def create_new():
items = Knead(PATH + "/data/reliwiki/new-churches.csv",
has_header=True).data()
CITY = "Amsterdam"
for church in items:
print()
print(f"Creating new church", church)
pageid = church["pageid"]
# Last, final check if this church doesn't exist
if claim_exists(Props.RELIWIKI, f'"{pageid}"'):
print(f"This Reliwiki ID exists, skipping")
continue
name = church["name"]
item = WikidataItem(
summary=f"Creating new item for Dutch church with name {name}",
labels={
"en": name,
"nl": name
},
descriptions={
"de": f"Kirche in {CITY} (Niederlande)",
"en": f"church in {CITY}, the Netherlands",
"es": f"iglesia en {CITY} (Holanda)",
"fr": f"Église d'{CITY} (Pays-Bas)",
"nl": f"kerk in {CITY}"
})
item.add_item_claim(Props.INSTANCE_OF, Items.CHURCH_BUILDING)
item.add_string_claim(Props.RELIWIKI, pageid)
item.add_item_claim(Props.COUNTRY, Items.NETHERLANDS)
item.add_item_claim(Props.LOCATED_IN, church["admin_qid"])
if church["sonneveld"] != "":
item.add_string_claim(Props.SONNEVELD,
church["sonneveld"],
references=get_refs(item, pageid))
if church["coordinates"] != "":
coord = church["coordinates"].split(",")
item.add_coordinate(Props.COORDINATES,
coord,
references=get_refs(item, pageid))
if church["zipcode"] != "":
item.add_string_claim(Props.ZIP,
church["zipcode"],
references=get_refs(item, pageid))
if church["address"] != "":
item.add_monoling_claim(Props.STREET_ADDRESS,
church["address"],
"nl",
references=get_refs(item, pageid))
if church["denomination_qid"] != "":
item.add_item_claim(Props.RELIGION,
church["denomination_qid"],
references=get_refs(item, pageid))
if church["year_use"] != "":
if "s" in church["year_use"]:
decade = int(church["year_use"].replace("s", ""))
time = WbTime(year=decade, precision="decade")
else:
time = WbTime(year=int(church["year_use"]))
item.add_time_claim(Props.INCEPTION,
time,
references=get_refs(item, pageid))
print()
break
def add_item(data, qid=None):
name = data["name"]
location = data["location"]
desc = {
"label_en": f"Stolperstein dedicated to {name}",
"label_nl": f"Stolperstein ter herinnering aan {name}",
"description_en": f"stumbling stone in {location}, the Netherlands",
"description_nl": f"struikelsteen in {location}",
"aliases_nl": [
f"struikelsteen ter herinnering aan {name}",
]
}
print(desc)
if qid:
print("HAS QID")
item = WikidataItem(qid)
else:
item = WikidataItem(
summary=f"Creating new item for a Stolperstein for {name}",
labels={
"en": desc["label_en"],
"nl": desc["label_nl"]
},
descriptions={
"en": desc["description_en"],
"nl": desc["description_nl"]
},
aliases={"nl": desc["aliases_nl"]})
# These are the same for all stolpersteine
# item.add_item_claim(Props.INSTANCE_OF, Items.STOLPERSTEIN)
# item.add_item_claim(Props.PART_OF, Items. STOLPERSTEINE_PROJECT)
# item.add_item_claim(Props.COUNTRY, Items.NETHERLANDS)
# item.add_item_claim(Props.CREATOR, Items.GUNTER_DEMNIG)
# item.add_item_claim(Props.MATERIAL_USED, Items.BRASS)
# # These are not
# item.add_commonsmedia(Props.IMAGE, data["image"])
# item.add_item_claim(Props.LOCATED_IN, data["location_qid"])
# item.add_coordinate(Props.COORDINATES, [data["lat"], data["lon"]])
# item.add_monoling_claim(Props.INSCRIPTION, data["inscription"], "nl")
# I hate this f*****g hack
def get_ref():
# Check if we have an url, that's a reference
if data["url"]:
return [
item.get_claim(Props.RETRIEVED, wbtime_now()),
item.get_url_claim(Props.REF_URL, data["url"]),
