def get_evaluate_max(index_name):
max_result = {}
index_type = 'bci'
evaluate_index = ['user_index']
for evaluate in evaluate_index:
query_body = {
'query': {
'match_all': {}
},
'size': 1,
'sort': [{
evaluate: {
'order': 'desc'
}
}]
}
# try:
result = es_cluster.search(index=index_name,
doc_type=index_type,
body=query_body)['hits']['hits']
# except Exception, e:
# raise e
max_evaluate = result[0]['_source'][evaluate]
max_result[evaluate] = max_evaluate
return max_result
def get_user_detail(date, input_result):
bci_date = ts2datetime(datetime2ts(date) - DAY)
results = []
uid_list = input_result
if date!='all':
index_name = 'bci_' + ''.join(bci_date.split('-'))
else:
now_ts = time.time()
now_date = ts2datetime(now_ts)
index_name = 'bci_' + ''.join(now_date.split('-'))
index_type = 'bci'
user_bci_result = es_cluster.mget(index=index_name, doc_type=index_type, body={'ids':uid_list}, _source=True)['docs'] #INFLUENCE,fans,status
user_profile_result = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={'ids':uid_list}, _source=True)['docs'] #个人姓名，注册地
max_evaluate_influ = get_evaluate_max(index_name)
for i in range(0, len(uid_list)):
uid = uid_list[i]
bci_dict = user_bci_result[i]
profile_dict = user_profile_result[i]
try:
bci_source = bci_dict['_source']
except:
bci_source = None
if bci_source:
influence = bci_source['user_index']
influence = math.log(influence/float(max_evaluate_influ['user_index']) * 9 + 1 ,10)
influence = influence * 100
else:
influence = ''
try:
profile_source = profile_dict['_source']
except:
profile_source = None
if profile_source:
uname = profile_source['nick_name']
location = profile_source['user_location']
try:
fansnum = bci_dict['fields']['user_fansnum'][0]
except:
fansnum = 0
try:
statusnum = bci_dict['fields']['weibo_month_sum'][0]
except:
statusnum = 0
else:
uname = uid
location = ''
try:
fansnum = bci_dict['fields']['user_fansnum'][0]
except:
fansnum = 0
try:
statusnum = bci_dict['fields']['weibo_month_sum'][0]
except:
statusnum = 0
results.append({'uid':uid, 'uname':uname, 'location':location, 'fansnum':fansnum, 'statusnum':statusnum, 'influence':round(influence,2)})
return results
def get_detail_org(uid_list, user_name):
if len(uid_list) == 0:
return {}
result = {}
user_bci_result = es_cluster.mget(index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs']
search_result = es_user_portrait.mget(index=portrait_index_name,
doc_type=portrait_index_type,
body={"ids": uid_list})["docs"]
if len(search_result) == 0:
return result
for i in range(0, len(search_result)):
item = search_result[i]
uid = item['_id']
if not item['found']:
result[uid] = {}
continue
else:
data = item['_source']
if not data['uname']:
name = ''
else:
name = data['uname'].encode('utf-8')
if not data['location']:
location = ''
else:
location = data['location'].encode('utf-8')
if not data['verify_type']:
verified = ''
else:
verified = ver_data[data['verify_type']]
work_tag = data['function_mark'].encode('utf-8')
tags = work_tag.split('&')
tag_list = []
for tag in tags:
u, t = tag.split('_')
if u == user_name:
tag_str.append(t)
bci_dict = user_bci_result[i]
try:
fansnum = bci_dict['fields']['user_fansnum'][0]
except:
fansnum = 0
result[uid] = {
'name': name,
'location': location,
'verified': verified,
'tag': work_tag,
'fansnum': fansnum
}
return result
def search_bci(uid):#获取用户的粉丝数、关注数和微博数
uid_list = [uid]
date = 1480176000#time.time()
bci_date = ts2datetime(date - DAY)
index_name = 'bci_' + ''.join(bci_date.split('-'))
index_type = 'bci'
user_bci_result = es_cluster.mget(index=index_name, doc_type=index_type, body={'ids':uid_list})['docs']
if len(user_bci_result):
return {'fansnum':'', 'statusnum':'', 'friendnum':''}
result = {'fansnum':'', 'statusnum':'', 'friendnum':''}
for item in user_bci_result:
if not item['found']:
return result
else:
data = item['_source']
fansnum = data['user_fansnum']
friendsnum = data['user_friendsnum']
statusnum = data['origin_weibo_number']+data['retweeted_weibo_number']
result = {'fansnum':fansnum, 'statusnum':statusnum, 'friendnum':friendsnum}
return result
}
try:
top_sensitive_result = es_bci_history.search(
index=ES_SENSITIVE_INDEX,
doc_type=DOCTYPE_SENSITIVE_INDEX,
body=query_sensitive_body,
_source=False,
fields=[sensitive_string])['hits']['hits']
top_sensitive = top_sensitive_result[0]['fields'][sensitive_string][0]
except Exception, reason:
print Exception, reason
top_sensitive = 400
index_type = 'bci'
user_bci_result = es_cluster.mget(
index=index_name,
doc_type=index_type,
body={'ids': uid_list},
_source=True)['docs'] #INFLUENCE,fans,status
user_profile_result = es_user_profile.mget(index='weibo_user',
doc_type='user',
body={'ids': uid_list},
_source=True)['docs'] #个人姓名，注册地
# bci_history_result = es_bci_history.mget(index=bci_history_index_name, doc_type=bci_history_index_type, body={"ids":uid_list}, fields=['user_fansnum', 'weibo_month_sum'])['docs']
# sensitive_history_result = es_bci_history.mget(index=ES_SENSITIVE_INDEX, doc_type=DOCTYPE_SENSITIVE_INDEX, body={'ids':uid_list}, fields=[sensitive_string], _source=False)['docs']
max_evaluate_influ = get_evaluate_max(index_name)
for i in range(0, len(uid_list)):
uid = uid_list[i]
bci_dict = user_bci_result[i]
profile_dict = user_profile_result[i]
# bci_history_dict = bci_history_result[i]
# sensitive_history_dict = sensitive_history_result[i]
