def get_text(top_list, date, style):
# input: [[mid1, no.1], [mid2, no.2], ['mid3', no.3]]
# output: [[text1, no.1], [text2, no.2], [text3, no.3]]
# mid, retweeted, comment, text, geo, timestamp, sentiment, mid_url
results = []
index_flow_text = pre_text_index + date
#index_list = get_text_index(date)
if len(top_list) != 0: # no one
mid_list = []
for item in top_list:
mid_list.append(item[0])
search_result = es.mget(index=index_flow_text, doc_type=flow_text_index_type, body={"ids":mid_list})["docs"]
for i in range(len(top_list)):
temp = []
temp.extend(top_list[i])
if search_result[i]['found']:
source = search_result[i]['_source']
temp.append(source["text"])
temp.append(source["geo"])
temp.append(ts2date(source["timestamp"]))
temp.append(source["sentiment"])
temp.append(weiboinfo2url(source['uid'], source['mid']))
temp.append(uid_url+source['uid'])
temp.append(source['uid'])
try:
uname = es_profile.get(index=profile_index_name, doc_type=profile_index_type, id=source['uid'])["_source"]["nick_name"]
temp.append(uname)
except:
temp.append("unknown")
else:
temp.extend(["", "", "", "", "", "", "", ""])
results.append(temp)
return results
def get_influence_content(uid, timestamp_from, timestamp_to):
weibo_list = []
#split timestamp range to new_range_dict_list
from_date_ts = datetime2ts(ts2datetime(timestamp_from))
to_date_ts = datetime2ts(ts2datetime(timestamp_to))
new_range_dict_list = []
if from_date_ts != to_date_ts:
iter_date_ts = from_date_ts
while iter_date_ts < to_date_ts:
iter_next_date_ts = iter_date_ts + DAY
new_range_dict_list.append({
'range': {
'timestamp': {
'gte': iter_date_ts,
'lt': iter_next_date_ts
}
}
})
iter_date_ts = iter_next_date_ts
if new_range_dict_list[0]['range']['timestamp']['gte'] < timestamp_from:
new_range_dict_list[0]['range']['timestamp'][
'gte'] = timestamp_from
if new_range_dict_list[-1]['range']['timestamp']['lt'] > timestamp_to:
new_range_dict_list[-1]['range']['timestamp']['lt'] = timestamp_to
else:
new_range_dict_list = [{
'range': {
'timestamp': {
'gte': timestamp_from,
'lt': timestamp_to
}
}
}]
#iter date to search flow_text
iter_result = []
for range_item in new_range_dict_list:
range_from_ts = range_item['range']['timestamp']['gte']
range_from_date = ts2datetime(range_from_ts)
flow_text_index_name = flow_text_index_name_pre + range_from_date
query = []
query.append({'term': {'uid': uid}})
query.append(range_item)
try:
flow_text_exist = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
body={'query':{'bool':{'must': query}}, 'sort':[{'timestamp':'asc'}]})['hits']['hits']
except:
flow_text_exist = []
iter_result.extend(flow_text_exist)
# get weibo list
for item in flow_text_exist:
source = item['_source']
weibo = {}
weibo['timestamp'] = ts2date(source['timestamp'])
weibo['ip'] = source['ip']
weibo['text'] = source['text']
weibo['geo'] = '\t'.join(source['geo'].split('&'))
weibo_list.append(weibo)
return weibo_list
def get_activity_weibo(task_name, start_ts, submit_user):
results = []
task_id = submit_user + '-' + task_name
#step1: get task_name uid
try:
group_result = es_group_result.get(index=group_index_name, doc_type=group_index_type ,\
id=task_id, _source=False, fields=['uid_list'])
except:
group_result = {}
if group_result == {}:
return 'task name invalid'
try:
uid_list = group_result['fields']['uid_list']
except:
uid_list = []
if uid_list == []:
return 'task uid list null'
#step2: get uid2uname
uid2uname = {}
try:
user_portrait_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
body = {'ids':uid_list}, _source=False, fields=['uname'])['docs']
except:
user_portrait_result = []
for item in user_portrait_result:
uid = item['_id']
if item['found']==True:
uname = item['fields']['uname'][0]
uid2uname[uid] = uname
#step3: search time_segment weibo
time_segment = FOUR_HOUR
end_ts = start_ts + time_segment
time_date = ts2datetime(start_ts)
flow_text_index_name = flow_text_index_name_pre + time_date
query = []
query.append({'terms':{'uid': uid_list}})
query.append({'range':{'timestamp':{'gte':start_ts, 'lt':end_ts}}})
try:
flow_text_es_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type, \
body={'query':{'bool':{'must':query}}, 'sort':'timestamp', 'size':MAX_VALUE})['hits']['hits']
except:
flow_text_es_result = []
for item in flow_text_es_result:
weibo = {}
source = item['_source']
weibo['timestamp'] = ts2date(source['timestamp'])
weibo['ip'] = source['ip']
weibo['text'] = source['text']
weibo['geo'] = '\t'.join(source['geo'])
results.append(weibo)
return results
def get_activity_weibo(task_name, start_ts, submit_user):
results = []
task_id = submit_user + '-' + task_name
#step1: get task_name uid
try:
group_result = es_group_result.get(index=group_index_name, doc_type=group_index_type ,\
id=task_id, _source=False, fields=['uid_list'])
except:
group_result = {}
if group_result == {}:
return 'task name invalid'
try:
uid_list = group_result['fields']['uid_list']
except:
uid_list = []
if uid_list == []:
return 'task uid list null'
#step2: get uid2uname
uid2uname = {}
try:
user_portrait_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
body = {'ids':uid_list}, _source=False, fields=['uname'])['docs']
except:
user_portrait_result = []
for item in user_portrait_result:
uid = item['_id']
if item['found'] == True:
uname = item['fields']['uname'][0]
uid2uname[uid] = uname
#step3: search time_segment weibo
time_segment = FOUR_HOUR
end_ts = start_ts + time_segment
time_date = ts2datetime(start_ts)
flow_text_index_name = flow_text_index_name_pre + time_date
query = []
query.append({'terms': {'uid': uid_list}})
query.append({'range': {'timestamp': {'gte': start_ts, 'lt': end_ts}}})
try:
flow_text_es_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type, \
body={'query':{'bool':{'must':query}}, 'sort':'timestamp', 'size':MAX_VALUE})['hits']['hits']
except:
flow_text_es_result = []
for item in flow_text_es_result:
weibo = {}
source = item['_source']
weibo['timestamp'] = ts2date(source['timestamp'])
weibo['ip'] = source['ip']
weibo['text'] = source['text']
weibo['geo'] = '\t'.join(source['geo'])
results.append(weibo)
return results
def get_influence_content(uid, timestamp_from, timestamp_to):
weibo_list = []
#split timestamp range to new_range_dict_list
from_date_ts = datetime2ts(ts2datetime(timestamp_from))
to_date_ts = datetime2ts(ts2datetime(timestamp_to))
new_range_dict_list = []
if from_date_ts != to_date_ts:
iter_date_ts = from_date_ts
while iter_date_ts < to_date_ts:
iter_next_date_ts = iter_date_ts + DAY
new_range_dict_list.append({'range':{'timestamp':{'gte':iter_date_ts, 'lt':iter_next_date_ts}}})
iter_date_ts = iter_next_date_ts
if new_range_dict_list[0]['range']['timestamp']['gte'] < timestamp_from:
new_range_dict_list[0]['range']['timestamp']['gte'] = timestamp_from
if new_range_dict_list[-1]['range']['timestamp']['lt'] > timestamp_to:
new_range_dict_list[-1]['range']['timestamp']['lt'] = timestamp_to
else:
new_range_dict_list = [{'range':{'timestamp':{'gte':timestamp_from, 'lt':timestamp_to}}}]
#iter date to search flow_text
iter_result = []
for range_item in new_range_dict_list:
range_from_ts = range_item['range']['timestamp']['gte']
range_from_date = ts2datetime(range_from_ts)
flow_text_index_name = flow_text_index_name_pre + range_from_date
query = []
query.append({'term':{'uid':uid}})
query.append(range_item)
try:
flow_text_exist = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
body={'query':{'bool':{'must': query}}, 'sort':[{'timestamp':'asc'}]})['hits']['hits']
except:
flow_text_exist = []
iter_result.extend(flow_text_exist)
# get weibo list
for item in flow_text_exist:
source = item['_source']
weibo = {}
weibo['timestamp'] = ts2date(source['timestamp'])
weibo['ip'] = source['ip']
weibo['text'] = source['text']
weibo['geo'] = '\t'.join(source['geo'].split('&'))
weibo_list.append(weibo)
return weibo_list
def group_user_weibo(task_name, submit_user, sort_type):
weibo_list = []
now_date = ts2datetime(time.time())
if sort_type == 'retweet':
sort_type = 'retweeted'
#run_type
if RUN_TYPE == 0:
now_date = RUN_TEST_TIME
sort_type = 'timestamp'
#step1: get group user
task_id = submit_user + '-' + task_name
try:
group_exist_result = es_group_result.get(index=group_index_name, doc_type=group_index_type,\
id=task_id)['_source']
except:
group_exist_result = {}
if not group_exist_result:
return 'group no exist'
#step2: get user weibo list
uid_list = group_exist_result['uid_list']
for i in range(6,-1,-1):
iter_date = ts2datetime(datetime2ts(now_date) - i * DAY)
index_name = flow_text_index_name_pre + iter_date
try:
weibo_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
body={'query':{'filtered':{'filter':{'terms':{'uid': uid_list}}}}, 'sort':[{sort_type: {'order': 'desc'}}], 'size':100})['hits']['hits']
except:
weibo_result = []
if weibo_result:
weibo_list.extend(weibo_result)
#sort_weibo_list = sorted(weibo_list, key=lambda x:x['_source'][sort_type], reverse=True)[:100]
sort_weibo_list = weibo_list
#step3: get user name
try:
portrait_exist_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
body={'ids':uid_list})['docs']
except:
portrait_exist_result = []
uid2uname_dict = {}
for portrait_item in portrait_exist_result:
uid = portrait_item['_id']
if portrait_item['found'] == True:
source = portrait_item['_source']
uname = source['uname']
else:
uname = 'unknown'
uid2uname_dict[uid] = uname
weibo_list = []
for weibo_item in sort_weibo_list:
source = weibo_item['_source']
mid = source['mid']
uid = source['uid']
uname = uid2uname_dict[uid]
text = source['text']
ip = source['geo']
timestamp = source['timestamp']
date = ts2date(timestamp)
sentiment = source['sentiment']
weibo_url = weiboinfo2url(uid, mid)
#run_type:
if RUN_TYPE == 1:
try:
retweet_count = source['retweeted']
except:
retweet_count = 0
try:
comment_count = source['comment']
except:
comment_count = 0
try:
sensitive_score = source['sensitive']
except:
sensitive_score = 0
else:
retweet_count = 0
comment_count = 0
sensitive_score = 0
city = ip2city(ip)
weibo_list.append([mid, uid, uname, text, ip, city, timestamp, date, retweet_count, comment_count, sensitive_score, weibo_url])
if sort_type == 'timestamp':
new_weibo_list = sorted(weibo_list, key=lambda x:x[6], reverse=True)
elif sort_type == 'retweeted':
new_weibo_list = sorted(weibo_list, key=lambda x:x[8], reverse=True)
elif sort_type == 'comment':
new_weibo_list = sorted(weibo_list, key=lambda x:x[9], reverse=True)
elif sort_type == 'sensitive':
new_weibo_list = sorted(weibo_list, key=lambda x:x[10], reverse=True)
return new_weibo_list
def search_task(task_name, submit_date, state, status, submit_user):
results = []
query = []
condition_num = 0
if task_name:
task_name_list = task_name.split(' ')
for item in task_name_list:
query.append({'wildcard':{'task_name': '*' + item + '*'}})
condition_num += 1
if submit_date:
submit_date_ts = datetime2ts(submit_date)
submit_date_start = submit_date_ts
submit_date_end = submit_date_ts + DAY
query.append({'range':{'submit_date': {'gte': submit_date_start, 'lt': submit_date_end}}})
condition_num += 1
if state:
state_list = state.split(' ')
for item in state_list:
query.append({'wildcard':{'state': '*' + item + '*'}})
condition_num += 1
if status:
query.append({'match':{'status': status}})
condition_num += 1
if submit_user:
query.append({'term':{'submit_user': submit_user}})
condition_num += 1
print es_group_result,group_index_name,group_index_type
if condition_num > 0:
query.append({'term':{'task_type': 'analysis'}})
try:
source = es_group_result.search(
index = group_index_name,
doc_type = group_index_type,
body = {
'query':{
'bool':{
'must':query
}
},
'sort': [{'count':{'order': 'desc'}}],
'size': MAX_VALUE
}
)
except Exception as e:
raise e
else:
query.append({'term':{'task_type': 'analysis'}})
source = es.search(
index = group_index_name,
doc_type = group_index_type,
body = {
'query':{'bool':{
'must':query
}
},
'sort': [{'count': {'order': 'desc'}}],
'size': MAX_VALUE
}
)
try:
task_dict_list = source['hits']['hits']
except:
return None
result = []
for task_dict in task_dict_list:
try:
state = task_dict['_source']['state']
except:
state = ''
try:
status = task_dict['_source']['status']
except:
status = 0
#result.append([task_dict['_source']['task_name'], task_dict['_source']['submit_date'], task_dict['_source']['count'], state, status])
result.append({'task_name':task_dict['_source']['task_name'],'submit_date':ts2date(task_dict['_source']['submit_date']), 'group_count':task_dict['_source']['count'], 'status':status})
return result
def new_get_user_weibo(uid, sort_type):
results = []
weibo_list = []
now_date = ts2datetime(time.time())
#run_type
if RUN_TYPE == 0:
now_date = RUN_TEST_TIME
sort_type = 'timestamp'
#step1:get user name
print '708'
try:
user_profile_result = es_user_profile.get(index=profile_index_name, doc_type=profile_index_type,\
id=uid, _source=False, fields=['nick_name'])
except:
user_profile_result = {}
print '714',len(user_profile_result)
if user_profile_result:
uname = user_profile_result['fields']['nick_name'][0]
else:
uname = ''
#step2:get user weibo
for i in range(7, 0, -1):
if RUN_TYPE == 1:
iter_date = ts2datetime(datetime2ts(now_date) - i * DAY)
else:
iter_date = '2013-09-01'
index_name = flow_text_index_name_pre + iter_date
print '726'
try:
weibo_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
body={'query':{'filtered':{'filter':{'term': {'uid': uid}}}}, 'size':MAX_VALUE})['hits']['hits']
#print weibo_result
except:
weibo_result = []
print '732',len(weibo_result)
if weibo_result:
weibo_list.extend(weibo_result)
#sort_weibo_list = sorted(weibo_list, key=lambda x:x['_source'][sort_type], reverse=True)[:100]
mid_set = set()
for weibo_item in weibo_list:
source = weibo_item['_source']
mid = source['mid']
uid = source['uid']
text = source['text']
ip = source['ip']
timestamp = source['timestamp']
date = ts2date(timestamp)
sentiment = source['sentiment']
weibo_url = weiboinfo2url(uid, mid)
#run_type
if RUN_TYPE == 1:
try:
retweet_count = source['retweeted']
except:
retweet_count = 0
try:
comment_count = source['comment']
except:
comment_count = 0
try:
sensitive_score = source['sensitive']
except:
sensitive_score = 0
else:
retweet_count = 0
comment_count = 0
sensitive_score = 0
city = ip2city(ip)
if mid not in mid_set:
results.append([mid, uid, text, ip, city,timestamp, date, retweet_count, comment_count, sensitive_score, weibo_url])
mid_set.add(mid)
if sort_type == 'timestamp':
sort_results = sorted(results, key=lambda x:x[5], reverse=True)
elif sort_type == 'retweet_count':
sort_results = sorted(results, key=lambda x:x[7], reverse=True)
elif sort_type == 'comment_count':
sort_results = sorted(results, key=lambda x:x[8], reverse=True)
elif sort_type == 'sensitive':
sort_results = sorted(results, key=lambda x:x[9], reverse=True)
print '778'
return sort_results
def group_user_weibo(task_name, submit_user, sort_type):
weibo_list = []
now_date = ts2datetime(time.time())
if sort_type == 'retweet':
sort_type = 'retweeted'
#run_type
if RUN_TYPE == 0:
now_date = RUN_TEST_TIME
sort_type = 'timestamp'
#step1: get group user
task_id = submit_user + '-' + task_name
try:
group_exist_result = es_group_result.get(index=group_index_name, doc_type=group_index_type,\
id=task_id)['_source']
except:
group_exist_result = {}
if not group_exist_result:
return 'group no exist'
#step2: get user weibo list
uid_list = group_exist_result['uid_list']
for i in range(6, -1, -1):
iter_date = ts2datetime(datetime2ts(now_date) - i * DAY)
index_name = flow_text_index_name_pre + iter_date
try:
weibo_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
body={'query':{'filtered':{'filter':{'terms':{'uid': uid_list}}}}, 'sort':[{sort_type: {'order': 'desc'}}], 'size':100})['hits']['hits']
except:
weibo_result = []
if weibo_result:
weibo_list.extend(weibo_result)
#sort_weibo_list = sorted(weibo_list, key=lambda x:x['_source'][sort_type], reverse=True)[:100]
sort_weibo_list = weibo_list
#step3: get user name
try:
portrait_exist_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
body={'ids':uid_list})['docs']
except:
portrait_exist_result = []
uid2uname_dict = {}
for portrait_item in portrait_exist_result:
uid = portrait_item['_id']
if portrait_item['found'] == True:
source = portrait_item['_source']
uname = source['uname']
else:
uname = 'unknown'
uid2uname_dict[uid] = uname
weibo_list = []
for weibo_item in sort_weibo_list:
source = weibo_item['_source']
mid = source['mid']
uid = source['uid']
uname = uid2uname_dict[uid]
text = source['text']
ip = source['geo']
timestamp = source['timestamp']
date = ts2date(timestamp)
sentiment = source['sentiment']
weibo_url = weiboinfo2url(uid, mid)
#run_type:
if RUN_TYPE == 1:
try:
retweet_count = source['retweeted']
except:
retweet_count = 0
try:
comment_count = source['comment']
except:
comment_count = 0
try:
sensitive_score = source['sensitive']
except:
sensitive_score = 0
else:
retweet_count = 0
comment_count = 0
sensitive_score = 0
city = ip2city(ip)
weibo_list.append([
mid, uid, uname, text, ip, city, timestamp, date, retweet_count,
comment_count, sensitive_score, weibo_url
])
if sort_type == 'timestamp':
new_weibo_list = sorted(weibo_list, key=lambda x: x[6], reverse=True)
elif sort_type == 'retweeted':
new_weibo_list = sorted(weibo_list, key=lambda x: x[8], reverse=True)
elif sort_type == 'comment':
new_weibo_list = sorted(weibo_list, key=lambda x: x[9], reverse=True)
elif sort_type == 'sensitive':
new_weibo_list = sorted(weibo_list, key=lambda x: x[10], reverse=True)
return new_weibo_list
def get_origin_weibo_detail(ts, user, task_name, size, order, message_type=1):
_id = user + '-' + task_name
task_detail = es_user_portrait.get(index=index_sensing_task, doc_type=_id, id=ts)['_source']
print '37',index_sensing_task,_id
mid_value = json.loads(task_detail['mid_topic_value'])
duplicate_dict = json.loads(task_detail['duplicate_dict'])
tmp_duplicate_dict = dict()
for k,v in duplicate_dict.iteritems():
try:
tmp_duplicate_dict[v].append(k)
except:
tmp_duplicate_dict[v] = [k, v]
if message_type == 1:
