Python批量写入ES索引数据的示例代码

wget [https://bootstrap.pypa.io/pip/2.7/get-pip.py](https://bootstrap.pypa.io/pip/2.7/get-pip.py)

python get-pip.py

[root@manager data]# pip --version

pip 20.3.4 from /usr/lib/python2.7/site-packages/pip (python 2.7)

pip install elasticsearch

# coding: utf-8
from elasticsearch import Elasticsearch
from elasticsearch import helpers
import random
import time
import sys


reload(sys)
sys.setdefaultencoding('utf-8')
es = Elasticsearch(hosts='http://10.180.249.94:9200')
# print(es)

names = ['刘一', '陈二', '张三', '李四', '王五', '赵六', '孙七', '周八', '吴九', '郑十']
names2 = ['刘一没有曾用名', '陈二没有曾用名', '张三没有曾用名', '李四也没有曾用名啊', '王五没有曾用名', '赵六也没有曾用名']
sexs = ['男', '女']
subjects = ['语文', '数学', '英语', '生物', '地理','物理','化学','思想','历史']
grades = [85, 77, 96, 74, 85, 69, 84, 59, 67, 69, 86, 96, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86]
ages = [12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30]
likes = ['接天莲叶无穷碧','映日荷花别样红','不识庐山真面目','只缘身在此山中','两个黄鹂鸣翠柳','一行白鹭上青天','姑苏城外寒山寺','夜半钟声到客船','窗含西岭千秋雪','门泊东吴万里船']
webs = ['https://api.paugram.com/help/acgm','https://docs.tenapi.cn/img.html','https://api.mz-moe.cn/img.php','https://www.jinrishici.com/doc/#instance-right','https://www.bookmarkearth.com','https://www.yijianlogo.com/template']
datas = ['西风吹老洞庭波，一夜湘君白发多。醉后不知天在水，满船清梦压星河。','凿破苍苔地，偷他一片天。白云生镜里，明月落阶前。','春风倚棹阖闾城，水国春寒阴复晴。细雨湿衣看不见，闲花落地听无声。','日斜江上孤帆影，草绿湖南万里情。东道若逢相识问，青袍今日误儒生。','浪花有意千里雪，桃李无言一队春。一壶酒，一竿身，快活如侬有几人？','岸阔樯稀波渺茫，独凭危槛思何长。萧萧远树疏林外 ，一半秋山带夕阳。']
dates = ['2002-10-12-11:00:02','2022-12-12-15:18:09','2023-12-08-11:00:02','2022-11-22-16:01:01','2021-09-19-13:55:55','2019-11-11-15:07:06','2010-08-09-11:56:09','2023-06-18-01:06:01','2022-12-12-19:06:04','2023-10-15-16:13:02']

start = time.time()
# 开始批量写入es数据库
# 批量写入数据
for j in range(2000):
    print(j)
    action = [
        {
            "_index": "grades_v3",
            "_type": "_doc",
            "_id": i,
            "_source": {
                "id": i,
                "name": random.choice(names),
                "old_name": random.choice(names2),
                "sex": random.choice(sexs),
                "subject": random.choice(subjects),
                "grade": random.choice(grades),
                "ages": random.choice(ages),
                "likes": random.choice(likes),
                "likes2": random.choice(likes),
                "others2": random.choice(datas),
                "websites": random.choice(webs),
                "others": random.choice(likes),
                "login_date":  random.choice(dates),
                "others3": random.choice(datas)
            }
        } for i in range(10000 * j, 10000 * j + 10000)
    ]
    helpers.bulk(es, action)
end = time.time()
print('Total Time Spent: ', end - start)

# 定义要创建的索引及其设置，包括主分片数为3  
create_index_body = {  
    "settings": {  
        "index": {  
            "number_of_shards": 3,  # 设置主分片数为3  
            "number_of_replicas": 1  # 设置副本数为1，可以根据需要调整  
        }  
    }  
}  
  
# 创建索引  
if not es.indices.exists(index="my_index"):  
    es.indices.create(index="my_index", body=create_index_body)