User:TolBot/Task 5
Appearance
Status | Approved |
---|---|
Wiki | x |
Summary | Update COVID-19 pandemic data |
Page(s) | Pages:
|
Period | daily |
Language | Python |
Supervision | automatic |
Excl. compl.? | No |
Requests for approval
[edit]- w:en: Approved
- w:uk: Approved
- w:et: Approved
- w:fr: Approved
- w:zh: Approved
- w:af: Unapproved
- w:simple: Approved
Source
[edit]Version 1.3.0, updated 21 Sep 2024. |
---|
run = True
languages = {
'en': {
'page': 'Template:COVID-19 data/data',
'summary': '[[m:User:TolBot/Task 5|Task 5]]: update COVID-19 pandemic data'
},
'fr': {
'page': 'Modèle:Données de la pandémie de Covid-19/données',
'summary': '[[m:User:TolBot/Task 5|Tâche 5]]: mettre à jour les données de la pandémie de COVID-19'
},
'et': {
'page': 'Mall:Koroonapandeemia riigiti/andmed',
'summary': '[[m:User:TolBot/Task 5|Ülesanne 5]]: värskendada COVID-19 pandeemia andmeid'
},
'af': {
'page': 'Sjabloon:Koronaviruspandemie van 2019-2020/data',
'summary': '[[m:User:TolBot/Task 5|Taak 5]]: dateer COVID-19-pandemiedata op'
},
'uk': {
'page': 'Шаблон:Пандемія COVID-19 за країнами та територіями/дані',
'summary': '[[m:User:TolBot/Task 5|Завдання 5]]: оновити дані про пандемію COVID-19'
},
'zh': {
'page': 'Template:COVID-19 data/data',
'summary': '[[m:User:TolBot/Task 5|任務5]]:更新 COVID-19 疫情数据'
}
}
bot_username = ''
bot_password = ''
bot_credentials = (bot_username, bot_password)
import requests
import json
import pandas as pd
import re
api = 'https://{0}.wikipedia.org/w/api.php?format=json&formatversion=2'
owid_url = 'https://catalog.ourworldindata.org/garden/covid/latest/compact/compact.csv'
owid_translator = {
'countries': {
'OWID_WRL': 'XW',
'OWID_EU27': 'EU',
'OWID_CYN': 'XC', # Northern Cyprus
'OWID_KOS': 'XK', # Kosovo
'OWID_TRS': 'XT', # Transnistria
'ABW': 'AW',
'AFG': 'AF',
'AGO': 'AO',
'AIA': 'AI',
'ALA': 'AX',
'ALB': 'AL',
'AND': 'AD',
'ARE': 'AE',
'ARG': 'AR',
'ARM': 'AM',
'ASM': 'AS',
'ATA': 'AQ',
'ATF': 'TF',
'ATG': 'AG',
'AUS': 'AU',
'AUT': 'AT',
'AZE': 'AZ',
'BDI': 'BI',
'BEL': 'BE',
'BEN': 'BJ',
'BES': 'BQ',
'BFA': 'BF',
'BGD': 'BD',
'BGR': 'BG',
'BHR': 'BH',
'BHS': 'BS',
'BIH': 'BA',
'BLM': 'BL',
'BLR': 'BY',
'BLZ': 'BZ',
'BMU': 'BM',
'BOL': 'BO',
'BRA': 'BR',
'BRB': 'BB',
'BRN': 'BN',
'BTN': 'BT',
'BVT': 'BV',
'BWA': 'BW',
'CAF': 'CF',
'CAN': 'CA',
'CCK': 'CC',
'CHE': 'CH',
'CHL': 'CL',
'CHN': 'CN',
'CIV': 'CI',
'CMR': 'CM',
'COD': 'CD',
'COG': 'CG',
'COK': 'CK',
'COL': 'CO',
'COM': 'KM',
'CPV': 'CV',
'CRI': 'CR',
'CUB': 'CU',
'CUW': 'CW',
'CXR': 'CX',
'CYM': 'KY',
'CYP': 'CY',
'CZE': 'CZ',
'DEU': 'DE',
'DJI': 'DJ',
'DMA': 'DM',
'DNK': 'DK',
'DOM': 'DO',
'DZA': 'DZ',
'ECU': 'EC',
'EGY': 'EG',
'ERI': 'ER',
'ESH': 'EH',
'ESP': 'ES',
'EST': 'EE',
'ETH': 'ET',
'FIN': 'FI',
'FJI': 'FJ',
'FLK': 'FK',
'FRA': 'FR',
'FRO': 'FO',
'FSM': 'FM',
'GAB': 'GA',
'GBR': 'GB',
'GEO': 'GE',
'GGY': 'GG',
'GHA': 'GH',
'GIB': 'GI',
'GIN': 'GN',
'GLP': 'GP',
'GMB': 'GM',
'GNB': 'GW',
'GNQ': 'GQ',
'GRC': 'GR',
'GRD': 'GD',
'GRL': 'GL',
'GTM': 'GT',
'GUF': 'GF',
'GUM': 'GU',
'GUY': 'GY',
'HKG': 'HK',
'HMD': 'HM',
'HND': 'HN',
'HRV': 'HR',
'HTI': 'HT',
'HUN': 'HU',
'IDN': 'ID',
'IMN': 'IM',
'IND': 'IN',
'IOT': 'IO',
'IRL': 'IE',
'IRN': 'IR',
'IRQ': 'IQ',
'ISL': 'IS',
'ISR': 'IL',
'ITA': 'IT',
'JAM': 'JM',
'JEY': 'JE',
'JOR': 'JO',
'JPN': 'JP',
'KAZ': 'KZ',
'KEN': 'KE',
'KGZ': 'KG',
'KHM': 'KH',
'KIR': 'KI',
'KNA': 'KN',
'KOR': 'KR',
'KWT': 'KW',
'LAO': 'LA',
'LBN': 'LB',
'LBR': 'LR',
'LBY': 'LY',
'LCA': 'LC',
'LIE': 'LI',
'LKA': 'LK',
'LSO': 'LS',
'LTU': 'LT',
'LUX': 'LU',
'LVA': 'LV',
'MAC': 'MO',
'MAF': 'MF',
'MAR': 'MA',
'MCO': 'MC',
'MDA': 'MD',
'MDG': 'MG',
'MDV': 'MV',
'MEX': 'MX',
'MHL': 'MH',
'MKD': 'MK',
'MLI': 'ML',
'MLT': 'MT',
'MMR': 'MM',
'MNE': 'ME',
'MNG': 'MN',
'MNP': 'MP',
'MOZ': 'MZ',
'MRT': 'MR',
'MSR': 'MS',
'MTQ': 'MQ',
'MUS': 'MU',
'MWI': 'MW',
'MYS': 'MY',
'MYT': 'YT',
'NAM': 'NA',
'NCL': 'NC',
'NER': 'NE',
'NFK': 'NF',
'NGA': 'NG',
'NIC': 'NI',
'NIU': 'NU',
'NLD': 'NL',
'NOR': 'NO',
'NPL': 'NP',
'NRU': 'NR',
'NZL': 'NZ',
'OMN': 'OM',
'PAK': 'PK',
'PAN': 'PA',
'PCN': 'PN',
'PER': 'PE',
'PHL': 'PH',
'PLW': 'PW',
'PNG': 'PG',
'POL': 'PL',
'PRI': 'PR',
'PRK': 'KP',
'PRT': 'PT',
'PRY': 'PY',
'PSE': 'PS',
'PYF': 'PF',
'QAT': 'QA',
'REU': 'RE',
'ROU': 'RO',
'RUS': 'RU',
'RWA': 'RW',
'SAU': 'SA',
'SDN': 'SD',
'SEN': 'SN',
'SGP': 'SG',
'SGS': 'GS',
'SHN': 'SH',
'SJM': 'SJ',
'SLB': 'SB',
'SLE': 'SL',
'SLV': 'SV',
'SMR': 'SM',
'SOM': 'SO',
'SPM': 'PM',
'SRB': 'RS',
'SSD': 'SS',
'STP': 'ST',
'SUR': 'SR',
'SVK': 'SK',
'SVN': 'SI',
'SWE': 'SE',
'SWZ': 'SZ',
'SXM': 'SX',
'SYC': 'SC',
'SYR': 'SY',
'TCA': 'TC',
'TCD': 'TD',
'TGO': 'TG',
'THA': 'TH',
'TJK': 'TJ',
'TKL': 'TK',
'TKM': 'TM',
'TLS': 'TL',
'TON': 'TO',
'TTO': 'TT',
'TUN': 'TN',
'TUR': 'TR',
'TUV': 'TV',
'TWN': 'TW',
'TZA': 'TZ',
'UGA': 'UG',
'UKR': 'UA',
'UMI': 'UM',
'URY': 'UY',
'USA': 'US',
'UZB': 'UZ',
'VAT': 'VA',
'VCT': 'VC',
'VEN': 'VE',
'VGB': 'VG',
'VIR': 'VI',
'VNM': 'VN',
'VUT': 'VU',
'WLF': 'WF',
'WSM': 'WS',
'YEM': 'YE',
'ZAF': 'ZA',
'ZMB': 'ZM',
'ZWE': 'ZW'
},
'columns': {
'people_vaccinated': 'total_vaccinated',
'people_fully_vaccinated': 'fully_vaccinated',
'total_vaccinations': 'vaccine_doses',
'total_cases': 'cases',
'total_deaths': 'deaths',
'people_vaccinated_per_hundred': 'percent_vaccinated',
'people_fully_vaccinated_per_hundred': 'percent_fully_vaccinated',
'total_deaths_per_million': 'deaths_per_million',
'population': 'population'
}
}
# Login
def login(api, session, credentials):
token_params = {
'action': 'query',
'meta': 'tokens',
'type': 'login'
}
token_q = session.post(api, data=token_params).json()
token = token_q['query']['tokens']['logintoken']
username, password = credentials
login_params = {
'action': 'login',
'lgname': username,
'lgpassword': password,
'lgtoken': token
}
login_q = session.post(api, data=login_params).json()
return session
# Get and parse current data on page
def parse_json(api, session, page):
params = {
'action': 'parse',
'prop': 'wikitext',
'page': page
}
q = session.post(api, data=params).json()
