Python 操作 ElasticSearch的完整代碼
官方文檔:https://elasticsearch-py.readthedocs.io/en/master/
1、介紹
python提供了操作ElasticSearch 接口,因此要用python來操作ElasticSearch,首先要安裝python的ElasticSearch包,用命令pip install elasticsearch安裝或下載安裝:https://pypi.python.org/pypi/elasticsearch/5.4.0
2、創(chuàng)建索引
假如創(chuàng)建索引名稱為ott,類型為ott_type的索引,該索引中有五個字段:
title:存儲中文標(biāo)題,
date:存儲日期格式(2017-09-08),
keyword:存儲中文關(guān)鍵字,
source:存儲中文來源,
link:存儲鏈接,
創(chuàng)建映射:


3、索引數(shù)據(jù)

批量索引
利用bulk批量索引數(shù)據(jù)

4、查詢索引
5、刪除數(shù)據(jù)

6、完整代碼
#coding:utf8
import os
import time
from os import walk
import CSVOP
from datetime import datetime
from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk
class ElasticObj:
def __init__(self, index_name,index_type,ip ="127.0.0.1"):
'''
:param index_name: 索引名稱
:param index_type: 索引類型
'''
self.index_name =index_name
self.index_type = index_type
# 無用戶名密碼狀態(tài)
#self.es = Elasticsearch([ip])
#用戶名密碼狀態(tài)
self.es = Elasticsearch([ip],http_auth=('elastic', 'password'),port=9200)
def create_index(self,index_name="ott",index_type="ott_type"):
'''
創(chuàng)建索引,創(chuàng)建索引名稱為ott,類型為ott_type的索引
:param ex: Elasticsearch對象
:return:
'''
#創(chuàng)建映射
_index_mappings = {
"mappings": {
self.index_type: {
"properties": {
"title": {
"type": "text",
"index": True,
"analyzer": "ik_max_word",
"search_analyzer": "ik_max_word"
},
"date": {
"type": "text",
"index": True
},
"keyword": {
"type": "string",
"index": "not_analyzed"
},
"source": {
"type": "string",
"index": "not_analyzed"
},
"link": {
"type": "string",
"index": "not_analyzed"
}
}
}
}
}
if self.es.indices.exists(index=self.index_name) is not True:
res = self.es.indices.create(index=self.index_name, body=_index_mappings)
print res
def IndexData(self):
es = Elasticsearch()
csvdir = 'D:/work/ElasticSearch/exportExcels'
filenamelist = []
for (dirpath, dirnames, filenames) in walk(csvdir):
filenamelist.extend(filenames)
break
total = 0
for file in filenamelist:
csvfile = csvdir + '/' + file
self.Index_Data_FromCSV(csvfile,es)
total += 1
print total
time.sleep(10)
def Index_Data_FromCSV(self,csvfile):
'''
從CSV文件中讀取數(shù)據(jù),并存儲到es中
:param csvfile: csv文件,包括完整路徑
:return:
'''
list = CSVOP.ReadCSV(csvfile)
index = 0
doc = {}
for item in list:
if index > 1:#第一行是標(biāo)題
doc['title'] = item[0]
doc['link'] = item[1]
doc['date'] = item[2]
doc['source'] = item[3]
doc['keyword'] = item[4]
res = self.es.index(index=self.index_name, doc_type=self.index_type, body=doc)
print(res['created'])
index += 1
print index
def Index_Data(self):
'''
數(shù)據(jù)存儲到es
:return:
'''
list = [
{ "date": "2017-09-13",
"source": "慧聰網(wǎng)",
"link": "http://info.broadcast.hc360.com/2017/09/130859749974.shtml",
"keyword": "電視",
"title": "付費(fèi) 電視 行業(yè)面臨的轉(zhuǎn)型和挑戰(zhàn)"
},
{ "date": "2017-09-13",
"source": "中國文明網(wǎng)",
"link": "http://www.wenming.cn/xj_pd/yw/201709/t20170913_4421323.shtml",
"keyword": "電視",
"title": "電視 專題片《巡視利劍》廣獲好評:鐵腕反腐凝聚黨心民心"
}
]
for item in list:
res = self.es.index(index=self.index_name, doc_type=self.index_type, body=item)
print(res['created'])
def bulk_Index_Data(self):
'''
用bulk將批量數(shù)據(jù)存儲到es
:return:
'''
list = [
{"date": "2017-09-13",
"source": "慧聰網(wǎng)",
"link": "http://info.broadcast.hc360.com/2017/09/130859749974.shtml",
"keyword": "電視",
"title": "付費(fèi) 電視 行業(yè)面臨的轉(zhuǎn)型和挑戰(zhàn)"
