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、創建索引
假如創建索引名稱為ott，類型為ott_type的索引，該索引中有五個字段：
title：存儲中文標題，
date：存儲日期格式（2017-09-08），
keyword：存儲中文關鍵字，
source：存儲中文來源，
link：存儲鏈接，
創建映射：
3、索引數據
批量索引
利用bulk批量索引數據
4、查詢索引
5、刪除數據
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
#self.es = Elasticsearch([ip])
#用戶名密碼狀態
self.es = Elasticsearch([ip],http_auth=('elastic', 'password'),port=9200)
def create_index(self,index_name="ott",index_type="ott_type"):
'''
創建索引,創建索引名稱為ott，類型為ott_type的索引
:param ex: Elasticsearch對象
:return:
'''
#創建映射
_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文件中讀取數據，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):
'''
數據存儲到es
:return:
'''
list = [
{ "date": "2017-09-13",
"source": "慧聰網",
"link": "http://info.broadcast.hc360.com/2017/09/130859749974.shtml",
"keyword": "電視",
"title": "付費 電視 行業面臨的轉型和挑戰"
},
{ "date": "2017-09-13",
"source": "中國文明網",
"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將批量數據存儲到es
:return:
'''
list = [
{"date": "2017-09-13",
"source": "慧聰網",
"link": "http://info.broadcast.hc360.com/2017/09/130859749974.shtml",
"keyword": "電視",
"title": "付費 電視 行業面臨的轉型和挑戰"
},
{"date": "2017-09-13",
"source": "中國文明網",
"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?啟程--人民 電視 --人民網"
},
{"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
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，小編會及時回復大家的！
更多文章、技術交流、商務合作、聯系博主
微信掃碼或搜索：z360901061
微信掃一掃加我為好友
QQ號聯系： 360901061
您的支持是博主寫作最大的動力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點擊下面給點支持吧，站長非常感激您！手機微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點擊微信右上角掃一掃功能，選擇支付二維碼完成支付。
【本文對您有幫助就好】元
