def count_maxweibouser_influence(end_time):
date_time = ts2datetimestr(end_time)
index_name = weibo_bci_index_name_pre + date_time
print 'max index_name:', index_name
query_body = {
'query': {
'match_all': {}
},
'size': 1,
'sort': {
'user_index': {
'order': 'desc'
}
}
}
try:
#if S_TYPE == 'test':
# temp_index_name='bci_20161121'
# max_result=es_user_profile.search(index=temp_index_name,doc_type=weibo_bci_index_type,body=query_body)['hits']['hits']
#else:
max_result = es_user_profile.search(index=index_name,
doc_type=weibo_bci_index_type,
body=query_body)['hits']['hits']
for item in max_result:
max_user_index = item['_source']['user_index']
except:
max_user_index = 1
return max_user_index
def get_nick_name_unique(nick_name):
query_body = {
'query':{
'term':{'nick_name':nick_name}
}
}
es_profile_results = es_user_profile.search(index=profile_index_name,doc_type=profile_index_type,body=query_body)['hits']['hits']
es_xnr_results = es.search(index=weibo_xnr_index_name,doc_type=weibo_xnr_index_type,body=query_body)['hits']['hits']
if es_profile_results and es_xnr_results:
mark = False
else:
mark = True
return mark
def lookup_active_weibouser(classify_id, weiboxnr_id, start_time, end_time):
time_gap = end_time - start_time
now_time = time.time()
test_time_gap = datetime2ts(
ts2datetime(now_time)) - datetime2ts(S_DATE_BCI)
#print 'from, to:', ts2date(start_time), ts2date(end_time)
today_date_time = end_time - DAY
if S_TYPE == 'test':
today_date_time = datetime2ts(S_DATE_BCI)
start_time = start_time - test_time_gap
end_time = end_time - test_time_gap
from_date_ts = datetime2ts(ts2datetime(start_time))
to_date_ts = datetime2ts(ts2datetime(end_time))
#print 's_date_bci:', S_DATE_BCI
#print 'from_date_ts, to_date_ts:', ts2date(from_date_ts), ts2date(to_date_ts)
bci_index_name = weibo_bci_index_name_pre + ''.join(
ts2datetime(today_date_time).split('-'))
print 'bci_index_name:', bci_index_name
print 'end_time:', ts2date(end_time)
#step1: users condition
#make sure the users range by classify choice
userlist = lookup_weiboxnr_concernedusers(weiboxnr_id)
if classify_id == 1: #concrenedusers
condition_list = [{'bool': {'must': {'terms': {'uid': userlist}}}}]
elif classify_id == 2: #unconcrenedusers
condition_list = [{
'bool': {
'must_not': [{
'terms': {
'uid': userlist
}
}]
}
}]
elif classify_id == 0:
condition_list = [{'match_all': {}}]
print userlist, classify_id, condition_list
#step 2:lookup users
user_max_index = count_maxweibouser_influence(end_time - DAY)
results = []
for item in condition_list:
query_body = {
'query': item,
'size': HOT_WEIBO_NUM, #查询影响力排名前50的用户即可
'sort': {
'user_index': {
'order': 'desc'
}
}
}
try:
#print 'query_body:', query_body
flow_text_exist=es_user_portrait.search(index=bci_index_name,\
doc_type=weibo_bci_index_type,body=query_body)['hits']['hits']
search_uid_list = [
item['_source']['user'] for item in flow_text_exist
]
weibo_user_exist = es_user_profile.search(index=profile_index_name,\
doc_type=profile_index_type,body={'query':{'terms':{'uid':search_uid_list}}})['hits']['hits']
#print 'weibo_user_exist:', weibo_user_exist
weibo_user_dict = dict()
for item in weibo_user_exist:
uid = item['_source']['uid']
weibo_user_dict[uid] = item['_source']
for item in flow_text_exist:
#print 'item:', item['_source']
influence = item['_source']['user_index'] / user_max_index * 100
fans_num = item['_source']['user_fansnum']
friends_num = item['_source']['user_friendsnum']
total_number = item['_source']['total_number']
uid = item['_source']['user']
try:
weibo_user_info = weibo_user_dict[uid]
uname = weibo_user_info['nick_name']
location = weibo_user_info['user_location']
url = weibo_user_info['photo_url']
except:
uname = ''
location = ''
url = ''
#print 'uid:', uid
results.append({'uid':uid, 'influence':influence, 'fans_num':fans_num, \
'total_number':total_number, 'friends_num':friends_num,\
'uname': uname, 'location':location, 'url': url})
#print 'results:', results
'''
uid=item['_source']['uid']
#微博数
item['_source']['weibos_sum']=count_weibouser_weibosum(uid,end_time)
#影响力
user_index=count_weibouser_index(uid,end_time)
if user_max_index >0:
item['_source']['influence']=user_index/user_max_index*100
else:
item['_source']['influence']=0
if item['_source']['influence']>=INFLUENCE_MIN:
results.append(item['_source'])
'''
except:
results = []
return results