num_stories_last_year'] = full_count
return media
def _media_list_edit_worker(media_id):
user_mc = user_admin_mediacloud_client()
# latest scrape job
scrape_jobs = user_mc.feedsScrapeStatus(media_id)
latest_scrape_job = None
if len(scrape_jobs['job_states']) > 0:
latest_scrape_job = scrape_jobs['job_states'][0]
# active feed count
feeds = source_feed_list(media_id)
active_syndicated_feeds = [f for f in feeds if f['active'] and f['type'] == 'syndicated']
active_feed_count = len(active_syndicated_feeds)
query = "media_id:{}".format(media_id)
full_count = apicache.timeperiod_story_count(user_mc, query, QUERY_LAST_YEAR)['count']
return {
'media_id': media_id,
'latest_scrape_job': latest_scrape_job,
'active_feed_count': active_feed_count,
'num_stories_last_year': full_count,
}
def api_source_review_info(media_id):
user_mc = user_admin_mediacloud_client()
# latest scrape job
scrape_jobs = user_mc.feedsScrapeStatus(media_id)
latest_scrape_job = None
if len(scrape_jobs['job_states']) > 0:
latest_scrape_job = scrape_jobs['job_states'][0]
# active feed count
feeds = source_feed_list(media_id)
active_syndicated_feeds = [
f for f in feeds if f['active'] and f['type'] == 'syndicated'
]
active_feed_count = len(active_syndicated_feeds)
query = "media_id:{}".format(media_id)
full_count = apicache.timeperiod_story_count(query,
QUERY_LAST_YEAR)['count']
info = {
'media_id': int(media_id),
'latest_scrape_job': latest_scrape_job,
'active_feed_count': active_feed_count,
'num_stories_last_year': full_count,
}
return jsonify(info)