wikidata-query-from-commandline.sh : codesnippets / examples for bash

bash--query-wikidata-en-return-json.sh

#!/usr/bin/env bash
##### Query Wikidata Entities from bash - alternative
# returns only very basic graphs NOT via the SPARQL endpoint
# knb 2020
WDURL='https://www.wikidata.org/w/api.php'
WDQS='action=wbgetentities&format=json&sites=enwiki'
WGE="$WDURL?$WDQS"
echo $WGE >&2
#curl -s: means --silent
WDITEM=Solar_System
# returns "Solar System"
curl -sL "$WGE&titles=$WDITEM" | jq -r '.entities[].labels.en.value' >&2
# Solar System: get the wikidata identifier ("wd"- prefix) result value: "Q544"
SOLSYS_ID=$(curl -sL "$WGE&titles=Solar_System&sites=enwiki" | jq -r '.entities[].id') 
# perform query
curl -s "$WGE&ids=$SOLSYS_ID" | jq -r ".entities.$SOLSYS_ID"

# returns
#{
#  "pageid": 804,
#  "ns": 0,
#  "title": "Q544",
#  "lastrevid": 1320739025,
#  "modified": "2020-12-10T09:06:57Z",
#  "type": "item",
#  "id": "Q544",
#  "labels": {
#    "en": {
#      "language": "en",
#      "value": "Solar System"
#    },
#    "pl": {
#      "language": "pl",
#      "value": "Układ Słoneczny"
#    }, ...
#  }
#}

bash--wikidata-commandline.sh

#!/usr/bin/env bash
# submit a complex SPARQL query to Wikidata, 
# a CONSTRUCT query that returns a graph.
# Read SPARQL queryfile, POST it as "query", text/turtle results to stdout
curl -sL --data-urlencode "query@rockAndRollBandData.rq" \
   -H "Accept: text/turtle" \
   https://query.wikidata.org/bigdata/namespace/wdq/sparql

# return JSON results to file rockAndRollBands.json
curl -sL --data-urlencode "query@rockAndRollBandData.rq" \
   -H "Accept: application/json" \
   -o rockAndRollBands.json \
   https://query.wikidata.org/bigdata/namespace/wdq/sparql

# read in JSON results from rockAndRollBands.json, convert them to CSV on the fly.
< rockAndRollBands.json jq -r  \
  '.results.bindings | map({"p":.predicate.value, "s":.subject.value,  "o":.object.value})' \
  | jq -r '(map(keys) | add | unique) as $cols | map(. as $row | $cols | map($row[.])) as $rows | $cols, $rows[] | @csv'

## ?
## Groups.csv  tail -n +2   | cut -dQ -f 2 | xargs -i echo Q{} | xargs -i echo 'curl -sL "$WGE&ids={}" | jq -r ".entities.{}.labels.en.value"'




curl --data-urlencode "query@wikipedia-german-compsci-alive.rq" \
   -H "Accept: application/json" \
   https://query.wikidata.org/bigdata/namespace/wdq/sparql

< german-compsci.json jq -r  \
  '.results.bindings | map({"p":.person.value, "n":.personLabel.value,  "dob":.dateOfBirth.value, "dod":.dateOfDeath.value})' \
  | jq -r '(map(keys) | add | unique) as $cols | map(. as $row | $cols | map($row[.])) as $rows | $cols, $rows[] | @csv'


# https://opendata.stackexchange.com/a/7153/5763
# Querying Wikidata : WDQ vs. WDQS / SPARQL
# Perl commandline tool for querying Wikidata
# -t: add label/description, or both
wdq -tplanet '?planet wdt:P31 wd:Q44559; wdt:P397 ?sun' > sun-and-stars-and-exoplanets--3890.json

### count results
< sun-and-stars-and-exoplanets.json jq -r '.[]' | jq -c | wc -l

# convert to csv
< sun-and-stars-and-exoplanets--3890.json jq -r  \
  '.results.bindings | map({"p":.planet, "pl":.planetLabel.value,  "pd":.planetDescription.value, "sun":.sun.value})' \
  | jq -r '(map(keys) | add | unique) as $cols | map(. as $row | $cols | map($row[.])) as $rows | $cols, $rows[] | @csv'


< Groups.csv  tail -n +2   | cut -dQ -f 2 | xargs -i echo Q{}  | while read q; do wdq -tperson "$q"; done > people.json

rockAndRollBandData.rq

PREFIX schema: <http://schema.org/>
PREFIX wd:     <http://www.wikidata.org/entity/>
PREFIX wdt:    <http://www.wikidata.org/prop/direct/>
PREFIX rdfs:   <http://www.w3.org/2000/01/rdf-schema#>
prefix owl: <http://www.w3.org/2002/07/owl#>

CONSTRUCT {

   ?band   a schema:MusicGroup ;
           schema:name ?bandName ;
           schema:musicGroupMember ?member ;
           schema:albums ?album .

