def search_by_xnr_number(xnr_qq_number, current_date,group_qq_name):
group_qq_name_list = group_qq_name.encode('utf-8').split('，')
# 用于显示操作页面初始的所有群历史信息
query_body = {
"query": {
"filtered":{
"filter":{
"bool":{
"must":[
{"term":{"xnr_qq_number":xnr_qq_number}},
{'terms':{'qq_group_nickname':group_qq_name_list}}
]
}
}
}
},
"size": MAX_VALUE,
"sort":{"timestamp":{"order":"desc"}}
}
enddate = current_date
startdate = ts2datetime(datetime2ts(enddate)-group_message_windowsize*DAY)
index_names = get_groupmessage_index_list(startdate,enddate)
print 'index_names::',index_names
index_names.reverse()
results = {}
for index_name in index_names:
# if not es_xnr.indices.exsits(index=index_name):
# continue
try:
result = es_xnr.search(index=index_name, doc_type=group_message_index_type,body=query_body)
if results != {}:
results['hits']['hits'].extend(result['hits']['hits'])
else:
results=result #.copy()
except:
pass
# results_new = []
# for index_name in index_names:
# try:
# es_results = es_xnr.search(index=index_name, doc_type=group_message_index_type,body=query_body)['hits']['hits']
# print 'es_results::',es_results
# for es_result in es_results:
# es_result = es_result['_source']
# results_new.append(es_result)
# except:
# continue
return results
def search_by_period(xnr_qq_number, startdate, enddate, group_qq_name):
group_qq_name_list = group_qq_name.encode('utf-8').split('，')
results = {}
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"term": {
"xnr_qq_number": xnr_qq_number
}
}, {
'terms': {
'qq_group_nickname': group_qq_name_list
}
}]
}
}
}
},
"size": MAX_VALUE,
"sort": {
"timestamp": {
"order": "desc"
}
}
}
# es.search(index=”flow_text_2013-09-02”, doc_type=”text”, body=query_body)
index_names = get_groupmessage_index_list(startdate, enddate)
index_names.reverse()
#print 'index_names::',index_names
for index_name in index_names:
# if not es_xnr.indices.exsits(index_name):
# continue
print index_name
try:
result = es_xnr.search(index=index_name,
doc_type=group_message_index_type,
body=query_body)
print result
if results != {}:
results['hits']['hits'].extend(result['hits']['hits'])
else:
results = result.copy()
except:
pass
if results == {}:
results = {'hits': {'hits': []}}
return results
def search_by_xnr_number(xnr_qq_number, current_date):
# 用于显示操作页面初始的所有群历史信息
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"term": {
"xnr_qq_number": xnr_qq_number
},
"term": {
"sensitive_flag": 1
}
}]
}
}
}
},
"size": MAX_VALUE,
"sort": {
"sensitive_value": {
"order": "desc"
}
}
}
enddate = current_date
startdate = ts2datetime(
datetime2ts(enddate) - group_message_windowsize * DAY)
index_names = get_groupmessage_index_list(startdate, enddate)
# print index_names
results = []
for index_name in index_names:
# if not es_xnr.indices.exsits(index=index_name):
# continue
try:
result = es_xnr.search(index=index_name,
doc_type=group_message_index_type,
body=query_body)['hits']['hits']
# if results != {}:
# results['hits']['hits'].extend(result['hits']['hits'])
# else:
# results=result.copy()
if result:
for item in result:
item['_source']['_id'] = item['_id']
results.append(item['_source'])
else:
pass
except:
pass
# print 'results:',results
return results
def search_by_period(xnr_qq_number, startdate, enddate):
results = []
query_body = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"term": {
"xnr_qq_number": xnr_qq_number
},
"term": {
"sensitive_flag": 1
}
}]
}
}
}
},
"size": MAX_VALUE,
"sort": {
"timestamp": {
"order": "desc"
}
}
}
# es.search(index=”flow_text_2013-09-02”, doc_type=”text”, body=query_body)
index_names = get_groupmessage_index_list(startdate, enddate)
for index_name in index_names:
# if not es_xnr.indices.exsits(index_name):
# continue
try:
result = es_xnr.search(index=index_name,
doc_type=group_message_index_type,
body=query_body)['hits']['hits']
# if results != {}:
# results['hits']['hits'].extend(result['hits']['hits'])
# else:
# results=result.copy()
if result:
for item in result:
item['_source']['_id'] = item['_id']
results.append(item['_source'])
else:
pass
except:
pass
# if results == {}:
# results={'hits':{'hits':[]}}
return results
def aggr_sen_users(xnr_qq_number, startdate, enddate):
# print 'startdate:',startdate,type(startdate)
start_ts = datetime2ts(startdate)
end_ts = datetime2ts(enddate)
query_body = {
"query": {
"bool": {
"must": [{
'term': {
'xnr_qq_number': xnr_qq_number
}
}, {
"term": {
"sensitive_flag": 1
}
}, {
'range': {
'timestamp': {
'gte': start_ts,
'lt': end_ts
}
}
}]
}
},
"aggs": {
"all_senusers": {
# "terms":{"field": "speaker_qq_number"}
"terms": {
"field": "speaker_nickname"
}
}
}
}
#enddate = datetime.datetime.now().strftime('%Y-%m-%d')
#startdate = ts2datetime(datetime2ts(enddate)-group_message_windowsize*DAY)
index_names = get_groupmessage_index_list(startdate, enddate)
print index_names
results = []
for index_name in index_names:
try:
result = es_xnr.search(index=index_name,\
doc_type=group_message_index_type,\
body=query_body)["aggregations"]["all_senusers"]["buckets"]
except Exception, e:
result = []
print 'index_name,result:', index_name, result
if result != []:
for item in result:
# print 'item:',item
inner_item = {}
# inner_item['qq_number'] = item['key']
inner_item['qq_nick'] = item['key']
inner_item['count'] = item['doc_count']
info = get_speaker_info(item['key'], index_name)
if info == {}:
# inner_item['qq_nick'] = ''
inner_item['qq_number'] = ''
inner_item['qq_groups'] = ''
inner_item['last_speak_ts'] = ''
inner_item['text'] = []
else:
# inner_item['qq_nick'] = info['qq_nick']
inner_item['qq_number'] = info['qq_number']
inner_item['qq_groups'] = info['qq_groups']
inner_item['last_speak_ts'] = info['last_speak_ts']
inner_item['text'] = info['text']
flag = 1
for aa in results: #检验是否已经在结果中
# if aa['qq_number'] == inner_item['qq_number']:
if aa['qq_nick'] == inner_item['qq_nick']:
aa['count'] += inner_item['count']
aa['last_speak_ts'] = inner_item['last_speak_ts']
aa['qq_groups'].update(
inner_item['qq_groups']) # 多个群发言的更新
aa['text'].extend(inner_item['text'])
flag = 0
continue
if flag:
results.append(inner_item)
