finished function for dict import, started function to check for existing entities, already running for ishuman (q5)
This commit is contained in:
parent
d01b379ad8
commit
7ade95deb5
6 changed files with 70 additions and 2 deletions
Binary file not shown.
2
main.py
2
main.py
|
@ -25,3 +25,5 @@ listOfCountries = ['nicaragua']
|
||||||
wikidataPEP = WikidataPEP(config)
|
wikidataPEP = WikidataPEP(config)
|
||||||
|
|
||||||
wikidataPEP.importMembersOfParliamentDict(listOfCountries)
|
wikidataPEP.importMembersOfParliamentDict(listOfCountries)
|
||||||
|
|
||||||
|
wikidataPEP.checkForEntityIds(listOfCountries)
|
||||||
|
|
33
q5.txt
Normal file
33
q5.txt
Normal file
|
@ -0,0 +1,33 @@
|
||||||
|
started to parse data of members of nicaragua ..
|
||||||
|
Q107326760
|
||||||
|
---------
|
||||||
|
Ángela Espinoza Tórrez
|
||||||
|
is a human
|
||||||
|
Q475730
|
||||||
|
---------
|
||||||
|
Carlos Humberto Ruíz
|
||||||
|
is a human
|
||||||
|
Q107316535
|
||||||
|
---------
|
||||||
|
Iris Marina Montenegro Blandón
|
||||||
|
is a human
|
||||||
|
Q107332750
|
||||||
|
---------
|
||||||
|
Iris Marina Montenegro Blandón
|
||||||
|
is a human
|
||||||
|
Q107320919
|
||||||
|
---------
|
||||||
|
Iris Marina Montenegro Blandón
|
||||||
|
is a human
|
||||||
|
Q63794924
|
||||||
|
---------
|
||||||
|
Loria Raquel Dixon Brautigam
|
||||||
|
is a human
|
||||||
|
Q107406987
|
||||||
|
---------
|
||||||
|
María Haydee Osuna Ruíz
|
||||||
|
is a human
|
||||||
|
Q106514750
|
||||||
|
---------
|
||||||
|
Shaira Natasha Downs Morgan
|
||||||
|
is a human
|
BIN
wikidata/.wdPEP.py.kate-swp
Normal file
BIN
wikidata/.wdPEP.py.kate-swp
Normal file
Binary file not shown.
Binary file not shown.
|
@ -24,14 +24,47 @@ class WikidataPEP(object):
|
||||||
|
|
||||||
for country in listOfCountries:
|
for country in listOfCountries:
|
||||||
|
|
||||||
print('started to parse data of member of ' + country + ' ..')
|
print('started to parse data of members of ' + country + ' ..')
|
||||||
|
|
||||||
f = open('crawlers/output/' + country +'MemberList.txt')
|
f = open('crawlers/output/' + country +'MemberList.txt')
|
||||||
text = f.read()
|
text = f.read()
|
||||||
|
|
||||||
self.fullDictionaryMemberLists[country] = eval(text)
|
self.fullDictionaryMemberLists[country] = eval(text)
|
||||||
|
|
||||||
print(self.fullDictionaryMemberLists)
|
#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')
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue