def create_task_list(given_ts):
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
now_ts = datehour2ts(ts2datehour(time.time() - 3600))
print_log = "&".join([file_path, "start", ts2date(now_ts)])
print print_log
#ts = ts - 3600
query_body = {"query": {"match_all": {}}}
search_results = es.search(index=index_sensing,
doc_type=type_sensing,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
_id = iter_item['_id']
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(json.loads(item['social_sensors'])) # social sensors
#task.append(now_ts)
task.append(given_ts)
r.lpush('task_name', json.dumps(task))
count += 1
print count
print_log = "&".join([file_path, "end", ts2date(time.time())])
print print_log
def create_task_list():
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
if RUN_TYPE == 0:
now_ts = 1463241600 # 1378008000
else:
i = int(sys.argv[1])
now_ts = 1463241600 + 3600 * i
#now_ts = date_hour2ts(ts2date_hour(time.time()))
print_log = "&".join([file_path, "start", ts2date(now_ts)])
print print_log
#ts = ts - 3600
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"term": {
"finish": "0"
}
}, {
"term": {
"processing_status": "1"
}
}]
}
}
}
}
}
search_results = es.search(index=index_name,
doc_type=task_doc_type,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
_id = iter_item['_id']
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(item['keywords']) # keywords
task.append(item['stop_time']) # stop time
task.append(item['create_by'])
task.append(now_ts)
r.lpush('task_name', json.dumps(task))
count += 1
print count
print_log = "&".join([file_path, "end", ts2date(time.time())])
print print_log
def create_task_list(ts):
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "start", now_ts])
print print_log
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"term": {
"finish": "0"
}
}, {
"term": {
"processing_status": "1"
}
}]
}
}
}
}
}
search_results = es.search(index=index_name,
doc_type=task_doc_type,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(json.loads(item['social_sensors'])) # social sensors
task.append(json.loads(item['keywords'])) # filter keywords
task.append(json.loads(
item['sensitive_words'])) #load sensitive_words
task.append(item['stop_time']) # stop time
task.append(item['warning_status']) # last step status
task.append(item['task_type']) # task type
task.append(ts)
r.lpush('task_name', json.dumps(task))
count += 1
print count
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "end", now_ts])
print print_log
def create_task_list():
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
if RUN_TYPE == 0:
now_ts = 1463241600 # 1378008000
else:
i = int(sys.argv[1])
now_ts = 1463241600 + 3600 * i
#now_ts = date_hour2ts(ts2date_hour(time.time()))
print_log = "&".join([file_path, "start", ts2date(now_ts)])
print print_log
#ts = ts - 3600
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"term":{"finish": "0"}},
{"term":{"processing_status": "1"}}
]
}
}
}
}
}
search_results = es.search(index=index_name, doc_type=task_doc_type, body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
_id = iter_item['_id']
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(item['keywords']) # keywords
task.append(item['stop_time']) # stop time
task.append(item['create_by'])
task.append(now_ts)
r.lpush('task_name', json.dumps(task))
count += 1
print count
print_log = "&".join([file_path, "end", ts2date(time.time())])
print print_log
def create_task_list(ts):
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "start", now_ts])
print print_log
query_body = {
"query":{
"filtered":{
"filter":{
"bool":{
"must":[
{"term":{"finish": "0"}},
{"term":{"processing_status": "1"}}
]
}
}
}
}
}
search_results = es.search(index=index_name, doc_type=task_doc_type, body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(json.loads(item['social_sensors'])) # social sensors
task.append(json.loads(item['keywords'])) # filter keywords
task.append(json.loads(item['sensitive_words'])) #load sensitive_words
task.append(item['stop_time']) # stop time
task.append(item['warning_status']) # last step status
task.append(item['task_type']) # task type
task.append(ts)
task.append(item['create_by'])
r.lpush('task_name', json.dumps(task))
count += 1
print count
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "end", now_ts])
print print_log
def social_sensing_task(ts):
# 1. print start info
count = 0
current_path = os.getcwd()
file_path = os.path.join(current_path, 'social_sensing.py')
now_ts = str(ts)
print_log = "&".join([file_path, "start", now_ts])
print print_log #打印开始信息
while 1:
temp = r.rpop("task_name")
