用elasticsearch分析中国大学省份分布

1.去教育部官网下载excel数据：http://www.moe.gov.cn/srcsite/A03/moe_634/201706/W020170616379651135432.xls

2.把xls数据转换成json格式 https://blog.csdn.net/aomeishangpin/article/details/84404462

[root@do1_qy_10479 opt]# cat  just4json.py
# encoding: utf-8

import xlrd
from collections import OrderedDict
import json
import codecs

wb = xlrd.open_workbook('aa.xls')
convert_list = []
#sh ==> sheet
sh = wb.sheet_by_index(0)
title = sh.row_values(2)
for rownum in range(4,sh.nrows):
    rowvalue = sh.row_values(rownum)
    single = OrderedDict()
    for colnum in range(0,len(rowvalue)):
        print(title[colnum],rowvalue[colnum])
        single[title[colnum]] = rowvalue[colnum]
    convert_list.append(single)
j = json.dumps(convert_list,ensure_ascii=False)
with codecs.open('tojson.json',"w","utf-8") as f:
    f.write(j)

3.得到的json数据

[{"rowid": 2631.0, "name": "新疆工业职业技术学院", "code": "", "charge": "新疆维吾尔自治区", "location": "乌鲁木齐市", "level": "专科", "remark": ""}]

4.把json格式的数据倒进elastic search

#python 3.6
# -*- coding:utf-8 -*-
__author__ = 'BH8ANK'

import json
import os

#文件预处理
a = open(r"/opt/englishjson.json", "r",encoding='UTF-8')
out = a.read()
tmp = json.dumps(out)
tmp = json.loads(out)

#构造curl语句上传数据
num = len(tmp)
i = 0
while i < num:
    data = json.dumps(tmp[i],ensure_ascii=False)
    i = str(i)
    curl_word_1 = """ curl -XPUT "http://172.31.250.16:9200/daxue04/_doc/""" + i       #此处设置ES的IP:PORT
    curl_word_2 =  '''" -H 'Content-Type: application/json' -d'''
    curl_word_3 = "'" + data + "'"
    curl_words = curl_word_1 + curl_word_2 + curl_word_3
    os.system(curl_words)
    print(curl_words)
    i = int(i)
    i = i + 1

5.查询es的数据

 GET daxue05/_doc/0
{
  "_index" : "daxue05",
  "_type" : "_doc",
  "_id" : "",
  "_version" : 1,
  "_seq_no" : 0,
  "_primary_term" : 1,
  "found" : true,
  "_source" : {
    "rowid" : 1.0,
    "name" : "北京大学",
    "code" : "",
    "charge" : "教育部",
    "location" : "北京市",
    "level" : "本科",
    "remark" : ""
  }
}

6.参考：https://cloud.tencent.com/developer/article/1430850

7.