wikitext = q['parse']['wikitext']
data = json.loads(wikitext)
return data
def get(url):
return pd.read_csv(url).groupby('code').max('date')
# Update with OWID data
def update_owid(owid_data, data, translator):
for owid_code, location_data in owid_data.iterrows():
if owid_code in translator['countries']:
code = translator['countries'][owid_code]
for owid_col, col in translator['columns'].items():
if owid_col in location_data:
if not code in data:
data[code] = {}
if not pd.isna(location_data[owid_col]):
data[code][col] = location_data[owid_col]
return data
# Old update_owid() for reference, used with:
# https://covid.ourworldindata.org/data/latest/owid-covid-latest.json
# (broken now that GitHub repo not updated)
#
# def update_owid(owid_data, data, translator):
# for owid_code, location_data in owid_data.items():
# if owid_code in translator['countries']:
# for owid_col, col in translator['columns'].items():
# if owid_col in location_data:
# code = translator['countries'][owid_code]
# if not code in data:
# data[code] = {}
# if location_data[owid_col]:
# data[code][col] = location_data[owid_col]
# return data
# Edit page with updated data
def edit(api, session, page, data, summary):
text = json.dumps(data, ensure_ascii=False, sort_keys=True)
token_params = {
'action': 'query',
'meta': 'tokens'
}
token_q = session.post(api, data=token_params).json()
token = token_q['query']['tokens']['csrftoken']
edit_params = {
'action': 'edit',
'title': page,
'text': text,
'summary': summary,
'token': token
}
edit_q = session.post(api, data=edit_params).json()
return edit_q
session = requests.Session()
if run:
for lang in languages:
login(api.format(lang), session, bot_credentials)
owid_data = get(owid_url)
for lang, lang_data in languages.items():
data = parse_json(api.format(lang), session, lang_data['page'])
data = update_owid(owid_data, data, owid_translator)
if run:
print(lang, edit(
api.format(lang),
session,
lang_data['page'],
data,
lang_data['summary']
))
else:
print(
'\n\n', lang, '\n',
json.dumps(data, indent=2, ensure_ascii=False, sort_keys=True)
)
|
Licensing
[edit]This work (all source code in this level 2 section) is licensed under:
- The Creative Commons Attribution-ShareAlike 3.0 (CC BY-SA 3.0) license
- The Creative Commons Attribution-ShareAlike 4.0 (CC BY-SA 4.0) license
- The GNU Lesser General Public License (LGPL), version 3 or any later version
- The GNU Free Documentation License (GFDL), version 1.3 or any later version, with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts
Version history
[edit]- 1.0.0: Initial release. 23 Jul 2021.
- 1.1.0: Use JSON latest data instead of CSV all data. 26 Jul 2021.
- 1.1.1: Add percent fully vaccinated. 31 Aug 2021.
- 1.1.2: Add deaths per million. 23 Sep 2021.
- 1.2.0: Make compatible with multiple language Wikipedias. 15 Oct 2021.
- 1.2.1: Add population. 16 Oct 2021.
- 1.2.2: Cleanup code. 27 Dec 2021.
- 1.3.0: Rewrite
get()
andupdate_owid()
to handle CSV input due to GitHub dataset deprecation. 21 Sep 2024.