   ?album  a schema:MusicAlbum ;
           schema:name ?albumTitle ;
           schema:datePublished ?releaseDate .

   ?member schema:name ?memberName ;
           schema:roleName ?roleName .
   
   
}
WHERE {
   ?band wdt:P136 wd:Q11399 ;            # band has genre of rock and roll
         rdfs:label ?bandName ;
         wdt:P527 ?member  .             # band has-part ?member
   
   FILTER ( lang(?bandName) = "en" )

   ?member rdfs:label ?memberName .
   
   FILTER ( lang(?memberName) = "en" )
   OPTIONAL {                                     # Member's role.
      ?member p:P361 ?roleStatement .             # part-of role statement.
      ?roleStatement rdf:type wikibase:BestRank ; # The best role statement!
                     pq:P2868 ?role .             # subject-has-role ?role.
      ?role rdfs:label ?roleName .
      FILTER ( lang(?roleName) = "en" )
   }

   { ?album wdt:P31 wd:Q482994 . }       # instance of album (wd:Q482994)
   UNION
   { ?album wdt:P31 ?albumSubclass .     # or a subclass of that such as
     ?albumSubclass p:P279 wd:Q482994 .  # live or compilation album
   }
   UNION
   { ?album wdt:P31 ?albumSubclass .
     ?albumSubclass p:P279 ?albumClassStatement .   # subclass of
     ?albumClassStatement ps:P279 wd:Q482994 ;
                          rdf:type wikibase:BestRank .
   }

   ?album wdt:P175 ?band ;                      # has performer
          rdfs:label ?albumTitle ;
          p:P577 ?releaseDateStatement .        # publication date

   FILTER ( lang(?albumTitle) = "en" )

   ?releaseDateStatement ps:P577 ?releaseDate ; # release date as ISO 8601
          rdf:type wikibase:BestRank .          # Only the best!
   
   
}

wikidata--rock-and-roll-bands--first-100-lines-of-35k.ttl

@prefix schema: <http://schema.org/> .
@prefix wd: <http://www.wikidata.org/entity/> .
@prefix wdt: <http://www.wikidata.org/prop/direct/> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix sesame: <http://www.openrdf.org/schema/sesame#> .
@prefix owl: <http://www.w3.org/2002/07/owl#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix fn: <http://www.w3.org/2005/xpath-functions#> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix dc: <http://purl.org/dc/elements/1.1/> .
@prefix hint: <http://www.bigdata.com/queryHints#> .
@prefix bd: <http://www.bigdata.com/rdf#> .
@prefix bds: <http://www.bigdata.com/rdf/search#> .
@prefix psn: <http://www.wikidata.org/prop/statement/value-normalized/> .
@prefix pqn: <http://www.wikidata.org/prop/qualifier/value-normalized/> .
@prefix prn: <http://www.wikidata.org/prop/reference/value-normalized/> .
@prefix mwapi: <https://www.mediawiki.org/ontology#API/> .
@prefix gas: <http://www.bigdata.com/rdf/gas#> .
@prefix wdtn: <http://www.wikidata.org/prop/direct-normalized/> .
@prefix psv: <http://www.wikidata.org/prop/statement/value/> .
@prefix ps: <http://www.wikidata.org/prop/statement/> .
@prefix pqv: <http://www.wikidata.org/prop/qualifier/value/> .
@prefix pq: <http://www.wikidata.org/prop/qualifier/> .
@prefix prv: <http://www.wikidata.org/prop/reference/value/> .
@prefix pr: <http://www.wikidata.org/prop/reference/> .
@prefix wdno: <http://www.wikidata.org/prop/novalue/> .
@prefix p: <http://www.wikidata.org/prop/> .
@prefix wikibase: <http://wikiba.se/ontology#> .
@prefix wdata: <http://www.wikidata.org/wiki/Special:EntityData/> .
@prefix wds: <http://www.wikidata.org/entity/statement/> .
@prefix wdv: <http://www.wikidata.org/value/> .
@prefix wdref: <http://www.wikidata.org/reference/> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix skos: <http://www.w3.org/2004/02/skos/core#> .
@prefix geo: <http://www.opengis.net/ont/geosparql#> .
@prefix geof: <http://www.opengis.net/def/geosparql/function/> .
@prefix mediawiki: <https://www.mediawiki.org/ontology#> .
@prefix ontolex: <http://www.w3.org/ns/lemon/ontolex#> .
@prefix dct: <http://purl.org/dc/terms/> .

