def test_get_label_1(self) -> None:
"""Assert correct behavior in get_label method."""
q42_dict = _load_item_dict(typedefs.ItemId("Q42"))
en_label = q42_dict["labels"][EN]["value"]
de_label = q42_dict["labels"][DE]["value"]
item = WikidataItem(q42_dict)
assert item.get_label() == en_label
assert item.get_label(lang=EN) == en_label
assert item.get_label(lang=DE) == de_label
assert item.get_label(lang=NO) == ""
p279_dict = _load_property_dict(typedefs.PropertyId("P279"))
en_label = p279_dict["labels"][EN]["value"]
de_label = p279_dict["labels"][DE]["value"]
prop = WikidataProperty(p279_dict)
assert prop.get_label() == en_label
assert prop.get_label(lang=EN) == en_label
assert prop.get_label(lang=DE) == de_label
assert prop.get_label(lang=NO) == ""
def main(search_term):
wikipedia = MediaWiki(lang='pap', user_agent='code-for-nl-pap-parser')
wikidata = MediaWiki(url='https://www.wikidata.org/w/api.php',
user_agent='code-for-nl-pap-parser')
search_result = wikipedia.search(search_term, results=4)
for result_item in search_result:
page = wikipedia.page(result_item)
print(
'I found page \'%s\' for term \'%s\'' % (result_item, search_term),
'with categories', '/'.join(page.categories),
'https://pap.wikipedia.org/wiki/' +
urllib.parse.quote(result_item))
# print(page.images)
# Now I am going to search this one on wikidata, this will return a code. like Q215887
search_data = wikidata.search(result_item, results=1)
for data_item in search_data:
Q_CODE = data_item
print(result_item, 'is known on wikidata with the code', Q_CODE,
'https://www.wikidata.org/wiki/' + Q_CODE)
# Now try the qwikidata interface
entity = get_entity_dict_from_api(Q_CODE)
q = WikidataItem(entity)
pap_data_label = q.get_label(lang='pap')
nl_data_label = q.get_label(lang='nl')
if pap_data_label and nl_data_label:
# First get the page. Read the images found
data_page = wikidata.page(result_item)
# print(data_page.images)
print(pap_data_label, 'is called', nl_data_label, 'in dutch')
elif pap_data_label and not nl_data_label:
print(pap_data_label, 'has no entry for dutch!')
elif not pap_data_label and nl_data_label:
print(Q_CODE, 'does not match papiamentu entry')
elif not pap_data_label and not nl_data_label:
print(pap_data_label, 'has no entry for dutch or papiamentu!')
def is_matched(q: WikidataItem) -> bool:
# 確認是否有中文名
if q.get_label("zh") == "":
print(f'Skip, no zh label: {q.get_enwiki_title()}')
return False
# entity不能是人
cg = q.get_claim_group("P31") # P31:instance_of
instanceof = [c.mainsnak.datavalue.value['id'] for c in cg]
if "Q5" in instanceof: # Q5:human
print(f'Skip, is a person: {q.get_enwiki_title()}')
return False
# entity不能有位置claim
cg = q.get_claim_group("P625") # P625:coordinate_location
if cg.property_id is not None:
print(f'Skip, has coordinate location: {q.get_enwiki_title()}')
return False
return True
def get_place_from_wikidata(entity_id):
parents = set()
entity = WikidataItem(get_entity_dict_from_api(entity_id))
claims_groups = entity.get_truthy_claim_groups()
place = Place()
place.set_gramps_id(entity_id)
name = PlaceName()
name.set_language('sv')
name.set_value(entity.get_label('sv'))
place.set_name(name=name)
place.set_title(entity.get_label('sv'))
for lang in ['sv', 'en', 'de', 'fi', 'no', 'nn', 'da', 'se']:
wiki_name = entity.get_label(lang)
if len(wiki_name):
place_name = PlaceName()
place_name.set_language(lang)
place_name.set_value(wiki_name)
place.add_alternative_name(name=place_name)
for alias in entity.get_aliases(lang):
alt_name = PlaceName()
alt_name.set_language(lang)
alt_name.set_value(alias)
place.add_alternative_name(name=alt_name)
for link in entity.get_sitelinks(lang).values():
