def get_user(uidlist): #返回用户的背景信息
'''
返回用户的景信息
输入数据：uid列表
输出数据：users列表
'''
user_list = dict()
search_result = es_user_profile.mget(index=profile_index_name,
doc_type=profile_index_type,
body={"ids": uidlist})["docs"]
for item in search_result:
uid = item['_id']
if not item['found']:
user_list[str(uid)] = 'other'
else:
data = item['_source']
row = dict()
for k, v in data.items():
if k in set(zh_text):
row[k] = v.encode('utf-8')
else:
row[k] = v
user_list[str(uid)] = row
return user_list
def get_user(uidlist): # 返回用户的背景信息
"""
返回用户的景信息
输入数据：uid列表
输出数据：users列表
"""
user_list = dict()
search_result = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids": uidlist})[
"docs"
]
for item in search_result:
uid = item["_id"]
if not item["found"]:
user_list[str(uid)] = "other"
else:
data = item["_source"]
row = dict()
for k, v in data.items():
if k in set(zh_text):
row[k] = v.encode("utf-8")
else:
row[k] = v
user_list[str(uid)] = row
return user_list
def search_attention(uid):
stat_results = dict()
results = dict()
for db_num in R_DICT:
r = R_DICT[db_num]
ruid_results = r.hgetall('retweet_'+str(uid))
if ruid_results:
for ruid in ruid_results:
if ruid != uid:
try:
stat_results[ruid] += ruid_results[ruid]
except:
stat_results[ruid] = ruid_results[ruid]
# print 'results:', stat_results
if not stat_results:
return [None, 0]
try:
sort_state_results = sorted(stat_results.items(), key=lambda x:x[1], reverse=True)[:20]
except:
return [None, 0]
#print 'sort_state_results:', sort_state_results
uid_list = [item[0] for item in sort_state_results]
es_profile_results = es_user_profile.mget(index='weibo_user', doc_type='user', body={'ids':uid_list})['docs']
es_portrait_results = es_user_portrait.mget(index='user_portrait', doc_type='user', body={'ids':uid_list})['docs']
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item['_id']
try:
source = item['_source']
uname = source['nick_name']
except:
uname = u'未知'
# identify uid is in the user_portrait
portrait_item = es_portrait_results[i]
try:
source = portrait_item[i]
in_status = 1
except:
in_status = 0
result_list[uid] = [uid,[uname, stat_results[uid], in_status]]
return [result_list, len(stat_results)]
def search_attention(uid):
stat_results = dict()
results = dict()
for db_num in R_DICT:
r = R_DICT[db_num]
ruid_results = r.hgetall("retweet_" + str(uid))
if ruid_results:
for ruid in ruid_results:
if ruid != uid:
try:
stat_results[ruid] += ruid_results[ruid]
except:
stat_results[ruid] = ruid_results[ruid]
# print 'results:', stat_results
if not stat_results:
return [None, 0]
try:
sort_state_results = sorted(stat_results.items(), key=lambda x: x[1], reverse=True)[:20]
except:
return [None, 0]
# print 'sort_state_results:', sort_state_results
uid_list = [item[0] for item in sort_state_results]
es_profile_results = es_user_profile.mget(index="weibo_user", doc_type="user", body={"ids": uid_list})["docs"]
es_portrait_results = es_user_portrait.mget(index="user_portrait", doc_type="user", body={"ids": uid_list})["docs"]
result_list = dict()
for i in range(len(es_profile_results)):
item = es_profile_results[i]
uid = item["_id"]
try:
source = item["_source"]
uname = source["nick_name"]
except:
uname = u"未知"
# identify uid is in the user_portrait
portrait_item = es_portrait_results[i]
try:
source = portrait_item[i]
in_status = 1
except:
in_status = 0
result_list[uid] = [uid, [uname, stat_results[uid], in_status]]
return [result_list, len(stat_results)]
def get_user(uidlist):#返回用户的背景信息
'''
返回用户的景信息
输入数据：uid列表
输出数据：users列表
'''
user_list = dict()
search_result = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids": uidlist})["docs"]
for item in search_result:
uid = item['_id']
if not item['found']:
user_list[str(uid)] = 'other'
else:
data = item['_source']
row = dict()
for k,v in data.items():
if k in set(zh_text):
row[k] = v.encode('utf-8')
else:
row[k] = v
user_list[str(uid)] = row
return user_list