def main():
items = Knead(PATH + "/data/uds/monuments-with-qids.csv").data()
skiplist = Skiplist("projects/skiplists/uds.txt")
for index, item in enumerate(items):
print(item)
qid = item["qid"]
bag = item["bag_ok"]
url = item["url"]
print()
print(f"#{index} / #{len(items)}")
print(f"Handling {qid} / {bag} / {url}")
if skiplist.has(qid):
print(f"{qid} in skiplist, skipping")
continue
wd_item = WikidataItem(qid)
claims = wd_item.get_claims()
if Props.BAG_BUILDING in claims:
print("This item already has a BAG building ID, skipping")
continue
wd_item.add_string_claim(
Props.BAG_BUILDING,
bag,
references=[
wd_item.get_item_claim(Props.STATED_IN, Items.UDS_DOC),
wd_item.get_url_claim(Props.REF_URL, url),
wd_item.get_item_claim(Props.LANGUAGE_WORK, Items.DUTCH)
])
skiplist.add(qid)
def add_sites():
PATH = str(Path(__file__).parent)
sites = Knead(PATH + "/data/zomergasten/guest-sites.csv").data()
for site in sites:
qid = site["qid"]
url = site["url"]
name = site["guest"]
print()
print(f"Now handling {qid} / {name}")
item = WikidataItem(qid)
claims = item.get_claims()
if Props.OFFICIAL_WEBSITE in claims:
print("Already got a site, skip")
continue
item.add_url_claim(
Props.OFFICIAL_WEBSITE,
url,
qualifiers=[item.get_item_claim(Props.LANGUAGE_WORK, Items.DUTCH)],
references=[
item.get_claim(Props.RETRIEVED, wbtime_now()),
item.get_url_claim(
Props.REF_URL,
"https://www.vpro.nl/programmas/zomergasten/a-z.html"),
item.get_item_claim(Props.LANGUAGE_WORK, Items.DUTCH)
])
def add_image_alias(item):
qid = item["item"]
img = item["Afbeelding"]
alias = item["alias"]
item = WikidataItem(qid)
claims = item.get_claims()
aliases = item.get_aliases("nl")
if img != "" and Props.IMAGE not in claims:
item.add_commonsmedia(
Props.IMAGE, img,
references = [
item.get_item_claim(Props.IMPORTED_FROM, Items.WIKIPEDIA_NL),
item.get_url_claim(Props.WM_IMPORT_URL, WP_PERMALINK)
]
)
else:
print("has an image already")
if (alias != "") and (not aliases):
print(f"Setting alias: {alias}")
item.edit_aliases({
"nl" : [ alias ]
})
else:
print("Already has aliases")
def add_party_data(row):
print("----" * 20)
print()
print(row)
title = row["title"]
qid = row["qid"]
if skiplist.has(qid):
print(f"In skiplist, skipping")
return
item = WikidataItem(qid)
if Props.NR_OF_SEATS in item.get_claims():
print("Got seats already, skipping party")
return
for key, val in row.items():
if not key.isdigit():
continue
year = int(key)
if val == "":
continue
seats = int(val)
print(f"{title} ({qid}) had {seats} seats in {year}")
item.add_quantity_claim(
Props.NR_OF_SEATS,
seats,
qualifiers=[
item.get_item_claim(Props.LEGISLATIVE_BODY,
Items.NL_LOWER_HOUSE),
item.get_claim(Props.START_TIME, WbTime(year=year))
],
references=[
item.get_item_claim(Props.IMPORTED_FROM, Items.WIKIPEDIA_NL),
item.get_url_claim(Props.WM_IMPORT_URL, WP_PERMALINK)
])
skiplist.add(qid)
def add_inventory(item):
qid = item["item"]
url = item["url"]
if "https://www.nijmegen.nl/kos/kunstwerk" not in url:
return
kid = url.replace("https://www.nijmegen.nl/kos/kunstwerk.aspx?id=", "")
item = WikidataItem(qid)
if Props.INVENTORY_NR in item.get_claims():
print("has inventory!")
return
item.add_string_claim(
Props.INVENTORY_NR, kid,
qualifiers = [
item.get_item_claim(Props.COLLECTION, Items.PUBLIC_ART_IN_NIJMEGEN)
],
references = get_refs(item, url)
)
def main():
items = Knead("projects/data/churchseats/seats-qids.csv").data()
skiplist = Skiplist("projects/skiplists/churchseats.txt")
permalink = "https://nl.wikipedia.org/w/index.php?title=Lijst_van_grootste_Nederlandse_kerkgebouwen_naar_zitplaatsen&oldid=56777124"
for index, item in enumerate(items):
qid = item["qid"]
title = item["name"]
seats = item["seats"]
print()
print(f"#{index} / #{len(items)}")
print(f"Handling {qid} / {title} / {seats} seats")
print(item)
if skiplist.has(qid):
print(f"{qid} in skiplist, skipping")
continue
wd_item = WikidataItem(qid)
claims = wd_item.get_claims()
if Props.CAPACITY in claims:
print("This item already has capacity, skipping")
continue
wd_item.add_quantity_claim(
Props.CAPACITY,
seats,
references=[
wd_item.get_item_claim(Props.IMPORTED_FROM,
Items.WIKIPEDIA_NL),
wd_item.get_url_claim(Props.WM_IMPORT_URL, permalink)
])
skiplist.add(qid)
def add_item(data):
print("----" * 20)
print()
print(data)
title = data["title"]
url = data["url"]
kid = data["id"]
# if kid != "50":
# return
print(f"Handling {title}")
if skiplist.has(kid):
print(f"In skiplist, skipping")
return
creator = data["creator"]
if creator == "":
desc_nl = "kunstwerk in de openbare ruimte te Nijmegen"
desc_en = "public artwork in Nijmegen, the Netherlands"
elif creator == "Onbekend":
desc_nl = "kunstwerk in de openbare ruimte van een onbekende maker te Nijmegen"
desc_en = "public artwork by an unknown artist in Nijmegen, the Netherlands"
else:
desc_nl = f"kunstwerk van {creator} in de openbare ruimte te Nijmegen"
desc_en = f"public artwork by {creator} in Nijmegen, the Netherlands"
item = WikidataItem(
summary = f"public artwork '{title}' in Nijmegen, the Netherlands",
labels = {
"nl" : title
}
)
item.edit_descriptions({
"de" : f"Kunst im öffentlichen Raum in Nijmegen (Niederlande)",
"en" : desc_en,
"es" : f"arte público en Nijmegen (Holanda)",
"fr" : f"art public à Nimègue (Pays-Bas)",
"nl" : desc_nl
})
item.edit_aliases({
"en" : title
})
# Basics
item.add_item_claim(Props.INSTANCE_OF, Items.SCULPTURE)
item.add_item_claim(Props.COUNTRY, Items.NETHERLANDS)
item.add_item_claim(Props.LOCATED_IN_ADMIN, Items.NIJMEGEN_MUNIP)
item.add_item_claim(Props.GENRE, Items.PUBLIC_ART)
# Actual data
coord = [data["lat"], data["lon"]]
item.add_coordinate(
Props.COORDINATES, coord, references = get_refs(item, url)
)
item.add_string_claim(
Props.INVENTORY_NR, kid,
qualifiers = [
item.get_item_claim(Props.COLLECTION, Items.PUBLIC_ART_IN_NIJMEGEN)
],
references = get_refs(item, url)
)
item.add_string_claim(
Props.DESCRIBED_AT_URL,
url,
qualifiers = [
item.get_item_claim(Props.LANGUAGE_WORK, Items.DUTCH)
]
)
if data["year"] != "":
year = int(data["year"])
item.add_time_claim(
Props.INCEPTION, WbTime(year = year), references = get_refs(item, url)
)
if data["creator_qid"] != "":
item.add_item_claim(
Props.CREATOR, data["creator_qid"], references = get_refs(item, url)
)
elif data["creator"] == "Onbekend":
item.add_item_claim(
Props.CREATOR, "somevalue", references = get_refs(item, url)
)
if data["owner"] == "gemeente":
item.add_item_claim(
Props.COLLECTION, Items.NIJMEGEN_MUNIP, references = get_refs(item, url)
)
elif data["owner"] == "particulier":
item.add_item_claim(
Props.COLLECTION, Items.PRIVATE_COLLECTION, references = get_refs(item, url)
)
if data["location_clean"] != "":
item.add_monoling_claim(
Props.STREET_ADDRESS, data["location_clean"], "nl", references = get_refs(item, url)
)
skiplist.add(kid)