python 使用 elasticsearch 常用方法（检索）

最新推荐文章于 2024-05-11 17:17:44 发布

weixin_38170468

最新推荐文章于 2024-05-11 17:17:44 发布

阅读量352

点赞数

文章标签：大数据 python json

原文链接：http://www.cnblogs.com/loveyouyou616/p/11573080.html

版权

#记录es查询等方法

#清楚数据
curl -XDELETE http://xx.xx.xx.xx:9200/test6

#初始化数据
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/1' -d '{"name": "tom", "age":18, "info": "tom"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/2' -d '{"name": "jack", "age":29, "info": "jack"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/3' -d '{"name": "jetty", "age":18, "info": "jetty"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/4' -d '{"name": "daival", "age":19, "info": "daival"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/5' -d '{"name": "lilei", "age":18, "info": "lilei"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/6' -d '{"name": "lili", "age":29, "info": "lili"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/7' -d '{"name": "tom1", "age":30, "info": "tom1"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/8' -d '{"name": "tom2", "age":31, "info": "tom2"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/9' -d '{"name": "tom3", "age":32, "info": "tom3"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/10' -d '{"name": "tom4", "age":33, "info": "tom4"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/11' -d '{"name": "tom5", "age":34, "info": "tom5"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/12' -d '{"name": "tom6", "age":35, "info": "tom6"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/13' -d '{"name": "tom7", "age":36, "info": "tom7"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/14' -d '{"name": "tom8", "age":37, "info": "tom8"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/15' -d '{"name": "tom9", "age":38, "info": "tom9"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/16' -d '{"name": "john", "age":38, "info": "john"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/17' -d '{"name": "marry", "age":38, "info": "marry and john are friend"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/18' -d '{"name": "john", "age":32, "info": "john"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/19' -d '{"name": "tom is a little boy", "age":7, "info": "tom is a little boy"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/20' -d '{"name": "tom is a student", "age":12, "info": "tom is a student"}'
curl -H "Content-Type: application/json" -XPUT 'http://xx.xx.xx.xx:9200/test6/user/21' -d '{"name": "jack is a little boy", "age":22, "info": "jack"}'


from elasticsearch import Elasticsearch

def foreach(doc):
    doc = res['hits']['hits']

    if len(doc):
        for item in doc:
            print(item['_source'])

es = Elasticsearch(['xx.xx.xx.xx:9200'])

#查询所有数据
#方法1
#res = es.search(index='test6', size=20)
#方法2
res = es.search(index='test6', size=20, body = {
    "query": {
        "match_all": {}
    }
})

#foreach(res)


#等于查询 term与terms, 查询 name='tom cat' 这个值不会分词必须完全包含
res = es.search(index='test6', size=20, body= {
    "query": {
        "term": {
            "name": "tom cat"
        }
    }
})
#foreach(res)

#等于查询 term与terms, 查询 name='tom' 或 name='lili'
res = es.search(index= 'test6', size= 20, body= {
    "query": {
        "terms": {
            "name": ["tom","lili"]
        }
    }
})
#foreach(res)

#包含查询，match与multi_match
# match: 匹配name包含"tom cat"关键字的数据, 会进行分词包含tom或者cat的
res = es.search(index='test6', size=20, body={
    "query": {
        "match": {
            "name": "tom cat"
        }
    }
})
#foreach(res)

#multi_match: 在name或info里匹配包含little的关键字的数据
res = es.search(index='test6', size=20, body={
    "query": {
        "multi_match": {
            "query": "little",
            "fields": ["name", "info"]
        }
    }
})
#foreach(res)


#ids , 查询id 1, 2的数据 相当于mysql的 in
res = es.search(index='test6', size=20, body={
    "query": {
        "ids": {
            "values": ["1", "2"]
        }
    }
})
#foreach(res)


#复合查询bool , bool有3类查询关系，must(都满足),should(其中一个满足),must_not(都不满足)
#name包含"tom" and term包含 "18"
res = es.search(index='test6', size=20, body={
    "query": {
        "bool": {
            "must": [
                {
                    "term": {
                        "name": "tom",
                    },

                },
                {
                    "term": {
                        "age": 18,
                    },

                },
            ]
        }
    }
})
#foreach(res)

#name包含"tom" or term包含"19"
res = es.search(index='test6', size=20, body={
    "query": {
        "bool": {
            "should": [
                {
                    "term": {
                        "name": "tom",
                    },

                },
                {
                    "term": {
                        "age": 19,
                    },

                },
            ]
        }
    }
})

#foreach(res)


#切片式查询
res = es.search(index='test6', size=20, body={
    "query": {
        "bool": {
            "should": [
                {
                    "term": {
                        "name": "tom",
                    },

                },
                {
                    "term": {
                        "age": 19,
                    },

                },
            ]
        }
    },
    "from": 2, #从第二条数据开始
    "size": 4, # 获取4条数据
})
#foreach(res)

#范围查询
res = es.search(index='test6', size=20, body={
    "query": {
        "range": {
            "age": {
                "gte": 18, #>=18
                "lte": 30  #<=30
            }
        }
    }
})
#foreach(res)


#前缀查询
res = es.search(index='test6', size=20, body={
    "query": {
        "prefix": {
            "name": "tom"
        }
    }
})
#foreach(res)


#通配符查询
res = es.search(index='test6', size=20, body={
    "query": {
        "wildcard": {
            "name": "*i"
        }
    }
})
#foreach(res)


#排序
res = es.search(index='test6', size=20, body={
    "query": {
        "wildcard": {
            "name": "*i"
        }
    },
    "sort": {
        "age": {
            "order": "desc" #降序
        }
    }
})
#foreach(res)


# count, 执行查询并获取该查询的匹配数
c = es.count(index='test6')
print(c)

# 短语匹配 match_phrase (搜索is a little的短语,不进行切分)
res = es.search(index='test6', size=20, body={
    "query": {
        "match_phrase": {
            "name": "is a little"
        }
    }
})
foreach(res)

转载于:https://www.cnblogs.com/loveyouyou616/p/11573080.html