diff options
| author | Arthur de Jong <arthur@arthurdejong.org> | 2018-01-01 13:15:50 +0100 |
|---|---|---|
| committer | Arthur de Jong <arthur@arthurdejong.org> | 2018-01-01 14:01:39 +0100 |
| commit | e781eeea908018fce0c00c03378d3f40031dc2a7 (patch) | |
| tree | 2519dbf3979cba2ed2fbe45bf6fc9c79eee34bdc /update/eu_nace.py | |
| parent | 442aa8235b6621fbc79c7402e4da6231e3c7b4c6 (diff) | |
Move update scripts to own directory
This moves all the update scripts to their own directory so they don't
clutter the toplevel directory.
This also ensures that the scripts are passed through flake8 and makes
some adjustments for that alongside a few other cleanups.
Diffstat (limited to 'update/eu_nace.py')
| -rwxr-xr-x | update/eu_nace.py | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/update/eu_nace.py b/update/eu_nace.py new file mode 100755 index 0000000..af831f1 --- /dev/null +++ b/update/eu_nace.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python3 + +# update/eu_nace.py - script to get the NACE v2 catalogue +# +# Copyright (C) 2017-2018 Arthur de Jong +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA +# 02110-1301 USA + +"""This script downloads XML data from the European commission RAMON Eurostat +Metadata Server and extracts the information that is used for validating NACE +codes.""" + +import cgi +import urllib.request +from xml.etree import ElementTree + + +# the location of the ISBN Ranges XML file +download_url = 'http://ec.europa.eu/eurostat/ramon/nomenclatures/index.cfm?TargetUrl=ACT_OTH_CLS_DLD&StrNom=NACE_REV2&StrFormat=XML&StrLanguageCode=EN' + + +if __name__ == '__main__': + f = urllib.request.urlopen(download_url) + _, params = cgi.parse_header(f.info().get('Content-Disposition', '')) + filename = params.get('filename', '?') + print('# generated from %s, downloaded from' % filename) + print('# %s' % download_url) + + # parse XML document + doc = ElementTree.parse(f).getroot() + + # output header + print('# %s: %s' % ( + doc.find('Classification').get('id'), + doc.find('Classification/Label/LabelText[@language="EN"]').text)) + + for item in doc.findall('Classification/Item'): + number = item.get('id') + level = int(item.get('idLevel', 0)) + label = item.find('Label/LabelText[@language="EN"]').text + isic = item.find( + 'Property[@genericName="ISIC4_REF"]/PropertyQualifier/' + + 'PropertyText').text + if level == 1: + section = number + print('%s label="%s" isic="%s"' % (number, label, isic)) + elif level == 2: + print('%s section="%s" label="%s" isic="%s"' % ( + number, section, label, isic)) + else: + print('%s%s label="%s" isic="%s"' % ( + ' ' * (level - 2), number[level], label, isic)) |