explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

reading types, claims and sitelinks

Browse Source
This commit is contained in:
svlandeg 2019-04-11 21:42:44 +02:00
parent 6e997be4b4
commit b31a390a9a
1 changed files with 20 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
examples/pipeline/wikidata_entity_linking.py
View File

@ -30,6 +30,8 @@ def _read_wikidata():
# TODO remove hardcoded path # TODO remove hardcoded path
languages = {'en', 'de'} languages = {'en', 'de'}
properties = {'P31'}
sites = {'enwiki'}
with bz2.open('C:/Users/Sofie/Documents/data/wikidata/wikidata-20190304-all.json.bz2', mode='rb') as file: with bz2.open('C:/Users/Sofie/Documents/data/wikidata/wikidata-20190304-all.json.bz2', mode='rb') as file:
line = file.readline() line = file.readline()
@ -40,8 +42,25 @@ def _read_wikidata():
clean_line = clean_line[:-1] clean_line = clean_line[:-1]
if len(clean_line) > 1: if len(clean_line) > 1:
obj = json.loads(clean_line) obj = json.loads(clean_line)
unique_id = obj["id"] unique_id = obj["id"]
print(unique_id) print("ID:", unique_id)
entry_type = obj["type"]
print("type:", entry_type)
# TODO: filter on rank: preferred, normal or deprecated
claims = obj["claims"]
for prop in properties:
claim_property = claims.get(prop, None)
if claim_property:
for cp in claim_property:
print(prop, cp['mainsnak']['datavalue']['value']['id'])
entry_sites = obj["sitelinks"]
for site in sites:
site_value = entry_sites.get(site, None)
print(site, ":", site_value['title'])
labels = obj["labels"] labels = obj["labels"]
if labels: if labels: