def main():
# Mariniersbrug
qid = "Q2461755"
item = WikidataItem(qid)
claims = item.get_claims()
monument_id = claims[Props.RIJKSMONUMENT_ID]
print(f"monument_id: {monument_id}")
def parse():
for feature in coords["features"]:
pid = feature["properties"]["id"]
coord = feature["geometry"]["coordinates"]
coord.reverse()
plantage = get_plantage(pid)
qid = plantage["qid"]
name = plantage["name"]
if not qid:
continue
print()
print("---" * 20)
print(pid, coord, name, qid)
item = WikidataItem(qid)
claims = item.get_claims()
if Props.COORDINATES in claims:
print("Already has coordinates, skipping!")
continue
item.add_coordinate(Props.COORDINATES,
coord,
references=get_refs(item, pid))
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_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 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)
class BotJob:
def __init__(self, data, item=None, dry_run=False):
self.is_aborted = False
self.data = data
self.dry_run = dry_run
self.item = item
def abort(self, message):
print(f"Abort: {message}")
self.is_aborted = True
# Lifted from https://github.com/multichill/toollabs/blob/master/bot/wikidata/artdatabot.py
def archive_url(self, url):
"""
Links to paintings are subject to link rot. When creating a new item, have the Wayback Machine make a snapshot.
That way always have a copy of the page we used to source a bunch of statements.
See also https://www.wikidata.org/wiki/Wikidata:WikiProject_sum_of_all_paintings/Link_rot
"""
print(f"Backing up to the Wayback Machine: {url}")
wayback_url = f"https://web.archive.org/save/{url}"
try:
requests.post(wayback_url)
except requests.exceptions.RequestException:
print(f"Wayback Machine save failed")
def create_item(self, summary, labels, descriptions=None, aliases=None):
if self.item:
raise Exception("Job already has an item")
print(f"Creating new item")
dd({
"summary": summary,
"labels": labels,
"descriptions": descriptions,
"aliases": aliases
})
try:
self.item = WikidataItem(summary=summary,
labels=labels,
descriptions=descriptions,
aliases=aliases)
except Exception as e:
print("Got an exception while creating item", e)
# Re-raise
raise (e)
print("Okay, created a new item")
def has_prop(self, pid):
claims = self.item.get_claims()
return pid in claims
def set_item_by_qid(self, qid):
self.item = WikidataItem(qid)
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 main():
items = Knead("projects/data/churches/import.json").data()
skiplist = Skiplist("projects/skiplists/churches.txt")
for index, item in enumerate(items):
qid = item["qid"]
title = item["title"]
print()
print(f"#{index} / #{len(items)}")
print(f"Handling {qid} / {title}")
if not any([item["inception"], item["demolished"], item["restored"]]):
print("No inception, demolished, restored, skipping")
continue
print(item)
if skiplist.has(qid):
print(f"{qid} in skiplist, skipping")
continue
wd_item = WikidataItem(qid)
claims = wd_item.get_claims()
permalink = get_permalink("nl", title)
if item["inception"] and Props.INCEPTION not in claims:
set_year_claim(wd_item, Props.INCEPTION, item["inception"],
permalink)
if item["demolished"] and Props.DISSOLVED not in claims:
set_year_claim(wd_item, Props.DISSOLVED, item["demolished"],
permalink)
if item["restored"] and Props.SIG_EVENT not in claims:
set_sig_claim(wd_item, Items.RECONSTRUCTION, item["restored"],
permalink)
if item["expanded"] and Props.SIG_EVENT not in claims:
set_sig_claim(wd_item, Items.BUILDING_EXPANSION, item["expanded"],
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)