LoginSignup
4
7

More than 5 years have passed since last update.

@yh0sh

e-StatのAPI(ver.2)に対応したPythonスクリプトの作成

Last updated at Posted at 2015-09-23

e-StatのAPI(ver.2)について

e-StatのAPI仕様がバージョンアップしました．

qiita150923.png

Pythonスクリプトの作成

先人の投稿を参考にver.2に対応したスクリプトを作りました(Python 2.7)．

政府統計の総合窓口(e-Stat)のAPIを使ってみよう

編集前のスクリプトは，引数にAPI IDを含んでいますが，毎回入力するのは面倒なので，コード内で書いています．

また，政府統計コードをstats_codeで入力するようにしています．

統計表情報の検索

getStatsListSample2015.py
#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib
import urllib2
from lxml import etree
import sys
import codecs

def main(argvs, argc):
 if argc != 3:
  print ("Usage #python %s api_key search_kind stats_code" % argvs[0])
  return 1
 api_key = '' #取得したAPI IDを入力
 search_kind = argvs[1]
 stats_code = argvs[2]
 stats_code = urllib.quote(stats_code.encode('utf-8'))

 url = ('http://api.e-stat.go.jp/rest/2.0/app/getStatsList?appId=%s&lang=J&statsCode=%s&searchKind=%s' % (api_key, stats_code, search_kind))
 req = urllib2.Request(url)
 opener = urllib2.build_opener()
 conn = opener.open(req)
 cont = conn.read()
 parser = etree.XMLParser(recover=True)
 root = etree.fromstring(cont, parser)
 result = root.find('RESULT')
 data_list = root.find('DATALIST_INF')
 table_infs = data_list.xpath('./TABLE_INF')

 for table_inf in table_infs:
  print ((u'--------------').encode('utf-8'))
  for iterator in table_inf.getiterator():
   if iterator.text is not None:
    itag  = iterator.tag.encode('utf-8')
    itext = iterator.text.encode('utf-8')
   if iterator.items() is not None:
    if iterator.get('id') is not None:
     print itag,iterator.get('id').encode('utf-8'),itext
    elif iterator.get('code') is not None:
     print itag,iterator.get('code').encode('utf-8'),itext
    elif iterator.get('no') is not None:
     print itag,iterator.get('no').encode('utf-8'),itext
    else:
     print itag,itext


if __name__ == '__main__':
 argvs = sys.argv
 argc = len(argvs)
 sys.exit(main(argvs, argc))

使用例:

python getStatsListSample2015.py 1 00200521 > gSLS00200521.dat

結果:

gSLS00200521.dat
--------------
TABLE_INF 0000030001 

STAT_NAME 00200521 国勢調査
GOV_ORG 00200 総務省
STATISTICS_NAME 昭和55年国勢調査 第1次基本集計 全国編
TITLE 00101 男女の別（性別）（３），年齢５歳階級（２３），人口 全国・市部・郡部・都道府県（４７），全域・人口集中地区の別
CYCLE -
SURVEY_DATE 198010
OPEN_DATE 2007-10-05
SMALL_AREA 0
MAIN_CATEGORY 02 人口・世帯
SUB_CATEGORY 01 人口
OVERALL_TOTAL_NUMBER 3651
UPDATED_DATE 2008-03-19
--------------
TABLE_INF 0000030002 

STAT_NAME 00200521 国勢調査
GOV_ORG 00200 総務省
STATISTICS_NAME 昭和55年国勢調査 第1次基本集計 全国編
TITLE 00102 男女の別（性別）（３），年齢各歳階級（１０３），人口 全国・市部・郡部・都道府県（４７），全域・人口集中地区の別
CYCLE -
SURVEY_DATE 198010
OPEN_DATE 2007-10-05
SMALL_AREA 0
MAIN_CATEGORY 02 人口・世帯
SUB_CATEGORY 01 人口
OVERALL_TOTAL_NUMBER 16365
UPDATED_DATE 2008-03-19
--------------
・
・
・

統計表をcsvにして出力

export_csv2015.py
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
import urllib2
from lxml import etree
import csv

def export_statical_data(writer, api_key, stats_data_id, class_object, start_position):
    """
    統計情報のエクスポート
    """
    url = ('http://api.e-stat.go.jp/rest/2.0/app/getStatsData?limit=10000&appId=%s&lang=J&statsDataId=%s&metaGetFlg=N&cntGetFlg=N' % (api_key, stats_data_id))
    if start_position > 0:
        url = url + ('&startPosition=%d' % start_position)

    req = urllib2.Request(url)
    opener = urllib2.build_opener()
    conn = opener.open(req)
    cont = conn.read()
    parser = etree.XMLParser(recover=True)
    root = etree.fromstring(cont, parser)

