automated Pipeline for parsing profiles of politically exposed persons (PEP) into Wikidata
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

112 lines
3.8 KiB

import os
import yaml
import json
class WikidataPEP(object):
def __init__(self, configFile):
with open(configFile, "r") as stream:
try:
self.config = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
def importMembersOfParliamentDict(self, listOfCountries):
self.fullDictionaryMemberLists = {}
for country in listOfCountries:
print('started to parse data of members of ' + country + ' ..')
f = open('crawlers/output/' + country +'MemberList.txt')
text = f.read()
self.fullDictionaryMemberLists[country] = eval(text)
#print(self.fullDictionaryMemberLists)
def checkForEntityIds(self, listOfCountries):
from wikibaseintegrator import WikibaseIntegrator
from wikibaseintegrator import wbi_helpers
fullDictionaryMemberLists = self.fullDictionaryMemberLists
for country in listOfCountries:
for memberId in fullDictionaryMemberLists[country].keys():
name = fullDictionaryMemberLists[country][memberId]['name']
results = wbi_helpers.search_entities(search_string=name)
for entityId in results:
wbi = WikibaseIntegrator()
wikidata_item = wbi.item.get(entity_id=entityId)
for claimkey in wikidata_item.get_json()['claims'].keys():
if claimkey == 'P31':
if wikidata_item.get_json()['claims'][claimkey][0]['mainsnak']['datavalue']['value']['id'] == 'Q5':
print(entityId)
print('---------')
print(name)
print('is a human')
def createMemberOnWikidata(self):
from wikibaseintegrator import wbi_login, WikibaseIntegrator
from wikibaseintegrator.datatypes import ExternalID, Item
from wikibaseintegrator.wbi_config import config as wbi_config
wbi_config['USER_AGENT'] = 'PEPimport/1.0 (https://www.wikidata.org/wiki/User:Username)'
# login object
login_instance = wbi_login.OAuth2(consumer_token='', consumer_secret='')
wbi = WikibaseIntegrator(login=login_instance)
# data type object, e.g. for a NCBI gene entrez ID
isHuman = Item(value='Q5', prop_nr='P31')
occupationPolitician = ExternalID(value='Q82955', prop_nr='P106')
occupationDeputy = ExternalID(value='Q1055894', prop_nr='P106')
#referenceURL = URL(value='http://legislacion.asamblea.gob.ni/Tablas%20Generales.nsf/InfoDiputado.xsp?documentId=3D4CFDC4B3006D70062587C5007C29E1&action=openDocument&SessionID=1868803A06AB73D50B7F89BD0AB', prop_nr='P106')
# print(isHuman)
# print(referenceURL)
# data goes into a list, because many data objects can be provided to
data1 = [isHuman]
data2 = [occupationDeputy]
data3 = [occupationPolitician]
# Create a new item
item = wbi.item.new()
# Set an english label
item.labels.set(language='en', value='Carlos Humberto Ruíz')
# Set a French description
item.descriptions.set(language='en', value='Nicaraguan National Assembly Deputy')
item.claims.add(data1)
#item.claims.add(data2)
#item.claims.add(data3)
print(item.write())