python-elasticsearch

Python Elasticsearch客户端文档：https://elasticsearch-py.readthedocs.io/en/master/index.html

 

　　1、安装Elasticsearch包 

 pip install elasticsearch

 

　　2、连接ES

from elasticsearch import Elasticsearch
# 连接ES
es = Elasticsearch([{'host': 'localhost', 'port': 9200}], timeout=3600)

　　　　用户名认证：

from elasticsearch import Elasticsearch
# 连接ES
es = Elasticsearch([{'host': 'localhost', 'port': 9200}], http_auth=('elastic', 'XcF8EbPPmgRgiLqoVAcI'), timeout=3600)

 

　　3、Elasticsearch操作

from elasticsearch import Elasticsearch

# 连接ES
es = Elasticsearch([{'host': 'localhost', 'port': 9200}], http_auth=('elastic', 'XcF8EbPPmgRgiLqoVAcI'), timeout=3600)

# 查询
query = {
    "query": {
        "match_all": {}
    }
}
result = es.search(index="megacorp", body=query)
print(result)

# 插入
es.index(index="megacorp",
         body={"first_name": "xiao", "last_name": "mi", 'age': 25, 'about': 'I love to go rock climbing',
               'interests': ['phone', 'tv']})

# 删除
es.delete(index='megacorp', id='24dYV34Bin_Y48vkEG7y')

# 更新
# 修改last_name字段
# 修改部分字段
doc_body = {
    "doc": {"last_name": "yongjie"}
}
# 增加字段
doc_body = {
    'script': "ctx._source.address = '南京'"
}
# 根据id更新
es.update(index="megacorp", id=1, body=doc_body)

# 更新所有满足条件的文档
query = {
    "query": {
        "match": {
            "last_name": "Smith"
        }
    },
    "script": {
        "ctx._source.address = '南京'",
    }
}
result = es.update_by_query(index="megacorp", body=query)
print(result)

 

 

bulk操作：

  helpers：

from elasticsearch import Elasticsearch, helpers

# 连接ES
es = Elasticsearch([{'host': 'localhost', 'port': 9200}], http_auth=('elastic', 'XcF8EbPPmgRgiLqoVAcI'), timeout=3600)

actions = [
    {
        '_op_type': 'index',  # 操作 index update create delete
        '_index': 'index-name',
        '_type': 'doc',
        '_source': {'level': 'info'}
    },
    {
        '_op_type': 'delete',
        '_index': 'index-name',
        '_id': 42,
    },
    {
        '_op_type': 'update',
        '_index': 'index-name',
        '_id': 42,
        'doc': {'question': 'The life, universe and everything.'}
    }
]
# 使用bulk方式
helpers.bulk(client=es, actions=actions)
# streaming_bulk与parallel_bulk类似  需要遍历才会运行
# 都可以设置每个批次的大小，parallel_bulk还可以设置线程数
for ok, response in helpers.streaming_bulk(es, actions):
    if not ok:
        print(response)

  RESTful:

resp = client.bulk(
    body=[
        {"index": {"_index": "test", "_id": "1"}},
        {"field1": "value1"},
        {"delete": {"_index": "test", "_id": "2"}},
        {"create": {"_index": "test", "_id": "3"}},
        {"field1": "value3"},
        {"update": {"_id": "1", "_index": "test"}},
        {"doc": {"field2": "value2"}},
    ],
)
print(resp)

 

END.