},
{"date": "2017-09-13",
"source": "中國文明網(wǎng)",
"link": "http://www.wenming.cn/xj_pd/yw/201709/t20170913_4421323.shtml",
"keyword": "電視",
"title": "電視 專題片《巡視利劍》廣獲好評:鐵腕反腐凝聚黨心民心"
},
{"date": "2017-09-13",
"source": "人民電視",
"link": "http://tv.people.com.cn/BIG5/n1/2017/0913/c67816-29533981.html",
"keyword": "電視",
"title": "中國第21批赴剛果(金)維和部隊(duì)啟程--人民 電視 --人民網(wǎng)"
},
{"date": "2017-09-13",
"source": "站長之家",
"link": "http://www.chinaz.com/news/2017/0913/804263.shtml",
"keyword": "電視",
"title": "電視 盒子 哪個牌子好? 吐血奉獻(xiàn)三大選購秘笈"
}
]
ACTIONS = []
i = 1
for line in list:
action = {
"_index": self.index_name,
"_type": self.index_type,
"_id": i, #_id 也可以默認(rèn)生成,不賦值
"_source": {
"date": line['date'],
"source": line['source'].decode('utf8'),
"link": line['link'],
"keyword": line['keyword'].decode('utf8'),
"title": line['title'].decode('utf8')}
}
i += 1
ACTIONS.append(action)
# 批量處理
success, _ = bulk(self.es, ACTIONS, index=self.index_name, raise_on_error=True)
print('Performed %d actions' % success)
def Delete_Index_Data(self,id):
'''
刪除索引中的一條
: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)
print(res['_source'])
print '------------------------------------------------------------------'
#
# # 輸出查詢到的結(jié)果
for hit in res['hits']['hits']:
# print hit['_source']
print hit['_source']['date'],hit['_source']['source'],hit['_source']['link'],hit['_source']['keyword'],hit['_source']['title']
def Get_Data_By_Body(self):
# doc = {'query': {'match_all': {}}}
doc = {
"query": {
"match": {
"keyword": "電視"
}
}
}
_searched = self.es.search(index=self.index_name, doc_type=self.index_type, body=doc)
for hit in _searched['hits']['hits']:
# print hit['_source']
print hit['_source']['date'], hit['_source']['source'], hit['_source']['link'], hit['_source']['keyword'], \
hit['_source']['title']
obj =ElasticObj("ott","ott_type",ip ="47.93.117.127")
# obj = ElasticObj("ott1", "ott_type1")
# obj.create_index()
obj.Index_Data()
# obj.bulk_Index_Data()
# obj.IndexData()
# obj.Delete_Index_Data(1)
# csvfile = 'D:/work/ElasticSearch/exportExcels/2017-08-31_info.csv'
# obj.Index_Data_FromCSV(csvfile)
# obj.GetData(es)
總結(jié)
以上所述是小編給大家介紹的Python 操作 ElasticSearch的完整代碼,希望對大家有所幫助,如果大家有任何疑問歡迎給我留言,小編會及時(shí)回復(fù)大家的!
相關(guān)文章
人臉檢測實(shí)戰(zhàn)終極之OpenCV+Python實(shí)現(xiàn)人臉對齊
這篇文章主要是為了演示如何使用 OpenCV、Python 和面部標(biāo)志從而實(shí)現(xiàn)對齊人臉。文中示例代碼對我們的工作或?qū)W習(xí)有一定的幫助,感興趣的小伙伴可以學(xué)習(xí)一下2021-12-12
Python進(jìn)階-函數(shù)默認(rèn)參數(shù)(詳解)
下面小編就為大家?guī)硪黄狿ython進(jìn)階-函數(shù)默認(rèn)參數(shù)(詳解)。小編覺得挺不錯的,現(xiàn)在就分享給大家,也給大家做個參考。一起跟隨小編過來看看吧2017-05-05
OpenCV物體跟蹤樹莓派視覺小車實(shí)現(xiàn)過程學(xué)習(xí)
這篇文章主要介紹了OpenCV物體跟蹤樹莓派視覺小車的實(shí)現(xiàn)過程學(xué)習(xí),有需要的朋友可以借鑒參考下,希望能夠有所幫助,祝大家多多進(jìn)步2021-10-10
淺談python socket函數(shù)中,send與sendall的區(qū)別與使用方法
下面小編就為大家?guī)硪黄獪\談python socket函數(shù)中,send與sendall的區(qū)別與使用方法。小編覺得挺不錯的,現(xiàn)在就分享給大家,也給大家做個參考。一起跟隨小編過來看看吧2017-05-05
Python用內(nèi)置模塊來構(gòu)建REST服務(wù)與RPC服務(wù)實(shí)戰(zhàn)
這篇文章主要介紹了Python用內(nèi)置模塊來構(gòu)建REST服務(wù)與RPC服務(wù)實(shí)戰(zhàn),python在網(wǎng)絡(luò)方面封裝一些內(nèi)置模塊,可以用很簡潔的代碼實(shí)現(xiàn)端到端的通信,比如HTTP、RPC服務(wù),下文實(shí)戰(zhàn)詳情,需要的朋友可以參考一下2022-09-09
Pytorch中TensorDataset與DataLoader的使用方式
這篇文章主要介紹了Pytorch中TensorDataset與DataLoader的使用方式,具有很好的參考價(jià)值,希望對大家有所幫助,如有錯誤或未考慮完全的地方,望不吝賜教2023-09-09