item.get_item_claim(Props.LANGUAGE_WORK, Items.DUTCH)
]
else:
return None
# Inception and opening
date = partial_date_to_wbtime(data["inception"])
item.add_time_claim(Props.INCEPTION, date, references=get_ref())
item.add_item_claim(Props.SIG_EVENT,
Items.OPENING_CEREMONY,
qualifiers=[item.get_claim(Props.POINT_IN_TIME, date)],
references=get_ref())
# Street as item
item.add_item_claim(Props.LOCATED_ON_STREET,
data["street_qid"],
qualifiers=[
item.get_string_claim(Props.STREET_NUMBER,
data["street_nr"])
])
# Street as address
address = data["street"] + " " + data["street_nr"] + ", " + data["location"]
item.add_monoling_claim(Props.STREET_ADDRESS, address, "nl")
item.add_item_claim(
Props.COMMEMORATES,
"somevalue",
qualifiers=[item.get_monoling_claim(Props.NAME, name, "nl")])
def match_seasons():
PATH = str(Path(__file__).parent)
seasons = Knead(PATH + "/data/zomergasten/seasons.csv").data()
episodes = Knead(PATH + "/data/zomergasten/episodes.csv").data()
skiplist = Skiplist(PATH + "/skiplists/zomergasten-seasons.txt")
def get_season_by_year(year):
for season in seasons:
if season["year"] == year:
return season
return None
prev_ep = None
next_ep = None
cur_year = "1988"
ep_index = 1
for index, episode in enumerate(episodes):
ep_qid = episode["item"]
ep_year = episode["year"]
ep_title = episode["itemLabel"]
season = get_season_by_year(ep_year)
season_qid = season["item"]
season_title = season["itemLabel"]
if skiplist.has(ep_qid):
print(f"{ep_qid} ({ep_title}) in skiplist, skipping")
if season["year"] != cur_year:
print("reset")
ep_index = 1
cur_year = season["year"]
prev_ep = episode
ep_index += 1
continue
if season["year"] != cur_year:
ep_index = 1
cur_year = season["year"]
try:
next_ep = episodes[index + 1]
except:
next_ep = None
print("---" * 20)
print(
f"{ep_qid} - {ep_title} / #{ep_index} {season_qid} {season_title}")
print(f"{prev_ep} / {next_ep}")
print("---" * 20)
print()
item = WikidataItem(ep_qid)
item.add_item_claim(Props.SEASON,
season_qid,
qualifiers=[
item.get_string_claim(Props.SERIES_ORDINAL,
str(ep_index))
])
if prev_ep:
item.add_item_claim(Props.FOLLOWS, prev_ep["item"])
if next_ep:
item.add_item_claim(Props.FOLLOWED_BY, next_ep["item"])
skiplist.add(ep_qid)
prev_ep = episode
ep_index += 1
def create_episodes():
PATH = str(Path(__file__).parent)
seasons = Knead(PATH + "/data/zomergasten/zomergasten-2021.json").data()
# Sort seasons by season_nr
seasons.sort(key=lambda i: i["season_nr"])
episode_nr = 176 # last episode of 2020
for season in seasons:
print()
print(f"Handling season #{season['season_nr']}")
year = season["year"]
presenter_name = season["presenter"]["title"]
presenter_qid = season["presenter"]["qid"]
for guest in season["guests"]:
episode_nr += 1
guest_name = guest["guest"]["text"]
guest_qid = guest["guest"]["qid"]
print("----" * 20)
print()
print(f"Handling episode #{episode_nr}, guest {guest_name}")
date = parse_isodate(guest["date_parsed"])
if episode_nr < 8:
print("Already handled, skipping")
continue
desc = {
"label_en":
f"Zomergasten with {guest_name} ({year})",
"label_nl":
f"Zomergasten met {guest_name} ({year})",
"description_en":
f"episode {episode_nr} of the Dutch talk show 'Zomergasten', as broadcasted by VPRO on {date['en']}",
"description_nl":
f"aflevering {episode_nr} van het VPRO-televisieprogramma 'Zomergasten', uitgezonden op {date['nl']}",
"aliases_en": [
f"{presenter_name} with {guest_name}",
