def delete_session(self, id):
session_connector = Es_connector(index=self.sessions_index,
doc_type=self.sessions_doc_type)
session = session_connector.get(id)
if session:
print("delete Session")
# print(session)
# 1. Delete session data from the tweets
tweets_connector = Es_connector(
index=session['_source']['s_index'],
doc_type=session['_source']['s_type'])
session_name = 'session_' + session['_source']['s_name']
print(session_name)
tweets_connector.remove_field_all(session_name)
# 2. Delete the session
session_connector.delete(id)
return True
else:
return False
"aggs": {
"duplicated_by_str_id": {
"terms": {
"field": "id_str.keyword",
"min_doc_count": 2,
"size": 20
}
}
}
})
buckets_size = len(res['aggregations']['duplicated_by_str_id']['buckets'])
for bucket in res['aggregations']['duplicated_by_str_id']['buckets']:
print("Deleting ", bucket["key"])
duplicated_res = my_conn.search(
{"query": {
"match": {
"id_str": bucket["key"]
}
}})
total_dup_files = duplicated_res["hits"]["total"]
for i in range(0, total_dup_files - 1):
doc = duplicated_res["hits"]["hits"][i]
my_conn.delete(doc["_id"])
time.sleep(2) # Sleep 2 seconds to avoid errors in the next loop
print("Done!")