Created
October 31, 2020 07:01
-
-
Save Ladsgroup/670bce20b3a4d14d1854a760e34aa65d to your computer and use it in GitHub Desktop.
Adding refs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from collections import defaultdict, OrderedDict | |
import pywikibot | |
import json | |
import sys | |
site = pywikibot.Site('wikidata', 'wikidata') | |
repo = site.data_repository() | |
site.login() | |
with open(sys.argv[1], 'r') as f: | |
for line in f: | |
try: | |
data = json.loads(line.strip('\n')) | |
except KeyboardInterrupt: | |
sys.exit() | |
except: | |
continue | |
item = pywikibot.ItemPage(repo, data['itemId']) | |
try: | |
item.get() | |
except KeyboardInterrupt: | |
sys.exit() | |
except: | |
continue | |
try: | |
claims = item.claims[data['statement']['pid']] | |
except: | |
continue | |
for claim in claims: | |
if claim.getSources(): | |
continue | |
if data['statement']['value'].get('entity-type') == 'item' and isinstance(claim.getTarget(), pywikibot.ItemPage): | |
pass | |
else: | |
print('kill me') | |
continue | |
if data['statement']['value']['id'] != claim.getTarget().getID(): | |
print(data['statement']['value']['id'], claim.getTarget().getID()) | |
continue | |
break | |
else: | |
continue | |
source_claims = [] | |
for pid in data['reference']['referenceMetadata']: | |
if pid == 'dateRetrieved': | |
source_claim = pywikibot.Claim(site, 'P813') | |
value = data['reference']['referenceMetadata'][pid] | |
value = value.split(' ')[0].split('-') | |
value = [int(i) for i in value] | |
value = pywikibot.WbTime(*value) | |
else: | |
source_claim = pywikibot.Claim(site, pid) | |
value = data['reference']['referenceMetadata'][pid] | |
source_claim.setTarget(value) | |
source_claims.append(source_claim) | |
claim.addSources(source_claims, summary='Bot: Add reference based on [[Wikidata:Automated finding references input]] - October 2020 dump') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment