glam/scripts/query_wikidata_mexican_institutions.py

#!/usr/bin/env python3
"""
Query Wikidata for Mexican heritage institutions using SPARQL.
Saves results to JSON for fuzzy matching in Batch 2 enrichment.
"""

from SPARQLWrapper import SPARQLWrapper, JSON
import json
from pathlib import Path

def query_wikidata_mexican_glam():
    """Query Wikidata for Mexican GLAM institutions."""
    
    endpoint = SPARQLWrapper("https://query.wikidata.org/sparql")
    endpoint.setRequestMethod('POST')
    
    # Query for museums, libraries, archives, galleries in Mexico
    query = """
    SELECT DISTINCT ?item ?itemLabel ?itemAltLabel ?viaf ?isil ?coords ?typeLabel ?location ?locationLabel WHERE {
      # Instance of museum, library, archive, or gallery
      VALUES ?type { 
        wd:Q33506    # museum
        wd:Q7075     # library
        wd:Q166118   # archive
        wd:Q1007870  # art museum
        wd:Q22698    # park
        wd:Q207694   # art gallery
      }
      ?item wdt:P31/wdt:P279* ?type .
      
      # Located in Mexico
      ?item wdt:P17 wd:Q96 .
      
      # Optional: external identifiers
      OPTIONAL { ?item wdt:P214 ?viaf }      # VIAF ID
      OPTIONAL { ?item wdt:P791 ?isil }      # ISIL code
      OPTIONAL { ?item wdt:P625 ?coords }    # Coordinates
      
      # Optional: location (city/state)
      OPTIONAL { 
        ?item wdt:P131 ?location .
        ?location rdfs:label ?locationLabel .
        FILTER(LANG(?locationLabel) = "es" || LANG(?locationLabel) = "en")
      }
      
      # Get labels in Spanish and English
      SERVICE wikibase:label { 
        bd:serviceParam wikibase:language "es,en" .
        ?item rdfs:label ?itemLabel .
        ?type rdfs:label ?typeLabel .
      }
      
      # Optional: alternative names
      OPTIONAL {
        ?item skos:altLabel ?itemAltLabel .
        FILTER(LANG(?itemAltLabel) = "es" || LANG(?itemAltLabel) = "en")
      }
    }
    LIMIT 500
    """
    
    endpoint.setQuery(query)
    endpoint.setReturnFormat(JSON)
    
    print("Querying Wikidata for Mexican heritage institutions...")
    print("This may take 30-60 seconds...")
    
    try:
        results = endpoint.query().convert()
        return results['results']['bindings']
    except Exception as e:
        print(f"Error querying Wikidata: {e}")
        return []

def parse_wikidata_results(results):
    """Parse SPARQL results into structured format."""
    
    institutions = {}
    
    for result in results:
        # Extract Q-number from URI
        item_uri = result['item']['value']
        q_number = item_uri.split('/')[-1]
        
        # Get name
        name = result.get('itemLabel', {}).get('value', '')
        
        # Skip generic labels
        if name.startswith('Q') or not name:
            continue
        
        # Initialize or update institution record
        if q_number not in institutions:
            institutions[q_number] = {
                'q_number': q_number,
                'name': name,
                'alternative_names': [],
                'viaf': None,
                'isil': None,
                'coordinates': None,
                'type': result.get('typeLabel', {}).get('value', ''),
                'location': result.get('locationLabel', {}).get('value', '')
            }
        
        # Add alternative name if present
        if 'itemAltLabel' in result:
            alt_name = result['itemAltLabel']['value']
            if alt_name not in institutions[q_number]['alternative_names']:
                institutions[q_number]['alternative_names'].append(alt_name)
        
        # Add identifiers
        if 'viaf' in result and not institutions[q_number]['viaf']:
            institutions[q_number]['viaf'] = result['viaf']['value']
        
        if 'isil' in result and not institutions[q_number]['isil']:
            institutions[q_number]['isil'] = result['isil']['value']
        
        if 'coords' in result and not institutions[q_number]['coordinates']:
            institutions[q_number]['coordinates'] = result['coords']['value']
    
    return list(institutions.values())

def main():
    # Query Wikidata
    results = query_wikidata_mexican_glam()
    
    if not results:
        print("No results found or query failed.")
        return
    
    print(f"Received {len(results)} results from Wikidata")
    
    # Parse results
    institutions = parse_wikidata_results(results)
    print(f"Parsed {len(institutions)} unique Mexican institutions")
    
    # Save to JSON
    output_path = Path(__file__).parent.parent / 'data' / 'wikidata' / 'mexican_institutions_wikidata.json'
    output_path.parent.mkdir(parents=True, exist_ok=True)
    
    with open(output_path, 'w', encoding='utf-8') as f:
        json.dump(institutions, f, ensure_ascii=False, indent=2)
    
    print(f"\nSaved {len(institutions)} institutions to {output_path}")
    
    # Print sample results
    print("\nSample results:")
    for inst in institutions[:10]:
        print(f"  - {inst['name']} ({inst['q_number']})")
        if inst['viaf']:
            print(f"    VIAF: {inst['viaf']}")
        if inst['isil']:
            print(f"    ISIL: {inst['isil']}")

if __name__ == '__main__':
    main()