wd:Q1814025 a schema:MusicGroup ;
	schema:name "True Symphonic Rockestra"@en ;
	schema:musicGroupMember wd:Q296039 ;
	schema:albums wd:Q5158585 .

wd:Q5158585 a schema:MusicAlbum ;
	schema:name "Concerto in True Minor"@en ;
	schema:datePublished "2008-01-01T00:00:00Z"^^xsd:dateTime .

wd:Q296039 schema:name "James LaBrie"@en ;
	schema:roleName "front person"@en .

wd:Q11036 a schema:MusicGroup ;
	schema:name "The Rolling Stones"@en ;
	schema:musicGroupMember wd:Q216051 ;
	schema:albums wd:Q1139077 .

wd:Q1139077 a schema:MusicAlbum ;
	schema:name "Undercover"@en ;
	schema:datePublished "1983-11-07T00:00:00Z"^^xsd:dateTime .

wd:Q216051 schema:name "Charlie Watts"@en ;
	schema:roleName "drummer"@en .

wd:Q11036 schema:albums wd:Q31665 .

wd:Q31665 a schema:MusicAlbum ;
	schema:name "GRRR!"@en ;
	schema:datePublished "2012-11-12T00:00:00Z"^^xsd:dateTime .

wd:Q11036 schema:albums wd:Q12632908 .

wd:Q12632908 a schema:MusicAlbum ;
	schema:name "In Concert"@en ;
	schema:datePublished "1982-07-21T00:00:00Z"^^xsd:dateTime .

wd:Q11036 schema:albums wd:Q62607106 .

wd:Q62607106 a schema:MusicAlbum ;
	schema:name "Hot Rocks 1964-1971"@en ;
	schema:datePublished "1971-12-20T00:00:00Z"^^xsd:dateTime .

wd:Q11036 schema:albums wd:Q1137354 .

wd:Q1137354 a schema:MusicAlbum ;
	schema:name "Steel Wheels"@en ;
	schema:datePublished "1989-08-29T00:00:00Z"^^xsd:dateTime .

wd:Q11036 schema:albums wd:Q62602690 .

wd:Q62602690 a schema:MusicAlbum ;
	schema:name "Through the Past, Darkly (Big Hits Vol. 2)"@en ;
	schema:datePublished "1969-11-01T00:00:00Z"^^xsd:dateTime .

wd:Q11036 schema:albums wd:Q63107624 .

wd:Q63107624 a schema:MusicAlbum ;
	schema:name "Aftermath"@en ;
	schema:datePublished "1966-04-15T00:00:00Z"^^xsd:dateTime .

wikidata-singleitem-label-in-language.sh

#!/usr/bin/env bash
# knb 202012
# https://opendata.stackexchange.com/questions/5248/how-to-get-the-name-of-a-wikidata-item
OPTIND=1
declare VERBOSE="--silent"
declare ID=Q19675  # Q19675 -> Louvre 
declare LANG=es
declare HEADER1="User-Agent: VSCodeSparqlExecutor/1.2.1+; (github.com/danwhitfield/sparql-executor-vscode-extension; <Driller001> knb.findme@gmail.com)"

while getopts 'd:i:l:h:' opt 
do
    case "$opt" in 
        d)  VERBOSE=""  
    ;;
        i)  ID="${OPTARG}"  # entity code we want to translate
    ;;
        l)  LANG="${OPTARG}"  # natural language to translate to
    ;;
        h)  HEADER1="${OPTARG}"  # user-agent header. wikidata recommends
    ;;
        *) echo "Usage: $0 [-v] (more verbose output)" && exit 0 ;;
    esac 
done

URL="https://www.wikidata.org/w/api.php?action=wbgetentities&props=labels&languages=$LANG&format=json&ids=$ID"

< <(curl -sL -H "$HEADER1" "$URL") jq -r .entities.$ID.labels.$LANG.value
#echo "curl -sL -H '$HEADER1' '$URL' 2>/dev/null"
#echo "curl -sL '$URL' 2>/dev/null"