1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
import requests
import math
import json
"""
This script extracts official country names based on the UNTERM database.
The United Nations Terminology Database is a multilingual database for official terminology relevant to the work of the United Nations
Official terminology is provided in the six official languages of the United Nations — Arabic, Chinese, English, French, Spanish and Russian.
"""
GET_RECORDS_ID_URL = "https://conferences.unite.un.org/untermapi/api/term/search?query=*&page="
GET_INFO_COUNTRY_URL = "https://conferences.unite.un.org/untermapi/api/record/"
OUTPUT_FILE_NAME = "un_formal_country_names.json"
OUTPUT_FILE_NAME_SMALL = "un_formal_country_names_min.json"
REQUEST_HEADERS = {
'content-type': 'application/json',
'accept': 'application/json, text/plain'
}
REQUEST_DATA = {
"searchTerm": "*",
"searchType": 0,
"searchLanguages": ["ar", "es", "en", "fr", "ru", "zh"],
"languagesDisplay": ["en", "fr"],
"datasets": ["UNHQ"],
"bodies": [],
"subjects": ["Country names"],
"recordTypes": [],
"acronymSearch": True,
"localDBSearch": True,
"termTitleSearch": True,
"phraseologySearch": False,
"footnoteSearch": False,
"fullTextSearch": False,
"facetedSearch": True,
"buildSubjectList": False
}
languagesIDToLanguage = {
'5a504ded-6ba9-49c9-98aa-c8418cbb1ce9': 'arabic',
'676ccfad-a7b3-4e36-8d49-b21a9b5e0d7d': 'chinese',
'77ebac02-6a97-4722-859a-de5896a4d34e': 'english',
'ca7853cf-0f94-4aa6-be0a-ea586361c19e': 'french',
'496bcad8-7cd0-4f46-85c7-23b91e7a4ad2': 'russian',
'af320177-7bdb-40df-9521-6d2e0478f129': 'spanish',
}
def main():
countries = {}
recordsID = getRecordsID()
for records in recordsID:
infoLang = getInfoCountry(records)
countries[infoLang['iso_a2']] = infoLang
# Sort the dictionnary to get the same result every times.
countries = {i2: countries[i2] for i2 in sorted(list(countries.keys()))}
with open(OUTPUT_FILE_NAME, 'w') as f:
json.dump(countries, f)
with open(OUTPUT_FILE_NAME_SMALL, 'w') as f:
json.dump(countries, f, ensure_ascii=False)
def getRecordsID():
"""
This function extracts the recordID of every results of every page so they can be queried later
"""
def getRecordsIDFromResponse(resp):
"""
This function extracts all the recordID of a page and return them.
"""
data = resp.json()
if 'results' not in data:
print("Missing results in request")
exit(4)
return [r['recordID'] for r in data['results'] if 'recordID' in r]
firstRequest = requests.post(GET_RECORDS_ID_URL + "0", data=json.dumps(REQUEST_DATA), headers=REQUEST_HEADERS)
if firstRequest.status_code != 200:
print("The first request failed. Check the URL")
print(firstRequest.status_code)
print(firstRequest.text)
exit(1)
data = firstRequest.json()
if 'results' not in data:
print("Missing results")
exit(3)
recordsID = getRecordsIDFromResponse(firstRequest)
nbPage = int(math.ceil(data['totalHits']) / int(data['pageSize']))
for page in range(1, nbPage + 1):
print(page)
res = requests.post(GET_RECORDS_ID_URL + str(page), data=json.dumps(REQUEST_DATA), headers=REQUEST_HEADERS)
if res.status_code != 200:
print("Unable to get a page that should be accessible")
exit(5)
recordsID.extend(getRecordsIDFromResponse(res))
return recordsID
def getInfoCountry(recordID):
"""
This function extract the information of a recordID.
Each record should match a country so this function extract the names of a country in the 6 offical UN languages.
"""
def removeExtraInfo(countryName):
if '(' in countryName:
return countryName[:countryName.index('(')].strip()
else:
return countryName
res = requests.get(GET_INFO_COUNTRY_URL + recordID)
if res.status_code != 200:
print("Error {res.status_code} requesting {rec}")
exit(2)
data = res.json()
countryInfo = {}
for lang in sorted(data['languages']):
lang = lang.lower()
countryInfo[lang] = {'short': '', 'full': ''}
for i in range(len(data[lang]['terms'])):
countryInfo[lang][data[lang]['terms'][i]['termType']] = data[lang]['terms'][i]['term']
# The UK doesn't have official short name in russian. ¯\_(ツ)_/¯
if not countryInfo[lang]['short'] and countryInfo[lang]['full']:
countryInfo[lang]['short'] = countryInfo[lang]['full']
try:
countryInfo[lang]['map_usable'] = removeExtraInfo(countryInfo[lang]['short'])
except KeyError:
print(f"What the fuck {lang}?!")
print(f"Missing name for this country in {lang}", countryInfo)
for field in sorted(data['specialFields'], key=lambda item: item['name']):
match field['name']:
case "ISO Country alpha-2-code":
countryInfo['iso_a2'] = field['value']
case "ISO Country alpha-3-code":
countryInfo['iso_a3'] = field['value']
case 'Monetary Unit':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['monetary_unit'] = field['value']
case 'Currency Designation':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['currency_designation'] = field['value']
case 'Currency Symbol':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['currency_symbol'] = field['value']
case 'Fractional Unit':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['fractional_unit'] = field['value']
case 'Capital City':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['capital_city'] = field['value']
case 'Adjective':
if field['languageId'] in languagesIDToLanguage:
lang = languagesIDToLanguage[field['languageId']]
countryInfo[lang]['adjective'] = field['value']
case 'Date of Entry in UN':
countryInfo['un_entry_date'] = field['value']
return countryInfo
if __name__ == "__main__":
main()
|