weibo_detail = json.loads(task_detail['origin_weibo_detail'])
elif message_type == 2:
weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
else:
weibo_detail = json.loads(task_detail['sensitive_weibo_detail'])
weibo_detail_list = []
if weibo_detail:
for iter_mid, item in weibo_detail.iteritems():
tmp = []
tmp.append(iter_mid)
tmp.append(item[iter_mid])
tmp.append(item['retweeted'])
tmp.append(item['comment'])
weibo_detail_list.append(tmp)
mid_list = weibo_detail.keys()
print len(mid_list)
results = []
query_body = {
"query":{
"filtered":{
"filter":{
"terms":{"mid": mid_list}
}
}
},
"size": 1000,
"sort": {"timestamp": {"order": "desc"}}
}
index_list = []
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-DAY)
index_name = flow_text_index_name_pre + datetime
print es_text
exist_es = es_text.indices.exists(index_name)
print exist_es
if exist_es:
index_list.append(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
if exist_es_1:
index_list.append(index_name_1)
if index_list and mid_list:
search_results = es_text.search(index=index_list, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
text_dict = dict() # 文本信息
portrait_dict = dict() # 背景信息
sort_results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
text_dict[item['_id']] = item['_source'] # _id是mid
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for item in portrait_result:
if item['found']:
portrait_dict[item['_id']] = {"nick_name": item["fields"]["nick_name"][0], "photo_url": item["fields"]["photo_url"][0]}
else:
portrait_dict[item['_id']] = {"nick_name": item['_id'], "photo_url":""}
if order == "total":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[1], reverse=True)[:10]
elif order == "retweeted":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[2], reverse=True)[:10]
elif order == "comment":
sorted_list = sorted(weibo_detail_list, key=lambda x:x[3], reverse=True)[:10]
else:
sorted_list = weibo_detail_list
count_n = 0
results_dict = dict()
mid_index_dict = dict()
for item in sorted_list: # size
mid = item[0]
iter_text = text_dict.get(mid, {})
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, keywords_string, message_type
if iter_text:
uid = iter_text['uid']
temp.append(uid)
iter_portrait = portrait_dict.get(uid, {})
if iter_portrait:
temp.append(iter_portrait['nick_name'])
temp.append(iter_portrait['photo_url'])
else:
temp.extend([uid,''])
temp.append(iter_text["text"])
temp.append(iter_text["sentiment"])
temp.append(ts2date(iter_text['timestamp']))
temp.append(iter_text['geo'])
if message_type == 1:
temp.append(1)
elif message_type == 2:
temp.append(3)
else:
temp.append(iter_text['message_type'])
#jln 提取关键词
f_key = get_weibo_single(iter_text['text'])
temp.append(sorted(f_key.iteritems(),key=lambda x:x[1],reverse=True))
temp.append(item[2])
temp.append(item[3])
temp.append(iter_text.get('sensitive', 0))
temp.append(iter_text['timestamp'])
temp.append(mid_value[mid])
temp.append(mid)
results.append(temp)
count_n += 1
results = sorted(results, key=operator.itemgetter(-4, -2, -6), reverse=True) # -4 -2 -3
sort_results = []
count = 0
for item in results:
sort_results.append([item])
mid_index_dict[item[-1]] = count
count += 1
if tmp_duplicate_dict:
remove_list = []
value_list = tmp_duplicate_dict.values() # [[mid, mid], ]
for item in value_list:
tmp = []
for mid in item:
if mid_index_dict.get(mid, 0):
tmp.append(mid_index_dict[mid])
if len(tmp) > 1:
tmp_min = min(tmp)
else:
continue
tmp.remove(tmp_min)
for iter_count in tmp:
sort_results[tmp_min].extend(sort_results[iter_count])
remove_list.append(sort_results[iter_count])
if remove_list:
for item in remove_list:
sort_results.remove(item)
return sort_results
def get_positive_weibo_detail(ts, social_sensors, keywords_list, size, sentiment_type=1):
former_mid_list = query_mid_list(ts-time_interval, keywords_list, time_segment, social_sensors) # 前一段时间内的微博mid list
current_mid_list = query_mid_list(ts, keywords_list, time_interval, social_sensors)
mid_list = []
mid_list.extend(former_mid_list)
mid_list.extend(current_mid_list)
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"range":{
"timestamp":{
"gte": ts - time_interval,
"lt": ts
}
}},
],
"should":[
{"terms": {"root_mid": mid_list}},
{"terms": {"mid": mid_list}},
{"terms":{"keywords_string": keywords_list}}
]
}
}
}
},
"sort": {"timestamp": {"order": "desc"}},
"size": 100
}
#if social_sensors and int(sentiment_type) == 1:
# query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"terms":{"uid": social_sensors}})
if int(sentiment_type) == 1 or int(sentiment_type) == 0:
query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"term":{"sentiment":sentiment_type}})
else:
query_body["query"]["filtered"]["filter"]["bool"]["must"] = [{"terms":{"sentiment": ["2", "3"]}}]
# 判断当前ts和ts-time_interval是否属于同一天，确定查询哪个es
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 聚合原创微博mid list
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append("unknown")
temp.append("")
temp.append(item["text"])
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
keywords_set = set(item['keywords_string'].split('&'))
common_keywords = set(keywords_list) & keywords_set
temp.append(list(common_keywords))
temp.append(item['message_type'])
results.append(temp)
return results
def get_retweet_weibo_detail(ts, user, task_name, size, text_type, type_value):
_id = user + '-' + task_name
task_detail = es_user_portrait.get(index=index_sensing_task, doc_type=_id, id=ts)['_source']
origin_weibo_detail = json.loads(task_detail['origin_weibo_detail'])
retweeted_weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
mid_list = []
mid_list.extend(origin_weibo_detail.keys())
mid_list.extend(retweeted_weibo_detail.keys())
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"range":{
"timestamp":{
"gte": ts - time_interval,
"lt": ts
}
}},
{"terms": {"root_mid": mid_list}}
]
}
}
}
},
"sort": {"timestamp": {"order": "desc"}},
"size": 100
}
if text_type == "message_type":
query_body['query']['filtered']['filter']['bool']['must'].append({"term":{text_type: type_value}})
if text_type == "sentiment":
#if isinstance(type_value, str):
if len(type_value) == 1:
query_body['query']['filtered']['filter']['bool']['must'].append({"term":{text_type: type_value}})
else:
query_body['query']['filtered']['filter']['bool']['must'].append({"terms":{text_type: type_value}})
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts-time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 查询微博
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body)["hits"]["hits"]
else:
search_results = []
#print search_results
# 2. 获取微博相关信息
results = []
uid_list = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(index=profile_index_name, doc_type=profile_index_type, body={"ids":uid_list}, fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append(item['uid'])
temp.append("")
temp.append(item["text"])
#print item['text']
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
temp.append(item["message_type"])
results.append(temp)
return results
def search_task(task_name, submit_date, state, status, submit_user):
results = []
query = []
condition_num = 0
if task_name:
task_name_list = task_name.split(' ')
for item in task_name_list:
query.append({'wildcard': {'task_name': '*' + item + '*'}})
condition_num += 1
if submit_date:
submit_date_ts = datetime2ts(submit_date)
submit_date_start = submit_date_ts
submit_date_end = submit_date_ts + DAY
query.append({
'range': {
'submit_date': {
'gte': submit_date_start,
'lt': submit_date_end
}
}
})
condition_num += 1
if state:
state_list = state.split(' ')
for item in state_list:
query.append({'wildcard': {'state': '*' + item + '*'}})
condition_num += 1
if status:
query.append({'match': {'status': status}})
condition_num += 1
if submit_user:
query.append({'term': {'submit_user': submit_user}})
condition_num += 1
print es_group_result, group_index_name, group_index_type
if condition_num > 0:
query.append({'term': {'task_type': 'analysis'}})
try:
source = es_group_result.search(index=group_index_name,
doc_type=group_index_type,
body={
'query': {
'bool': {
'must': query
}
},
'sort': [{
'count': {
'order': 'desc'
}
}],
'size':
MAX_VALUE
})
except Exception as e:
raise e
else:
query.append({'term': {'task_type': 'analysis'}})
source = es.search(index=group_index_name,
doc_type=group_index_type,
body={
'query': {
'bool': {
'must': query
}
},
'sort': [{
'count': {
'order': 'desc'
}
}],
'size': MAX_VALUE
})
try:
task_dict_list = source['hits']['hits']
except:
return None
result = []
for task_dict in task_dict_list:
try:
state = task_dict['_source']['state']
except:
state = ''
try:
status = task_dict['_source']['status']
except:
status = 0
#result.append([task_dict['_source']['task_name'], task_dict['_source']['submit_date'], task_dict['_source']['count'], state, status])
result.append({
'task_name':
task_dict['_source']['task_name'],
'submit_date':
ts2date(task_dict['_source']['submit_date']),
'group_count':
task_dict['_source']['count'],
'status':
status
})
return result
def get_positive_weibo_detail(ts,
social_sensors,
keywords_list,
size,
sentiment_type=1):
former_mid_list = query_mid_list(ts - time_interval, keywords_list,
time_segment,
social_sensors) # 前一段时间内的微博mid list
current_mid_list = query_mid_list(ts, keywords_list, time_interval,
social_sensors)
mid_list = []
mid_list.extend(former_mid_list)
mid_list.extend(current_mid_list)
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [
{
"range": {
"timestamp": {
"gte": ts - time_interval,
"lt": ts
}
}
},
],
"should": [{
"terms": {
"root_mid": mid_list
}
}, {
"terms": {
"mid": mid_list
}
}, {
"terms": {
"keywords_string": keywords_list
}
}]
}
}
}
},
"sort": {
"timestamp": {
"order": "desc"
}
},
"size": 100
}
#if social_sensors and int(sentiment_type) == 1:
# query_body["query"]["filtered"]["filter"]["bool"]["must"].append({"terms":{"uid": social_sensors}})
if int(sentiment_type) == 1 or int(sentiment_type) == 0:
query_body["query"]["filtered"]["filter"]["bool"]["must"].append(
{"term": {
"sentiment": sentiment_type
}})
else:
query_body["query"]["filtered"]["filter"]["bool"]["must"] = [{
"terms": {
"sentiment": ["2", "3"]
}
}]
# 判断当前ts和ts-time_interval是否属于同一天，确定查询哪个es
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts - time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 聚合原创微博mid list
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name,
doc_type=flow_text_index_type,
body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1,
doc_type=flow_text_index_type,
body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(
index=profile_index_name,
doc_type=profile_index_type,
body={"ids": uid_list},
fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append("unknown")
temp.append("")
temp.append(item["text"])
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
keywords_set = set(item['keywords_string'].split('&'))
common_keywords = set(keywords_list) & keywords_set
temp.append(list(common_keywords))
temp.append(item['message_type'])
results.append(temp)
return results
def get_origin_weibo_detail(ts, user, task_name, size, order, message_type=1):
_id = user + '-' + task_name
task_detail = es_user_portrait.get(index=index_sensing_task,
doc_type=_id,
id=ts)['_source']
print '37', index_sensing_task, _id
mid_value = json.loads(task_detail['mid_topic_value'])
duplicate_dict = json.loads(task_detail['duplicate_dict'])
tmp_duplicate_dict = dict()
for k, v in duplicate_dict.iteritems():
try:
tmp_duplicate_dict[v].append(k)
except:
tmp_duplicate_dict[v] = [k, v]
if message_type == 1:
weibo_detail = json.loads(task_detail['origin_weibo_detail'])
elif message_type == 2:
weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
else:
weibo_detail = json.loads(task_detail['sensitive_weibo_detail'])
weibo_detail_list = []
if weibo_detail:
for iter_mid, item in weibo_detail.iteritems():
tmp = []
tmp.append(iter_mid)
tmp.append(item[iter_mid])
tmp.append(item['retweeted'])
tmp.append(item['comment'])
weibo_detail_list.append(tmp)
mid_list = weibo_detail.keys()
print len(mid_list)
results = []
query_body = {
"query": {
"filtered": {
"filter": {
"terms": {
"mid": mid_list
}
}
}
},
"size": 1000,
"sort": {
"timestamp": {
"order": "desc"
}
}
}
index_list = []
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts - DAY)
index_name = flow_text_index_name_pre + datetime
print es_text
exist_es = es_text.indices.exists(index_name)
print exist_es
if exist_es:
index_list.append(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
if exist_es_1:
index_list.append(index_name_1)
if index_list and mid_list:
search_results = es_text.search(index=index_list,
doc_type=flow_text_index_type,
body=query_body)["hits"]["hits"]
else:
search_results = []
uid_list = []
text_dict = dict() # 文本信息
portrait_dict = dict() # 背景信息
sort_results = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
text_dict[item['_id']] = item['_source'] # _id是mid
if uid_list:
portrait_result = es_profile.mget(
index=profile_index_name,
doc_type=profile_index_type,
body={"ids": uid_list},
fields=['nick_name', 'photo_url'])["docs"]
for item in portrait_result:
if item['found']:
portrait_dict[item['_id']] = {
"nick_name": item["fields"]["nick_name"][0],
"photo_url": item["fields"]["photo_url"][0]
}
else:
portrait_dict[item['_id']] = {
"nick_name": item['_id'],
"photo_url": ""
}
if order == "total":
sorted_list = sorted(weibo_detail_list,
key=lambda x: x[1],
reverse=True)[:10]
elif order == "retweeted":
sorted_list = sorted(weibo_detail_list,
key=lambda x: x[2],
reverse=True)[:10]
elif order == "comment":
