python elasticsearch环境搭建

Posted 2022-09-21 i-love-python

windows linux环境搭建

windows下载zip
linux下载tar
下载地址：https://www.elastic.co/downloads/elasticsearch

解压后运行：bin/elasticsearch (or bin\elasticsearch.bat on Windows)
检查是否成功：访问 http://localhost:9200

linux下不能以root用户运行，
普通用户运行报错：
java.nio.file.AccessDeniedException

原因：当前用户没有执行权限
解决方法： chown linux用户名 elasticsearch安装目录 -R
例如：chown ealsticsearch /data/wwwroot/elasticsearch-6.2.4 -R
PS：其他Java软件报.AccessDeniedException错误也可以同样方式解决，给 执行用户相应的目录权限即可

代码实例

如下的代码实现类似链家网小区搜索功能。
从文件读取小区及地址信息写入es,然后通过小区所在城市code及搜索关键字 匹配到对应小区。
代码主要包含三部分内容：
1.创建索引
2.用bulk将批量数据存储到es
3.数据搜索
注意：
代码的es版本交低2.xx版本，高版本在创建的索引数据类型有所不同

#coding:utf8
from __future__ import unicode_literals
import os
import time
import config
from datetime import datetime
from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk

class ElasticSearch():
    def __init__(self, index_name,index_type,ip ="127.0.0.1"):
        '''
        :param index_name: 索引名称
        :param index_type: 索引类型
        '''
        self.index_name =index_name
        self.index_type = index_type
        # 无用户名密码状态
        #self.es = Elasticsearch([ip])
        #用户名密码状态
        self.es = Elasticsearch([ip],http_auth=('elastic', 'password'),port=9200)
    def create_index(self,index_name="ftech360",index_type="community"):
        '''
        创建索引,创建索引名称为ott，类型为ott_type的索引
        :param ex: Elasticsearch对象
        :return:
        '''
        #创建映射
        _index_mappings = 
            "mappings": 
                self.index_type: 
                    "properties": 
                        "city_code": 
                            "type": "string",
                            # "index": "not_analyzed"
                        ,
                        "name": 
                            "type": "string",
                            # "index": "not_analyzed"
                        ,
                        "address": 
                            "type": "string",
                            # "index": "not_analyzed"
                        
                    
                

            
        
        if self.es.indices.exists(index=self.index_name) is True:
            self.es.indices.delete(index=self.index_name)
        res = self.es.indices.create(index=self.index_name, body=_index_mappings)
        print res

    def build_data_dict(self):
        name_dict = 
        with open(os.path.join(config.datamining_dir,'data_output','house_community.dat')) as f:
            for line in f:
                line_list = line.decode('utf-8').split('\t')
                community_code = line_list[6]
                name = line_list[7]
                city_code = line_list[0]
                name_dict[community_code] = (name,city_code)

        address_dict = 
        with open(os.path.join(config.datamining_dir,'data_output','house_community_detail.dat')) as f:
            for line in f:
                line_list = line.decode('utf-8').split('\t')
                community_code = line_list[6]
                address = line_list[10]
                address_dict[community_code] = address

        return name_dict,address_dict

    def bulk_index_data(self,name_dict,address_dict):
        '''
        用bulk将批量数据存储到es
        :return:
        '''
        list_data = []
        for community_code, data in name_dict.items():
            tmp = 
            tmp['code'] = community_code
            tmp['name'] = data[0]
            tmp['city_code'] = data[1]
            
            if community_code in address_dict:
                tmp['address'] = address_dict[community_code]
            else:
                tmp['address'] = ''

            list_data.append(tmp)
        ACTIONS = []
        for line in list_data:
            action = 
                "_index": self.index_name,
                "_type": self.index_type,
                "_id": line['code'], #_id 小区code
                "_source": 
                    "city_code": line['city_code'],
                    "name": line['name'],
                    "address": line['address']
                    
            
            ACTIONS.append(action)
            # 批量处理
        success, _ = bulk(self.es, ACTIONS, index=self.index_name, raise_on_error=True)
        #单条写入 单条写入速度很慢
        #self.es.index(index=self.index_name,doc_type="doc_type_test",body = action)

        print('Performed %d actions' % success)

    def delete_index_data(self,id):
        '''
        删除索引中的一条
        :param id:
        :return:
        '''
        res = self.es.delete(index=self.index_name, doc_type=self.index_type, id=id)
        print res

    def get_data_id(self,id):
        res = self.es.get(index=self.index_name, doc_type=self.index_type,id=id)
        # # 输出查询到的结果
        print res['_source']['city_code'], res['_id'],  res['_source']['name'], res['_source']['address']

    def get_data_by_body(self, name, city_code):
        # doc = 'query': 'match_all': 
        doc = 
            "query": 
                "bool":
                    "filter":
                        "term":
                        "city_code": city_code
                        
                    ,
                    "must":
                        "multi_match": 
                            "query": name,
                            "type":"phrase_prefix",
                            "fields": ['name^3', 'address'],
                            "slop":1,
                            
                            

                    
                
            
        
        _searched = self.es.search(index=self.index_name, doc_type=self.index_type, body=doc)
        data = _searched['hits']['hits']
        return data
         

if __name__=='__main__':
    #数据插入es
    obj = ElasticSearch("ftech360","community")
    obj.create_index()
    name_dict, address_dict = obj.build_data_dict()
    obj.bulk_index_data(name_dict,address_dict)

    #从es读取数据
    obj2 = ElasticSearch("ftech360","community")
    obj2.get_data_by_body(u'保利','510100')