f"Zomergasten episode {episode_nr}"
],
"aliases_nl": [
f"{presenter_name} met {guest_name}",
f"Zomergasten aflevering {episode_nr}"
]
}
if "qid" in guest:
print(f"Getting a qid: {guest['qid']}")
item = WikidataItem(guest["qid"])
else:
item = WikidataItem(
summary=
f"Creating new item for the Zomergasten episode with {guest_name}",
labels={
"en": desc["label_en"],
"nl": desc["label_nl"]
},
descriptions={
"en": desc["description_en"],
"nl": desc["description_nl"]
},
aliases={
"en": desc["aliases_en"],
"nl": desc["aliases_nl"]
})
item.add_item_claim(Props.INSTANCE_OF, Items.TV_SERIES_EPISODE)
item.add_item_claim(Props.PART_OF_SERIES,
Items.ZOMERGASTEN,
qualifiers=[
item.get_string_claim(
Props.SERIES_ORDINAL, str(episode_nr))
])
item.add_item_claim(Props.PRESENTER,
presenter_qid,
references=get_ref(item))
item.add_time_claim(Props.PUB_DATE,
pywikibot.WbTime(year=date["year"],
month=date["month"],
day=date["day"]),
references=get_ref(item))
item.add_item_claim(Props.TALK_SHOW_GUEST,
guest_qid,
references=get_ref(item))
item.add_item_claim(Props.GENRE, Items.TALK_SHOW)
item.add_item_claim(Props.ORIGINAL_BROADCASTER, Items.VPRO)
item.add_item_claim(Props.COUNTRY_OF_ORIGIN, Items.NETHERLANDS)
item.add_item_claim(Props.LANGUAGE_SHOW, Items.DUTCH)
item.add_item_claim(Props.DISTRIBUTED_BY, Items.NPO)
def create_seasons():
PATH = str(Path(__file__).parent)
seasons = Knead(PATH + "/data/zomergasten/zomergasten.json").data()
# Sort seasons by season_nr
seasons.sort(key=lambda i: i["season_nr"])
for season in seasons:
season_nr = season["season_nr"]
print("----" * 20)
print()
print(f"Handling season #{season_nr}")
year = season["year"]
presenter_name = season["presenter"]["title"]
presenter_qid = season["presenter"]["qid"]
episodes_count = len(season["guests"])
if season_nr < 4:
print("Existing season, skipping")
continue
desc = {
"label_en":
f"Zomergasten season {season_nr} ({year})",
"label_nl":
f"Zomergasten seizoen {season_nr} ({year})",
"description_en":
f"Season {season_nr} of the Dutch talk show 'Zomergasten', as broadcasted by VPRO in {year}",
"description_nl":
f"Seizoen {season_nr} van het VPRO-televisieprogramma 'Zomergasten', uitgezonden in {year}",
"aliases_en":
[f"Zomergasten {year}", f"Zomergasten season {season_nr}"],
"aliases_nl":
[f"Zomergasten {year}", f"Zomergasten seizoen {season_nr}"]
}
item = WikidataItem(
summary=f"Creating new item for the Zomergasten season {season_nr}",
labels={
"en": desc["label_en"],
"nl": desc["label_nl"]
},
descriptions={
"en": desc["description_en"],
"nl": desc["description_nl"]
},
aliases={
"en": desc["aliases_en"],
"nl": desc["aliases_nl"]
})
item.add_item_claim(Props.INSTANCE_OF, Items.TV_SERIES_SEASON)
item.add_item_claim(Props.PART_OF_SERIES,
Items.ZOMERGASTEN,
qualifiers=[
item.get_string_claim(Props.SERIES_ORDINAL,
str(season_nr))
])
item.add_item_claim(Props.PRESENTER,
presenter_qid,
references=get_ref(item))
item.add_time_claim(Props.PUB_DATE,
pywikibot.WbTime(year=year),
references=get_ref(item))
item.add_item_claim(Props.GENRE, Items.TALK_SHOW)
item.add_item_claim(Props.ORIGINAL_BROADCASTER, Items.VPRO)
item.add_item_claim(Props.COUNTRY_OF_ORIGIN, Items.NETHERLANDS)
item.add_item_claim(Props.LANGUAGE_SHOW, Items.DUTCH)
item.add_item_claim(Props.DISTRIBUTED_BY, Items.NPO)
item.add_quantity_claim(Props.NR_OF_EPISODES,
episodes_count,
references=get_ref(item))
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)