wikipedia_url = Url()
wikipedia_url.set_path(link['url'])
wikipedia_url.set_type('Wikipedia entry')
wikipedia_url.set_description('Wikipedia %s:%s' %
(link["title"], link["site"]))
place.add_url(wikipedia_url)
# Instance of -> PlaceType
if PROPERTY_INSTANCE_OF in claims_groups:
for claim in claims_groups[PROPERTY_INSTANCE_OF]:
instance_of = claim.mainsnak.datavalue.value['id']
if ITEM_PARISH == instance_of:
place.set_type(PlaceType.PARISH)
elif ITEM_SOCKEN == instance_of:
place.set_type(PlaceType.PARISH)
elif ITEM_ISLAND == instance_of:
place.set_type(PlaceType.UNKNOWN) # No islands in Gramps
elif ITEM_MUNICIPALITY_OF_SWEDEN == instance_of:
place.set_type(PlaceType.MUNICIPALITY)
elif ITEM_MUNICIPALITY == instance_of:
place.set_type(PlaceType.MUNICIPALITY)
elif ITEM_COUNTRY == instance_of:
place.set_type(PlaceType.COUNTRY)
elif ITEM_SOVEREIGN_STATE == instance_of:
place.set_type(PlaceType.COUNTRY)
elif ITEM_STATE_OF_US == instance_of:
place.set_type(PlaceType.STATE)
elif ITEM_FEDERAL_STATE == instance_of:
place.set_type(PlaceType.STATE)
elif ITEM_COUNTY == instance_of:
place.set_type(PlaceType.COUNTY)
elif ITEM_COUNTY_OF_SWEDEN == instance_of:
place.set_type(PlaceType.COUNTY)
elif ITEM_FORMER_COUNTY_OF_SWEDEN == instance_of:
place.set_type(PlaceType.COUNTY)
elif ITEM_PROVINCE_OF_SWEDEN == instance_of:
place.set_type(PlaceType.PROVINCE)
elif ITEM_PROVINCE == instance_of:
place.set_type(PlaceType.PROVINCE)
elif ITEM_ADM_REGION == instance_of:
place.set_type(PlaceType.REGION)
elif ITEM_NEIGHBORHOOD == instance_of:
place.set_type(PlaceType.NEIGHBORHOOD)
elif ITEM_DISTRICT == instance_of:
place.set_type(PlaceType.DISTRICT)
elif ITEM_BOROUGH == instance_of:
place.set_type(PlaceType.BOROUGH)
elif ITEM_TOWN == instance_of:
place.set_type(PlaceType.TOWN)
elif ITEM_LARGE_VILLAGE == instance_of:
place.set_type(PlaceType.VILLAGE)
elif ITEM_VILLAGE == instance_of:
place.set_type(PlaceType.VILLAGE)
elif ITEM_URBAN_AREA_IN_SWEDEN == instance_of:
place.set_type(PlaceType.VILLAGE)
elif ITEM_HAMLET == instance_of:
place.set_type(PlaceType.HAMLET)
elif ITEM_FARM == instance_of:
place.set_type(PlaceType.FARM)
elif ITEM_BUILDING == instance_of:
place.set_type(PlaceType.BUILDING)
if PROPERTY_COORDINATE_LOCATION in claims_groups:
for claim in claims_groups[PROPERTY_COORDINATE_LOCATION]:
datavalue = claim.mainsnak.datavalue
place.set_latitude(str(datavalue.value['latitude']))
place.set_longitude(str(datavalue.value['longitude']))
extract_located_in(claims_groups, PROPERTY_LOCATED_IN_PRESENT, parents)
extract_located_in(claims_groups, PROPERTY_LOCATED_IN_ADM, parents)
extract_located_in(claims_groups, PROPERTY_LOCATED, parents)
return place, parents
try:
personDict = get_entity_dict_from_api(name) # Insert QCode here
except:
missingCodes = open("missingCodes.txt", "a")
missingCodes.write(name + '\n')
continue
person = WikidataItem(personDict)
claim_groups = person.get_truthy_claim_groups(
) # Gets a person's different Wikidata attributes
try:
eduGroups = claim_groups[
"P69"] # Grabs person's education from those attributes
foundCount += 1
except:
print(str(cnt) + ".", "Education not there for", person.get_label())
missingCount += 1
if (cnt % 10 == 0):
readyToAppend = True
continue
eduEntries = len(eduGroups) # How many different entries there are
print(str(cnt) + ".", "Writing education for", person.get_label())
eduList = []
for i in range(eduEntries):
try:
eduEntry = eduGroups[i] # Get list entry
qid = eduEntry.mainsnak.datavalue.value["id"] # Get its ID
eduValue = WikidataItem(
get_entity_dict_from_api(qid)) # Get its actual name
eduList.append(eduValue.get_label())