if not temp:
print count
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "end", now_ts])
print print_log # 打印终止信息
break # finish all task in task_list
task_detail = json.loads(temp)
count += 1
# """
if int(task_detail[6]) == 2:
specific_keywords_burst_dection(task_detail)
elif int(task_detail[6]) == 3:
sensors_keywords_detection(task_detail)
else:
pass
def push_crawler_task_redis():
query_body = {"query": {"match_all": {}}}
search_results = es.search(index=index_monitor_task,
doc_type=type_monitor_task,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
task.append(item['keywords']) # keywords
r.lpush(item['task_name'], json.dumps(task))
count += 1
print 'task_count_sum:', count
def social_sensing_task():
while 1:
temp = r.rpop("task_name")
if not temp:
now_date = ts2date(time.time())
print 'All tasks Finished:',now_date
break
task_detail = json.loads(temp)
social_sensing(task_detail)
print json.loads(temp)[0],':Finished'
def create_task_list():
# 1. search from manage_sensing_task
# 2. push to redis list-----task_work
# print start info
current_path = os.getcwd()
file_path = os.path.join(current_path, 'task_list.py')
if S_TYPE == 'test':
now_ts = datetime2ts(S_DATE)
else:
now_ts = datehour2ts(ts2datehour(time.time() - 3600))
print_log = " ".join([file_path, "--start:"])
print print_log
query_body = {"query": {"match_all": {}}}
search_results = es.search(index=index_manage_sensing,
doc_type=type_manage_sensing,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
_id = iter_item['_id']
item = iter_item['_source']
task = []
task.append(item['task_name']) # task_name
try:
task.append(json.loads(
item['social_sensors'])) # social sensors
except:
task.append(item['social_sensors']) # social sensors
task.append(now_ts)
r.lpush("task_name", json.dumps(task))
count += 1
print 'task_count_sum:', count
def push_calculate_task_redis():
query_body = {"query": {"match_all": {}}}
search_results = es.search(index=index_monitor_task,
doc_type=type_monitor_task,
body=query_body)['hits']['hits']
count = 0
if search_results:
for iter_item in search_results:
item = iter_item['_source']
task = []
task.append(item['task_name'])
task.append(item['event_category'])
task.append(item['create_at'])
task.append(item['processing_status'])
r.lpush(item['task_name'], json.dumps(task))
count += 1
print 'task_count_sum:', count
def pop_crawler_task_redis():
count = 0
while 1:
temp = r.rpop("task_name")
if temp:
print "current_task:", json.loads(temp)[0]
if not temp:
print 'the last task NO:', count
now_date = ts2date(time.time())
print 'All tasks Finished:', now_date
break
task_detail = json.loads(temp)
count += 1
crawler_task_start(task_detail)
print json.loads(temp)[0], ':Finished'
def social_sensing_task():
# 1. print start info
count = 0
current_path = os.getcwd()
file_path = os.path.join(current_path, 'social_sensing.py')
now_ts = ts2date(time.time())
print_log = "&".join([file_path, "start", now_ts])
# print print_log #打印开始信息
while 1:
temp = r.rpop("task_name")
if not temp:
print count
now_ts = str(int(time.time()))
print_log = "&".join([file_path, "end", now_ts])
break # finish all task in task_list
task_detail = json.loads(temp)
count += 1
social_sensing(task_detail)
def social_sensing_task():
count = 0
now_ts = ts2date(time.time())
while 1:
temp = r.rpop("task_name")
if temp:
print "current_task:", json.loads(temp)[0]
if not temp:
print 'the last task:', count
now_date = ts2date(time.time())
print 'All tasks Finished:', now_date
break
task_detail = json.loads(temp)
count += 1
social_sensing(task_detail)
print json.loads(temp)[0], ':Finished'
# -*- coding:utf-8 -*-
import json
import sys
reload(sys)
sys.path.append('./../')
from global_utils import R_SOCIAL_SENSING as r
sensing_words = [
"民主", "法治", "宪政", "维权", "上访", "强拆", "政府", "歹徒", "腐败", "暴恐", "爆炸", "袭击",
"地震", "坠亡", "不雅", "火灾", "车祸", "中毒", "抢劫", "强奸", "死亡", "雾霾", "污染"
]
r.hset("sensing_words", "sensing_words", json.dumps(sensing_words))
sensitive_words = ["宪政", "暴恐", "维权", "强拆"]
r.hset("sensitive_words", "sensitive_words", json.dumps(sensitive_words))
# -*- coding:utf-8 -*-
import json
import sys
reload(sys)
sys.path.append('./../')
from global_utils import R_SOCIAL_SENSING as r
sensing_words = ["民主", "法治", "宪政", "维权", "上访", "强拆", "政府", "歹徒", "腐败", "暴恐", "爆炸", "袭击", "地震", "坠亡","不雅", "火灾", "车祸", "中毒", "抢劫", "强奸", "死亡", "雾霾", "污染"]
r.hset("sensing_words", "sensing_words", json.dumps(sensing_words))
sensitive_words = ["宪政", "暴恐", "维权", "强拆"]
r.hset("sensitive_words", "sensitive_words", json.dumps(sensitive_words))
def find_hashtag(uid):
re_scan = r.hsan('hashtag_1456848000' 0)
