如下所示:
"""提取文檔數超過10000的數據按照某個字段的值具有唯一性進行升序,按照@timestamp進行降序,第一次查詢,先將10000條數據取出,取出最后一個時間戳,在第二次查詢中,設定@timestamp小于將第一次得到的最后一個時間戳,同時設定某個字段的值具有唯一性進行升序,按照@timestamp進行降序,"""from elasticsearch import Elasticsearchimport oswrite_path = "E://公司//案例數據采集//olt告警案例分析//10000_data.txt"es = Elasticsearch(hosts="", timeout=1500)write_file = open(write_path, "a+")def _first_query(): index_ = "gather-010" _source = ["TWICE_BOOK_TIME", "@timestamp"] try: rs = es.search(index=index_, body={ "size": 10000, "query": { "match_all": {} }, "sort": [ { "@timestamp": { "order": "desc" } }, { "TASK_RECEIVE_ID.keyword": { "order": "asc" } } ], "_source": _source }) return rs except: raise Exception("{0} search error".format(index_))def _get_first_data(first_rs): i = 0 if first_rs: for hit in first_rs['hits']['hits']: IptvAccount = hit['_source']['TWICE_BOOK_TIME'] timestamp = hit['_source']['@timestamp'] if IptvAccount is None: IptvAccount = "" write_file.write(IptvAccount + "," + timestamp + "/n") i += 1 if i == 10000: return timestampdef _second_query(timestamp): index_ = "gather-010" _source = ["TWICE_BOOK_TIME", "@timestamp"] try: rs = es.search(index=index_, body={ "size": 10000, "query": { "bool": { "filter": { "range": { "@timestamp": { "lt": timestamp } } } } }, "sort": [ { "@timestamp": { "order": "desc" } }, { "TASK_RECEIVE_ID.keyword": { "order": "asc" } } ], "_source": _source }) return rs except: raise Exception("{0} search error".format(index_))if __name__ == "__main__": first_rs = _first_query() first_timestamp = _get_first_data(first_rs) print(first_timestamp) while True: second_rs = _second_query(first_timestamp) first_timestamp = _get_first_data(second_rs) if first_timestamp is None: break print(first_timestamp)以上這篇python批量從es取數據的方法(文檔數超過10000)就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支持VEVB武林網。
新聞熱點
疑難解答