python操作es批量读取数据

Python连接elasticserach

python连接elasticsearch有一下几种连接方式

pip3 instal elasticsearch

from elasticsearch import Elasticsearch   


es = Elasticsearch()  # 默认连接本地elasticsearch
es = Elasticsearch(["127.0.0.1:9200"])  # 连接本地9200端口
es = Elasticsearch(["192.168.1.10", "192.168.1.11",
"192.168.1.12"],  # 连接集群，以列表的形式存放各节点的IP地址 
sniff_on_start=True,    # 连接前测试    
sniff_on_connection_fail=True,  # 节点无响应时刷新节点   
sniff_timeout=60)    # 设置超时时间

配置可忽略的状态码

es = Elasticsearch(['127.0.0.1:9200'],ignore=400)  # 忽略返回的400状态码
es = Elasticsearch(['127.0.0.1:9200'],ignore=[400, 405, 502])  # 以列表的形式忽略多个状态码

Python操作es批量读取数据

from elasticsearch import Elasticsearch

es = Elasticsearch()

query_json = {
  "query": {
        "match_all": {}  # 获取所有数据
  }
}
page_num = 100  # 每次获取数据

query = es.search(index=8, body=query_json, scroll='5m', size=page_num)

results = query['hits']['hits']  # es查询出的结果第一页
total = query['hits']['total']  # es查询出的结果总量
scroll_id = query['_scroll_id']  # 游标用于输出es查询出的所有结果
every_num = int(total/page_num)  

alist = []
for i in range(0, every_num+1):
    # scroll参数必须指定否则会报错
    query_scroll = es.scroll(scroll_id=scroll_id, scroll='5m')['hits']['hits']
    results += query_scroll
for key in results:
    es_data_dict = key["_source"]["word"]
    # print(es_data_dict)
    alist.append(es_data_dict)
print(len(alist))