sorted_list = sorted(weibo_detail_list,
key=lambda x: x[3],
reverse=True)[:10]
else:
sorted_list = weibo_detail_list
count_n = 0
results_dict = dict()
mid_index_dict = dict()
for item in sorted_list: # size
mid = item[0]
iter_text = text_dict.get(mid, {})
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, keywords_string, message_type
if iter_text:
uid = iter_text['uid']
temp.append(uid)
iter_portrait = portrait_dict.get(uid, {})
if iter_portrait:
temp.append(iter_portrait['nick_name'])
temp.append(iter_portrait['photo_url'])
else:
temp.extend([uid, ''])
temp.append(iter_text["text"])
temp.append(iter_text["sentiment"])
temp.append(ts2date(iter_text['timestamp']))
temp.append(iter_text['geo'])
if message_type == 1:
temp.append(1)
elif message_type == 2:
temp.append(3)
else:
temp.append(iter_text['message_type'])
#jln 提取关键词
f_key = get_weibo_single(iter_text['text'])
temp.append(
sorted(f_key.iteritems(), key=lambda x: x[1],
reverse=True))
temp.append(item[2])
temp.append(item[3])
temp.append(iter_text.get('sensitive', 0))
temp.append(iter_text['timestamp'])
temp.append(mid_value[mid])
temp.append(mid)
results.append(temp)
count_n += 1
results = sorted(results,
key=operator.itemgetter(-4, -2, -6),
reverse=True) # -4 -2 -3
sort_results = []
count = 0
for item in results:
sort_results.append([item])
mid_index_dict[item[-1]] = count
count += 1
if tmp_duplicate_dict:
remove_list = []
value_list = tmp_duplicate_dict.values() # [[mid, mid], ]
for item in value_list:
tmp = []
for mid in item:
if mid_index_dict.get(mid, 0):
tmp.append(mid_index_dict[mid])
if len(tmp) > 1:
tmp_min = min(tmp)
else:
continue
tmp.remove(tmp_min)
for iter_count in tmp:
sort_results[tmp_min].extend(sort_results[iter_count])
remove_list.append(sort_results[iter_count])
if remove_list:
for item in remove_list:
sort_results.remove(item)
return sort_results
def get_retweet_weibo_detail(ts, user, task_name, size, text_type, type_value):
_id = user + '-' + task_name
task_detail = es_user_portrait.get(index=index_sensing_task,
doc_type=_id,
id=ts)['_source']
origin_weibo_detail = json.loads(task_detail['origin_weibo_detail'])
retweeted_weibo_detail = json.loads(task_detail['retweeted_weibo_detail'])
mid_list = []
mid_list.extend(origin_weibo_detail.keys())
mid_list.extend(retweeted_weibo_detail.keys())
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"range": {
"timestamp": {
"gte": ts - time_interval,
"lt": ts
}
}
}, {
"terms": {
"root_mid": mid_list
}
}]
}
}
}
},
"sort": {
"timestamp": {
"order": "desc"
}
},
"size": 100
}
if text_type == "message_type":
query_body['query']['filtered']['filter']['bool']['must'].append(
{"term": {
text_type: type_value
}})
if text_type == "sentiment":
#if isinstance(type_value, str):
if len(type_value) == 1:
query_body['query']['filtered']['filter']['bool']['must'].append(
{"term": {
text_type: type_value
}})
else:
query_body['query']['filtered']['filter']['bool']['must'].append(
{"terms": {
text_type: type_value
}})
datetime = ts2datetime(ts)
datetime_1 = ts2datetime(ts - time_interval)
index_name = flow_text_index_name_pre + datetime
exist_es = es_text.indices.exists(index_name)
index_name_1 = flow_text_index_name_pre + datetime_1
exist_es_1 = es_text.indices.exists(index_name_1)
# 1. 查询微博
if datetime == datetime_1 and exist_es:
search_results = es_text.search(index=index_name,
doc_type=flow_text_index_type,
body=query_body)["hits"]["hits"]
elif datetime != datetime_1 and exist_es_1:
search_results = es_text.search(index=index_name_1,
doc_type=flow_text_index_type,
body=query_body)["hits"]["hits"]
else:
search_results = []
#print search_results
# 2. 获取微博相关信息
results = []
uid_list = []
if search_results:
for item in search_results:
uid_list.append(item["_source"]['uid'])
if uid_list:
portrait_result = es_profile.mget(
index=profile_index_name,
doc_type=profile_index_type,
body={"ids": uid_list},
fields=['nick_name', 'photo_url'])["docs"]
for i in range(len(uid_list)):
item = search_results[i]['_source']
temp = []
# uid, nick_name, photo_url, text, sentiment, timestamp, geo, common_keywords, message_type
temp.append(item['uid'])
if portrait_result[i]['found']:
temp.append(portrait_result[i]["fields"]["nick_name"][0])
temp.append(portrait_result[i]["fields"]["photo_url"][0])
else:
temp.append(item['uid'])
temp.append("")
temp.append(item["text"])
#print item['text']
temp.append(item["sentiment"])
temp.append(ts2date(item['timestamp']))
temp.append(item['geo'])
temp.append(item["message_type"])
results.append(temp)
return results