#!/usr/bin/env python3 """ Query Wikidata for Chilean Museums using SPARQL Uses Wikidata Query Service to find museums in Chile with their Q-numbers """ import yaml from SPARQLWrapper import SPARQLWrapper, JSON from typing import List, Dict from pathlib import Path def query_chilean_museums() -> List[Dict]: """Query Wikidata for all museums in Chile.""" sparql = SPARQLWrapper("https://query.wikidata.org/sparql") # SPARQL query for museums in Chile # P31 = instance of, P17 = country, Q298 = Chile # Q33506 = museum, Q207694 = art museum, Q1459900 = archaeological museum, etc. query = """ SELECT DISTINCT ?museum ?museumLabel ?cityLabel ?coords ?founded WHERE { # Museum types (including subclasses) ?museum wdt:P31/wdt:P279* wd:Q33506 . # Located in Chile ?museum wdt:P17 wd:Q298 . # Get city/location OPTIONAL { ?museum wdt:P131 ?city . } # Get coordinates OPTIONAL { ?museum wdt:P625 ?coords . } # Get founding date OPTIONAL { ?museum wdt:P571 ?founded . } # Get labels in Spanish and English SERVICE wikibase:label { bd:serviceParam wikibase:language "es,en" . } } ORDER BY ?museumLabel """ sparql.setQuery(query) sparql.setReturnFormat(JSON) print("🔍 Querying Wikidata for Chilean museums...") print(" Endpoint: https://query.wikidata.org/sparql") print() try: results = sparql.query().convert() # type: ignore museums = [] for result in results["results"]["bindings"]: # type: ignore museum_uri = result["museum"]["value"] # type: ignore q_number = museum_uri.split("/")[-1] museum = { "q_number": q_number, "name": result.get("museumLabel", {}).get("value", ""), # type: ignore "city": result.get("cityLabel", {}).get("value", ""), # type: ignore "founded": result.get("founded", {}).get("value", "")[:4] if "founded" in result else "", # type: ignore "wikidata_url": f"https://www.wikidata.org/wiki/{q_number}" } museums.append(museum) return museums except Exception as e: print(f"❌ Error querying Wikidata: {e}") return [] def load_chilean_institutions(file_path: Path) -> List[Dict]: """Load Chilean institutions from YAML file.""" with open(file_path, 'r', encoding='utf-8') as f: return yaml.safe_load(f) def normalize_name(name: str) -> str: """Normalize institution name for matching.""" return name.lower().strip().replace("'", "").replace(" ", " ") def find_matches(institutions: List[Dict], wikidata_museums: List[Dict]) -> List[Dict]: """Find matches between our institutions and Wikidata museums.""" matches = [] # Filter institutions without Wikidata museums_without_wd = [ inst for inst in institutions if inst.get('institution_type') == 'MUSEUM' and not any( id_obj.get('identifier_scheme') == 'Wikidata' for id_obj in inst.get('identifiers', []) ) ] print(f"📊 Matching {len(museums_without_wd)} institutions against {len(wikidata_museums)} Wikidata entries...") print() for inst in museums_without_wd: inst_name = normalize_name(inst['name']) inst_city = inst.get('locations', [{}])[0].get('city', '').lower() for wd_museum in wikidata_museums: wd_name = normalize_name(wd_museum['name']) wd_city = wd_museum['city'].lower() # Name match strategies name_match = False # Strategy 1: Exact match if inst_name == wd_name: name_match = True # Strategy 2: Partial match (institution name contains Wikidata name or vice versa) elif inst_name in wd_name or wd_name in inst_name: name_match = True # Strategy 3: Key words match (museo + significant word) elif 'museo' in inst_name and 'museo' in wd_name: inst_words = set(inst_name.split()) wd_words = set(wd_name.split()) common_words = inst_words & wd_words # Must share at least 2 significant words beyond "museo" significant_common = common_words - {'de', 'del', 'la', 'el', 'museo', 'museum'} if len(significant_common) >= 2: name_match = True # City match (flexible - allows partial matches) city_match = False if inst_city and wd_city: if inst_city in wd_city or wd_city in inst_city: city_match = True # Accept match if name matches and either city matches or no city info if name_match and (city_match or not wd_city): match = { 'institution': inst, 'wikidata': wd_museum, 'name_confidence': 'exact' if inst_name == wd_name else 'partial', 'city_match': city_match } matches.append(match) break # Only take first match per institution return matches def main(): print("=" * 80) print("WIKIDATA SPARQL QUERY - CHILEAN MUSEUMS") print("=" * 80) print() # Query Wikidata wikidata_museums = query_chilean_museums() if not wikidata_museums: print("❌ No results from Wikidata") return print(f"✅ Found {len(wikidata_museums)} museums in Wikidata") print() # Show sample print("Sample results (first 10):") for i, museum in enumerate(wikidata_museums[:10], 1): print(f" {i}. {museum['name']} ({museum['city']}) → {museum['q_number']}") print() # Load our institutions input_file = Path('data/instances/chile/chilean_institutions_batch6_enriched.yaml') institutions = load_chilean_institutions(input_file) print(f"📖 Loaded {len(institutions)} Chilean institutions") museums_count = sum(1 for i in institutions if i.get('institution_type') == 'MUSEUM') print(f" {museums_count} are museums") with_wikidata = sum( 1 for inst in institutions if inst.get('institution_type') == 'MUSEUM' and any( id_obj.get('identifier_scheme') == 'Wikidata' for id_obj in inst.get('identifiers', []) ) ) print(f" {with_wikidata} already have Wikidata") print(f" {museums_count - with_wikidata} need enrichment") print() # Find matches matches = find_matches(institutions, wikidata_museums) print("=" * 80) print(f"MATCHING RESULTS: {len(matches)} potential matches found") print("=" * 80) print() # Display matches for i, match in enumerate(matches, 1): inst = match['institution'] wd = match['wikidata'] print(f"{i}. {inst['name']}") print(f" Our city: {inst.get('locations', [{}])[0].get('city', 'Unknown')}") print(f" ↓ MATCH ({match['name_confidence']} name, city: {match['city_match']})") print(f" Wikidata: {wd['name']} ({wd['city']})") print(f" Q-number: {wd['q_number']}") if wd['founded']: print(f" Founded: {wd['founded']}") print() # Export matches to JSON for batch processing output_file = Path('data/instances/chile/wikidata_matches_batch7.json') import json match_data = [ { 'institution_name': match['institution']['name'], 'institution_city': match['institution'].get('locations', [{}])[0].get('city', ''), 'q_number': match['wikidata']['q_number'], 'wikidata_name': match['wikidata']['name'], 'wikidata_city': match['wikidata']['city'], 'founded': match['wikidata']['founded'], 'confidence': match['name_confidence'], 'city_match': match['city_match'] } for match in matches ] with open(output_file, 'w', encoding='utf-8') as f: json.dump(match_data, f, indent=2, ensure_ascii=False) print(f"💾 Saved {len(matches)} matches to: {output_file}") print() print("🎯 Next step: Review matches and create Batch 7 enrichment script") if __name__ == '__main__': main()