python 操作es 定义函数，先读后写

 

from elasticsearch import Elasticsearch
from elasticsearch import helpers
import datetime
from ES import setting
import time

#定义es链接
def conn_to_es():
    client = Elasticsearch(hosts=["http://{0}:{1}".format(setting.ES_HOST, setting.ES_PORT)],
                           http_auth=(setting.ES_USER, setting.ES_PASSWORD))
    return client

es = conn_to_es()


#定义读取es函数
def read_es(index,query=""):
    if es.ping():
        print("Successfully connect!")
    else:
        print("Failed.....")
        exit()
    if query == "":  # query为es的搜索条件
        query = {
            "query": {
                "match_all": {}
            },
            # "size":1000
        }
    res = helpers.scan(es, index=index, scroll="20m", query=query)
    return res

# 连接到集群，提供节点，不一定要全部节点
# es = Elasticsearch(["172.16.208.149:9200"])

# 打开文件准备读取数据
file_name = 'test.txt'
wbfile = open(file_name, 'r', encoding='utf-8', errors='ignore')
actions = []

# 循环每一行，写入数据
for line in wbfile:
    fields = line.split('#')
    # print(fields)
    # print(fields[2])
    action = {
        "_index": "estest_2019_04_19",
        "_type": "_doc",
        "_id": int(fields[0]),
        "_source": {"sid": int(fields[0]),
                    "c@receive_time": datetime.datetime.strptime("2020-04-19 16:30:16", "%Y-%m-%d %H:%M:%S"),
                    "sname": fields[1],
                    "sage": int(fields[2]),
                    "score": int(fields[3])
                    }
                    }

    actions.append(action)
    # 每1完条批量导入一次
    if len(actions)==1000:
        # helper批量导入
        helpers.bulk(es, actions)
        actions = []
        print("insert 10000")
if len(actions) > 0:
    # 导入最后剩余的数据
    helpers.bulk(es, actions)
print("finish")

time.sleep(10)

#定义读es

data=read_es("estest_2019_04_19",query="")
for i in data:
	print(i) #i是一个字典类型