    row = []
    datas = {}
    value_tags = root.xpath('//STATISTICAL_DATA/DATA_INF/VALUE')
    for value_tag in value_tags:
        row = []
        for key in class_object:
            val = value_tag.get(key)
            if val in class_object[key]['objects']:
                level = '';
                if 'level' in class_object[key]['objects'][val]:
                    if class_object[key]['objects'][val]['level'].isdigit():
                        level = ' ' * (int(class_object[key]['objects'][val]['level']) - 1)
                text = ("%s%s" % (level , class_object[key]['objects'][val]['name']))
                row.append(text.encode('utf-8'))
            else:
                row.append(val.encode('utf-8'))
        row.append(value_tag.text)
        writer.writerow(row)

    next_tags = root.xpath('//STATISTICAL_DATA/TABLE_INF/NEXT_KEY')
    if next_tags:
        if next_tags[0].text:
            export_statical_data(writer, api_key, stats_data_id, class_object, int(next_tags[0].text))

def get_meta_data(api_key, stats_data_id):
    """
    メタ情報取得
    """
    url = ('http://api.e-stat.go.jp/rest/2.0/app/getMetaInfo?appId=%s&lang=J&statsDataId=%s' % (api_key, stats_data_id))
    req = urllib2.Request(url)
    opener = urllib2.build_opener()
    conn = opener.open(req)
    cont = conn.read()
    parser = etree.XMLParser(recover=True)
    root = etree.fromstring(cont, parser)
    class_object_tags = root.xpath('//METADATA_INF/CLASS_INF/CLASS_OBJ')
    class_object = {}

    for class_object_tag in class_object_tags:
        class_object_id = class_object_tag.get('id')
        class_object_name = class_object_tag.get('name')
        class_object_item = {
            'id' : class_object_id,
            'name' : class_object_name,
            'objects' : {}
        }
        class_tags = class_object_tag.xpath('.//CLASS')
        for class_tag in class_tags:
            class_item = {
                'code' : class_tag.get('code'),
                'name' : class_tag.get('name'),
                'level' : class_tag.get('level'),
                'unit' : class_tag.get('unit')
            }
            class_object_item['objects'][class_item['code']] = class_item
        class_object[class_object_id] = class_object_item
    return class_object

def export_csv(api_key, stats_data_id, output_path):
    """
    指定の統計情報をCSVにエクスポートする.
    """
    writer = csv.writer(open(output_path, 'wb'),quoting=csv.QUOTE_ALL)

    class_object = get_meta_data(api_key, stats_data_id)
    row = []
    for key in class_object:
        title = class_object[key]['name']
        row.append(title.encode('utf-8'))
    row.append('VALUE')
    writer.writerow(row)

    export_statical_data(writer, api_key, stats_data_id, class_object, 1)

def main(argvs, argc):
    if argc != 2:
        print ("Usage #python %s api_key stats_data_id output_path" % argvs[0])
        return 1
    api_key = '' #取得したAPI IDを入力
    stats_data_id = argvs[1]
    output_path = 'e-stat' + argvs[1] + '.csv'
    export_csv(api_key, stats_data_id, output_path)

if __name__ == '__main__':
    argvs = sys.argv
    argc = len(argvs)
    sys.exit(main(argvs, argc))

使用例:

python export_csv2015.py 0000030001

結果:

e-stat0000030001.csv
"全域・集中の別030002","年齢５歳階級Ａ030002","男女Ａ030001","時間軸(年次)","全国都道府県030001","VALUE"
"全域","総数","男女総数","1980年","全国","117060396"
"全域","総数","男女総数","1980年","全国市部","89187409"
"全域","総数","男女総数","1980年","全国郡部","27872987"
"全域","総数","男女総数","1980年","北海道","5575989"
"全域","総数","男女総数","1980年","青森県","1523907"
"全域","総数","男女総数","1980年","岩手県","1421927"
"全域","総数","男女総数","1980年","宮城県","2082320"
"全域","総数","男女総数","1980年","秋田県","1256745"
"全域","総数","男女総数","1980年","山形県","1251917"
"全域","総数","男女総数","1980年","福島県","2035272"
"全域","総数","男女総数","1980年","茨城県","2558007"
"全域","総数","男女総数","1980年","栃木県","1792201"
"全域","総数","男女総数","1980年","群馬県","1848562"
"全域","総数","男女総数","1980年","埼玉県","5420480"
"全域","総数","男女総数","1980年","千葉県","4735424"
"全域","総数","男女総数","1980年","東京都","11618281"
"全域","総数","男女総数","1980年","神奈川県","6924348"
"全域","総数","男女総数","1980年","新潟県","2451357"
"全域","総数","男女総数","1980年","富山県","1103459"
・
・
・

Python 3しか無い方

Python 2.7でないと動かないので，Python 3しか無い方は環境構築しておきましょう．

PyenvによるPython3.x環境構築(CentOS, Ubuntu)

4
7
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
Sign upLogin
4
7